commit from root
Browse files- Baichuan-13B-Chat-lora-Task/README.md +0 -9
- Baichuan-13B-Chat-lora-Task/adapter_config.json +0 -20
- Baichuan-13B-Chat-lora-Task/adapter_model.bin +0 -3
- Baichuan-13B-Chat-lora-Task/all_results.json +0 -11
- Baichuan-13B-Chat-lora-Task/eval_results.json +0 -7
- Baichuan-13B-Chat-lora-Task/special_tokens_map.json +0 -30
- Baichuan-13B-Chat-lora-Task/tokenization_baichuan.py +0 -232
- Baichuan-13B-Chat-lora-Task/tokenizer.model +0 -3
- Baichuan-13B-Chat-lora-Task/tokenizer_config.json +0 -48
- Baichuan-13B-Chat-lora-Task/train_results.json +0 -7
- Baichuan-13B-Chat-lora-Task/trainer_log.jsonl +0 -287
- Baichuan-13B-Chat-lora-Task/trainer_state.json +0 -1761
- Baichuan-13B-Chat-lora-Task/training_args.bin +0 -3
- Baichuan-13B-Chat-lora-Task/training_eval_loss.png +0 -0
- Baichuan-13B-Chat-lora-Task/training_loss.png +0 -0
Baichuan-13B-Chat-lora-Task/README.md
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
---
|
| 4 |
-
## Training procedure
|
| 5 |
-
|
| 6 |
-
### Framework versions
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
- PEFT 0.5.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/adapter_config.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "baichuan-inc/Baichuan-13B-Chat",
|
| 4 |
-
"bias": "none",
|
| 5 |
-
"fan_in_fan_out": false,
|
| 6 |
-
"inference_mode": true,
|
| 7 |
-
"init_lora_weights": true,
|
| 8 |
-
"layers_pattern": null,
|
| 9 |
-
"layers_to_transform": null,
|
| 10 |
-
"lora_alpha": 32.0,
|
| 11 |
-
"lora_dropout": 0.1,
|
| 12 |
-
"modules_to_save": null,
|
| 13 |
-
"peft_type": "LORA",
|
| 14 |
-
"r": 8,
|
| 15 |
-
"revision": null,
|
| 16 |
-
"target_modules": [
|
| 17 |
-
"W_pack"
|
| 18 |
-
],
|
| 19 |
-
"task_type": "CAUSAL_LM"
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/adapter_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:84594037c53e9a300bbdebbc3534f704f22f429b6b912fe36e32aeec5a928e3a
|
| 3 |
-
size 26243422
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/all_results.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.0,
|
| 3 |
-
"eval_loss": 0.41885045170783997,
|
| 4 |
-
"eval_runtime": 69.6555,
|
| 5 |
-
"eval_samples_per_second": 15.821,
|
| 6 |
-
"eval_steps_per_second": 1.594,
|
| 7 |
-
"train_loss": 0.46561298847898175,
|
| 8 |
-
"train_runtime": 35477.4141,
|
| 9 |
-
"train_samples_per_second": 6.149,
|
| 10 |
-
"train_steps_per_second": 0.077
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/eval_results.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.0,
|
| 3 |
-
"eval_loss": 0.41885045170783997,
|
| 4 |
-
"eval_runtime": 69.6555,
|
| 5 |
-
"eval_samples_per_second": 15.821,
|
| 6 |
-
"eval_steps_per_second": 1.594
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/special_tokens_map.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<s>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": true
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": true
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<unk>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": true,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": true
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<unk>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": true,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": true
|
| 29 |
-
}
|
| 30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/tokenization_baichuan.py
DELETED
|
@@ -1,232 +0,0 @@
|
|
| 1 |
-
# Copyright (c) 2023, Baichuan Intelligent Technology. All rights reserved.
|
| 2 |
-
|
| 3 |
-
import os
|
| 4 |
-
from shutil import copyfile
|
| 5 |
-
from typing import Any, Dict, List, Optional, Tuple
|
| 6 |
-
|
| 7 |
-
import sentencepiece as spm
|
| 8 |
-
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
|
| 9 |
-
from transformers.utils import logging
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
logger = logging.get_logger(__name__)
|
| 13 |
-
|
| 14 |
-
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
|
| 15 |
-
|
| 16 |
-
PRETRAINED_VOCAB_FILES_MAP = {
|
| 17 |
-
"vocab_file": {},
|
| 18 |
-
"tokenizer_file": {},
|
| 19 |
-
}
|
| 20 |
-
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
class BaichuanTokenizer(PreTrainedTokenizer):
|
| 24 |
-
"""
|
| 25 |
-
Construct a Baichuan tokenizer. Based on byte-level Byte-Pair-Encoding.
|
| 26 |
-
|
| 27 |
-
Args:
|
| 28 |
-
vocab_file (`str`):
|
| 29 |
-
Path to the vocabulary file.
|
| 30 |
-
"""
|
| 31 |
-
|
| 32 |
-
vocab_files_names = VOCAB_FILES_NAMES
|
| 33 |
-
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
| 34 |
-
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
|
| 35 |
-
model_input_names = ["input_ids", "attention_mask"]
|
| 36 |
-
|
| 37 |
-
def __init__(
|
| 38 |
-
self,
|
| 39 |
-
vocab_file,
|
| 40 |
-
unk_token="<unk>",
|
| 41 |
-
bos_token="<s>",
|
| 42 |
-
eos_token="</s>",
|
| 43 |
-
pad_token=None,
|
| 44 |
-
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
| 45 |
-
add_bos_token=True,
|
| 46 |
-
add_eos_token=False,
|
| 47 |
-
clean_up_tokenization_spaces=False,
|
| 48 |
-
**kwargs,
|
| 49 |
-
):
|
| 50 |
-
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
| 51 |
-
bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
|
| 52 |
-
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
|
| 53 |
-
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
|
| 54 |
-
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
|
| 55 |
-
super().__init__(
|
| 56 |
-
bos_token=bos_token,
|
| 57 |
-
eos_token=eos_token,
|
| 58 |
-
unk_token=unk_token,
|
| 59 |
-
pad_token=pad_token,
|
| 60 |
-
add_bos_token=add_bos_token,
|
| 61 |
-
add_eos_token=add_eos_token,
|
| 62 |
-
sp_model_kwargs=self.sp_model_kwargs,
|
| 63 |
-
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
| 64 |
-
**kwargs,
|
| 65 |
-
)
|
| 66 |
-
self.vocab_file = vocab_file
|
| 67 |
-
self.add_bos_token = add_bos_token
|
| 68 |
-
self.add_eos_token = add_eos_token
|
| 69 |
-
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 70 |
-
self.sp_model.Load(vocab_file)
|
| 71 |
-
|
| 72 |
-
def __getstate__(self):
|
| 73 |
-
state = self.__dict__.copy()
|
| 74 |
-
state["sp_model"] = None
|
| 75 |
-
return state
|
| 76 |
-
|
| 77 |
-
def __setstate__(self, d):
|
| 78 |
-
self.__dict__ = d
|
| 79 |
-
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 80 |
-
self.sp_model.Load(self.vocab_file)
|
| 81 |
-
|
| 82 |
-
@property
|
| 83 |
-
def vocab_size(self):
|
| 84 |
-
"""Returns vocab size"""
|
| 85 |
-
return self.sp_model.get_piece_size()
|
| 86 |
-
|
| 87 |
-
def get_vocab(self):
|
| 88 |
-
"""Returns vocab as a dict"""
|
| 89 |
-
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
| 90 |
-
vocab.update(self.added_tokens_encoder)
|
| 91 |
-
return vocab
|
| 92 |
-
|
| 93 |
-
def _tokenize(self, text):
|
| 94 |
-
"""Returns a tokenized string."""
|
| 95 |
-
return self.sp_model.encode(text, out_type=str)
|
| 96 |
-
|
| 97 |
-
def _convert_token_to_id(self, token):
|
| 98 |
-
"""Converts a token (str) in an id using the vocab."""
|
| 99 |
-
return self.sp_model.piece_to_id(token)
|
| 100 |
-
|
| 101 |
-
def _convert_id_to_token(self, index):
|
| 102 |
-
"""Converts an index (integer) in a token (str) using the vocab."""
|
| 103 |
-
token = self.sp_model.IdToPiece(index)
|
| 104 |
-
return token
|
| 105 |
-
|
| 106 |
-
def convert_tokens_to_string(self, tokens):
|
| 107 |
-
"""Converts a sequence of tokens (string) in a single string."""
|
| 108 |
-
current_sub_tokens = []
|
| 109 |
-
out_string = ""
|
| 110 |
-
prev_is_special = False
|
| 111 |
-
for i, token in enumerate(tokens):
|
| 112 |
-
# make sure that special tokens are not decoded using sentencepiece model
|
| 113 |
-
if token in self.all_special_tokens:
|
| 114 |
-
if not prev_is_special and i != 0:
|
| 115 |
-
out_string += " "
|
| 116 |
-
out_string += self.sp_model.decode(current_sub_tokens) + token
|
| 117 |
-
prev_is_special = True
|
| 118 |
-
current_sub_tokens = []
|
| 119 |
-
else:
|
| 120 |
-
current_sub_tokens.append(token)
|
| 121 |
-
prev_is_special = False
|
| 122 |
-
out_string += self.sp_model.decode(current_sub_tokens)
|
| 123 |
-
return out_string
|
| 124 |
-
|
| 125 |
-
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
| 126 |
-
"""
|
| 127 |
-
Save the vocabulary and special tokens file to a directory.
|
| 128 |
-
|
| 129 |
-
Args:
|
| 130 |
-
save_directory (`str`):
|
| 131 |
-
The directory in which to save the vocabulary.
|
| 132 |
-
|
| 133 |
-
Returns:
|
| 134 |
-
`Tuple(str)`: Paths to the files saved.
|
| 135 |
-
"""
|
| 136 |
-
if not os.path.isdir(save_directory):
|
| 137 |
-
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
| 138 |
-
return
|
| 139 |
-
out_vocab_file = os.path.join(
|
| 140 |
-
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
|
| 141 |
-
)
|
| 142 |
-
|
| 143 |
-
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
| 144 |
-
copyfile(self.vocab_file, out_vocab_file)
|
| 145 |
-
elif not os.path.isfile(self.vocab_file):
|
| 146 |
-
with open(out_vocab_file, "wb") as fi:
|
| 147 |
-
content_spiece_model = self.sp_model.serialized_model_proto()
|
| 148 |
-
fi.write(content_spiece_model)
|
| 149 |
-
|
| 150 |
-
return (out_vocab_file,)
|
| 151 |
-
|
| 152 |
-
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
| 153 |
-
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
| 154 |
-
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
| 155 |
-
|
| 156 |
-
output = bos_token_id + token_ids_0 + eos_token_id
|
| 157 |
-
|
| 158 |
-
if token_ids_1 is not None:
|
| 159 |
-
output = output + bos_token_id + token_ids_1 + eos_token_id
|
| 160 |
-
|
| 161 |
-
return output
|
| 162 |
-
|
| 163 |
-
def get_special_tokens_mask(
|
| 164 |
-
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
| 165 |
-
) -> List[int]:
|
| 166 |
-
"""
|
| 167 |
-
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
| 168 |
-
special tokens using the tokenizer `prepare_for_model` method.
|
| 169 |
-
|
| 170 |
-
Args:
|
| 171 |
-
token_ids_0 (`List[int]`):
|
| 172 |
-
List of IDs.
|
| 173 |
-
token_ids_1 (`List[int]`, *optional*):
|
| 174 |
-
Optional second list of IDs for sequence pairs.
|
| 175 |
-
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 176 |
-
Whether or not the token list is already formatted with special tokens for the model.
|
| 177 |
-
|
| 178 |
-
Returns:
|
| 179 |
-
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
| 180 |
-
"""
|
| 181 |
-
if already_has_special_tokens:
|
| 182 |
-
return super().get_special_tokens_mask(
|
| 183 |
-
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
| 184 |
-
)
|
| 185 |
-
|
| 186 |
-
bos_token_id = [1] if self.add_bos_token else []
|
| 187 |
-
eos_token_id = [1] if self.add_eos_token else []
|
| 188 |
-
|
| 189 |
-
if token_ids_1 is None:
|
| 190 |
-
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
|
| 191 |
-
return (
|
| 192 |
-
bos_token_id
|
| 193 |
-
+ ([0] * len(token_ids_0))
|
| 194 |
-
+ eos_token_id
|
| 195 |
-
+ bos_token_id
|
| 196 |
-
+ ([0] * len(token_ids_1))
|
| 197 |
-
+ eos_token_id
|
| 198 |
-
)
|
| 199 |
-
|
| 200 |
-
def create_token_type_ids_from_sequences(
|
| 201 |
-
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
| 202 |
-
) -> List[int]:
|
| 203 |
-
"""
|
| 204 |
-
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
|
| 205 |
-
sequence pair mask has the following format:
|
| 206 |
-
|
| 207 |
-
```
|
| 208 |
-
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
|
| 209 |
-
| first sequence | second sequence |
|
| 210 |
-
```
|
| 211 |
-
|
| 212 |
-
if token_ids_1 is None, only returns the first portion of the mask (0s).
|
| 213 |
-
|
| 214 |
-
Args:
|
| 215 |
-
token_ids_0 (`List[int]`):
|
| 216 |
-
List of ids.
|
| 217 |
-
token_ids_1 (`List[int]`, *optional*):
|
| 218 |
-
Optional second list of IDs for sequence pairs.
|
| 219 |
-
|
| 220 |
-
Returns:
|
| 221 |
-
`List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
|
| 222 |
-
"""
|
| 223 |
-
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
| 224 |
-
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
| 225 |
-
|
| 226 |
-
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
|
| 227 |
-
|
| 228 |
-
if token_ids_1 is not None:
|
| 229 |
-
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
|
| 230 |
-
|
| 231 |
-
return output
|
| 232 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/tokenizer.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f7d1ab69d25c74644af5c5e4dcd1cc6e96d33783dbd257b6bdea55b643c72813
|
| 3 |
-
size 1136765
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/tokenizer_config.json
DELETED
|
@@ -1,48 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"auto_map": {
|
| 5 |
-
"AutoTokenizer": [
|
| 6 |
-
"tokenization_baichuan.BaichuanTokenizer",
|
| 7 |
-
null
|
| 8 |
-
]
|
| 9 |
-
},
|
| 10 |
-
"bos_token": {
|
| 11 |
-
"__type": "AddedToken",
|
| 12 |
-
"content": "<s>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": true,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": true
|
| 17 |
-
},
|
| 18 |
-
"clean_up_tokenization_spaces": false,
|
| 19 |
-
"eos_token": {
|
| 20 |
-
"__type": "AddedToken",
|
| 21 |
-
"content": "</s>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": true,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": true
|
| 26 |
-
},
|
| 27 |
-
"model_max_length": 4096,
|
| 28 |
-
"pad_token": {
|
| 29 |
-
"__type": "AddedToken",
|
| 30 |
-
"content": "<unk>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": true,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": true
|
| 35 |
-
},
|
| 36 |
-
"padding_side": "right",
|
| 37 |
-
"sp_model_kwargs": {},
|
| 38 |
-
"split_special_tokens": false,
|
| 39 |
-
"tokenizer_class": "BaichuanTokenizer",
|
| 40 |
-
"unk_token": {
|
| 41 |
-
"__type": "AddedToken",
|
| 42 |
-
"content": "<unk>",
|
| 43 |
-
"lstrip": false,
|
| 44 |
-
"normalized": true,
|
| 45 |
-
"rstrip": false,
|
| 46 |
-
"single_word": true
|
| 47 |
-
}
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/train_results.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.46561298847898175,
|
| 4 |
-
"train_runtime": 35477.4141,
|
| 5 |
-
"train_samples_per_second": 6.149,
|
| 6 |
-
"train_steps_per_second": 0.077
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/trainer_log.jsonl
DELETED
|
@@ -1,287 +0,0 @@
|
|
| 1 |
-
{"current_steps": 10, "total_steps": 2726, "loss": 1.5452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999865525734509e-05, "epoch": 0.01, "percentage": 0.37, "elapsed_time": "0:02:32", "remaining_time": "11:29:51"}
|
| 2 |
-
{"current_steps": 20, "total_steps": 2726, "loss": 1.3291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9994621174046976e-05, "epoch": 0.01, "percentage": 0.73, "elapsed_time": "0:04:36", "remaining_time": "10:23:36"}
|
| 3 |
-
{"current_steps": 30, "total_steps": 2726, "loss": 1.1048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9986985231938546e-05, "epoch": 0.02, "percentage": 1.1, "elapsed_time": "0:06:36", "remaining_time": "9:54:30"}
|
| 4 |
-
{"current_steps": 40, "total_steps": 2726, "loss": 0.9155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.99760306731191e-05, "epoch": 0.03, "percentage": 1.47, "elapsed_time": "0:08:47", "remaining_time": "9:50:47"}
|
| 5 |
-
{"current_steps": 50, "total_steps": 2726, "loss": 0.8856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9961758952505326e-05, "epoch": 0.04, "percentage": 1.83, "elapsed_time": "0:10:46", "remaining_time": "9:36:34"}
|
| 6 |
-
{"current_steps": 60, "total_steps": 2726, "loss": 0.8052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9944171965578836e-05, "epoch": 0.04, "percentage": 2.2, "elapsed_time": "0:13:03", "remaining_time": "9:40:26"}
|
| 7 |
-
{"current_steps": 70, "total_steps": 2726, "loss": 0.7332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.992327204813435e-05, "epoch": 0.05, "percentage": 2.57, "elapsed_time": "0:15:01", "remaining_time": "9:30:01"}
|
| 8 |
-
{"current_steps": 80, "total_steps": 2726, "loss": 0.6982, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.989906197596955e-05, "epoch": 0.06, "percentage": 2.93, "elapsed_time": "0:17:01", "remaining_time": "9:22:57"}
|
| 9 |
-
{"current_steps": 90, "total_steps": 2726, "loss": 0.6811, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.987154496451635e-05, "epoch": 0.07, "percentage": 3.3, "elapsed_time": "0:18:51", "remaining_time": "9:12:22"}
|
| 10 |
-
