Model save
Browse files- README.md +78 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +450 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-2-2b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: gemma
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Gemma-2-2B_task-2_60-samples_config-1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Gemma-2-2B_task-2_60-samples_config-1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.4146
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 50
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 1.0003 | 0.8696 | 5 | 1.0526 |
|
| 57 |
+
| 0.9778 | 1.9130 | 11 | 0.9144 |
|
| 58 |
+
| 0.8521 | 2.9565 | 17 | 0.8022 |
|
| 59 |
+
| 0.7041 | 4.0 | 23 | 0.7458 |
|
| 60 |
+
| 0.6478 | 4.8696 | 28 | 0.7177 |
|
| 61 |
+
| 0.5764 | 5.9130 | 34 | 0.7000 |
|
| 62 |
+
| 0.4782 | 6.9565 | 40 | 0.6944 |
|
| 63 |
+
| 0.4344 | 8.0 | 46 | 0.6963 |
|
| 64 |
+
| 0.3571 | 8.8696 | 51 | 0.7276 |
|
| 65 |
+
| 0.2965 | 9.9130 | 57 | 0.8026 |
|
| 66 |
+
| 0.2046 | 10.9565 | 63 | 0.9341 |
|
| 67 |
+
| 0.119 | 12.0 | 69 | 1.0343 |
|
| 68 |
+
| 0.064 | 12.8696 | 74 | 1.2800 |
|
| 69 |
+
| 0.0358 | 13.9130 | 80 | 1.4146 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.12.0
|
| 75 |
+
- Transformers 4.44.0
|
| 76 |
+
- Pytorch 2.1.2+cu121
|
| 77 |
+
- Datasets 2.20.0
|
| 78 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83115256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c92f4b63ac8496eab9fe26ffb6fcc5e08ee0b074f3a23ee136ec81c5866a105b
|
| 3 |
size 83115256
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 13.91304347826087,
|
| 3 |
+
"total_flos": 2.1337014435577856e+16,
|
| 4 |
+
"train_loss": 0.48295602201251314,
|
| 5 |
+
"train_runtime": 925.7582,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 2.484,
|
| 8 |
+
"train_steps_per_second": 0.27
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 13.91304347826087,
|
| 3 |
+
"total_flos": 2.1337014435577856e+16,
|
| 4 |
+
"train_loss": 0.48295602201251314,
|
| 5 |
+
"train_runtime": 925.7582,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 2.484,
|
| 8 |
+
"train_steps_per_second": 0.27
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6944165229797363,
|
| 3 |
+
"best_model_checkpoint": "data/Gemma-2-2B_task-2_60-samples_config-1/checkpoint-40",
|
| 4 |
+
"epoch": 13.91304347826087,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 80,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17391304347826086,
|
| 13 |
+
"grad_norm": 0.7895397543907166,
|
| 14 |
+
"learning_rate": 4.000000000000001e-06,
|
| 15 |
+
"loss": 1.0312,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.34782608695652173,
|
| 20 |
+
"grad_norm": 0.9888849258422852,
|
| 21 |
+
"learning_rate": 8.000000000000001e-06,
|
| 22 |
+
"loss": 1.0807,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"grad_norm": 0.8398869633674622,
|
| 28 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 29 |
+
"loss": 1.0003,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8695652173913043,
|
| 34 |
+
"eval_loss": 1.0525766611099243,
|
| 35 |
+
"eval_runtime": 5.3262,
|
| 36 |
+
"eval_samples_per_second": 2.253,
|
| 37 |
+
"eval_steps_per_second": 2.253,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0434782608695652,
|
| 42 |
+
"grad_norm": 0.8245088458061218,
|
| 43 |
+
"learning_rate": 2.4e-05,
|
| 44 |
+
"loss": 0.9811,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.391304347826087,
|
| 49 |
+
"grad_norm": 0.7923673391342163,
|
| 50 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 51 |
+
"loss": 0.9591,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.7391304347826086,
|
| 56 |
+
"grad_norm": 0.7004882097244263,
|
| 57 |
+
"learning_rate": 4e-05,
|
| 58 |
+
"loss": 0.9778,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.9130434782608696,
