Delete files checkpoint-5589/ with huggingface_hub
Browse files- checkpoint-5589/config.json +0 -36
- checkpoint-5589/model.safetensors +0 -3
- checkpoint-5589/optimizer.pt +0 -3
- checkpoint-5589/rng_state.pth +0 -3
- checkpoint-5589/scaler.pt +0 -3
- checkpoint-5589/scheduler.pt +0 -3
- checkpoint-5589/special_tokens_map.json +0 -7
- checkpoint-5589/tokenizer.json +0 -0
- checkpoint-5589/tokenizer_config.json +0 -58
- checkpoint-5589/trainer_state.json +0 -141
- checkpoint-5589/training_args.bin +0 -3
- checkpoint-5589/vocab.txt +0 -0
checkpoint-5589/config.json
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForSequenceClassification"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"classifier_dropout": null,
|
| 7 |
-
"gradient_checkpointing": false,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size": 768,
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "positive",
|
| 13 |
-
"1": "negative",
|
| 14 |
-
"2": "neutral"
|
| 15 |
-
},
|
| 16 |
-
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size": 3072,
|
| 18 |
-
"label2id": {
|
| 19 |
-
"negative": 1,
|
| 20 |
-
"neutral": 2,
|
| 21 |
-
"positive": 0
|
| 22 |
-
},
|
| 23 |
-
"layer_norm_eps": 1e-12,
|
| 24 |
-
"max_position_embeddings": 512,
|
| 25 |
-
"model_type": "bert",
|
| 26 |
-
"num_attention_heads": 12,
|
| 27 |
-
"num_hidden_layers": 12,
|
| 28 |
-
"pad_token_id": 0,
|
| 29 |
-
"position_embedding_type": "absolute",
|
| 30 |
-
"problem_type": "single_label_classification",
|
| 31 |
-
"torch_dtype": "float32",
|
| 32 |
-
"transformers_version": "4.52.4",
|
| 33 |
-
"type_vocab_size": 2,
|
| 34 |
-
"use_cache": true,
|
| 35 |
-
"vocab_size": 30522
|
| 36 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:759e5a842f3048c57bd55eebe211cb92e2b5dacebb3e68541014273e94b2a3a4
|
| 3 |
-
size 437961724
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9b13b05f5ace592687e86e3e153782e7c21a58ffb7b857f9a3820dad0119d978
|
| 3 |
-
size 876044939
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bb46cbd184ddb3ea6c036b3de056d6c9c0bf79965383996adb97a80324eecba0
|
| 3 |
-
size 14645
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:011cddbd80d56274c6cdf2ef6540a6631fc71a1c4ee2a3bd48f51af7775d9509
|
| 3 |
-
size 1383
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:39ae5c533a8277d8e0a3e4f104cbbde54d66196b4b2c290e7fff9f5732b5ce7d
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-5589/tokenizer_config.json
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "[PAD]",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"100": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"101": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"102": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"103": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"clean_up_tokenization_spaces": true,
|
| 45 |
-
"cls_token": "[CLS]",
|
| 46 |
-
"do_basic_tokenize": true,
|
| 47 |
-
"do_lower_case": true,
|
| 48 |
-
"extra_special_tokens": {},
|
| 49 |
-
"mask_token": "[MASK]",
|
| 50 |
-
"model_max_length": 512,
|
| 51 |
-
"never_split": null,
|
| 52 |
-
"pad_token": "[PAD]",
|
| 53 |
-
"sep_token": "[SEP]",
|
| 54 |
-
"strip_accents": null,
|
| 55 |
-
"tokenize_chinese_chars": true,
|
| 56 |
-
"tokenizer_class": "BertTokenizer",
|
| 57 |
-
"unk_token": "[UNK]"
|
| 58 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/trainer_state.json
DELETED
|
@@ -1,141 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 3726,
|
| 3 |
-
"best_metric": 0.18097351491451263,
|
| 4 |
-
"best_model_checkpoint": "./model\\checkpoint-3726",
|
| 5 |
-
"epoch": 3.0,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 5589,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.2683843263553409,
|
| 14 |
-
"grad_norm": 4.979691505432129,
|
| 15 |
-
"learning_rate": 4.557165861513688e-05,
|
| 16 |
-
"loss": 0.618,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.5367686527106817,
|
| 21 |
-
"grad_norm": 10.513946533203125,
|
| 22 |
-
"learning_rate": 4.109858650921453e-05,
|
| 23 |
-