{"current_steps": 100, "total_steps": 2726, "loss": 0.6323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.984072466841389e-05, "epoch": 0.07, "percentage": 3.67, "elapsed_time": "0:21:04", "remaining_time": "9:13:18"}
|
| 11 |
-
{"current_steps": 110, "total_steps": 2726, "loss": 0.6234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.981016546765289e-05, "epoch": 0.08, "percentage": 4.04, "elapsed_time": "0:23:02", "remaining_time": "9:07:57"}
|
| 12 |
-
{"current_steps": 120, "total_steps": 2726, "loss": 0.6125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.977308057009269e-05, "epoch": 0.09, "percentage": 4.4, "elapsed_time": "0:25:11", "remaining_time": "9:07:04"}
|
| 13 |
-
{"current_steps": 130, "total_steps": 2726, "loss": 0.5977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.97327054653146e-05, "epoch": 0.1, "percentage": 4.77, "elapsed_time": "0:27:29", "remaining_time": "9:08:54"}
|
| 14 |
-
{"current_steps": 140, "total_steps": 2726, "loss": 0.6179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.968904551569013e-05, "epoch": 0.1, "percentage": 5.14, "elapsed_time": "0:29:47", "remaining_time": "9:10:22"}
|
| 15 |
-
{"current_steps": 150, "total_steps": 2726, "loss": 0.5879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9642106519863544e-05, "epoch": 0.11, "percentage": 5.5, "elapsed_time": "0:31:46", "remaining_time": "9:05:40"}
|
| 16 |
-
{"current_steps": 160, "total_steps": 2726, "loss": 0.5472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.959189471198171e-05, "epoch": 0.12, "percentage": 5.87, "elapsed_time": "0:33:38", "remaining_time": "8:59:28"}
|
| 17 |
-
{"current_steps": 170, "total_steps": 2726, "loss": 0.602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.953841676086613e-05, "epoch": 0.12, "percentage": 6.24, "elapsed_time": "0:35:33", "remaining_time": "8:54:43"}
|
| 18 |
-
{"current_steps": 180, "total_steps": 2726, "loss": 0.5773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9481679769127275e-05, "epoch": 0.13, "percentage": 6.6, "elapsed_time": "0:37:48", "remaining_time": "8:54:48"}
|
| 19 |
-
{"current_steps": 190, "total_steps": 2726, "loss": 0.5615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9421691272221167e-05, "epoch": 0.14, "percentage": 6.97, "elapsed_time": "0:39:45", "remaining_time": "8:50:36"}
|
| 20 |
-
{"current_steps": 200, "total_steps": 2726, "loss": 0.5704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.935845923744865e-05, "epoch": 0.15, "percentage": 7.34, "elapsed_time": "0:41:50", "remaining_time": "8:48:29"}
|
| 21 |
-
{"current_steps": 200, "total_steps": 2726, "loss": null, "eval_loss": 0.5564362406730652, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.15, "percentage": 7.34, "elapsed_time": "0:41:50", "remaining_time": "8:48:29"}
|
| 22 |
-
{"current_steps": 210, "total_steps": 2726, "loss": 0.5803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9291992062897183e-05, "epoch": 0.15, "percentage": 7.7, "elapsed_time": "0:44:59", "remaining_time": "8:59:06"}
|
| 23 |
-
{"current_steps": 220, "total_steps": 2726, "loss": 0.5655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.922229857632545e-05, "epoch": 0.16, "percentage": 8.07, "elapsed_time": "0:46:42", "remaining_time": "8:52:03"}
|
| 24 |
-
{"current_steps": 230, "total_steps": 2726, "loss": 0.5769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9149388033990966e-05, "epoch": 0.17, "percentage": 8.44, "elapsed_time": "0:49:02", "remaining_time": "8:52:13"}
|
| 25 |
-
{"current_steps": 240, "total_steps": 2726, "loss": 0.5862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9073270119420635e-05, "epoch": 0.18, "percentage": 8.8, "elapsed_time": "0:51:04", "remaining_time": "8:49:08"}
|
| 26 |
-
{"current_steps": 250, "total_steps": 2726, "loss": 0.5506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.899395494212471e-05, "epoch": 0.18, "percentage": 9.17, "elapsed_time": "0:53:13", "remaining_time": "8:47:07"}
|
| 27 |
-
{"current_steps": 260, "total_steps": 2726, "loss": 0.5183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.891145303625408e-05, "epoch": 0.19, "percentage": 9.54, "elapsed_time": "0:55:40", "remaining_time": "8:48:05"}
|
| 28 |
-
{"current_steps": 270, "total_steps": 2726, "loss": 0.575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.882577535920121e-05, "epoch": 0.2, "percentage": 9.9, "elapsed_time": "0:58:06", "remaining_time": "8:48:33"}
|
| 29 |
-
{"current_steps": 280, "total_steps": 2726, "loss": 0.5359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8736933290144815e-05, "epoch": 0.21, "percentage": 10.27, "elapsed_time": "1:00:24", "remaining_time": "8:47:41"}
|
| 30 |
-
{"current_steps": 290, "total_steps": 2726, "loss": 0.5302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8644938628538606e-05, "epoch": 0.21, "percentage": 10.64, "elapsed_time": "1:02:22", "remaining_time": "8:43:57"}
|
| 31 |
-
{"current_steps": 300, "total_steps": 2726, "loss": 0.5399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8549803592544076e-05, "epoch": 0.22, "percentage": 11.01, "elapsed_time": "1:04:13", "remaining_time": "8:39:25"}
|
| 32 |
-
{"current_steps": 310, "total_steps": 2726, "loss": 0.5379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.845154081740783e-05, "epoch": 0.23, "percentage": 11.37, "elapsed_time": "1:06:13", "remaining_time": "8:36:11"}
|
| 33 |
-
{"current_steps": 320, "total_steps": 2726, "loss": 0.5299, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.835016335378343e-05, "epoch": 0.23, "percentage": 11.74, "elapsed_time": "1:08:08", "remaining_time": "8:32:17"}
|
| 34 |
-
{"current_steps": 330, "total_steps": 2726, "loss": 0.535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8245684665998073e-05, "epoch": 0.24, "percentage": 12.11, "elapsed_time": "1:10:23", "remaining_time": "8:31:06"}
|
| 35 |
-
{"current_steps": 340, "total_steps": 2726, "loss": 0.5145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.813811863026436e-05, "epoch": 0.25, "percentage": 12.47, "elapsed_time": "1:12:33", "remaining_time": "8:29:13"}
|
| 36 |
-
{"current_steps": 350, "total_steps": 2726, "loss": 0.5126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.802747953283732e-05, "epoch": 0.26, "percentage": 12.84, "elapsed_time": "1:14:40", "remaining_time": "8:26:55"}
|
| 37 |
-
{"current_steps": 360, "total_steps": 2726, "loss": 0.5012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.791378206811704e-05, "epoch": 0.26, "percentage": 13.21, "elapsed_time": "1:16:47", "remaining_time": "8:24:39"}
|
| 38 |
-
{"current_steps": 370, "total_steps": 2726, "loss": 0.5373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7797041336696995e-05, "epoch": 0.27, "percentage": 13.57, "elapsed_time": "1:19:07", "remaining_time": "8:23:47"}
|
| 39 |
-
{"current_steps": 380, "total_steps": 2726, "loss": 0.4778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.767727284335852e-05, "epoch": 0.28, "percentage": 13.94, "elapsed_time": "1:21:18", "remaining_time": "8:21:59"}
|
| 40 |
-
{"current_steps": 390, "total_steps": 2726, "loss": 0.4894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.755449249501155e-05, "epoch": 0.29, "percentage": 14.31, "elapsed_time": "1:23:03", "remaining_time": "8:17:32"}
|
| 41 |
-
{"current_steps": 400, "total_steps": 2726, "loss": 0.4986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7428716598581934e-05, "epoch": 0.29, "percentage": 14.67, "elapsed_time": "1:25:10", "remaining_time": "8:15:20"}
|
| 42 |
-
{"current_steps": 400, "total_steps": 2726, "loss": null, "eval_loss": 0.4967592656612396, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29, "percentage": 14.67, "elapsed_time": "1:25:10", "remaining_time": "8:15:20"}
|
| 43 |
-
{"current_steps": 410, "total_steps": 2726, "loss": 0.4928, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.729996185884571e-05, "epoch": 0.3, "percentage": 15.04, "elapsed_time": "1:28:14", "remaining_time": "8:18:25"}
|
| 44 |
-
{"current_steps": 420, "total_steps": 2726, "loss": 0.4807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.716824537621042e-05, "epoch": 0.31, "percentage": 15.41, "elapsed_time": "1:30:05", "remaining_time": "8:14:40"}
|
| 45 |
-
{"current_steps": 430, "total_steps": 2726, "loss": 0.4734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.703358464444397e-05, "epoch": 0.32, "percentage": 15.77, "elapsed_time": "1:32:27", "remaining_time": "8:13:42"}
|
| 46 |
-
{"current_steps": 440, "total_steps": 2726, "loss": 0.4603, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.689599754835122e-05, "epoch": 0.32, "percentage": 16.14, "elapsed_time": "1:34:29", "remaining_time": "8:10:56"}
|
| 47 |
-
{"current_steps": 450, "total_steps": 2726, "loss": 0.4661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6755502361398616e-05, "epoch": 0.33, "percentage": 16.51, "elapsed_time": "1:36:31", "remaining_time": "8:08:14"}
|
| 48 |
-
{"current_steps": 460, "total_steps": 2726, "loss": 0.5072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6612117743287234e-05, "epoch": 0.34, "percentage": 16.87, "elapsed_time": "1:38:36", "remaining_time": "8:05:42"}
|
| 49 |
-
{"current_steps": 470, "total_steps": 2726, "loss": 0.5056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.646586273747452e-05, "epoch": 0.34, "percentage": 17.24, "elapsed_time": "1:40:39", "remaining_time": "8:03:07"}
|
| 50 |
-
{"current_steps": 480, "total_steps": 2726, "loss": 0.4391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.631675676864503e-05, "epoch": 0.35, "percentage": 17.61, "elapsed_time": "1:43:01", "remaining_time": "8:02:03"}
|
| 51 |
-
{"current_steps": 490, "total_steps": 2726, "loss": 0.483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6164819640130595e-05, "epoch": 0.36, "percentage": 17.98, "elapsed_time": "1:45:28", "remaining_time": "8:01:17"}
|
| 52 |
-
{"current_steps": 500, "total_steps": 2726, "loss": 0.4774, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.601007153128014e-05, "epoch": 0.37, "percentage": 18.34, "elapsed_time": "1:47:35", "remaining_time": "7:59:00"}
|
| 53 |
-
{"current_steps": 510, "total_steps": 2726, "loss": 0.4848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5852532994779606e-05, "epoch": 0.37, "percentage": 18.71, "elapsed_time": "1:49:45", "remaining_time": "7:56:55"}
|
| 54 |
-
{"current_steps": 520, "total_steps": 2726, "loss": 0.5099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5692224953922266e-05, "epoch": 0.38, "percentage": 19.08, "elapsed_time": "1:51:38", "remaining_time": "7:53:35"}
|
| 55 |
-
{"current_steps": 530, "total_steps": 2726, "loss": 0.4851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5529168699829805e-05, "epoch": 0.39, "percentage": 19.44, "elapsed_time": "1:53:42", "remaining_time": "7:51:09"}
|
| 56 |
-
{"current_steps": 540, "total_steps": 2726, "loss": 0.498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.536338588862459e-05, "epoch": 0.4, "percentage": 19.81, "elapsed_time": "1:55:51", "remaining_time": "7:48:59"}
|
| 57 |
-
{"current_steps": 550, "total_steps": 2726, "loss": 0.5398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.519489853855341e-05, "epoch": 0.4, "percentage": 20.18, "elapsed_time": "1:58:05", "remaining_time": "7:47:11"}
|
| 58 |
-
{"current_steps": 560, "total_steps": 2726, "loss": 0.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.50237290270632e-05, "epoch": 0.41, "percentage": 20.54, "elapsed_time": "1:59:55", "remaining_time": "7:43:50"}
|
| 59 |
-
{"current_steps": 570, "total_steps": 2726, "loss": 0.4942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.484990008782893e-05, "epoch": 0.42, "percentage": 20.91, "elapsed_time": "2:01:51", "remaining_time": "7:40:56"}
|
| 60 |
-
{"current_steps": 580, "total_steps": 2726, "loss": 0.4625, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.467343480773433e-05, "epoch": 0.43, "percentage": 21.28, "elapsed_time": "2:04:02", "remaining_time": "7:38:55"}
|
| 61 |
-
{"current_steps": 590, "total_steps": 2726, "loss": 0.4703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.44943566238056e-05, "epoch": 0.43, "percentage": 21.64, "elapsed_time": "2:06:02", "remaining_time": "7:36:17"}
|
| 62 |
-
{"current_steps": 600, "total_steps": 2726, "loss": 0.464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.431268932009865e-05, "epoch": 0.44, "percentage": 22.01, "elapsed_time": "2:08:29", "remaining_time": "7:35:16"}
|
| 63 |
-
{"current_steps": 600, "total_steps": 2726, "loss": null, "eval_loss": 0.46821752190589905, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.44, "percentage": 22.01, "elapsed_time": "2:08:29", "remaining_time": "7:35:16"}
|
| 64 |
-
{"current_steps": 610, "total_steps": 2726, "loss": 0.4739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.412845702454024e-05, "epoch": 0.45, "percentage": 22.38, "elapsed_time": "2:11:46", "remaining_time": "7:37:07"}
|
| 65 |
-
{"current_steps": 620, "total_steps": 2726, "loss": 0.4529, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.394168420572349e-05, "epoch": 0.45, "percentage": 22.74, "elapsed_time": "2:14:01", "remaining_time": "7:35:15"}
|
| 66 |
-
{"current_steps": 630, "total_steps": 2726, "loss": 0.4433, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3752395669658086e-05, "epoch": 0.46, "percentage": 23.11, "elapsed_time": "2:16:41", "remaining_time": "7:34:47"}
|
| 67 |
-
{"current_steps": 640, "total_steps": 2726, "loss": 0.459, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.356061655647571e-05, "epoch": 0.47, "percentage": 23.48, "elapsed_time": "2:18:53", "remaining_time": "7:32:41"}
|
| 68 |
-
{"current_steps": 650, "total_steps": 2726, "loss": 0.4877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.336637233709107e-05, "epoch": 0.48, "percentage": 23.84, "elapsed_time": "2:20:42", "remaining_time": "7:29:22"}
|
| 69 |
-
{"current_steps": 660, "total_steps": 2726, "loss": 0.4676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.316968880981903e-05, "epoch": 0.48, "percentage": 24.21, "elapsed_time": "2:22:37", "remaining_time": "7:26:26"}
|
| 70 |
-
{"current_steps": 670, "total_steps": 2726, "loss": 0.4782, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2970592096948236e-05, "epoch": 0.49, "percentage": 24.58, "elapsed_time": "2:24:37", "remaining_time": "7:23:48"}
|
| 71 |
-
{"current_steps": 680, "total_steps": 2726, "loss": 0.4778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.276910864127168e-05, "epoch": 0.5, "percentage": 24.94, "elapsed_time": "2:26:47", "remaining_time": "7:21:39"}
|
| 72 |
-
{"current_steps": 690, "total_steps": 2726, "loss": 0.454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.25652652025748e-05, "epoch": 0.51, "percentage": 25.31, "elapsed_time": "2:28:42", "remaining_time": "7:18:47"}
|
| 73 |
-
{"current_steps": 700, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.235908885408133e-05, "epoch": 0.51, "percentage": 25.68, "elapsed_time": "2:30:54", "remaining_time": "7:16:47"}
|
| 74 |
-
{"current_steps": 710, "total_steps": 2726, "loss": 0.5106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.215060697885767e-05, "epoch": 0.52, "percentage": 26.05, "elapsed_time": "2:32:57", "remaining_time": "7:14:19"}
|
| 75 |
-
{"current_steps": 720, "total_steps": 2726, "loss": 0.4683, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1939847266176e-05, "epoch": 0.53, "percentage": 26.41, "elapsed_time": "2:35:12", "remaining_time": "7:12:26"}
|
| 76 |
-
{"current_steps": 730, "total_steps": 2726, "loss": 0.4896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.172683770783677e-05, "epoch": 0.54, "percentage": 26.78, "elapsed_time": "2:37:07", "remaining_time": "7:09:37"}
|
| 77 |
-
{"current_steps": 740, "total_steps": 2726, "loss": 0.4633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1511606594451016e-05, "epoch": 0.54, "percentage": 27.15, "elapsed_time": "2:39:14", "remaining_time": "7:07:20"}
|
| 78 |
-
{"current_steps": 750, "total_steps": 2726, "loss": 0.4486, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1294182511682946e-05, "epoch": 0.55, "percentage": 27.51, "elapsed_time": "2:41:16", "remaining_time": "7:04:53"}
|
| 79 |
-
{"current_steps": 760, "total_steps": 2726, "loss": 0.4706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1074594336453384e-05, "epoch": 0.56, "percentage": 27.88, "elapsed_time": "2:43:11", "remaining_time": "7:02:09"}
