Upload 7 files
Browse files- config.json +37 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +85 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.49.0",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4da13378a059986d121cd3bb5d8319bccb628d0e3f282fa29c1e14d45a7a5e3e
|
| 3 |
+
size 1340626860
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3edb7f3139d674468b069ed5557e70ea0e95ceea496dd00b06144e9f52be24
|
| 3 |
+
size 2681390906
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4b336c534258819cf324eff43e4acecf1273efc3efdf5ba5a1374e7f0d223b7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd6143a69576aeac9362ce4b277ee7cec45027efcc1769efeb32ee500b52865e
|
| 3 |
+
size 1000
|
trainer_state.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9201655011655012,
|
| 3 |
+
"best_model_checkpoint": "./FINAL_MODEL/results/google-bert_bert-large-uncased\\checkpoint-900",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.855,
|
| 14 |
+
"eval_f1": 0.8542790811339199,
|
| 15 |
+
"eval_loss": 0.4566820561885834,
|
| 16 |
+
"eval_precision": 0.8639506969003538,
|
| 17 |
+
"eval_recall": 0.855,
|
| 18 |
+
"eval_runtime": 2.6091,
|
| 19 |
+
"eval_samples_per_second": 76.656,
|
| 20 |
+
"eval_steps_per_second": 9.582,
|
| 21 |
+
"step": 300
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.6666666666666665,
|
| 25 |
+
"grad_norm": 0.20497265458106995,
|
| 26 |
+
"learning_rate": 9.826732673267328e-06,
|
| 27 |
+
"loss": 0.64,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_accuracy": 0.895,
|
| 33 |
+
"eval_f1": 0.8950875947754062,
|
| 34 |
+
"eval_loss": 0.31654176115989685,
|
| 35 |
+
"eval_precision": 0.9020870357712463,
|
| 36 |
+
"eval_recall": 0.895,
|
| 37 |
+
"eval_runtime": 2.7281,
|
| 38 |
+
"eval_samples_per_second": 73.312,
|
| 39 |
+
"eval_steps_per_second": 9.164,
|
| 40 |
+
"step": 600
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_accuracy": 0.92,
|
| 45 |
+
"eval_f1": 0.9201655011655012,
|
| 46 |
+
"eval_loss": 0.4490419030189514,
|
| 47 |
+
"eval_precision": 0.9214505597014926,
|
| 48 |
+
"eval_recall": 0.92,
|
| 49 |
+
"eval_runtime": 2.6499,
|
| 50 |
+
"eval_samples_per_second": 75.475,
|
| 51 |
+
"eval_steps_per_second": 9.434,
|
| 52 |
+
"step": 900
|
| 53 |
+
}
|
| 54 |
+
],
|
| 55 |
+
"logging_steps": 500,
|
| 56 |
+
"max_steps": 900,
|
| 57 |
+
"num_input_tokens_seen": 0,
|
| 58 |
+
"num_train_epochs": 3,
|
| 59 |
+
"save_steps": 500,
|
| 60 |
+
"stateful_callbacks": {
|
| 61 |
+
"EarlyStoppingCallback": {
|
| 62 |
+
"args": {
|
| 63 |
+
"early_stopping_patience": 1,
|
| 64 |
+
"early_stopping_threshold": 0.0
|
| 65 |
+
},
|
| 66 |
+
"attributes": {
|
| 67 |
+
"early_stopping_patience_counter": 0
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"TrainerControl": {
|
| 71 |
+
"args": {
|
| 72 |
+
"should_epoch_stop": false,
|
| 73 |
+
"should_evaluate": false,
|
| 74 |
+
"should_log": false,
|
| 75 |
+
"should_save": true,
|
| 76 |
+
"should_training_stop": true
|
| 77 |
+
},
|
| 78 |
+
"attributes": {}
|
| 79 |
+
}
|
| 80 |
+
},
|
| 81 |
+
"total_flos": 942535267203456.0,
|
| 82 |
+
"train_batch_size": 6,
|
| 83 |
+
"trial_name": null,
|
| 84 |
+
"trial_params": null
|
| 85 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21d236746cb3f4085518713a4792bbbeac0d2a5542e4eee2c07e4cbb0256fa1
|
| 3 |
+
size 5368
|