"loss": 0.3634,
|
| 24 |
-
"step": 1000
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.8051529790660226,
|
| 28 |
-
"grad_norm": 0.9428963661193848,
|
| 29 |
-
"learning_rate": 3.662551440329218e-05,
|
| 30 |
-
"loss": 0.2803,
|
| 31 |
-
"step": 1500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 1.0,
|
| 35 |
-
"eval_accuracy": 0.9363758389261745,
|
| 36 |
-
"eval_f1": 0.936185778659979,
|
| 37 |
-
"eval_loss": 0.21076564490795135,
|
| 38 |
-
"eval_runtime": 37.2544,
|
| 39 |
-
"eval_samples_per_second": 199.977,
|
| 40 |
-
"eval_steps_per_second": 12.509,
|
| 41 |
-
"step": 1863
|
| 42 |
-
},
|
| 43 |
-
{
|
| 44 |
-
"epoch": 1.0735373054213633,
|
| 45 |
-
"grad_norm": 4.273161888122559,
|
| 46 |
-
"learning_rate": 3.215244229736983e-05,
|
| 47 |
-
"loss": 0.2266,
|
| 48 |
-
"step": 2000
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 1.3419216317767042,
|
| 52 |
-
"grad_norm": 9.790454864501953,
|
| 53 |
-
"learning_rate": 2.767937019144749e-05,
|
| 54 |
-
"loss": 0.1773,
|
| 55 |
-
"step": 2500
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"epoch": 1.6103059581320451,
|
| 59 |
-
"grad_norm": 0.9836813807487488,
|
| 60 |
-
"learning_rate": 2.3215244229736983e-05,
|
| 61 |
-
"loss": 0.1549,
|
| 62 |
-
"step": 3000
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 1.8786902844873858,
|
| 66 |
-
"grad_norm": 5.523079872131348,
|
| 67 |
-
"learning_rate": 1.8751118268026483e-05,
|
| 68 |
-
"loss": 0.1524,
|
| 69 |
-
"step": 3500
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 2.0,
|
| 73 |
-
"eval_accuracy": 0.9499328859060403,
|
| 74 |
-
"eval_f1": 0.9499109066150679,
|
| 75 |
-
"eval_loss": 0.18097351491451263,
|
| 76 |
-
"eval_runtime": 37.2921,
|
| 77 |
-
"eval_samples_per_second": 199.774,
|
| 78 |
-
"eval_steps_per_second": 12.496,
|
| 79 |
-
"step": 3726
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 2.1470746108427265,
|
| 83 |
-
"grad_norm": 0.0565815269947052,
|
| 84 |
-
"learning_rate": 1.4278046162104134e-05,
|
| 85 |
-
"loss": 0.1086,
|
| 86 |
-
"step": 4000
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 2.4154589371980677,
|
| 90 |
-
"grad_norm": 0.1514054834842682,
|
| 91 |
-
"learning_rate": 9.804974056181785e-06,
|
| 92 |
-
"loss": 0.0918,
|
| 93 |
-
"step": 4500
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 2.6838432635534084,
|
| 97 |
-
"grad_norm": 0.029303351417183876,
|
| 98 |
-
"learning_rate": 5.331901950259439e-06,
|
| 99 |
-
"loss": 0.084,
|
| 100 |
-
"step": 5000
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 2.952227589908749,
|
| 104 |
-
"grad_norm": 0.0346352718770504,
|
| 105 |
-
"learning_rate": 8.588298443370907e-07,
|
| 106 |
-
"loss": 0.0709,
|
| 107 |
-
"step": 5500
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 3.0,
|
| 111 |
-
"eval_accuracy": 0.9575838926174497,
|
| 112 |
-
"eval_f1": 0.9576189144243515,
|
| 113 |
-
"eval_loss": 0.19314545392990112,
|
| 114 |
-
"eval_runtime": 37.4152,
|
| 115 |
-
"eval_samples_per_second": 199.117,
|
| 116 |
-
"eval_steps_per_second": 12.455,
|
| 117 |
-
"step": 5589
|
| 118 |
-
}
|
| 119 |
-
],
|
| 120 |
-
"logging_steps": 500,
|
| 121 |
-
"max_steps": 5589,
|
| 122 |
-
"num_input_tokens_seen": 0,
|
| 123 |
-
"num_train_epochs": 3,
|
| 124 |
-
"save_steps": 500,
|
| 125 |
-
"stateful_callbacks": {
|
| 126 |
-
"TrainerControl": {
|
| 127 |
-
"args": {
|
| 128 |
-
"should_epoch_stop": false,
|
| 129 |
-
"should_evaluate": false,
|
| 130 |
-
"should_log": false,
|
| 131 |
-
"should_save": true,
|
| 132 |
-
"should_training_stop": true
|
| 133 |
-
},
|
| 134 |
-
"attributes": {}
|
| 135 |
-
}
|
| 136 |
-
},
|
| 137 |
-
"total_flos": 2.3521550204630016e+16,
|
| 138 |
-
"train_batch_size": 16,
|
| 139 |
-
"trial_name": null,
|
| 140 |
-
"trial_params": null
|
| 141 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0bc1e524146d6310e51751575751860a0b7e8cf94fcc2f0fbef92d0e70c0d980
|
| 3 |
-
size 5649
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5589/vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|