|
| 80 |
-
{"current_steps": 770, "total_steps": 2726, "loss": 0.4797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.085287123310455e-05, "epoch": 0.56, "percentage": 28.25, "elapsed_time": "2:44:59", "remaining_time": "6:59:07"}
|
| 81 |
-
{"current_steps": 780, "total_steps": 2726, "loss": 0.4251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.062904264952657e-05, "epoch": 0.57, "percentage": 28.61, "elapsed_time": "2:47:04", "remaining_time": "6:56:49"}
|
| 82 |
-
{"current_steps": 790, "total_steps": 2726, "loss": 0.4687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0403138313246435e-05, "epoch": 0.58, "percentage": 28.98, "elapsed_time": "2:49:15", "remaining_time": "6:54:47"}
|
| 83 |
-
{"current_steps": 800, "total_steps": 2726, "loss": 0.48, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.017518822747976e-05, "epoch": 0.59, "percentage": 29.35, "elapsed_time": "2:51:34", "remaining_time": "6:53:03"}
|
| 84 |
-
{"current_steps": 800, "total_steps": 2726, "loss": null, "eval_loss": 0.4554018974304199, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.59, "percentage": 29.35, "elapsed_time": "2:51:34", "remaining_time": "6:53:03"}
|
| 85 |
-
{"current_steps": 810, "total_steps": 2726, "loss": 0.4662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.994522266714594e-05, "epoch": 0.59, "percentage": 29.71, "elapsed_time": "2:54:51", "remaining_time": "6:53:36"}
|
| 86 |
-
{"current_steps": 820, "total_steps": 2726, "loss": 0.4837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9713272174847246e-05, "epoch": 0.6, "percentage": 30.08, "elapsed_time": "2:57:25", "remaining_time": "6:52:24"}
|
| 87 |
-
{"current_steps": 830, "total_steps": 2726, "loss": 0.5014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.947936755681229e-05, "epoch": 0.61, "percentage": 30.45, "elapsed_time": "2:59:33", "remaining_time": "6:50:10"}
|
| 88 |
-
{"current_steps": 840, "total_steps": 2726, "loss": 0.4764, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.92435398788046e-05, "epoch": 0.62, "percentage": 30.81, "elapsed_time": "3:01:44", "remaining_time": "6:48:02"}
|
| 89 |
-
{"current_steps": 850, "total_steps": 2726, "loss": 0.4587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9005820461996604e-05, "epoch": 0.62, "percentage": 31.18, "elapsed_time": "3:03:52", "remaining_time": "6:45:49"}
|
| 90 |
-
{"current_steps": 860, "total_steps": 2726, "loss": 0.484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.876624087880979e-05, "epoch": 0.63, "percentage": 31.55, "elapsed_time": "3:06:00", "remaining_time": "6:43:35"}
|
| 91 |
-
{"current_steps": 870, "total_steps": 2726, "loss": 0.4285, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.85248329487214e-05, "epoch": 0.64, "percentage": 31.91, "elapsed_time": "3:08:03", "remaining_time": "6:41:10"}
|
| 92 |
-
{"current_steps": 880, "total_steps": 2726, "loss": 0.4742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.828162873403843e-05, "epoch": 0.65, "percentage": 32.28, "elapsed_time": "3:10:09", "remaining_time": "6:38:53"}
|
| 93 |
-
{"current_steps": 890, "total_steps": 2726, "loss": 0.4533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.803666053563926e-05, "epoch": 0.65, "percentage": 32.65, "elapsed_time": "3:12:20", "remaining_time": "6:36:48"}
|
| 94 |
-
{"current_steps": 900, "total_steps": 2726, "loss": 0.4395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.778996088868365e-05, "epoch": 0.66, "percentage": 33.02, "elapsed_time": "3:14:34", "remaining_time": "6:34:47"}
|
| 95 |
-
{"current_steps": 910, "total_steps": 2726, "loss": 0.4519, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.754156255829167e-05, "epoch": 0.67, "percentage": 33.38, "elapsed_time": "3:16:42", "remaining_time": "6:32:33"}
|
| 96 |
-
{"current_steps": 920, "total_steps": 2726, "loss": 0.4684, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7291498535191996e-05, "epoch": 0.67, "percentage": 33.75, "elapsed_time": "3:18:41", "remaining_time": "6:30:02"}
|
| 97 |
-
{"current_steps": 930, "total_steps": 2726, "loss": 0.4259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.703980203134029e-05, "epoch": 0.68, "percentage": 34.12, "elapsed_time": "3:20:24", "remaining_time": "6:27:00"}
|
| 98 |
-
{"current_steps": 940, "total_steps": 2726, "loss": 0.4576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.678650647550822e-05, "epoch": 0.69, "percentage": 34.48, "elapsed_time": "3:22:27", "remaining_time": "6:24:40"}
|
| 99 |
-
{"current_steps": 950, "total_steps": 2726, "loss": 0.446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6531645508843636e-05, "epoch": 0.7, "percentage": 34.85, "elapsed_time": "3:24:21", "remaining_time": "6:22:01"}
|
| 100 |
-
{"current_steps": 960, "total_steps": 2726, "loss": 0.4439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6275252980402544e-05, "epoch": 0.7, "percentage": 35.22, "elapsed_time": "3:26:18", "remaining_time": "6:19:31"}
|
| 101 |
-
{"current_steps": 970, "total_steps": 2726, "loss": 0.476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.601736294265354e-05, "epoch": 0.71, "percentage": 35.58, "elapsed_time": "3:28:32", "remaining_time": "6:17:31"}
|
| 102 |
-
{"current_steps": 980, "total_steps": 2726, "loss": 0.4153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5758009646955115e-05, "epoch": 0.72, "percentage": 35.95, "elapsed_time": "3:30:27", "remaining_time": "6:14:57"}
|
| 103 |
-
{"current_steps": 990, "total_steps": 2726, "loss": 0.4444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5497227539006614e-05, "epoch": 0.73, "percentage": 36.32, "elapsed_time": "3:32:34", "remaining_time": "6:12:46"}
|
| 104 |
-
{"current_steps": 1000, "total_steps": 2726, "loss": 0.4395, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.523505125427341e-05, "epoch": 0.73, "percentage": 36.68, "elapsed_time": "3:34:52", "remaining_time": "6:10:52"}
|
| 105 |
-
{"current_steps": 1000, "total_steps": 2726, "loss": null, "eval_loss": 0.44357746839523315, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.73, "percentage": 36.68, "elapsed_time": "3:34:52", "remaining_time": "6:10:52"}
|
| 106 |
-
{"current_steps": 1010, "total_steps": 2726, "loss": 0.4387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.497151561338678e-05, "epoch": 0.74, "percentage": 37.05, "elapsed_time": "3:38:14", "remaining_time": "6:10:46"}
|
| 107 |
-
{"current_steps": 1020, "total_steps": 2726, "loss": 0.4559, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.470665561751928e-05, "epoch": 0.75, "percentage": 37.42, "elapsed_time": "3:40:04", "remaining_time": "6:08:04"}
|
| 108 |
-
{"current_steps": 1030, "total_steps": 2726, "loss": 0.4349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.444050644373611e-05, "epoch": 0.76, "percentage": 37.78, "elapsed_time": "3:42:11", "remaining_time": "6:05:50"}
|
| 109 |
-
{"current_steps": 1040, "total_steps": 2726, "loss": 0.4661, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.417310344032309e-05, "epoch": 0.76, "percentage": 38.15, "elapsed_time": "3:44:11", "remaining_time": "6:03:26"}
|
| 110 |
-
{"current_steps": 1050, "total_steps": 2726, "loss": 0.4945, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.390448212209191e-05, "epoch": 0.77, "percentage": 38.52, "elapsed_time": "3:46:22", "remaining_time": "6:01:20"}
|
| 111 |
-
{"current_steps": 1060, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3634678165663325e-05, "epoch": 0.78, "percentage": 38.88, "elapsed_time": "3:48:36", "remaining_time": "5:59:18"}
|
| 112 |
-
{"current_steps": 1070, "total_steps": 2726, "loss": 0.4399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.336372740472877e-05, "epoch": 0.78, "percentage": 39.25, "elapsed_time": "3:50:31", "remaining_time": "5:56:47"}
|
| 113 |
-
{"current_steps": 1080, "total_steps": 2726, "loss": 0.4251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.309166582529114e-05, "epoch": 0.79, "percentage": 39.62, "elapsed_time": "3:52:21", "remaining_time": "5:54:08"}
|
| 114 |
-
{"current_steps": 1090, "total_steps": 2726, "loss": 0.4385, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.281852956088537e-05, "epoch": 0.8, "percentage": 39.99, "elapsed_time": "3:54:18", "remaining_time": "5:51:40"}
|
| 115 |
-
{"current_steps": 1100, "total_steps": 2726, "loss": 0.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.254435488777941e-05, "epoch": 0.81, "percentage": 40.35, "elapsed_time": "3:56:22", "remaining_time": "5:49:24"}
|
| 116 |
-
{"current_steps": 1110, "total_steps": 2726, "loss": 0.4352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.226917822015623e-05, "epoch": 0.81, "percentage": 40.72, "elapsed_time": "3:58:33", "remaining_time": "5:47:19"}
|
| 117 |
-
{"current_steps": 1120, "total_steps": 2726, "loss": 0.4617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.199303610527749e-05, "epoch": 0.82, "percentage": 41.09, "elapsed_time": "4:00:57", "remaining_time": "5:45:30"}
|
| 118 |
-
{"current_steps": 1130, "total_steps": 2726, "loss": 0.476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1715965218629595e-05, "epoch": 0.83, "percentage": 41.45, "elapsed_time": "4:02:46", "remaining_time": "5:42:54"}
|
| 119 |
-
{"current_steps": 1140, "total_steps": 2726, "loss": 0.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.143800235905268e-05, "epoch": 0.84, "percentage": 41.82, "elapsed_time": "4:04:46", "remaining_time": "5:40:32"}
|
| 120 |
-
{"current_steps": 1150, "total_steps": 2726, "loss": 0.4736, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.115918444385315e-05, "epoch": 0.84, "percentage": 42.19, "elapsed_time": "4:06:57", "remaining_time": "5:38:26"}
|
| 121 |
-
{"current_steps": 1160, "total_steps": 2726, "loss": 0.4322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0879548503900665e-05, "epoch": 0.85, "percentage": 42.55, "elapsed_time": "4:09:21", "remaining_time": "5:36:37"}
|
| 122 |
-
{"current_steps": 1170, "total_steps": 2726, "loss": 0.4152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0599131678709836e-05, "epoch": 0.86, "percentage": 42.92, "elapsed_time": "4:11:20", "remaining_time": "5:34:16"}
|
| 123 |
-
{"current_steps": 1180, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.031797121150764e-05, "epoch": 0.87, "percentage": 43.29, "elapsed_time": "4:13:18", "remaining_time": "5:31:52"}
|
| 124 |
-
{"current_steps": 1190, "total_steps": 2726, "loss": 0.4331, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0036104444286954e-05, "epoch": 0.87, "percentage": 43.65, "elapsed_time": "4:15:22", "remaining_time": "5:29:37"}
|
| 125 |
-
{"current_steps": 1200, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9753568812847065e-05, "epoch": 0.88, "percentage": 44.02, "elapsed_time": "4:17:56", "remaining_time": "5:28:00"}
|
| 126 |
-
{"current_steps": 1200, "total_steps": 2726, "loss": null, "eval_loss": 0.43782830238342285, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.88, "percentage": 44.02, "elapsed_time": "4:17:56", "remaining_time": "5:28:00"}
|
| 127 |
-
{"current_steps": 1210, "total_steps": 2726, "loss": 0.4457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9470401841821686e-05, "epoch": 0.89, "percentage": 44.39, "elapsed_time": "4:21:17", "remaining_time": "5:27:22"}
|
| 128 |
-
{"current_steps": 1220, "total_steps": 2726, "loss": 0.4667, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9186641139695108e-05, "epoch": 0.89, "percentage": 44.75, "elapsed_time": "4:23:21", "remaining_time": "5:25:05"}
|
| 129 |
-
{"current_steps": 1230, "total_steps": 2726, "loss": 0.4516, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8902324393807333e-05, "epoch": 0.9, "percentage": 45.12, "elapsed_time": "4:25:38", "remaining_time": "5:23:05"}
|
| 130 |
-
{"current_steps": 1240, "total_steps": 2726, "loss": 0.4695, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.861748936534867e-05, "epoch": 0.91, "percentage": 45.49, "elapsed_time": "4:27:43", "remaining_time": "5:20:50"}
|
| 131 |
-
{"current_steps": 1250, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8332173884344477e-05, "epoch": 0.92, "percentage": 45.85, "elapsed_time": "4:30:07", "remaining_time": "5:18:58"}
|
| 132 |
-
{"current_steps": 1260, "total_steps": 2726, "loss": 0.4246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8046415844630857e-05, "epoch": 0.92, "percentage": 46.22, "elapsed_time": "4:32:04", "remaining_time": "5:16:33"}
|
| 133 |
-
{"current_steps": 1270, "total_steps": 2726, "loss": 0.4449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7760253198821822e-05, "epoch": 0.93, "percentage": 46.59, "elapsed_time": "4:34:02", "remaining_time": "5:14:10"}
|
| 134 |
-
{"current_steps": 1280, "total_steps": 2726, "loss": 0.4217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7473723953268687e-05, "epoch": 0.94, "percentage": 46.96, "elapsed_time": "4:36:21", "remaining_time": "5:12:11"}
|
| 135 |
-
{"current_steps": 1290, "total_steps": 2726, "loss": 0.4495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7186866163012232e-05, "epoch": 0.95, "percentage": 47.32, "elapsed_time": "4:38:18", "remaining_time": "5:09:48"}
|
| 136 |
-
{"current_steps": 1300, "total_steps": 2726, "loss": 0.4523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6899717926728535e-05, "epoch": 0.95, "percentage": 47.69, "elapsed_time": "4:40:31", "remaining_time": "5:07:43"}
|
| 137 |
-
{"current_steps": 1310, "total_steps": 2726, "loss": 0.4523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6612317381668915e-05, "epoch": 0.96, "percentage": 48.06, "elapsed_time": "4:42:52", "remaining_time": "5:05:45"}
|
| 138 |
-
{"current_steps": 1320, "total_steps": 2726, "loss": 0.45, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.632470269859478e-05, "epoch": 0.97, "percentage": 48.42, "elapsed_time": "4:44:43", "remaining_time": "5:03:16"}
|
| 139 |
-
{"current_steps": 1330, "total_steps": 2726, "loss": 0.4371, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.603691207670803e-05, "epoch": 0.98, "percentage": 48.79, "elapsed_time": "4:46:50", "remaining_time": "5:01:04"}
|
| 140 |
-
{"current_steps": 1340, "total_steps": 2726, "loss": 0.4221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5748983738577653e-05, "epoch": 0.98, "percentage": 49.16, "elapsed_time": "4:49:12", "remaining_time": "4:59:08"}
|
| 141 |
-
{"current_steps": 1350, "total_steps": 2726, "loss": 0.4565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5460955925063268e-05, "epoch": 0.99, "percentage": 49.52, "elapsed_time": "4:51:37", "remaining_time": "4:57:14"}
|
| 142 |
-
{"current_steps": 1360, "total_steps": 2726, "loss": 0.3892, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5172866890236203e-05, "epoch": 1.0, "percentage": 49.89, "elapsed_time": "4:53:48", "remaining_time": "4:55:05"}
|
| 143 |
-
{"current_steps": 1370, "total_steps": 2726, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.48847548962988e-05, "epoch": 1.0, "percentage": 50.26, "elapsed_time": "4:56:07", "remaining_time": "4:53:06"}
|
| 144 |
-
{"current_steps": 1380, "total_steps": 2726, "loss": 0.4151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4596658208502713e-05, "epoch": 1.01, "percentage": 50.62, "elapsed_time": "4:58:09", "remaining_time": "4:50:48"}
|
| 145 |
-
{"current_steps": 1390, "total_steps": 2726, "loss": 0.3839, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4308615090066735e-05, "epoch": 1.02, "percentage": 50.99, "elapsed_time": "5:00:25", "remaining_time": "4:48:44"}
|
| 146 |
-
{"current_steps": 1400, "total_steps": 2726, "loss": 0.4062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4020663797094864e-05, "epoch": 1.03, "percentage": 51.36, "elapsed_time": "5:02:30", "remaining_time": "4:46:31"}
|
| 147 |
-
{"current_steps": 1400, "total_steps": 2726, "loss": null, "eval_loss": 0.43284282088279724, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.03, "percentage": 51.36, "elapsed_time": "5:02:30", "remaining_time": "4:46:31"}
|
| 148 |
-
{"current_steps": 1410, "total_steps": 2726, "loss": 0.4003, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.373284257349544e-05, "epoch": 1.03, "percentage": 51.72, "elapsed_time": "5:05:58", "remaining_time": "4:45:34"}
|
| 149 |
-
{"current_steps": 1420, "total_steps": 2726, "loss": 0.4447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3445189645901806e-05, "epoch": 1.04, "percentage": 52.09, "elapsed_time": "5:08:26", "remaining_time": "4:43:40"}