|
| 63 |
+
"eval_loss": 0.914442777633667,
|
| 64 |
+
"eval_runtime": 5.0249,
|
| 65 |
+
"eval_samples_per_second": 2.388,
|
| 66 |
+
"eval_steps_per_second": 2.388,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0869565217391304,
|
| 71 |
+
"grad_norm": 0.6176119446754456,
|
| 72 |
+
"learning_rate": 4.8e-05,
|
| 73 |
+
"loss": 0.849,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4347826086956523,
|
| 78 |
+
"grad_norm": 0.5323354005813599,
|
| 79 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 80 |
+
"loss": 0.7568,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.782608695652174,
|
| 85 |
+
"grad_norm": 0.4606993794441223,
|
| 86 |
+
"learning_rate": 6.400000000000001e-05,
|
| 87 |
+
"loss": 0.8521,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.9565217391304346,
|
| 92 |
+
"eval_loss": 0.8022434711456299,
|
| 93 |
+
"eval_runtime": 5.0227,
|
| 94 |
+
"eval_samples_per_second": 2.389,
|
| 95 |
+
"eval_steps_per_second": 2.389,
|
| 96 |
+
"step": 17
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.130434782608696,
|
| 100 |
+
"grad_norm": 0.44734710454940796,
|
| 101 |
+
"learning_rate": 7.2e-05,
|
| 102 |
+
"loss": 0.7085,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.4782608695652173,
|
| 107 |
+
"grad_norm": 0.491365522146225,
|
| 108 |
+
"learning_rate": 8e-05,
|
| 109 |
+
"loss": 0.6665,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.8260869565217392,
|
| 114 |
+
"grad_norm": 0.45671552419662476,
|
| 115 |
+
"learning_rate": 8.800000000000001e-05,
|
| 116 |
+
"loss": 0.7041,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 0.7458145022392273,
|
| 122 |
+
"eval_runtime": 5.0187,
|
| 123 |
+
"eval_samples_per_second": 2.391,
|
| 124 |
+
"eval_steps_per_second": 2.391,
|
| 125 |
+
"step": 23
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.173913043478261,
|
| 129 |
+
"grad_norm": 0.38127702474594116,
|
| 130 |
+
"learning_rate": 9.6e-05,
|
| 131 |
+
"loss": 0.6834,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.521739130434782,
|
| 136 |
+
"grad_norm": 0.40372902154922485,
|
| 137 |
+
"learning_rate": 9.999512620046522e-05,
|
| 138 |
+
"loss": 0.6341,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.869565217391305,
|
| 143 |
+
"grad_norm": 0.4290044605731964,
|
| 144 |
+
"learning_rate": 9.995614150494293e-05,
|
| 145 |
+
"loss": 0.6478,
|
| 146 |
+
"step": 28
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.869565217391305,
|
| 150 |
+
"eval_loss": 0.7177431583404541,
|
| 151 |
+
"eval_runtime": 5.0212,
|
| 152 |
+
"eval_samples_per_second": 2.39,
|
| 153 |
+
"eval_steps_per_second": 2.39,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.217391304347826,
|
| 158 |
+
"grad_norm": 0.35873129963874817,
|
| 159 |
+
"learning_rate": 9.987820251299122e-05,
|
| 160 |
+
"loss": 0.5597,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.565217391304348,
|
| 165 |
+
"grad_norm": 0.36796948313713074,
|
| 166 |
+
"learning_rate": 9.976136999909156e-05,
|
| 167 |
+
"loss": 0.5757,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.913043478260869,
|
| 172 |
+
"grad_norm": 0.3624632954597473,
|
| 173 |
+
"learning_rate": 9.96057350657239e-05,
|
| 174 |
+
"loss": 0.5764,
|
| 175 |
+
"step": 34
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.913043478260869,
|
| 179 |
+
"eval_loss": 0.6999881267547607,
|
| 180 |
+
"eval_runtime": 5.019,
|
| 181 |
+
"eval_samples_per_second": 2.391,
|
| 182 |
+
"eval_steps_per_second": 2.391,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.260869565217392,
|
| 187 |
+
"grad_norm": 0.35226380825042725,
|
| 188 |
+
"learning_rate": 9.941141907232765e-05,
|
| 189 |
+
"loss": 0.4908,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.608695652173913,
|
| 194 |
+
"grad_norm": 0.41741761565208435,
|
| 195 |
+