|
| 150 |
-
{"current_steps": 1430, "total_steps": 2726, "loss": 0.4565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3157743218595247e-05, "epoch": 1.05, "percentage": 52.46, "elapsed_time": "5:10:20", "remaining_time": "4:41:15"}
|
| 151 |
-
{"current_steps": 1440, "total_steps": 2726, "loss": 0.4265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.287054146843097e-05, "epoch": 1.06, "percentage": 52.82, "elapsed_time": "5:12:13", "remaining_time": "4:38:50"}
|
| 152 |
-
{"current_steps": 1450, "total_steps": 2726, "loss": 0.4056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2583622539767668e-05, "epoch": 1.06, "percentage": 53.19, "elapsed_time": "5:14:21", "remaining_time": "4:36:38"}
|
| 153 |
-
{"current_steps": 1460, "total_steps": 2726, "loss": 0.4074, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2297024539401463e-05, "epoch": 1.07, "percentage": 53.56, "elapsed_time": "5:16:26", "remaining_time": "4:34:23"}
|
| 154 |
-
{"current_steps": 1470, "total_steps": 2726, "loss": 0.4281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2010785531504716e-05, "epoch": 1.08, "percentage": 53.93, "elapsed_time": "5:18:46", "remaining_time": "4:32:22"}
|
| 155 |
-
{"current_steps": 1480, "total_steps": 2726, "loss": 0.4663, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.172494353257066e-05, "epoch": 1.09, "percentage": 54.29, "elapsed_time": "5:21:04", "remaining_time": "4:30:18"}
|
| 156 |
-
{"current_steps": 1490, "total_steps": 2726, "loss": 0.4281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1439536506364274e-05, "epoch": 1.09, "percentage": 54.66, "elapsed_time": "5:23:36", "remaining_time": "4:28:26"}
|
| 157 |
-
{"current_steps": 1500, "total_steps": 2726, "loss": 0.4111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1154602358880122e-05, "epoch": 1.1, "percentage": 55.03, "elapsed_time": "5:25:52", "remaining_time": "4:26:20"}
|
| 158 |
-
{"current_steps": 1510, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0870178933307948e-05, "epoch": 1.11, "percentage": 55.39, "elapsed_time": "5:27:49", "remaining_time": "4:23:59"}
|
| 159 |
-
{"current_steps": 1520, "total_steps": 2726, "loss": 0.3964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0586304005006585e-05, "epoch": 1.11, "percentage": 55.76, "elapsed_time": "5:30:05", "remaining_time": "4:21:54"}
|
| 160 |
-
{"current_steps": 1530, "total_steps": 2726, "loss": 0.4331, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.030301527648684e-05, "epoch": 1.12, "percentage": 56.13, "elapsed_time": "5:32:15", "remaining_time": "4:19:43"}
|
| 161 |
-
{"current_steps": 1540, "total_steps": 2726, "loss": 0.4432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0020350372404102e-05, "epoch": 1.13, "percentage": 56.49, "elapsed_time": "5:34:15", "remaining_time": "4:17:25"}
|
| 162 |
-
{"current_steps": 1550, "total_steps": 2726, "loss": 0.4056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9738346834561254e-05, "epoch": 1.14, "percentage": 56.86, "elapsed_time": "5:36:18", "remaining_time": "4:15:09"}
|
| 163 |
-
{"current_steps": 1560, "total_steps": 2726, "loss": 0.4354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.945704211692262e-05, "epoch": 1.14, "percentage": 57.23, "elapsed_time": "5:38:26", "remaining_time": "4:12:57"}
|
| 164 |
-
{"current_steps": 1570, "total_steps": 2726, "loss": 0.4309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9176473580639538e-05, "epoch": 1.15, "percentage": 57.59, "elapsed_time": "5:40:42", "remaining_time": "4:10:52"}
|
| 165 |
-
{"current_steps": 1580, "total_steps": 2726, "loss": 0.4058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8896678489088304e-05, "epoch": 1.16, "percentage": 57.96, "elapsed_time": "5:42:44", "remaining_time": "4:08:35"}
|
| 166 |
-
{"current_steps": 1590, "total_steps": 2726, "loss": 0.4319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8617694002921064e-05, "epoch": 1.17, "percentage": 58.33, "elapsed_time": "5:44:54", "remaining_time": "4:06:25"}
|
| 167 |
-
{"current_steps": 1600, "total_steps": 2726, "loss": 0.4267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8339557175130383e-05, "epoch": 1.17, "percentage": 58.69, "elapsed_time": "5:46:47", "remaining_time": "4:04:03"}
|
| 168 |
-
{"current_steps": 1600, "total_steps": 2726, "loss": null, "eval_loss": 0.42894992232322693, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.17, "percentage": 58.69, "elapsed_time": "5:46:47", "remaining_time": "4:04:03"}
|
| 169 |
-
{"current_steps": 1610, "total_steps": 2726, "loss": 0.3921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8062304946128073e-05, "epoch": 1.18, "percentage": 59.06, "elapsed_time": "5:50:11", "remaining_time": "4:02:44"}
|
| 170 |
-
{"current_steps": 1620, "total_steps": 2726, "loss": 0.4206, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7785974138839018e-05, "epoch": 1.19, "percentage": 59.43, "elapsed_time": "5:52:10", "remaining_time": "4:00:26"}
|
| 171 |
-
{"current_steps": 1630, "total_steps": 2726, "loss": 0.4356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7510601453810594e-05, "epoch": 1.2, "percentage": 59.79, "elapsed_time": "5:54:17", "remaining_time": "3:58:13"}
|
| 172 |
-
{"current_steps": 1640, "total_steps": 2726, "loss": 0.4167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.723622346433828e-05, "epoch": 1.2, "percentage": 60.16, "elapsed_time": "5:56:29", "remaining_time": "3:56:03"}
|
| 173 |
-
{"current_steps": 1650, "total_steps": 2726, "loss": 0.4233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6962876611608262e-05, "epoch": 1.21, "percentage": 60.53, "elapsed_time": "5:58:26", "remaining_time": "3:53:45"}
|
| 174 |
-
{"current_steps": 1660, "total_steps": 2726, "loss": 0.4176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6690597199857523e-05, "epoch": 1.22, "percentage": 60.9, "elapsed_time": "6:00:33", "remaining_time": "3:51:32"}
|
| 175 |
-
{"current_steps": 1670, "total_steps": 2726, "loss": 0.4241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6419421391552142e-05, "epoch": 1.22, "percentage": 61.26, "elapsed_time": "6:02:41", "remaining_time": "3:49:20"}
|
| 176 |
-
{"current_steps": 1680, "total_steps": 2726, "loss": 0.4524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6149385202584423e-05, "epoch": 1.23, "percentage": 61.63, "elapsed_time": "6:04:45", "remaining_time": "3:47:06"}
|
| 177 |
-
{"current_steps": 1690, "total_steps": 2726, "loss": 0.4647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5880524497489474e-05, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "6:07:03", "remaining_time": "3:45:01"}
|
| 178 |
-
{"current_steps": 1700, "total_steps": 2726, "loss": 0.4036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5612874984681923e-05, "epoch": 1.25, "percentage": 62.36, "elapsed_time": "6:09:03", "remaining_time": "3:42:44"}
|
| 179 |
-
{"current_steps": 1710, "total_steps": 2726, "loss": 0.4148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.534647221171334e-05, "epoch": 1.25, "percentage": 62.73, "elapsed_time": "6:11:22", "remaining_time": "3:40:38"}
|
| 180 |
-
{"current_steps": 1720, "total_steps": 2726, "loss": 0.408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5081351560551021e-05, "epoch": 1.26, "percentage": 63.1, "elapsed_time": "6:13:19", "remaining_time": "3:38:21"}
|
| 181 |
-
{"current_steps": 1730, "total_steps": 2726, "loss": 0.457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4817548242878759e-05, "epoch": 1.27, "percentage": 63.46, "elapsed_time": "6:15:23", "remaining_time": "3:36:07"}
|
| 182 |
-
{"current_steps": 1740, "total_steps": 2726, "loss": 0.4193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.45550972954203e-05, "epoch": 1.28, "percentage": 63.83, "elapsed_time": "6:17:21", "remaining_time": "3:33:50"}
|
| 183 |
-
{"current_steps": 1750, "total_steps": 2726, "loss": 0.4149, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4294033575285914e-05, "epoch": 1.28, "percentage": 64.2, "elapsed_time": "6:19:35", "remaining_time": "3:31:42"}
|
| 184 |
-
{"current_steps": 1760, "total_steps": 2726, "loss": 0.4032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4034391755342972e-05, "epoch": 1.29, "percentage": 64.56, "elapsed_time": "6:21:52", "remaining_time": "3:29:35"}
|
| 185 |
-
{"current_steps": 1770, "total_steps": 2726, "loss": 0.4078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3776206319610823e-05, "epoch": 1.3, "percentage": 64.93, "elapsed_time": "6:23:56", "remaining_time": "3:27:22"}
|
| 186 |
-
{"current_steps": 1780, "total_steps": 2726, "loss": 0.4123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3519511558680892e-05, "epoch": 1.31, "percentage": 65.3, "elapsed_time": "6:26:23", "remaining_time": "3:25:21"}
|
| 187 |
-
{"current_steps": 1790, "total_steps": 2726, "loss": 0.4089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3264341565162422e-05, "epoch": 1.31, "percentage": 65.66, "elapsed_time": "6:28:17", "remaining_time": "3:23:02"}
|
| 188 |
-
{"current_steps": 1800, "total_steps": 2726, "loss": 0.383, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3010730229154445e-05, "epoch": 1.32, "percentage": 66.03, "elapsed_time": "6:30:17", "remaining_time": "3:20:47"}
|
| 189 |
-
{"current_steps": 1800, "total_steps": 2726, "loss": null, "eval_loss": 0.4250344932079315, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.32, "percentage": 66.03, "elapsed_time": "6:30:17", "remaining_time": "3:20:47"}
|
| 190 |
-
{"current_steps": 1810, "total_steps": 2726, "loss": 0.3936, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2758711233744783e-05, "epoch": 1.33, "percentage": 66.4, "elapsed_time": "6:33:42", "remaining_time": "3:19:14"}
|
| 191 |
-
{"current_steps": 1820, "total_steps": 2726, "loss": 0.4127, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2508318050536421e-05, "epoch": 1.33, "percentage": 66.76, "elapsed_time": "6:35:33", "remaining_time": "3:16:54"}
|
| 192 |
-
{"current_steps": 1830, "total_steps": 2726, "loss": 0.4015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2259583935202062e-05, "epoch": 1.34, "percentage": 67.13, "elapsed_time": "6:37:28", "remaining_time": "3:14:36"}
|
| 193 |
-
{"current_steps": 1840, "total_steps": 2726, "loss": 0.4203, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2012541923067244e-05, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "6:39:29", "remaining_time": "3:12:21"}
|
| 194 |
-
{"current_steps": 1850, "total_steps": 2726, "loss": 0.4367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.176722482472286e-05, "epoch": 1.36, "percentage": 67.87, "elapsed_time": "6:41:25", "remaining_time": "3:10:04"}
|
| 195 |
-
{"current_steps": 1860, "total_steps": 2726, "loss": 0.4233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1523665221667398e-05, "epoch": 1.36, "percentage": 68.23, "elapsed_time": "6:43:12", "remaining_time": "3:07:44"}
|
| 196 |
-
{"current_steps": 1870, "total_steps": 2726, "loss": 0.4405, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1281895461979732e-05, "epoch": 1.37, "percentage": 68.6, "elapsed_time": "6:45:16", "remaining_time": "3:05:31"}
|
| 197 |
-
{"current_steps": 1880, "total_steps": 2726, "loss": 0.4379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.104194765602281e-05, "epoch": 1.38, "percentage": 68.97, "elapsed_time": "6:47:24", "remaining_time": "3:03:20"}
|
| 198 |
-
{"current_steps": 1890, "total_steps": 2726, "loss": 0.4146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0803853672178946e-05, "epoch": 1.39, "percentage": 69.33, "elapsed_time": "6:49:44", "remaining_time": "3:01:14"}
|
| 199 |
-
{"current_steps": 1900, "total_steps": 2726, "loss": 0.4438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0567645132617316e-05, "epoch": 1.39, "percentage": 69.7, "elapsed_time": "6:51:53", "remaining_time": "2:59:03"}
|
| 200 |
-
{"current_steps": 1910, "total_steps": 2726, "loss": 0.3915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0333353409094015e-05, "epoch": 1.4, "percentage": 70.07, "elapsed_time": "6:54:02", "remaining_time": "2:56:53"}
|
| 201 |
-
{"current_steps": 1920, "total_steps": 2726, "loss": 0.4063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0101009618785528e-05, "epoch": 1.41, "percentage": 70.43, "elapsed_time": "6:56:21", "remaining_time": "2:54:47"}
|
| 202 |
-
{"current_steps": 1930, "total_steps": 2726, "loss": 0.3974, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.870644620155877e-06, "epoch": 1.42, "percentage": 70.8, "elapsed_time": "6:58:32", "remaining_time": "2:52:37"}
|
| 203 |
-
{"current_steps": 1940, "total_steps": 2726, "loss": 0.4015, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.642289008858244e-06, "epoch": 1.42, "percentage": 71.17, "elapsed_time": "7:00:49", "remaining_time": "2:50:30"}
|
| 204 |
-
{"current_steps": 1950, "total_steps": 2726, "loss": 0.4264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.41597311367142e-06, "epoch": 1.43, "percentage": 71.53, "elapsed_time": "7:02:59", "remaining_time": "2:48:19"}
|
| 205 |
-
{"current_steps": 1960, "total_steps": 2726, "loss": 0.4334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.191726992471725e-06, "epoch": 1.44, "percentage": 71.9, "elapsed_time": "7:05:22", "remaining_time": "2:46:14"}
|
| 206 |
-
{"current_steps": 1970, "total_steps": 2726, "loss": 0.4197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.969580428240903e-06, "epoch": 1.44, "percentage": 72.27, "elapsed_time": "7:07:11", "remaining_time": "2:43:56"}
|
| 207 |
-
{"current_steps": 1980, "total_steps": 2726, "loss": 0.422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.74956292511056e-06, "epoch": 1.45, "percentage": 72.63, "elapsed_time": "7:09:23", "remaining_time": "2:41:46"}
|
| 208 |
-
{"current_steps": 1990, "total_steps": 2726, "loss": 0.4077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.531703704443575e-06, "epoch": 1.46, "percentage": 73.0, "elapsed_time": "7:11:33", "remaining_time": "2:39:36"}
|
| 209 |
-
{"current_steps": 2000, "total_steps": 2726, "loss": 0.4334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.316031700953086e-06, "epoch": 1.47, "percentage": 73.37, "elapsed_time": "7:13:58", "remaining_time": "2:37:31"}
|
| 210 |
-
{"current_steps": 2000, "total_steps": 2726, "loss": null, "eval_loss": 0.4206145107746124, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.47, "percentage": 73.37, "elapsed_time": "7:13:58", "remaining_time": "2:37:31"}
|
| 211 |
-
{"current_steps": 2010, "total_steps": 2726, "loss": 0.4171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.102575558859612e-06, "epoch": 1.47, "percentage": 73.73, "elapsed_time": "7:17:28", "remaining_time": "2:35:50"}
|
| 212 |
-
{"current_steps": 2020, "total_steps": 2726, "loss": 0.3957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.891363628086671e-06, "epoch": 1.48, "percentage": 74.1, "elapsed_time": "7:19:27", "remaining_time": "2:33:35"}
|
| 213 |
-
{"current_steps": 2030, "total_steps": 2726, "loss": 0.4174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.682423960495517e-06, "epoch": 1.49, "percentage": 74.47, "elapsed_time": "7:21:25", "remaining_time": "2:31:20"}
|
| 214 |
-
{"current_steps": 2040, "total_steps": 2726, "loss": 0.4187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.475784306159478e-06, "epoch": 1.5, "percentage": 74.83, "elapsed_time": "7:23:33", "remaining_time": "2:29:09"}
|
| 215 |
-
{"current_steps": 2050, "total_steps": 2726, "loss": 0.3775, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.271472109678379e-06, "epoch": 1.5, "percentage": 75.2, "elapsed_time": "7:25:41", "remaining_time": "2:26:58"}
|
| 216 |
-
{"current_steps": 2060, "total_steps": 2726, "loss": 0.4019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.0695145065334585e-06, "epoch": 1.51, "percentage": 75.57, "elapsed_time": "7:27:36", "remaining_time": "2:24:42"}
|
| 217 |
-
{"current_steps": 2070, "total_steps": 2726, "loss": 0.4143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.869938319483471e-06, "epoch": 1.52, "percentage": 75.94, "elapsed_time": "7:29:45", "remaining_time": "2:22:31"}
|
| 218 |
-
{"current_steps": 2080, "total_steps": 2726, "loss": 0.3853, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.67277005500222e-06, "epoch": 1.53, "percentage": 76.3, "elapsed_time": "7:31:46", "remaining_time": "2:20:18"}
|
| 219 |
-
{"current_steps": 2090, "total_steps": 2726, "loss": 0.4403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.478035899758139e-06, "epoch": 1.53, "percentage": 76.67, "elapsed_time": "7:33:54", "remaining_time": "2:18:07"}
|
| 220 |
-
{"current_steps": 2100, "total_steps": 2726, "loss": 0.3888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.285761717136335e-06, "epoch": 1.54, "percentage": 77.04, "elapsed_time": "7:36:12", "remaining_time": "2:15:59"}
|
| 221 |
-
{"current_steps": 2110, "total_steps": 2726, "loss": 0.4123, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.095973043803577e-06, "epoch": 1.55, "percentage": 77.4, "elapsed_time": "7:38:32", "remaining_time": "2:13:52"}
|
| 222 |
-
{"current_steps": 2120, "total_steps": 2726, "loss": 0.4035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.908695086316701e-06, "epoch": 1.55, "percentage": 77.77, "elapsed_time": "7:40:48", "remaining_time": "2:11:43"}
|
| 223 |
-
{"current_steps": 2130, "total_steps": 2726, "loss": 0.4219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.723952717774763e-06, "epoch": 1.56, "percentage": 78.14, "elapsed_time": "7:42:48", "remaining_time": "2:09:30"}
|
| 224 |
-
{"current_steps": 2140, "total_steps": 2726, "loss": 0.4209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.54177047451562e-06, "epoch": 1.57, "percentage": 78.5, "elapsed_time": "7:44:53", "remaining_time": "2:07:18"}
|
| 225 |
-
{"current_steps": 2150, "total_steps": 2726, "loss": 0.4286, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.362172552857128e-06, "epoch": 1.58, "percentage": 78.87, "elapsed_time": "7:47:02", "remaining_time": "2:05:07"}
|
| 226 |
-
{"current_steps": 2160, "total_steps": 2726, "loss": 0.4134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.18518280588354e-06, "epoch": 1.58, "percentage": 79.24, "elapsed_time": "7:49:04", "remaining_time": "2:02:54"}
|
| 227 |
-
{"current_steps": 2170, "total_steps": 2726, "loss": 0.4005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.010824740277501e-06, "epoch": 1.59, "percentage": 79.6, "elapsed_time": "7:51:12", "remaining_time": "2:00:44"}
|
| 228 |
-
{"current_steps": 2180, "total_steps": 2726, "loss": 0.3973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.83912151319802e-06, "epoch": 1.6, "percentage": 79.97, "elapsed_time": "7:53:12", "remaining_time": "1:58:31"}
|
| 229 |
-
{"current_steps": 2190, "total_steps": 2726, "loss": 0.3959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6700959292048875e-06, "epoch": 1.61, "percentage": 80.34, "elapsed_time": "7:55:29", "remaining_time": "1:56:22"}
|
| 230 |
-
{"current_steps": 2200, "total_steps": 2726, "loss": 0.4017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.503770437229918e-06, "epoch": 1.61, "percentage": 80.7, "elapsed_time": "7:57:38", "remaining_time": "1:54:12"}
|
| 231 |
-
{"current_steps": 2200, "total_steps": 2726, "loss": null, "eval_loss": 0.41970890760421753, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.61, "percentage": 80.7, "elapsed_time": "7:57:38", "remaining_time": "1:54:12"}
|
| 232 |
-
{"current_steps": 2210, "total_steps": 2726, "loss": 0.4013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.340167127595407e-06, "epoch": 1.62, "percentage": 81.07, "elapsed_time": "8:00:51", "remaining_time": "1:52:16"}
|
| 233 |
-
{"current_steps": 2220, "total_steps": 2726, "loss": 0.4069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.179307729080256e-06, "epoch": 1.63, "percentage": 81.44, "elapsed_time": "8:03:00", "remaining_time": "1:50:05"}
|
| 234 |
-
{"current_steps": 2230, "total_steps": 2726, "loss": 0.3857, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.021213606034064e-06, "epoch": 1.64, "percentage": 81.8, "elapsed_time": "8:05:05", "remaining_time": "1:47:53"}
|
| 235 |
-
{"current_steps": 2240, "total_steps": 2726, "loss": 0.4262, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8659057555396645e-06, "epoch": 1.64, "percentage": 82.17, "elapsed_time": "8:07:03", "remaining_time": "1:45:40"}
|
| 236 |
-
{"current_steps": 2250, "total_steps": 2726, "loss": 0.3953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.713404804624418e-06, "epoch": 1.65, "percentage": 82.54, "elapsed_time": "8:09:07", "remaining_time": "1:43:28"}
|
| 237 |
-
{"current_steps": 2260, "total_steps": 2726, "loss": 0.4231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5637310075206544e-06, "epoch": 1.66, "percentage": 82.91, "elapsed_time": "8:11:23", "remaining_time": "1:41:19"}
|
| 238 |
-
{"current_steps": 2270, "total_steps": 2726, "loss": 0.407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.416904242975635e-06, "epoch": 1.66, "percentage": 83.27, "elapsed_time": "8:13:23", "remaining_time": "1:39:06"}
|
| 239 |
-
{"current_steps": 2280, "total_steps": 2726, "loss": 0.4254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2729440116113843e-06, "epoch": 1.67, "percentage": 83.64, "elapsed_time": "8:15:40", "remaining_time": "1:36:57"}
|
| 240 |
-
{"current_steps": 2290, "total_steps": 2726, "loss": 0.4054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.131869433334725e-06, "epoch": 1.68, "percentage": 84.01, "elapsed_time": "8:17:43", "remaining_time": "1:34:45"}
|
| 241 |
-
{"current_steps": 2300, "total_steps": 2726, "loss": 0.3801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9936992447979068e-06, "epoch": 1.69, "percentage": 84.37, "elapsed_time": "8:20:05", "remaining_time": "1:32:37"}
|
| 242 |
-
{"current_steps": 2310, "total_steps": 2726, "loss": 0.4335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8584517969101054e-06, "epoch": 1.69, "percentage": 84.74, "elapsed_time": "8:21:46", "remaining_time": "1:30:21"}
|
| 243 |
-
{"current_steps": 2320, "total_steps": 2726, "loss": 0.412, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7261450524001807e-06, "epoch": 1.7, "percentage": 85.11, "elapsed_time": "8:23:37", "remaining_time": "1:28:08"}
|
| 244 |
-
{"current_steps": 2330, "total_steps": 2726, "loss": 0.4456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.596796583430969e-06, "epoch": 1.71, "percentage": 85.47, "elapsed_time": "8:25:39", "remaining_time": "1:25:56"}
|
| 245 |
-
{"current_steps": 2340, "total_steps": 2726, "loss": 0.3972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.470423569265462e-06, "epoch": 1.72, "percentage": 85.84, "elapsed_time": "8:27:30", "remaining_time": "1:23:43"}
|
| 246 |
-
{"current_steps": 2350, "total_steps": 2726, "loss": 0.3935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.34704279398516e-06, "epoch": 1.72, "percentage": 86.21, "elapsed_time": "8:29:12", "remaining_time": "1:21:28"}
|
| 247 |
-
{"current_steps": 2360, "total_steps": 2726, "loss": 0.3974, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2266706442609226e-06, "epoch": 1.73, "percentage": 86.57, "elapsed_time": "8:31:13", "remaining_time": "1:19:17"}
|
| 248 |
-
{"current_steps": 2370, "total_steps": 2726, "loss": 0.4157, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.109323107176578e-06, "epoch": 1.74, "percentage": 86.94, "elapsed_time": "8:33:31", "remaining_time": "1:17:08"}
|
| 249 |
-
{"current_steps": 2380, "total_steps": 2726, "loss": 0.4379, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9950157681056318e-06, "epoch": 1.75, "percentage": 87.31, "elapsed_time": "8:35:40", "remaining_time": "1:14:58"}
|
| 250 |
-
{"current_steps": 2390, "total_steps": 2726, "loss": 0.4035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8837638086413063e-06, "epoch": 1.75, "percentage": 87.67, "elapsed_time": "8:37:35", "remaining_time": "1:12:46"}
|
| 251 |
-
{"current_steps": 2400, "total_steps": 2726, "loss": 0.4455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7755820045802145e-06, "epoch": 1.76, "percentage": 88.04, "elapsed_time": "8:39:45", "remaining_time": "1:10:35"}
|
| 252 |
-
{"current_steps": 2400, "total_steps": 2726, "loss": null, "eval_loss": 0.41885045170783997, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.76, "percentage": 88.04, "elapsed_time": "8:39:45", "remaining_time": "1:10:35"}
|
| 253 |
-
{"current_steps": 2410, "total_steps": 2726, "loss": 0.4532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6704847239599364e-06, "epoch": 1.77, "percentage": 88.41, "elapsed_time": "8:43:09", "remaining_time": "1:08:35"}
|
| 254 |
-
{"current_steps": 2420, "total_steps": 2726, "loss": 0.4213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5684859251507394e-06, "epoch": 1.77, "percentage": 88.77, "elapsed_time": "8:45:22", "remaining_time": "1:06:25"}
|
| 255 |
-
{"current_steps": 2430, "total_steps": 2726, "loss": 0.3873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4695991550017164e-06, "epoch": 1.78, "percentage": 89.14, "elapsed_time": "8:47:29", "remaining_time": "1:04:15"}
|
| 256 |
-
{"current_steps": 2440, "total_steps": 2726, "loss": 0.4163, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.373837547041576e-06, "epoch": 1.79, "percentage": 89.51, "elapsed_time": "8:49:41", "remaining_time": "1:02:05"}
|
| 257 |
-
{"current_steps": 2450, "total_steps": 2726, "loss": 0.3946, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2812138197343392e-06, "epoch": 1.8, "percentage": 89.88, "elapsed_time": "8:51:48", "remaining_time": "0:59:54"}
|
| 258 |
-
{"current_steps": 2460, "total_steps": 2726, "loss": 0.41, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1917402747901152e-06, "epoch": 1.8, "percentage": 90.24, "elapsed_time": "8:53:44", "remaining_time": "0:57:42"}
|
| 259 |
-
{"current_steps": 2470, "total_steps": 2726, "loss": 0.4126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.105428795531327e-06, "epoch": 1.81, "percentage": 90.61, "elapsed_time": "8:55:59", "remaining_time": "0:55:33"}
|
| 260 |
-
{"current_steps": 2480, "total_steps": 2726, "loss": 0.4505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0222908453143804e-06, "epoch": 1.82, "percentage": 90.98, "elapsed_time": "8:58:09", "remaining_time": "0:53:22"}
|
| 261 |
-
{"current_steps": 2490, "total_steps": 2726, "loss": 0.4303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.423374660072065e-07, "epoch": 1.83, "percentage": 91.34, "elapsed_time": "9:00:00", "remaining_time": "0:51:10"}
|
| 262 |
-
{"current_steps": 2500, "total_steps": 2726, "loss": 0.4179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.655792765227405e-07, "epoch": 1.83, "percentage": 91.71, "elapsed_time": "9:01:58", "remaining_time": "0:48:59"}
|
| 263 |
-
{"current_steps": 2510, "total_steps": 2726, "loss": 0.4376, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.920264714085828e-07, "epoch": 1.84, "percentage": 92.08, "elapsed_time": "9:04:05", "remaining_time": "0:46:49"}
|
| 264 |
-
{"current_steps": 2520, "total_steps": 2726, "loss": 0.4069, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.216888194930272e-07, "epoch": 1.85, "percentage": 92.44, "elapsed_time": "9:06:08", "remaining_time": "0:44:38"}
|
| 265 |
-
{"current_steps": 2530, "total_steps": 2726, "loss": 0.3887, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.545756625876031e-07, "epoch": 1.86, "percentage": 92.81, "elapsed_time": "9:08:12", "remaining_time": "0:42:28"}
|
| 266 |
-
{"current_steps": 2540, "total_steps": 2726, "loss": 0.3972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.906959142463947e-07, "epoch": 1.86, "percentage": 93.18, "elapsed_time": "9:10:08", "remaining_time": "0:40:17"}
|
| 267 |
-
{"current_steps": 2550, "total_steps": 2726, "loss": 0.4078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.300580585821696e-07, "epoch": 1.87, "percentage": 93.54, "elapsed_time": "9:12:17", "remaining_time": "0:38:07"}
|
| 268 |
-
{"current_steps": 2560, "total_steps": 2726, "loss": 0.4467, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7267014913956463e-07, "epoch": 1.88, "percentage": 93.91, "elapsed_time": "9:14:11", "remaining_time": "0:35:56"}
|
| 269 |
-
{"current_steps": 2570, "total_steps": 2726, "loss": 0.4567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1853980782549097e-07, "epoch": 1.88, "percentage": 94.28, "elapsed_time": "9:16:09", "remaining_time": "0:33:45"}
|
| 270 |
-
{"current_steps": 2580, "total_steps": 2726, "loss": 0.4494, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6767422389682173e-07, "epoch": 1.89, "percentage": 94.64, "elapsed_time": "9:18:36", "remaining_time": "0:31:36"}
|
| 271 |
-
{"current_steps": 2590, "total_steps": 2726, "loss": 0.4344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2008015300555306e-07, "epoch": 1.9, "percentage": 95.01, "elapsed_time": "9:20:48", "remaining_time": "0:29:26"}
|
| 272 |
-
{"current_steps": 2600, "total_steps": 2726, "loss": 0.4101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.757639163015774e-07, "epoch": 1.91, "percentage": 95.38, "elapsed_time": "9:22:52", "remaining_time": "0:27:16"}
|
| 273 |
-
{"current_steps": 2600, "total_steps": 2726, "loss": null, "eval_loss": 0.41886425018310547, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.91, "percentage": 95.38, "elapsed_time": "9:22:52", "remaining_time": "0:27:16"}
|
| 274 |
-
{"current_steps": 2610, "total_steps": 2726, "loss": 0.4058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.347313995931466e-07, "epoch": 1.91, "percentage": 95.74, "elapsed_time": "9:26:02", "remaining_time": "0:25:09"}
|
| 275 |
-
{"current_steps": 2620, "total_steps": 2726, "loss": 0.414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9698805256513908e-07, "epoch": 1.92, "percentage": 96.11, "elapsed_time": "9:28:14", "remaining_time": "0:22:59"}
|
| 276 |
-
{"current_steps": 2630, "total_steps": 2726, "loss": 0.4254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6253888805527474e-07, "epoch": 1.93, "percentage": 96.48, "elapsed_time": "9:30:26", "remaining_time": "0:20:49"}
|
| 277 |
-
{"current_steps": 2640, "total_steps": 2726, "loss": 0.4017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3138848138835313e-07, "epoch": 1.94, "percentage": 96.85, "elapsed_time": "9:32:34", "remaining_time": "0:18:39"}
|
| 278 |
-
{"current_steps": 2650, "total_steps": 2726, "loss": 0.4258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0354096976856186e-07, "epoch": 1.94, "percentage": 97.21, "elapsed_time": "9:34:48", "remaining_time": "0:16:29"}
|
| 279 |
-
{"current_steps": 2660, "total_steps": 2726, "loss": 0.4098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.900005173002712e-08, "epoch": 1.95, "percentage": 97.58, "elapsed_time": "9:37:06", "remaining_time": "0:14:19"}
|
| 280 |
-
{"current_steps": 2670, "total_steps": 2726, "loss": 0.42, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.776898664557051e-08, "epoch": 1.96, "percentage": 97.95, "elapsed_time": "9:39:14", "remaining_time": "0:12:08"}
|
| 281 |
-
{"current_steps": 2680, "total_steps": 2726, "loss": 0.3886, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.985059429383875e-08, "epoch": 1.97, "percentage": 98.31, "elapsed_time": "9:41:31", "remaining_time": "0:09:58"}
|
| 282 |
-
{"current_steps": 2690, "total_steps": 2726, "loss": 0.4276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5247254484794813e-08, "epoch": 1.97, "percentage": 98.68, "elapsed_time": "9:43:48", "remaining_time": "0:07:48"}
|
| 283 |
-
{"current_steps": 2700, "total_steps": 2726, "loss": 0.4006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3960906743634706e-08, "epoch": 1.98, "percentage": 99.05, "elapsed_time": "9:45:40", "remaining_time": "0:05:38"}
|
| 284 |
-
{"current_steps": 2710, "total_steps": 2726, "loss": 0.4243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.993050053204607e-09, "epoch": 1.99, "percentage": 99.41, "elapsed_time": "9:47:47", "remaining_time": "0:03:28"}
|
| 285 |
-
{"current_steps": 2720, "total_steps": 2726, "loss": 0.4439, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3447426549129117e-09, "epoch": 1.99, "percentage": 99.78, "elapsed_time": "9:50:02", "remaining_time": "0:01:18"}
|
| 286 |
-
{"current_steps": 2726, "total_steps": 2726, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "9:51:16", "remaining_time": "0:00:00"}
|
| 287 |
-
{"current_steps": 111, "total_steps": 111, "loss": null, "eval_loss": 0.41885045170783997, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "9:52:25", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/trainer_state.json