"learning_rate": 9.917857354066931e-05,
|
| 196 |
+
"loss": 0.5364,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.956521739130435,
|
| 201 |
+
"grad_norm": 0.41319116950035095,
|
| 202 |
+
"learning_rate": 9.890738003669029e-05,
|
| 203 |
+
"loss": 0.4782,
|
| 204 |
+
"step": 40
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.956521739130435,
|
| 208 |
+
"eval_loss": 0.6944165229797363,
|
| 209 |
+
"eval_runtime": 5.0169,
|
| 210 |
+
"eval_samples_per_second": 2.392,
|
| 211 |
+
"eval_steps_per_second": 2.392,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.304347826086957,
|
| 216 |
+
"grad_norm": 0.36885157227516174,
|
| 217 |
+
"learning_rate": 9.859805002892732e-05,
|
| 218 |
+
"loss": 0.4893,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6521739130434785,
|
| 223 |
+
"grad_norm": 0.3935936689376831,
|
| 224 |
+
"learning_rate": 9.825082472361557e-05,
|
| 225 |
+
"loss": 0.4454,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 0.43766430020332336,
|
| 231 |
+
"learning_rate": 9.786597487660337e-05,
|
| 232 |
+
"loss": 0.4344,
|
| 233 |
+
"step": 46
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_loss": 0.6962693333625793,
|
| 238 |
+
"eval_runtime": 5.0166,
|
| 239 |
+
"eval_samples_per_second": 2.392,
|
| 240 |
+
"eval_steps_per_second": 2.392,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.347826086956522,
|
| 245 |
+
"grad_norm": 0.4267623722553253,
|
| 246 |
+
"learning_rate": 9.744380058222483e-05,
|
| 247 |
+
"loss": 0.4137,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.695652173913043,
|
| 252 |
+
"grad_norm": 0.5441224575042725,
|
| 253 |
+
"learning_rate": 9.698463103929542e-05,
|
| 254 |
+
"loss": 0.3571,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.869565217391305,
|
| 259 |
+
"eval_loss": 0.7275979518890381,
|
| 260 |
+
"eval_runtime": 5.016,
|
| 261 |
+
"eval_samples_per_second": 2.392,
|
| 262 |
+
"eval_steps_per_second": 2.392,
|
| 263 |
+
"step": 51
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.043478260869565,
|
| 267 |
+
"grad_norm": 0.5679859519004822,
|
| 268 |
+
"learning_rate": 9.648882429441257e-05,
|
| 269 |
+
"loss": 0.3658,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.391304347826088,
|
| 274 |
+
"grad_norm": 0.5481728911399841,
|
| 275 |
+
"learning_rate": 9.595676696276172e-05,
|
| 276 |
+
"loss": 0.3009,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.73913043478261,
|
| 281 |
+
"grad_norm": 0.6838057041168213,
|
| 282 |
+
"learning_rate": 9.538887392664544e-05,
|
| 283 |
+
"loss": 0.2965,
|
| 284 |
+
"step": 56
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.91304347826087,
|
| 288 |
+
"eval_loss": 0.8026370406150818,
|
| 289 |
+
"eval_runtime": 5.0264,
|
| 290 |
+
"eval_samples_per_second": 2.387,
|
| 291 |
+
"eval_steps_per_second": 2.387,
|
| 292 |
+
"step": 57
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.08695652173913,
|
| 296 |
+
"grad_norm": 0.660568356513977,
|
| 297 |
+
"learning_rate": 9.478558801197065e-05,
|
| 298 |
+
"loss": 0.2925,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.434782608695652,
|
| 303 |
+
"grad_norm": 0.6920638084411621,
|
| 304 |
+
"learning_rate": 9.414737964294636e-05,
|
| 305 |
+
"loss": 0.2164,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.782608695652174,
|
| 310 |
+
"grad_norm": 0.7863826751708984,
|
| 311 |
+
"learning_rate": 9.347474647526095e-05,
|
| 312 |
+
"loss": 0.2046,
|
| 313 |
+
"step": 62
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.956521739130435,
|
| 317 |
+
"eval_loss": 0.9340725541114807,
|
| 318 |
+
"eval_runtime": 5.0224,
|
| 319 |
+
"eval_samples_per_second": 2.389,
|
| 320 |
+
"eval_steps_per_second": 2.389,
|
| 321 |
+
"step": 63
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.130434782608695,
|
| 325 |
+
"grad_norm": 0.7646209001541138,