DELETED
|
@@ -1,1761 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": 0.41885045170783997,
|
| 3 |
-
"best_model_checkpoint": "output/Baichuan-13B-Chat_lora_wqs_nlp/checkpoint-2400",
|
| 4 |
-
"epoch": 1.9992665933259994,
|
| 5 |
-
"global_step": 2726,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.01,
|
| 12 |
-
"learning_rate": 4.999865525734509e-05,
|
| 13 |
-
"loss": 1.5452,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.01,
|
| 18 |
-
"learning_rate": 4.9994621174046976e-05,
|
| 19 |
-
"loss": 1.3291,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.02,
|
| 24 |
-
"learning_rate": 4.9986985231938546e-05,
|
| 25 |
-
"loss": 1.1048,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.03,
|
| 30 |
-
"learning_rate": 4.99760306731191e-05,
|
| 31 |
-
"loss": 0.9155,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.04,
|
| 36 |
-
"learning_rate": 4.9961758952505326e-05,
|
| 37 |
-
"loss": 0.8856,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.04,
|
| 42 |
-
"learning_rate": 4.9944171965578836e-05,
|
| 43 |
-
"loss": 0.8052,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.05,
|
| 48 |
-
"learning_rate": 4.992327204813435e-05,
|
| 49 |
-
"loss": 0.7332,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.06,
|
| 54 |
-
"learning_rate": 4.989906197596955e-05,
|
| 55 |
-
"loss": 0.6982,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.07,
|
| 60 |
-
"learning_rate": 4.987154496451635e-05,
|
| 61 |
-
"loss": 0.6811,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.07,
|
| 66 |
-
"learning_rate": 4.984072466841389e-05,
|
| 67 |
-
"loss": 0.6323,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 0.08,
|
| 72 |
-
"learning_rate": 4.981016546765289e-05,
|
| 73 |
-
"loss": 0.6234,
|
| 74 |
-
"step": 110
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 0.09,
|
| 78 |
-
"learning_rate": 4.977308057009269e-05,
|
| 79 |
-
"loss": 0.6125,
|
| 80 |
-
"step": 120
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 0.1,
|
| 84 |
-
"learning_rate": 4.97327054653146e-05,
|
| 85 |
-
"loss": 0.5977,
|
| 86 |
-
"step": 130
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.1,
|
| 90 |
-
"learning_rate": 4.968904551569013e-05,
|
| 91 |
-
"loss": 0.6179,
|
| 92 |
-
"step": 140
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.11,
|
| 96 |
-
"learning_rate": 4.9642106519863544e-05,
|
| 97 |
-
"loss": 0.5879,
|
| 98 |
-
"step": 150
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.12,
|
| 102 |
-
"learning_rate": 4.959189471198171e-05,
|
| 103 |
-
"loss": 0.5472,
|
| 104 |
-
"step": 160
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 0.12,
|
| 108 |
-
"learning_rate": 4.953841676086613e-05,
|
| 109 |
-
"loss": 0.602,
|
| 110 |
-
"step": 170
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 0.13,
|
| 114 |
-
"learning_rate": 4.9481679769127275e-05,
|
| 115 |
-
"loss": 0.5773,
|
| 116 |
-
"step": 180
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.14,
|
| 120 |
-
"learning_rate": 4.9421691272221167e-05,
|
| 121 |
-
"loss": 0.5615,
|
| 122 |
-
"step": 190
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.15,
|
| 126 |
-
"learning_rate": 4.935845923744865e-05,
|
| 127 |
-
"loss": 0.5704,
|
| 128 |
-
"step": 200
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.15,
|
| 132 |
-
"eval_loss": 0.5564362406730652,
|
| 133 |
-
"eval_runtime": 72.9469,
|
| 134 |
-
"eval_samples_per_second": 15.107,
|
| 135 |
-
"eval_steps_per_second": 1.522,
|
| 136 |
-
"step": 200
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.15,
|
| 140 |
-
"learning_rate": 4.9291992062897183e-05,
|
| 141 |
-
"loss": 0.5803,
|
| 142 |
-
"step": 210
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.16,
|
| 146 |
-
"learning_rate": 4.922229857632545e-05,
|
| 147 |
-
"loss": 0.5655,
|
| 148 |
-
"step": 220
|
| 149 |
-
},
|
| 150 |
-
{
|
| 151 |
-
"epoch": 0.17,
|
| 152 |
-
"learning_rate": 4.9149388033990966e-05,
|
| 153 |
-
"loss": 0.5769,
|
| 154 |
-
"step": 230
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 0.18,
|
| 158 |
-
"learning_rate": 4.9073270119420635e-05,
|
| 159 |
-
"loss": 0.5862,
|
| 160 |
-
"step": 240
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 0.18,
|
| 164 |
-
"learning_rate": 4.899395494212471e-05,
|
| 165 |
-
"loss": 0.5506,
|
| 166 |
-
"step": 250
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"epoch": 0.19,
|
| 170 |
-
"learning_rate": 4.891145303625408e-05,
|
| 171 |
-
"loss": 0.5183,
|
| 172 |
-
"step": 260
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.2,
|
| 176 |
-
"learning_rate": 4.882577535920121e-05,
|
| 177 |
-
"loss": 0.575,
|
| 178 |
-
"step": 270
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.21,
|
| 182 |
-
"learning_rate": 4.8736933290144815e-05,
|
| 183 |
-
"loss": 0.5359,
|
| 184 |
-
"step": 280
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.21,
|
| 188 |
-
"learning_rate": 4.8644938628538606e-05,
|
| 189 |
-
"loss": 0.5302,
|
| 190 |
-
"step": 290
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 0.22,
|
| 194 |
-
"learning_rate": 4.8549803592544076e-05,
|
| 195 |
-
"loss": 0.5399,
|
| 196 |
-
"step": 300
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 0.23,
|
| 200 |
-
"learning_rate": 4.845154081740783e-05,
|
| 201 |
-
"loss": 0.5379,
|
| 202 |
-
"step": 310
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"epoch": 0.23,
|
| 206 |
-
"learning_rate": 4.835016335378343e-05,
|
| 207 |
-
"loss": 0.5299,
|
| 208 |
-
"step": 320
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"epoch": 0.24,
|
| 212 |
-
"learning_rate": 4.8245684665998073e-05,
|
| 213 |
-
"loss": 0.535,
|
| 214 |
-
"step": 330
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.25,
|
| 218 |
-
"learning_rate": 4.813811863026436e-05,
|
| 219 |
-
"loss": 0.5145,
|
| 220 |
-
"step": 340
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.26,
|
| 224 |
-
"learning_rate": 4.802747953283732e-05,
|
| 225 |
-
"loss": 0.5126,
|
| 226 |
-
"step": 350
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 0.26,
|
| 230 |
-
"learning_rate": 4.791378206811704e-05,
|
| 231 |
-
"loss": 0.5012,
|
| 232 |
-
"step": 360
|
| 233 |
-
},
|
| 234 |
-
{
|
| 235 |
-
"epoch": 0.27,
|
| 236 |
-
"learning_rate": 4.7797041336696995e-05,
|
| 237 |
-
"loss": 0.5373,
|
| 238 |
-
"step": 370
|
| 239 |
-
},
|
| 240 |
-
{
|
| 241 |
-
"epoch": 0.28,
|
| 242 |
-
"learning_rate": 4.767727284335852e-05,
|
| 243 |
-
"loss": 0.4778,
|
| 244 |
-
"step": 380
|
| 245 |
-
},
|
| 246 |
-
{
|
| 247 |
-
"epoch": 0.29,
|
| 248 |
-
"learning_rate": 4.755449249501155e-05,
|
| 249 |
-
"loss": 0.4894,
|
| 250 |
-
"step": 390
|
| 251 |
-
},
|
| 252 |
-
{
|
| 253 |
-
"epoch": 0.29,
|
| 254 |
-
"learning_rate": 4.7428716598581934e-05,
|
| 255 |
-
"loss": 0.4986,
|
| 256 |
-
"step": 400
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.29,
|
| 260 |
-
"eval_loss": 0.4967592656612396,
|
| 261 |
-
"eval_runtime": 70.0948,
|
| 262 |
-
"eval_samples_per_second": 15.722,
|
| 263 |
-
"eval_steps_per_second": 1.584,
|
| 264 |
-
"step": 400
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 0.3,
|
| 268 |
-
"learning_rate": 4.729996185884571e-05,
|
| 269 |
-
"loss": 0.4928,
|
| 270 |
-
"step": 410
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.31,
|
| 274 |
-
"learning_rate": 4.716824537621042e-05,
|
| 275 |
-
"loss": 0.4807,
|
| 276 |
-
"step": 420
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.32,
|
| 280 |
-
"learning_rate": 4.703358464444397e-05,
|
| 281 |
-
"loss": 0.4734,
|
| 282 |
-
"step": 430
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 0.32,
|
| 286 |
-
"learning_rate": 4.689599754835122e-05,
|
| 287 |
-
"loss": 0.4603,
|
| 288 |
-
"step": 440
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 0.33,
|
| 292 |
-
"learning_rate": 4.6755502361398616e-05,
|
| 293 |
-
"loss": 0.4661,
|
| 294 |
-
"step": 450
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.34,
|
| 298 |
-
"learning_rate": 4.6612117743287234e-05,
|
| 299 |
-
"loss": 0.5072,
|
| 300 |
-
"step": 460
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.34,
|
| 304 |
-
"learning_rate": 4.646586273747452e-05,
|
| 305 |
-
"loss": 0.5056,
|
| 306 |
-
"step": 470
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 0.35,
|
| 310 |
-
"learning_rate": 4.631675676864503e-05,
|
| 311 |
-
"loss": 0.4391,
|
| 312 |
-
"step": 480
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 0.36,
|
| 316 |
-
"learning_rate": 4.6164819640130595e-05,
|
| 317 |
-
"loss": 0.483,
|
| 318 |
-
"step": 490
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 0.37,
|
| 322 |
-
"learning_rate": 4.601007153128014e-05,
|
| 323 |
-
"loss": 0.4774,
|
| 324 |
-
"step": 500
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.37,
|
| 328 |
-
"learning_rate": 4.5852532994779606e-05,
|
| 329 |
-
"loss": 0.4848,
|
| 330 |
-
"step": 510
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 0.38,
|
| 334 |
-
"learning_rate": 4.5692224953922266e-05,
|
| 335 |
-
"loss": 0.5099,
|
| 336 |
-
"step": 520
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 0.39,
|
| 340 |
-
"learning_rate": 4.5529168699829805e-05,
|
| 341 |
-
"loss": 0.4851,
|
| 342 |
-
"step": 530
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 0.4,
|
| 346 |
-
"learning_rate": 4.536338588862459e-05,
|
| 347 |
-
"loss": 0.498,
|
| 348 |
-
"step": 540
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.4,
|
| 352 |
-
"learning_rate": 4.519489853855341e-05,
|
| 353 |
-
"loss": 0.5398,
|
| 354 |
-
"step": 550
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 0.41,
|
| 358 |
-
"learning_rate": 4.50237290270632e-05,
|
| 359 |
-
"loss": 0.4566,
|
| 360 |
-
"step": 560
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.42,
|
| 364 |
-
"learning_rate": 4.484990008782893e-05,
|
| 365 |
-
"loss": 0.4942,
|
| 366 |
-
"step": 570
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 0.43,
|
| 370 |
-
"learning_rate": 4.467343480773433e-05,
|
| 371 |
-
"loss": 0.4625,
|
| 372 |
-
"step": 580
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 0.43,
|
| 376 |
-
"learning_rate": 4.44943566238056e-05,
|
| 377 |
-
"loss": 0.4703,
|
| 378 |
-
"step": 590
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 0.44,
|
| 382 |
-
"learning_rate": 4.431268932009865e-05,
|
| 383 |
-
"loss": 0.464,
|
| 384 |
-
"step": 600
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 0.44,
|
| 388 |
-
"eval_loss": 0.46821752190589905,
|
| 389 |
-
"eval_runtime": 69.9505,
|
| 390 |
-
"eval_samples_per_second": 15.754,
|
| 391 |
-
"eval_steps_per_second": 1.587,
|
| 392 |
-
"step": 600
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 0.45,
|
| 396 |
-
"learning_rate": 4.412845702454024e-05,
|
| 397 |
-
"loss": 0.4739,
|
| 398 |
-
"step": 610
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 0.45,
|
| 402 |
-
"learning_rate": 4.394168420572349e-05,
|
| 403 |
-
"loss": 0.4529,
|
| 404 |
-
"step": 620
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 0.46,
|
| 408 |
-
"learning_rate": 4.3752395669658086e-05,
|
| 409 |
-
"loss": 0.4433,
|
| 410 |
-
"step": 630
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.47,
|
| 414 |
-
"learning_rate": 4.356061655647571e-05,
|
| 415 |
-
"loss": 0.459,
|
| 416 |
-
"step": 640
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.48,
|
| 420 |
-
"learning_rate": 4.336637233709107e-05,
|
| 421 |
-
"loss": 0.4877,
|
| 422 |
-
"step": 650
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 0.48,
|
| 426 |
-
"learning_rate": 4.316968880981903e-05,
|
| 427 |
-
"loss": 0.4676,
|
| 428 |
-
"step": 660
|
| 429 |
-
},
|
| 430 |
-
{
|
| 431 |
-
"epoch": 0.49,
|
| 432 |
-
"learning_rate": 4.2970592096948236e-05,
|
| 433 |
-
"loss": 0.4782,
|
| 434 |
-
"step": 670
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 0.5,
|
| 438 |
-
"learning_rate": 4.276910864127168e-05,
|
| 439 |
-
"loss": 0.4778,
|
| 440 |
-
"step": 680
|
| 441 |
-
},
|
| 442 |
-
{
|
| 443 |
-
"epoch": 0.51,
|
| 444 |
-
"learning_rate": 4.25652652025748e-05,
|
| 445 |
-
"loss": 0.454,
|
| 446 |
-
"step": 690
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 0.51,
|
| 450 |
-
"learning_rate": 4.235908885408133e-05,
|
| 451 |
-
"loss": 0.4399,
|
| 452 |
-
"step": 700
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 0.52,
|
| 456 |
-
"learning_rate": 4.215060697885767e-05,
|
| 457 |
-
"loss": 0.5106,
|
| 458 |
-
"step": 710
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 0.53,
|
| 462 |
-
"learning_rate": 4.1939847266176e-05,
|
| 463 |
-
"loss": 0.4683,
|
| 464 |
-
"step": 720
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 0.54,
|
| 468 |
-
"learning_rate": 4.172683770783677e-05,
|
| 469 |
-
"loss": 0.4896,
|
| 470 |
-
"step": 730
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.54,
|
| 474 |
-
"learning_rate": 4.1511606594451016e-05,
|
| 475 |
-
"loss": 0.4633,
|
| 476 |
-
"step": 740
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 0.55,
|
| 480 |
-
"learning_rate": 4.1294182511682946e-05,
|
| 481 |
-
"loss": 0.4486,
|
| 482 |
-
"step": 750
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 0.56,
|
| 486 |
-
"learning_rate": 4.1074594336453384e-05,
|
| 487 |
-
"loss": 0.4706,
|
| 488 |
-
"step": 760
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 0.56,
|
| 492 |
-
"learning_rate": 4.085287123310455e-05,
|
| 493 |
-
"loss": 0.4797,
|
| 494 |
-
"step": 770
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.57,
|
| 498 |
-
"learning_rate": 4.062904264952657e-05,
|
| 499 |
-
"loss": 0.4251,
|
| 500 |
-
"step": 780
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.58,
|
| 504 |
-
"learning_rate": 4.0403138313246435e-05,
|
| 505 |
-
"loss": 0.4687,
|
| 506 |
-
"step": 790
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 0.59,
|
| 510 |
-
"learning_rate": 4.017518822747976e-05,
|
| 511 |
-
"loss": 0.48,
|
| 512 |
-
"step": 800
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 0.59,
|
| 516 |
-
"eval_loss": 0.4554018974304199,
|
| 517 |
-
"eval_runtime": 70.2392,
|
| 518 |
-
"eval_samples_per_second": 15.689,
|
| 519 |
-
"eval_steps_per_second": 1.58,
|
| 520 |
-
"step": 800
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 0.59,
|
| 524 |
-
"learning_rate": 3.994522266714594e-05,
|
| 525 |
-
"loss": 0.4662,
|
| 526 |
-
"step": 810
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 0.6,
|
| 530 |
-
"learning_rate": 3.9713272174847246e-05,
|
| 531 |
-
"loss": 0.4837,
|
| 532 |
-
"step": 820
|
| 533 |
-
},
|
| 534 |
-
{
|
| 535 |
-
"epoch": 0.61,
|
| 536 |
-
"learning_rate": 3.947936755681229e-05,
|
| 537 |
-
"loss": 0.5014,
|
| 538 |
-
"step": 830
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 0.62,
|
| 542 |
-
"learning_rate": 3.92435398788046e-05,
|
| 543 |
-
"loss": 0.4764,
|
| 544 |
-
"step": 840
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 0.62,
|
| 548 |
-
"learning_rate": 3.9005820461996604e-05,
|
| 549 |
-
"loss": 0.4587,
|
| 550 |
-
"step": 850
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 0.63,
|
| 554 |
-
"learning_rate": 3.876624087880979e-05,
|
| 555 |
-
"loss": 0.484,
|
| 556 |
-
"step": 860
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 0.64,
|
| 560 |
-
"learning_rate": 3.85248329487214e-05,
|
| 561 |
-
"loss": 0.4285,
|
| 562 |
-
"step": 870
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 0.65,
|
| 566 |
-
"learning_rate": 3.828162873403843e-05,
|
| 567 |
-
"loss": 0.4742,
|
| 568 |
-
"step": 880
|
| 569 |
-
},
|
| 570 |
-
{
|
| 571 |
-
"epoch": 0.65,
|
| 572 |
-
"learning_rate": 3.803666053563926e-05,
|
| 573 |
-
"loss": 0.4533,
|
| 574 |
-
"step": 890
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 0.66,
|
| 578 |
-
"learning_rate": 3.778996088868365e-05,
|
| 579 |
-
"loss": 0.4395,
|
| 580 |
-
"step": 900
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 0.67,
|
| 584 |
-
"learning_rate": 3.754156255829167e-05,
|
| 585 |
-
"loss": 0.4519,
|
| 586 |
-
"step": 910
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 0.67,
|
| 590 |
-
"learning_rate": 3.7291498535191996e-05,
|
| 591 |
-
"loss": 0.4684,
|
| 592 |
-
"step": 920
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 0.68,
|
| 596 |
-
"learning_rate": 3.703980203134029e-05,
|
| 597 |
-
"loss": 0.4259,
|
| 598 |
-
"step": 930
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"epoch": 0.69,
|
| 602 |
-
"learning_rate": 3.678650647550822e-05,
|
| 603 |
-
"loss": 0.4576,
|
| 604 |
-
"step": 940
|
| 605 |
-
},
|
| 606 |
-
{
|
| 607 |
-
"epoch": 0.7,
|
| 608 |
-
"learning_rate": 3.6531645508843636e-05,
|
| 609 |
-
"loss": 0.446,
|
| 610 |
-
"step": 950
|
| 611 |
-
},
|
| 612 |
-
{
|
| 613 |
-
"epoch": 0.7,
|
| 614 |
-
"learning_rate": 3.6275252980402544e-05,
|
| 615 |
-
"loss": 0.4439,
|
| 616 |
-
"step": 960
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 0.71,
|
| 620 |
-
"learning_rate": 3.601736294265354e-05,
|
| 621 |
-
"loss": 0.476,
|
| 622 |
-
"step": 970
|
| 623 |
-
},
|
| 624 |
-
{
|
| 625 |
-
"epoch": 0.72,
|
| 626 |
-
"learning_rate": 3.5758009646955115e-05,
|
| 627 |
-
"loss": 0.4153,
|
| 628 |
-
"step": 980
|
| 629 |
-
},
|
| 630 |
-
{
|
| 631 |
-
"epoch": 0.73,
|
| 632 |
-
"learning_rate": 3.5497227539006614e-05,
|
| 633 |
-
"loss": 0.4444,
|
| 634 |
-
"step": 990
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 0.73,
|
| 638 |
-
"learning_rate": 3.523505125427341e-05,
|
| 639 |
-
"loss": 0.4395,
|
| 640 |
-
"step": 1000
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 0.73,
|
| 644 |
-
"eval_loss": 0.44357746839523315,
|
| 645 |
-
"eval_runtime": 70.1513,
|
| 646 |
-
"eval_samples_per_second": 15.709,
|
| 647 |
-
"eval_steps_per_second": 1.582,
|
| 648 |
-
"step": 1000
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 0.74,
|
| 652 |
-
"learning_rate": 3.497151561338678e-05,
|
| 653 |
-
"loss": 0.4387,
|
| 654 |
-
"step": 1010
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 0.75,
|
| 658 |
-
"learning_rate": 3.470665561751928e-05,
|
| 659 |
-
"loss": 0.4559,
|
| 660 |
-
"step": 1020
|
| 661 |
-
},
|
| 662 |
-
{
|
| 663 |
-
"epoch": 0.76,
|
| 664 |
-
"learning_rate": 3.444050644373611e-05,
|
| 665 |
-
"loss": 0.4349,
|
| 666 |
-
"step": 1030
|
| 667 |
-
},
|
| 668 |
-
{
|
| 669 |
-
"epoch": 0.76,
|
| 670 |
-
"learning_rate": 3.417310344032309e-05,
|
| 671 |
-
"loss": 0.4661,
|
| 672 |
-
"step": 1040
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 0.77,
|
| 676 |
-
"learning_rate": 3.390448212209191e-05,
|
| 677 |
-
"loss": 0.4945,
|
| 678 |
-
"step": 1050
|
| 679 |
-
},
|
| 680 |
-
{
|
| 681 |
-
"epoch": 0.78,
|
| 682 |
-
"learning_rate": 3.3634678165663325e-05,
|
| 683 |
-
"loss": 0.4399,
|
| 684 |
-
"step": 1060
|
| 685 |
-
},
|
| 686 |
-
{
|
| 687 |
-
"epoch": 0.78,
|
| 688 |
-
"learning_rate": 3.336372740472877e-05,
|
| 689 |
-
"loss": 0.4399,
|
| 690 |
-
"step": 1070
|
| 691 |
-
},
|
| 692 |
-
{
|
| 693 |
-
"epoch": 0.79,
|
| 694 |
-
"learning_rate": 3.309166582529114e-05,
|
| 695 |
-
"loss": 0.4251,
|
| 696 |
-
"step": 1080
|
| 697 |
-
},
|
| 698 |
-
{
|
| 699 |
-
"epoch": 0.8,
|
| 700 |
-
"learning_rate": 3.281852956088537e-05,
|
| 701 |
-
"loss": 0.4385,
|
| 702 |
-
"step": 1090
|
| 703 |
-
},
|
| 704 |
-
{
|
| 705 |
-
"epoch": 0.81,
|
| 706 |
-
"learning_rate": 3.254435488777941e-05,
|
| 707 |
-
"loss": 0.4566,
|
| 708 |
-
"step": 1100
|
| 709 |
-
},
|
| 710 |
-
{
|
| 711 |
-
"epoch": 0.81,
|
| 712 |
-
"learning_rate": 3.226917822015623e-05,
|
| 713 |
-
"loss": 0.4352,
|
| 714 |
-
"step": 1110
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 0.82,
|
| 718 |
-
"learning_rate": 3.199303610527749e-05,
|
| 719 |
-
"loss": 0.4617,
|
| 720 |
-
"step": 1120
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 0.83,
|
| 724 |
-
"learning_rate": 3.1715965218629595e-05,
|
| 725 |
-
"loss": 0.476,
|
| 726 |
-
"step": 1130
|
| 727 |
-
},
|
| 728 |
-
{
|
| 729 |
-
"epoch": 0.84,
|
| 730 |
-
"learning_rate": 3.143800235905268e-05,
|
| 731 |
-
"loss": 0.4322,
|
| 732 |
-
"step": 1140
|
| 733 |
-
},
|
| 734 |
-
{
|
| 735 |
-
"epoch": 0.84,
|
| 736 |
-
"learning_rate": 3.115918444385315e-05,
|
| 737 |
-
"loss": 0.4736,
|
| 738 |
-
"step": 1150
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 0.85,
|
| 742 |
-
"learning_rate": 3.0879548503900665e-05,
|
| 743 |
-
"loss": 0.4322,
|
| 744 |
-
"step": 1160
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 0.86,
|
| 748 |
-
"learning_rate": 3.0599131678709836e-05,
|
| 749 |
-
"loss": 0.4152,
|
| 750 |
-
"step": 1170
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 0.87,
|
| 754 |
-
"learning_rate": 3.031797121150764e-05,
|
| 755 |
-
"loss": 0.4187,
|
| 756 |
-
"step": 1180
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 0.87,
|
| 760 |
-
"learning_rate": 3.0036104444286954e-05,
|
| 761 |
-
"loss": 0.4331,
|
| 762 |
-
"step": 1190
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 0.88,
|
| 766 |
-
"learning_rate": 2.9753568812847065e-05,
|
| 767 |
-
"loss": 0.45,
|
| 768 |
-
"step": 1200
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 0.88,
|
| 772 |
-
"eval_loss": 0.43782830238342285,
|
| 773 |
-
"eval_runtime": 70.0939,
|
| 774 |
-
"eval_samples_per_second": 15.722,
|
| 775 |
-
"eval_steps_per_second": 1.584,
|
| 776 |
-
"step": 1200
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 0.89,
|
| 780 |
-
"learning_rate": 2.9470401841821686e-05,
|
| 781 |
-
"loss": 0.4457,
|
| 782 |
-
"step": 1210
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 0.89,
|
| 786 |
-
"learning_rate": 2.9186641139695108e-05,
|
| 787 |
-
"loss": 0.4667,
|
| 788 |
-
"step": 1220
|
| 789 |
-
},
|
| 790 |
-
{
|
| 791 |
-
"epoch": 0.9,
|
| 792 |
-
"learning_rate": 2.8902324393807333e-05,
|
| 793 |
-
"loss": 0.4516,
|
| 794 |
-
"step": 1230
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 0.91,
|
| 798 |
-
"learning_rate": 2.861748936534867e-05,
|
| 799 |
-
"loss": 0.4695,
|
| 800 |
-
"step": 1240
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 0.92,
|
| 804 |
-
"learning_rate": 2.8332173884344477e-05,
|
| 805 |
-
"loss": 0.45,
|
| 806 |
-
"step": 1250
|
| 807 |
-
},
|
| 808 |
-
{
|
| 809 |
-
"epoch": 0.92,
|
| 810 |
-
"learning_rate": 2.8046415844630857e-05,
|
| 811 |
-
"loss": 0.4246,
|
| 812 |
-
"step": 1260
|
| 813 |
-
},
|
| 814 |
-
{
|
| 815 |
-
"epoch": 0.93,
|
| 816 |
-
"learning_rate": 2.7760253198821822e-05,
|
| 817 |
-
"loss": 0.4449,
|
| 818 |
-
"step": 1270
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 0.94,
|
| 822 |
-
"learning_rate": 2.7473723953268687e-05,
|
| 823 |
-
"loss": 0.4217,
|
| 824 |
-
"step": 1280
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 0.95,
|
| 828 |
-
"learning_rate": 2.7186866163012232e-05,
|
| 829 |
-
"loss": 0.4495,
|
| 830 |
-
"step": 1290
|
| 831 |
-
},
|
| 832 |
-
{
|
| 833 |
-
"epoch": 0.95,
|
| 834 |
-
"learning_rate": 2.6899717926728535e-05,
|
| 835 |
-
"loss": 0.4523,
|
| 836 |
-
"step": 1300
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 0.96,
|
| 840 |
-
"learning_rate": 2.6612317381668915e-05,
|
| 841 |
-
"loss": 0.4523,
|
| 842 |
-
"step": 1310
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 0.97,
|
| 846 |
-
"learning_rate": 2.632470269859478e-05,
|
| 847 |
-
"loss": 0.45,
|
| 848 |
-
"step": 1320
|
| 849 |
-
},
|
| 850 |
-
{
|
| 851 |
-
"epoch": 0.98,
|
| 852 |
-
"learning_rate": 2.603691207670803e-05,
|
| 853 |
-
"loss": 0.4371,
|
| 854 |
-
"step": 1330
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 0.98,
|
| 858 |
-
"learning_rate": 2.5748983738577653e-05,
|
| 859 |
-
"loss": 0.4221,
|
| 860 |
-
"step": 1340
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 0.99,
|
| 864 |
-
"learning_rate": 2.5460955925063268e-05,
|
| 865 |
-
"loss": 0.4565,
|
| 866 |
-
"step": 1350
|
| 867 |
-
},
|
| 868 |
-
{
|
| 869 |
-
"epoch": 1.0,
|
| 870 |
-
"learning_rate": 2.5172866890236203e-05,
|
| 871 |
-
"loss": 0.3892,
|
| 872 |
-
"step": 1360
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 1.0,
|
| 876 |
-
"learning_rate": 2.48847548962988e-05,
|
| 877 |
-
"loss": 0.3973,
|
| 878 |
-
"step": 1370
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 1.01,
|
| 882 |
-
"learning_rate": 2.4596658208502713e-05,
|
| 883 |
-
"loss": 0.4151,
|
| 884 |
-
"step": 1380
|
| 885 |
-
},
|
| 886 |
-
{
|
| 887 |
-
"epoch": 1.02,
|
| 888 |
-
"learning_rate": 2.4308615090066735e-05,
|
| 889 |
-
"loss": 0.3839,
|
| 890 |
-
"step": 1390
|
| 891 |
-
},
|
| 892 |
-
{
|
| 893 |
-
"epoch": 1.03,
|
| 894 |
-
"learning_rate": 2.4020663797094864e-05,
|
| 895 |
-
"loss": 0.4062,
|
| 896 |
-
"step": 1400
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 1.03,
|
| 900 |
-
"eval_loss": 0.43284282088279724,
|
| 901 |
-
"eval_runtime": 70.1658,
|
| 902 |
-
"eval_samples_per_second": 15.706,
|
| 903 |
-
"eval_steps_per_second": 1.582,
|
| 904 |
-
"step": 1400
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"epoch": 1.03,
|
| 908 |
-
"learning_rate": 2.373284257349544e-05,
|
| 909 |
-
"loss": 0.4003,
|
| 910 |
-
"step": 1410
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 1.04,
|
| 914 |
-
"learning_rate": 2.3445189645901806e-05,
|
| 915 |
-
"loss": 0.4447,
|
| 916 |
-
"step": 1420
|
| 917 |
-
},
|
| 918 |
-
{
|
| 919 |
-
"epoch": 1.05,
|
| 920 |
-
"learning_rate": 2.3157743218595247e-05,
|
| 921 |
-
"loss": 0.4565,
|
| 922 |
-
"step": 1430
|
| 923 |
-
},
|
| 924 |
-
{
|
| 925 |
-
"epoch": 1.06,
|
| 926 |
-
"learning_rate": 2.287054146843097e-05,
|
| 927 |
-
"loss": 0.4265,
|
| 928 |
-
"step": 1440
|
| 929 |
-
},
|
| 930 |
-
{
|
| 931 |
-
"epoch": 1.06,
|
| 932 |
-
"learning_rate": 2.2583622539767668e-05,
|
| 933 |
-
"loss": 0.4056,
|
| 934 |
-
"step": 1450
|
| 935 |
-
},
|
| 936 |
-
{
|
| 937 |
-
"epoch": 1.07,
|
| 938 |
-
"learning_rate": 2.2297024539401463e-05,
|
| 939 |
-
"loss": 0.4074,
|
| 940 |
-
"step": 1460
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 1.08,
|
| 944 |
-
"learning_rate": 2.2010785531504716e-05,
|
| 945 |
-
"loss": 0.4281,
|
| 946 |
-
"step": 1470
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 1.09,
|
| 950 |
-
"learning_rate": 2.172494353257066e-05,
|
| 951 |
-
"loss": 0.4663,
|
| 952 |
-
"step": 1480
|
| 953 |
-
},
|
| 954 |
-
{
|
| 955 |
-
"epoch": 1.09,
|
| 956 |
-
"learning_rate": 2.1439536506364274e-05,
|
| 957 |
-
"loss": 0.4281,
|
| 958 |
-
"step": 1490
|
| 959 |
-
},
|
| 960 |
-
{
|
| 961 |
-
"epoch": 1.1,
|
| 962 |
-
"learning_rate": 2.1154602358880122e-05,
|
| 963 |
-
"loss": 0.4111,
|
| 964 |
-
"step": 1500
|
| 965 |
-
},
|
| 966 |
-
{
|
| 967 |
-
"epoch": 1.11,
|
| 968 |
-
"learning_rate": 2.0870178933307948e-05,
|
| 969 |
-
"loss": 0.4187,
|
| 970 |
-
"step": 1510
|
| 971 |
-
},
|
| 972 |
-
{
|
| 973 |
-
"epoch": 1.11,
|
| 974 |
-
"learning_rate": 2.0586304005006585e-05,
|
| 975 |
-
"loss": 0.3964,
|
| 976 |
-
"step": 1520
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 1.12,
|
| 980 |
-
"learning_rate": 2.030301527648684e-05,
|
| 981 |
-
"loss": 0.4331,
|
| 982 |
-
"step": 1530
|
| 983 |
-
},
|
| 984 |
-
{
|
| 985 |
-
"epoch": 1.13,
|
| 986 |
-
"learning_rate": 2.0020350372404102e-05,
|
| 987 |
-
"loss": 0.4432,
|
| 988 |
-
"step": 1540
|
| 989 |
-
},
|
| 990 |
-
{
|
| 991 |
-
"epoch": 1.14,
|
| 992 |
-
"learning_rate": 1.9738346834561254e-05,
|
| 993 |
-
"loss": 0.4056,
|
| 994 |
-
"step": 1550
|
| 995 |
-
},
|
| 996 |
-
{
|
| 997 |
-
"epoch": 1.14,
|
| 998 |
-
"learning_rate": 1.945704211692262e-05,
|
| 999 |
-
"loss": 0.4354,
|
| 1000 |
-
"step": 1560
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"epoch": 1.15,
|
| 1004 |
-
"learning_rate": 1.9176473580639538e-05,
|
| 1005 |
-
"loss": 0.4309,
|
| 1006 |
-
"step": 1570
|
| 1007 |
-
},
|
| 1008 |
-
{
|
| 1009 |
-
"epoch": 1.16,
|
| 1010 |
-
"learning_rate": 1.8896678489088304e-05,
|
| 1011 |
-
"loss": 0.4058,
|
| 1012 |
-
"step": 1580
|
| 1013 |
-
},
|
| 1014 |
-
{
|
| 1015 |
-
"epoch": 1.17,
|
| 1016 |
-
"learning_rate": 1.8617694002921064e-05,
|
| 1017 |
-
"loss": 0.4319,
|
| 1018 |
-
"step": 1590
|
| 1019 |
-
},
|
| 1020 |
-
{
|
| 1021 |
-
"epoch": 1.17,
|
| 1022 |
-
"learning_rate": 1.8339557175130383e-05,
|
| 1023 |
-
"loss": 0.4267,
|
| 1024 |
-
"step": 1600
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 1.17,
|
| 1028 |
-
"eval_loss": 0.42894992232322693,
|
| 1029 |
-
"eval_runtime": 70.251,
|
| 1030 |
-
"eval_samples_per_second": 15.687,
|
| 1031 |
-
"eval_steps_per_second": 1.58,
|
| 1032 |
-
"step": 1600
|
| 1033 |
-
},
|
| 1034 |
-
{
|
| 1035 |
-
"epoch": 1.18,
|
| 1036 |
-
"learning_rate": 1.8062304946128073e-05,
|
| 1037 |
-
"loss": 0.3921,
|
| 1038 |
-
"step": 1610
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 1.19,
|
| 1042 |
-
"learning_rate": 1.7785974138839018e-05,
|
| 1043 |
-
"loss": 0.4206,
|
| 1044 |
-
"step": 1620
|
| 1045 |
-
},
|
| 1046 |
-
{
|
| 1047 |
-
"epoch": 1.2,
|
| 1048 |
-
"learning_rate": 1.7510601453810594e-05,
|
| 1049 |
-
"loss": 0.4356,
|
| 1050 |
-
"step": 1630
|
| 1051 |
-
},
|
| 1052 |
-
{
|
| 1053 |
-
"epoch": 1.2,
|
| 1054 |
-
"learning_rate": 1.723622346433828e-05,
|
| 1055 |
-
"loss": 0.4167,
|
| 1056 |
-
"step": 1640
|
| 1057 |
-
},
|
| 1058 |
-
{
|
| 1059 |
-
"epoch": 1.21,
|
| 1060 |
-
"learning_rate": 1.6962876611608262e-05,
|
| 1061 |
-
"loss": 0.4233,
|
| 1062 |
-
"step": 1650
|
| 1063 |
-
},
|
| 1064 |
-
{
|
| 1065 |
-
"epoch": 1.22,
|
| 1066 |
-
"learning_rate": 1.6690597199857523e-05,
|
| 1067 |
-
"loss": 0.4176,
|
| 1068 |
-
"step": 1660
|
| 1069 |
-
},
|
| 1070 |
-
{
|
| 1071 |
-
"epoch": 1.22,
|
| 1072 |
-
"learning_rate": 1.6419421391552142e-05,
|
| 1073 |
-
"loss": 0.4241,
|
| 1074 |
-
"step": 1670
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 1.23,
|
| 1078 |
-
"learning_rate": 1.6149385202584423e-05,
|
| 1079 |
-
"loss": 0.4524,
|
| 1080 |
-
"step": 1680
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 1.24,
|
| 1084 |
-
"learning_rate": 1.5880524497489474e-05,
|
| 1085 |
-
"loss": 0.4647,
|
| 1086 |
-
"step": 1690
|
| 1087 |
-
},
|
| 1088 |
-
{
|
| 1089 |
-
"epoch": 1.25,
|
| 1090 |
-
"learning_rate": 1.5612874984681923e-05,
|
| 1091 |
-
"loss": 0.4036,
|
| 1092 |
-
"step": 1700
|
| 1093 |
-
},
|
| 1094 |
-
{
|
| 1095 |
-
"epoch": 1.25,
|
| 1096 |
-
"learning_rate": 1.534647221171334e-05,
|
| 1097 |
-
"loss": 0.4148,
|
| 1098 |
-
"step": 1710
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 1.26,
|
| 1102 |
-
"learning_rate": 1.5081351560551021e-05,
|
| 1103 |
-
"loss": 0.408,
|
| 1104 |
-
"step": 1720
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 1.27,
|
| 1108 |
-
"learning_rate": 1.4817548242878759e-05,
|
| 1109 |
-
"loss": 0.457,
|
| 1110 |
-
"step": 1730
|
| 1111 |
-
},
|
| 1112 |
-
{
|
| 1113 |
-
"epoch": 1.28,
|
| 1114 |
-
"learning_rate": 1.45550972954203e-05,
|
| 1115 |
-
"loss": 0.4193,
|
| 1116 |
-
"step": 1740
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 1.28,
|
| 1120 |
-
"learning_rate": 1.4294033575285914e-05,
|
| 1121 |
-
"loss": 0.4149,
|
| 1122 |
-
"step": 1750
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 1.29,
|
| 1126 |
-
"learning_rate": 1.4034391755342972e-05,
|
| 1127 |
-
"loss": 0.4032,
|
| 1128 |
-
"step": 1760
|
| 1129 |
-
},
|
| 1130 |
-
{
|
| 1131 |
-
"epoch": 1.3,
|
| 1132 |
-
"learning_rate": 1.3776206319610823e-05,
|
| 1133 |
-
"loss": 0.4078,
|
| 1134 |
-
"step": 1770
|
| 1135 |
-
},
|
| 1136 |
-
{
|
| 1137 |
-
"epoch": 1.31,
|
| 1138 |
-
"learning_rate": 1.3519511558680892e-05,
|
| 1139 |
-
"loss": 0.4123,
|
| 1140 |
-
"step": 1780
|
| 1141 |
-
},
|
| 1142 |
-
{
|
| 1143 |
-
"epoch": 1.31,
|
| 1144 |
-
"learning_rate": 1.3264341565162422e-05,
|
| 1145 |
-
"loss": 0.4089,
|
| 1146 |
-
"step": 1790
|
| 1147 |
-
},
|
| 1148 |
-
{
|
| 1149 |
-
"epoch": 1.32,
|
| 1150 |
-
"learning_rate": 1.3010730229154445e-05,
|
| 1151 |
-
"loss": 0.383,
|
| 1152 |
-
"step": 1800
|
| 1153 |
-
},
|
| 1154 |
-
{
|
| 1155 |
-
"epoch": 1.32,
|
| 1156 |
-
"eval_loss": 0.4250344932079315,
|
| 1157 |
-
"eval_runtime": 70.4814,
|
| 1158 |
-
"eval_samples_per_second": 15.635,
|
| 1159 |
-
"eval_steps_per_second": 1.575,
|
| 1160 |
-
"step": 1800
|
| 1161 |
-
},
|
| 1162 |
-
{
|
| 1163 |
-
"epoch": 1.33,
|
| 1164 |
-
"learning_rate": 1.2758711233744783e-05,
|
| 1165 |
-
"loss": 0.3936,
|
| 1166 |
-
"step": 1810
|
| 1167 |
-
},
|
| 1168 |
-
{
|
| 1169 |
-
"epoch": 1.33,
|
| 1170 |
-
"learning_rate": 1.2508318050536421e-05,
|
| 1171 |
-
"loss": 0.4127,
|
| 1172 |
-
"step": 1820
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 1.34,
|
| 1176 |
-
"learning_rate": 1.2259583935202062e-05,
|
| 1177 |
-
"loss": 0.4015,
|
| 1178 |
-
"step": 1830
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 1.35,
|
| 1182 |
-
"learning_rate": 1.2012541923067244e-05,
|
| 1183 |
-
"loss": 0.4203,
|
| 1184 |
-
"step": 1840
|
| 1185 |
-
},
|
| 1186 |
-
{
|
| 1187 |
-
"epoch": 1.36,
|
| 1188 |
-
"learning_rate": 1.176722482472286e-05,
|
| 1189 |
-
"loss": 0.4367,
|
| 1190 |
-
"step": 1850
|
| 1191 |
-
},
|
| 1192 |
-
{
|
| 1193 |
-
"epoch": 1.36,
|
| 1194 |
-
"learning_rate": 1.1523665221667398e-05,