|
| 326 |
+
"learning_rate": 9.276821300802534e-05,
|
| 327 |
+
"loss": 0.182,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 11.478260869565217,
|
| 332 |
+
"grad_norm": 1.089479923248291,
|
| 333 |
+
"learning_rate": 9.202833017478422e-05,
|
| 334 |
+
"loss": 0.1571,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 11.826086956521738,
|
| 339 |
+
"grad_norm": 0.8993852138519287,
|
| 340 |
+
"learning_rate": 9.125567491391476e-05,
|
| 341 |
+
"loss": 0.119,
|
| 342 |
+
"step": 68
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 12.0,
|
| 346 |
+
"eval_loss": 1.0342997312545776,
|
| 347 |
+
"eval_runtime": 5.028,
|
| 348 |
+
"eval_samples_per_second": 2.387,
|
| 349 |
+
"eval_steps_per_second": 2.387,
|
| 350 |
+
"step": 69
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.173913043478262,
|
| 354 |
+
"grad_norm": 0.6343057751655579,
|
| 355 |
+
"learning_rate": 9.045084971874738e-05,
|
| 356 |
+
"loss": 0.091,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.521739130434783,
|
| 361 |
+
"grad_norm": 0.8913945555686951,
|
| 362 |
+
"learning_rate": 8.961448216775954e-05,
|
| 363 |
+
"loss": 0.0739,
|
| 364 |
+
"step": 72
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 12.869565217391305,
|
| 368 |
+
"grad_norm": 1.002933144569397,
|
| 369 |
+
"learning_rate": 8.874722443520899e-05,
|
| 370 |
+
"loss": 0.064,
|
| 371 |
+
"step": 74
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 12.869565217391305,
|
| 375 |
+
"eval_loss": 1.2800191640853882,
|
| 376 |
+
"eval_runtime": 5.0216,
|
| 377 |
+
"eval_samples_per_second": 2.39,
|
| 378 |
+
"eval_steps_per_second": 2.39,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.217391304347826,
|
| 383 |
+
"grad_norm": 0.5404753684997559,
|
| 384 |
+
"learning_rate": 8.784975278258783e-05,
|
| 385 |
+
"loss": 0.0483,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 13.565217391304348,
|
| 390 |
+
"grad_norm": 0.8066350221633911,
|
| 391 |
+
"learning_rate": 8.692276703129421e-05,
|
| 392 |
+
"loss": 0.0314,
|
| 393 |
+
"step": 78
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.91304347826087,
|
| 397 |
+
"grad_norm": 0.749337911605835,
|
| 398 |
+
"learning_rate": 8.596699001693255e-05,
|
| 399 |
+
"loss": 0.0358,
|
| 400 |
+
"step": 80
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.91304347826087,
|
| 404 |
+
"eval_loss": 1.414562702178955,
|
| 405 |
+
"eval_runtime": 5.0167,
|
| 406 |
+
"eval_samples_per_second": 2.392,
|
| 407 |
+
"eval_steps_per_second": 2.392,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 13.91304347826087,
|
| 412 |
+
"step": 80,
|
| 413 |
+
"total_flos": 2.1337014435577856e+16,
|
| 414 |
+
"train_loss": 0.48295602201251314,
|
| 415 |
+
"train_runtime": 925.7582,
|
| 416 |
+
"train_samples_per_second": 2.484,
|
| 417 |
+
"train_steps_per_second": 0.27
|
| 418 |
+
}
|
| 419 |
+
],
|
| 420 |
+
"logging_steps": 2,
|
| 421 |
+
"max_steps": 250,
|
| 422 |
+
"num_input_tokens_seen": 0,
|
| 423 |
+
"num_train_epochs": 50,
|
| 424 |
+
"save_steps": 25,
|
| 425 |
+
"stateful_callbacks": {
|
| 426 |
+
"EarlyStoppingCallback": {
|
| 427 |
+
"args": {
|
| 428 |
+
"early_stopping_patience": 7,
|
| 429 |
+
"early_stopping_threshold": 0.0
|
| 430 |
+
},
|
| 431 |
+
"attributes": {
|
| 432 |
+
"early_stopping_patience_counter": 0
|
| 433 |
+
}
|
| 434 |
+
},
|
| 435 |
+
"TrainerControl": {
|
| 436 |
+
"args": {
|
| 437 |
+
"should_epoch_stop": false,
|
| 438 |
+
"should_evaluate": false,
|
| 439 |
+
"should_log": false,
|
| 440 |
+
"should_save": true,
|
| 441 |
+
"should_training_stop": true
|
| 442 |
+
},
|
| 443 |
+
"attributes": {}
|
| 444 |
+
}
|
| 445 |
+
},
|
| 446 |
+
"total_flos": 2.1337014435577856e+16,
|
| 447 |
+
"train_batch_size": 1,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": null
|
| 450 |
+
}
|