|
| 1195 |
-
"loss": 0.4233,
|
| 1196 |
-
"step": 1860
|
| 1197 |
-
},
|
| 1198 |
-
{
|
| 1199 |
-
"epoch": 1.37,
|
| 1200 |
-
"learning_rate": 1.1281895461979732e-05,
|
| 1201 |
-
"loss": 0.4405,
|
| 1202 |
-
"step": 1870
|
| 1203 |
-
},
|
| 1204 |
-
{
|
| 1205 |
-
"epoch": 1.38,
|
| 1206 |
-
"learning_rate": 1.104194765602281e-05,
|
| 1207 |
-
"loss": 0.4379,
|
| 1208 |
-
"step": 1880
|
| 1209 |
-
},
|
| 1210 |
-
{
|
| 1211 |
-
"epoch": 1.39,
|
| 1212 |
-
"learning_rate": 1.0803853672178946e-05,
|
| 1213 |
-
"loss": 0.4146,
|
| 1214 |
-
"step": 1890
|
| 1215 |
-
},
|
| 1216 |
-
{
|
| 1217 |
-
"epoch": 1.39,
|
| 1218 |
-
"learning_rate": 1.0567645132617316e-05,
|
| 1219 |
-
"loss": 0.4438,
|
| 1220 |
-
"step": 1900
|
| 1221 |
-
},
|
| 1222 |
-
{
|
| 1223 |
-
"epoch": 1.4,
|
| 1224 |
-
"learning_rate": 1.0333353409094015e-05,
|
| 1225 |
-
"loss": 0.3915,
|
| 1226 |
-
"step": 1910
|
| 1227 |
-
},
|
| 1228 |
-
{
|
| 1229 |
-
"epoch": 1.41,
|
| 1230 |
-
"learning_rate": 1.0101009618785528e-05,
|
| 1231 |
-
"loss": 0.4063,
|
| 1232 |
-
"step": 1920
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 1.42,
|
| 1236 |
-
"learning_rate": 9.870644620155877e-06,
|
| 1237 |
-
"loss": 0.3974,
|
| 1238 |
-
"step": 1930
|
| 1239 |
-
},
|
| 1240 |
-
{
|
| 1241 |
-
"epoch": 1.42,
|
| 1242 |
-
"learning_rate": 9.642289008858244e-06,
|
| 1243 |
-
"loss": 0.4015,
|
| 1244 |
-
"step": 1940
|
| 1245 |
-
},
|
| 1246 |
-
{
|
| 1247 |
-
"epoch": 1.43,
|
| 1248 |
-
"learning_rate": 9.41597311367142e-06,
|
| 1249 |
-
"loss": 0.4264,
|
| 1250 |
-
"step": 1950
|
| 1251 |
-
},
|
| 1252 |
-
{
|
| 1253 |
-
"epoch": 1.44,
|
| 1254 |
-
"learning_rate": 9.191726992471725e-06,
|
| 1255 |
-
"loss": 0.4334,
|
| 1256 |
-
"step": 1960
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 1.44,
|
| 1260 |
-
"learning_rate": 8.969580428240903e-06,
|
| 1261 |
-
"loss": 0.4197,
|
| 1262 |
-
"step": 1970
|
| 1263 |
-
},
|
| 1264 |
-
{
|
| 1265 |
-
"epoch": 1.45,
|
| 1266 |
-
"learning_rate": 8.74956292511056e-06,
|
| 1267 |
-
"loss": 0.422,
|
| 1268 |
-
"step": 1980
|
| 1269 |
-
},
|
| 1270 |
-
{
|
| 1271 |
-
"epoch": 1.46,
|
| 1272 |
-
"learning_rate": 8.531703704443575e-06,
|
| 1273 |
-
"loss": 0.4077,
|
| 1274 |
-
"step": 1990
|
| 1275 |
-
},
|
| 1276 |
-
{
|
| 1277 |
-
"epoch": 1.47,
|
| 1278 |
-
"learning_rate": 8.316031700953086e-06,
|
| 1279 |
-
"loss": 0.4334,
|
| 1280 |
-
"step": 2000
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"epoch": 1.47,
|
| 1284 |
-
"eval_loss": 0.4206145107746124,
|
| 1285 |
-
"eval_runtime": 70.0533,
|
| 1286 |
-
"eval_samples_per_second": 15.731,
|
| 1287 |
-
"eval_steps_per_second": 1.585,
|
| 1288 |
-
"step": 2000
|
| 1289 |
-
},
|
| 1290 |
-
{
|
| 1291 |
-
"epoch": 1.47,
|
| 1292 |
-
"learning_rate": 8.102575558859612e-06,
|
| 1293 |
-
"loss": 0.4171,
|
| 1294 |
-
"step": 2010
|
| 1295 |
-
},
|
| 1296 |
-
{
|
| 1297 |
-
"epoch": 1.48,
|
| 1298 |
-
"learning_rate": 7.891363628086671e-06,
|
| 1299 |
-
"loss": 0.3957,
|
| 1300 |
-
"step": 2020
|
| 1301 |
-
},
|
| 1302 |
-
{
|
| 1303 |
-
"epoch": 1.49,
|
| 1304 |
-
"learning_rate": 7.682423960495517e-06,
|
| 1305 |
-
"loss": 0.4174,
|
| 1306 |
-
"step": 2030
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"epoch": 1.5,
|
| 1310 |
-
"learning_rate": 7.475784306159478e-06,
|
| 1311 |
-
"loss": 0.4187,
|
| 1312 |
-
"step": 2040
|
| 1313 |
-
},
|
| 1314 |
-
{
|
| 1315 |
-
"epoch": 1.5,
|
| 1316 |
-
"learning_rate": 7.271472109678379e-06,
|
| 1317 |
-
"loss": 0.3775,
|
| 1318 |
-
"step": 2050
|
| 1319 |
-
},
|
| 1320 |
-
{
|
| 1321 |
-
"epoch": 1.51,
|
| 1322 |
-
"learning_rate": 7.0695145065334585e-06,
|
| 1323 |
-
"loss": 0.4019,
|
| 1324 |
-
"step": 2060
|
| 1325 |
-
},
|
| 1326 |
-
{
|
| 1327 |
-
"epoch": 1.52,
|
| 1328 |
-
"learning_rate": 6.869938319483471e-06,
|
| 1329 |
-
"loss": 0.4143,
|
| 1330 |
-
"step": 2070
|
| 1331 |
-
},
|
| 1332 |
-
{
|
| 1333 |
-
"epoch": 1.53,
|
| 1334 |
-
"learning_rate": 6.67277005500222e-06,
|
| 1335 |
-
"loss": 0.3853,
|
| 1336 |
-
"step": 2080
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 1.53,
|
| 1340 |
-
"learning_rate": 6.478035899758139e-06,
|
| 1341 |
-
"loss": 0.4403,
|
| 1342 |
-
"step": 2090
|
| 1343 |
-
},
|
| 1344 |
-
{
|
| 1345 |
-
"epoch": 1.54,
|
| 1346 |
-
"learning_rate": 6.285761717136335e-06,
|
| 1347 |
-
"loss": 0.3888,
|
| 1348 |
-
"step": 2100
|
| 1349 |
-
},
|
| 1350 |
-
{
|
| 1351 |
-
"epoch": 1.55,
|
| 1352 |
-
"learning_rate": 6.095973043803577e-06,
|
| 1353 |
-
"loss": 0.4123,
|
| 1354 |
-
"step": 2110
|
| 1355 |
-
},
|
| 1356 |
-
{
|
| 1357 |
-
"epoch": 1.55,
|
| 1358 |
-
"learning_rate": 5.908695086316701e-06,
|
| 1359 |
-
"loss": 0.4035,
|
| 1360 |
-
"step": 2120
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 1.56,
|
| 1364 |
-
"learning_rate": 5.723952717774763e-06,
|
| 1365 |
-
"loss": 0.4219,
|
| 1366 |
-
"step": 2130
|
| 1367 |
-
},
|
| 1368 |
-
{
|
| 1369 |
-
"epoch": 1.57,
|
| 1370 |
-
"learning_rate": 5.54177047451562e-06,
|
| 1371 |
-
"loss": 0.4209,
|
| 1372 |
-
"step": 2140
|
| 1373 |
-
},
|
| 1374 |
-
{
|
| 1375 |
-
"epoch": 1.58,
|
| 1376 |
-
"learning_rate": 5.362172552857128e-06,
|
| 1377 |
-
"loss": 0.4286,
|
| 1378 |
-
"step": 2150
|
| 1379 |
-
},
|
| 1380 |
-
{
|
| 1381 |
-
"epoch": 1.58,
|
| 1382 |
-
"learning_rate": 5.18518280588354e-06,
|
| 1383 |
-
"loss": 0.4134,
|
| 1384 |
-
"step": 2160
|
| 1385 |
-
},
|
| 1386 |
-
{
|
| 1387 |
-
"epoch": 1.59,
|
| 1388 |
-
"learning_rate": 5.010824740277501e-06,
|
| 1389 |
-
"loss": 0.4005,
|
| 1390 |
-
"step": 2170
|
| 1391 |
-
},
|
| 1392 |
-
{
|
| 1393 |
-
"epoch": 1.6,
|
| 1394 |
-
"learning_rate": 4.83912151319802e-06,
|
| 1395 |
-
"loss": 0.3973,
|
| 1396 |
-
"step": 2180
|
| 1397 |
-
},
|
| 1398 |
-
{
|
| 1399 |
-
"epoch": 1.61,
|
| 1400 |
-
"learning_rate": 4.6700959292048875e-06,
|
| 1401 |
-
"loss": 0.3959,
|
| 1402 |
-
"step": 2190
|
| 1403 |
-
},
|
| 1404 |
-
{
|
| 1405 |
-
"epoch": 1.61,
|
| 1406 |
-
"learning_rate": 4.503770437229918e-06,
|
| 1407 |
-
"loss": 0.4017,
|
| 1408 |
-
"step": 2200
|
| 1409 |
-
},
|
| 1410 |
-
{
|
| 1411 |
-
"epoch": 1.61,
|
| 1412 |
-
"eval_loss": 0.41970890760421753,
|
| 1413 |
-
"eval_runtime": 69.9019,
|
| 1414 |
-
"eval_samples_per_second": 15.765,
|
| 1415 |
-
"eval_steps_per_second": 1.588,
|
| 1416 |
-
"step": 2200
|
| 1417 |
-
},
|
| 1418 |
-
{
|
| 1419 |
-
"epoch": 1.62,
|
| 1420 |
-
"learning_rate": 4.340167127595407e-06,
|
| 1421 |
-
"loss": 0.4013,
|
| 1422 |
-
"step": 2210
|
| 1423 |
-
},
|
| 1424 |
-
{
|
| 1425 |
-
"epoch": 1.63,
|
| 1426 |
-
"learning_rate": 4.179307729080256e-06,
|
| 1427 |
-
"loss": 0.4069,
|
| 1428 |
-
"step": 2220
|
| 1429 |
-
},
|
| 1430 |
-
{
|
| 1431 |
-
"epoch": 1.64,
|
| 1432 |
-
"learning_rate": 4.021213606034064e-06,
|
| 1433 |
-
"loss": 0.3857,
|
| 1434 |
-
"step": 2230
|
| 1435 |
-
},
|
| 1436 |
-
{
|
| 1437 |
-
"epoch": 1.64,
|
| 1438 |
-
"learning_rate": 3.8659057555396645e-06,
|
| 1439 |
-
"loss": 0.4262,
|
| 1440 |
-
"step": 2240
|
| 1441 |
-
},
|
| 1442 |
-
{
|
| 1443 |
-
"epoch": 1.65,
|
| 1444 |
-
"learning_rate": 3.713404804624418e-06,
|
| 1445 |
-
"loss": 0.3953,
|
| 1446 |
-
"step": 2250
|
| 1447 |
-
},
|
| 1448 |
-
{
|
| 1449 |
-
"epoch": 1.66,
|
| 1450 |
-
"learning_rate": 3.5637310075206544e-06,
|
| 1451 |
-
"loss": 0.4231,
|
| 1452 |
-
"step": 2260
|
| 1453 |
-
},
|
| 1454 |
-
{
|
| 1455 |
-
"epoch": 1.66,
|
| 1456 |
-
"learning_rate": 3.416904242975635e-06,
|
| 1457 |
-
"loss": 0.407,
|
| 1458 |
-
"step": 2270
|
| 1459 |
-
},
|
| 1460 |
-
{
|
| 1461 |
-
"epoch": 1.67,
|
| 1462 |
-
"learning_rate": 3.2729440116113843e-06,
|
| 1463 |
-
"loss": 0.4254,
|
| 1464 |
-
"step": 2280
|
| 1465 |
-
},
|
| 1466 |
-
{
|
| 1467 |
-
"epoch": 1.68,
|
| 1468 |
-
"learning_rate": 3.131869433334725e-06,
|
| 1469 |
-
"loss": 0.4054,
|
| 1470 |
-
"step": 2290
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 1.69,
|
| 1474 |
-
"learning_rate": 2.9936992447979068e-06,
|
| 1475 |
-
"loss": 0.3801,
|
| 1476 |
-
"step": 2300
|
| 1477 |
-
},
|
| 1478 |
-
{
|
| 1479 |
-
"epoch": 1.69,
|
| 1480 |
-
"learning_rate": 2.8584517969101054e-06,
|
| 1481 |
-
"loss": 0.4335,
|
| 1482 |
-
"step": 2310
|
| 1483 |
-
},
|
| 1484 |
-
{
|
| 1485 |
-
"epoch": 1.7,
|
| 1486 |
-
"learning_rate": 2.7261450524001807e-06,
|
| 1487 |
-
"loss": 0.412,
|
| 1488 |
-
"step": 2320
|
| 1489 |
-
},
|
| 1490 |
-
{
|
| 1491 |
-
"epoch": 1.71,
|
| 1492 |
-
"learning_rate": 2.596796583430969e-06,
|
| 1493 |
-
"loss": 0.4456,
|
| 1494 |
-
"step": 2330
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 1.72,
|
| 1498 |
-
"learning_rate": 2.470423569265462e-06,
|
| 1499 |
-
"loss": 0.3972,
|
| 1500 |
-
"step": 2340
|
| 1501 |
-
},
|
| 1502 |
-
{
|
| 1503 |
-
"epoch": 1.72,
|
| 1504 |
-
"learning_rate": 2.34704279398516e-06,
|
| 1505 |
-
"loss": 0.3935,
|
| 1506 |
-
"step": 2350
|
| 1507 |
-
},
|
| 1508 |
-
{
|
| 1509 |
-
"epoch": 1.73,
|
| 1510 |
-
"learning_rate": 2.2266706442609226e-06,
|
| 1511 |
-
"loss": 0.3974,
|
| 1512 |
-
"step": 2360
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 1.74,
|
| 1516 |
-
"learning_rate": 2.109323107176578e-06,
|
| 1517 |
-
"loss": 0.4157,
|
| 1518 |
-
"step": 2370
|
| 1519 |
-
},
|
| 1520 |
-
{
|
| 1521 |
-
"epoch": 1.75,
|
| 1522 |
-
"learning_rate": 1.9950157681056318e-06,
|
| 1523 |
-
"loss": 0.4379,
|
| 1524 |
-
"step": 2380
|
| 1525 |
-
},
|
| 1526 |
-
{
|
| 1527 |
-
"epoch": 1.75,
|
| 1528 |
-
"learning_rate": 1.8837638086413063e-06,
|
| 1529 |
-
"loss": 0.4035,
|
| 1530 |
-
"step": 2390
|
| 1531 |
-
},
|
| 1532 |
-
{
|
| 1533 |
-
"epoch": 1.76,
|
| 1534 |
-
"learning_rate": 1.7755820045802145e-06,
|
| 1535 |
-
"loss": 0.4455,
|
| 1536 |
-
"step": 2400
|
| 1537 |
-
},
|
| 1538 |
-
{
|
| 1539 |
-
"epoch": 1.76,
|
| 1540 |
-
"eval_loss": 0.41885045170783997,
|
| 1541 |
-
"eval_runtime": 70.0957,
|
| 1542 |
-
"eval_samples_per_second": 15.721,
|
| 1543 |
-
"eval_steps_per_second": 1.584,
|
| 1544 |
-
"step": 2400
|
| 1545 |
-
},
|
| 1546 |
-
{
|
| 1547 |
-
"epoch": 1.77,
|
| 1548 |
-
"learning_rate": 1.6704847239599364e-06,
|
| 1549 |
-
"loss": 0.4532,
|
| 1550 |
-
"step": 2410
|
| 1551 |
-
},
|
| 1552 |
-
{
|
| 1553 |
-
"epoch": 1.77,
|
| 1554 |
-
"learning_rate": 1.5684859251507394e-06,
|
| 1555 |
-
"loss": 0.4213,
|
| 1556 |
-
"step": 2420
|
| 1557 |
-
},
|
| 1558 |
-
{
|
| 1559 |
-
"epoch": 1.78,
|
| 1560 |
-
"learning_rate": 1.4695991550017164e-06,
|
| 1561 |
-
"loss": 0.3873,
|
| 1562 |
-
"step": 2430
|
| 1563 |
-
},
|
| 1564 |
-
{
|
| 1565 |
-
"epoch": 1.79,
|
| 1566 |
-
"learning_rate": 1.373837547041576e-06,
|
| 1567 |
-
"loss": 0.4163,
|
| 1568 |
-
"step": 2440
|
| 1569 |
-
},
|
| 1570 |
-
{
|
| 1571 |
-
"epoch": 1.8,
|
| 1572 |
-
"learning_rate": 1.2812138197343392e-06,
|
| 1573 |
-
"loss": 0.3946,
|
| 1574 |
-
"step": 2450
|
| 1575 |
-
},
|
| 1576 |
-
{
|
| 1577 |
-
"epoch": 1.8,
|
| 1578 |
-
"learning_rate": 1.1917402747901152e-06,
|
| 1579 |
-
"loss": 0.41,
|
| 1580 |
-
"step": 2460
|
| 1581 |
-
},
|
| 1582 |
-
{
|
| 1583 |
-
"epoch": 1.81,
|
| 1584 |
-
"learning_rate": 1.105428795531327e-06,
|
| 1585 |
-
"loss": 0.4126,
|
| 1586 |
-
"step": 2470
|
| 1587 |
-
},
|
| 1588 |
-
{
|
| 1589 |
-
"epoch": 1.82,
|
| 1590 |
-
"learning_rate": 1.0222908453143804e-06,
|
| 1591 |
-
"loss": 0.4505,
|
| 1592 |
-
"step": 2480
|
| 1593 |
-
},
|
| 1594 |
-
{
|
| 1595 |
-
"epoch": 1.83,
|
| 1596 |
-
"learning_rate": 9.423374660072065e-07,
|
| 1597 |
-
"loss": 0.4303,
|
| 1598 |
-
"step": 2490
|
| 1599 |
-
},
|
| 1600 |
-
{
|
| 1601 |
-
"epoch": 1.83,
|
| 1602 |
-
"learning_rate": 8.655792765227405e-07,
|
| 1603 |
-
"loss": 0.4179,
|
| 1604 |
-
"step": 2500
|
| 1605 |
-
},
|
| 1606 |
-
{
|
| 1607 |
-
"epoch": 1.84,
|
| 1608 |
-
"learning_rate": 7.920264714085828e-07,
|
| 1609 |
-
"loss": 0.4376,
|
| 1610 |
-
"step": 2510
|
| 1611 |
-
},
|
| 1612 |
-
{
|
| 1613 |
-
"epoch": 1.85,
|
| 1614 |
-
"learning_rate": 7.216888194930272e-07,
|
| 1615 |
-
"loss": 0.4069,
|
| 1616 |
-
"step": 2520
|
| 1617 |
-
},
|
| 1618 |
-
{
|
| 1619 |
-
"epoch": 1.86,
|
| 1620 |
-
"learning_rate": 6.545756625876031e-07,
|
| 1621 |
-
"loss": 0.3887,
|
| 1622 |
-
"step": 2530
|
| 1623 |
-
},
|
| 1624 |
-
{
|
| 1625 |
-
"epoch": 1.86,
|
| 1626 |
-
"learning_rate": 5.906959142463947e-07,
|
| 1627 |
-
"loss": 0.3972,
|
| 1628 |
-
"step": 2540
|
| 1629 |
-
},
|
| 1630 |
-
{
|
| 1631 |
-
"epoch": 1.87,
|
| 1632 |
-
"learning_rate": 5.300580585821696e-07,
|
| 1633 |
-
"loss": 0.4078,
|
| 1634 |
-
"step": 2550
|
| 1635 |
-
},
|
| 1636 |
-
{
|
| 1637 |
-
"epoch": 1.88,
|
| 1638 |
-
"learning_rate": 4.7267014913956463e-07,
|
| 1639 |
-
"loss": 0.4467,
|
| 1640 |
-
"step": 2560
|
| 1641 |
-
},
|
| 1642 |
-
{
|
| 1643 |
-
"epoch": 1.88,
|
| 1644 |
-
"learning_rate": 4.1853980782549097e-07,
|
| 1645 |
-
"loss": 0.4567,
|
| 1646 |
-
"step": 2570
|
| 1647 |
-
},
|
| 1648 |
-
{
|
| 1649 |
-
"epoch": 1.89,
|
| 1650 |
-
"learning_rate": 3.6767422389682173e-07,
|
| 1651 |
-
"loss": 0.4494,
|
| 1652 |
-
"step": 2580
|
| 1653 |
-
},
|
| 1654 |
-
{
|
| 1655 |
-
"epoch": 1.9,
|
| 1656 |
-
"learning_rate": 3.2008015300555306e-07,
|
| 1657 |
-
"loss": 0.4344,
|
| 1658 |
-
"step": 2590
|
| 1659 |
-
},
|
| 1660 |
-
{
|
| 1661 |
-
"epoch": 1.91,
|
| 1662 |
-
"learning_rate": 2.757639163015774e-07,
|
| 1663 |
-
"loss": 0.4101,
|
| 1664 |
-
"step": 2600
|
| 1665 |
-
},
|
| 1666 |
-
{
|
| 1667 |
-
"epoch": 1.91,
|
| 1668 |
-
"eval_loss": 0.41886425018310547,
|
| 1669 |
-
"eval_runtime": 70.2179,
|
| 1670 |
-
"eval_samples_per_second": 15.694,
|
| 1671 |
-
"eval_steps_per_second": 1.581,
|
| 1672 |
-
"step": 2600
|
| 1673 |
-
},
|
| 1674 |
-
{
|
| 1675 |
-
"epoch": 1.91,
|
| 1676 |
-
"learning_rate": 2.347313995931466e-07,
|
| 1677 |
-
"loss": 0.4058,
|
| 1678 |
-
"step": 2610
|
| 1679 |
-
},
|
| 1680 |
-
{
|
| 1681 |
-
"epoch": 1.92,
|
| 1682 |
-
"learning_rate": 1.9698805256513908e-07,
|
| 1683 |
-
"loss": 0.414,
|
| 1684 |
-
"step": 2620
|
| 1685 |
-
},
|
| 1686 |
-
{
|
| 1687 |
-
"epoch": 1.93,
|
| 1688 |
-
"learning_rate": 1.6253888805527474e-07,
|
| 1689 |
-
"loss": 0.4254,
|
| 1690 |
-
"step": 2630
|
| 1691 |
-
},
|
| 1692 |
-
{
|
| 1693 |
-
"epoch": 1.94,
|
| 1694 |
-
"learning_rate": 1.3138848138835313e-07,
|
| 1695 |
-
"loss": 0.4017,
|
| 1696 |
-
"step": 2640
|
| 1697 |
-
},
|
| 1698 |
-
{
|
| 1699 |
-
"epoch": 1.94,
|
| 1700 |
-
"learning_rate": 1.0354096976856186e-07,
|
| 1701 |
-
"loss": 0.4258,
|
| 1702 |
-
"step": 2650
|
| 1703 |
-
},
|
| 1704 |
-
{
|
| 1705 |
-
"epoch": 1.95,
|
| 1706 |
-
"learning_rate": 7.900005173002712e-08,
|
| 1707 |
-
"loss": 0.4098,
|
| 1708 |
-
"step": 2660
|
| 1709 |
-
},
|
| 1710 |
-
{
|
| 1711 |
-
"epoch": 1.96,
|
| 1712 |
-
"learning_rate": 5.776898664557051e-08,
|
| 1713 |
-
"loss": 0.42,
|
| 1714 |
-
"step": 2670
|
| 1715 |
-
},
|
| 1716 |
-
{
|
| 1717 |
-
"epoch": 1.97,
|
| 1718 |
-
"learning_rate": 3.985059429383875e-08,
|
| 1719 |
-
"loss": 0.3886,
|
| 1720 |
-
"step": 2680
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"epoch": 1.97,
|
| 1724 |
-
"learning_rate": 2.5247254484794813e-08,
|
| 1725 |
-
"loss": 0.4276,
|
| 1726 |
-
"step": 2690
|
| 1727 |
-
},
|
| 1728 |
-
{
|
| 1729 |
-
"epoch": 1.98,
|
| 1730 |
-
"learning_rate": 1.3960906743634706e-08,
|
| 1731 |
-
"loss": 0.4006,
|
| 1732 |
-
"step": 2700
|
| 1733 |
-
},
|
| 1734 |
-
{
|
| 1735 |
-
"epoch": 1.99,
|
| 1736 |
-
"learning_rate": 5.993050053204607e-09,
|
| 1737 |
-
"loss": 0.4243,
|
| 1738 |
-
"step": 2710
|
| 1739 |
-
},
|
| 1740 |
-
{
|
| 1741 |
-
"epoch": 1.99,
|
| 1742 |
-
"learning_rate": 1.3447426549129117e-09,
|
| 1743 |
-
"loss": 0.4439,
|
| 1744 |
-
"step": 2720
|
| 1745 |
-
},
|
| 1746 |
-
{
|
| 1747 |
-
"epoch": 2.0,
|
| 1748 |
-
"step": 2726,
|
| 1749 |
-
"total_flos": 1.1289170586615415e+19,
|
| 1750 |
-
"train_loss": 0.46561298847898175,
|
| 1751 |
-
"train_runtime": 35477.4141,
|
| 1752 |
-
"train_samples_per_second": 6.149,
|
| 1753 |
-
"train_steps_per_second": 0.077
|
| 1754 |
-
}
|
| 1755 |
-
],
|
| 1756 |
-
"max_steps": 2726,
|
| 1757 |
-
"num_train_epochs": 2,
|
| 1758 |
-
"total_flos": 1.1289170586615415e+19,
|
| 1759 |
-
"trial_name": null,
|
| 1760 |
-
"trial_params": null
|
| 1761 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0037c3e69fa21891dd65687a3f79ad20a8abc0a75790c554b437378b35c59fe9
|
| 3 |
-
size 4600
|
|
|
|
|
|
|
|
|
|
|
|
Baichuan-13B-Chat-lora-Task/training_eval_loss.png
DELETED
|
Binary file (36.1 kB)
|
|
|
Baichuan-13B-Chat-lora-Task/training_loss.png
DELETED
|
Binary file (39.2 kB)
|
|
|