Training in progress, epoch 7
Browse files- logs/events.out.tfevents.1713588876.1376c752d37a.9760.23 +2 -2
- model.safetensors +1 -1
- run-23/checkpoint-1284/config.json +34 -0
- run-23/checkpoint-1284/model.safetensors +3 -0
- run-23/checkpoint-1284/optimizer.pt +3 -0
- run-23/checkpoint-1284/rng_state.pth +3 -0
- run-23/checkpoint-1284/scheduler.pt +3 -0
- run-23/checkpoint-1284/special_tokens_map.json +7 -0
- run-23/checkpoint-1284/tokenizer.json +0 -0
- run-23/checkpoint-1284/tokenizer_config.json +57 -0
- run-23/checkpoint-1284/trainer_state.json +146 -0
- run-23/checkpoint-1284/training_args.bin +3 -0
- run-23/checkpoint-1284/vocab.txt +0 -0
- run-23/checkpoint-1498/config.json +34 -0
- run-23/checkpoint-1498/model.safetensors +3 -0
- run-23/checkpoint-1498/optimizer.pt +3 -0
- run-23/checkpoint-1498/rng_state.pth +3 -0
- run-23/checkpoint-1498/scheduler.pt +3 -0
- run-23/checkpoint-1498/special_tokens_map.json +7 -0
- run-23/checkpoint-1498/tokenizer.json +0 -0
- run-23/checkpoint-1498/tokenizer_config.json +57 -0
- run-23/checkpoint-1498/trainer_state.json +166 -0
- run-23/checkpoint-1498/training_args.bin +3 -0
- run-23/checkpoint-1498/vocab.txt +0 -0
logs/events.out.tfevents.1713588876.1376c752d37a.9760.23
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25b47c8225238d198efb3d7d4a716757e60dd124fe783d8c443377e99c4be7f7
|
| 3 |
+
size 9863
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17549312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ae476f7f8d03c3164f421d2391c3ca209062edfcb2bc1c23e6f822b2b5e62f
|
| 3 |
size 17549312
|
run-23/checkpoint-1284/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "negative",
|
| 13 |
+
"1": "positive"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 512,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"negative": "0",
|
| 19 |
+
"positive": "1"
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 2,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
run-23/checkpoint-1284/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d507a2afb71b5a00aab7b4dddc6f370c778a096278e3025ae554ef7fca34cc1
|
| 3 |
+
size 17549312
|
run-23/checkpoint-1284/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c15e0c961b4e9d90967fb9dec348796c76770d722888d1cdbfc2c35557681b
|
| 3 |
+
size 35123898
|
run-23/checkpoint-1284/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faa74fb48b8739c352726086ee20186281632dbf682ba20839e3522db3e3b091
|
| 3 |
+
size 14308
|
run-23/checkpoint-1284/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1a08e941b0b7219c30f47223378a143ec2e4d19927a7e3648f5a1c7251e3d9f
|
| 3 |
+
size 1064
|
run-23/checkpoint-1284/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-23/checkpoint-1284/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-23/checkpoint-1284/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-23/checkpoint-1284/trainer_state.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7545401288810779,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-1284",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1284,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 8.174213409423828,
|
| 14 |
+
"learning_rate": 0.00021193737357349756,
|
| 15 |
+
"loss": 0.6053,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7041593438781488,
|
| 21 |
+
"eval_f1": 0.4107351225204201,
|
| 22 |
+
"eval_loss": 0.5531450510025024,
|
| 23 |
+
"eval_mcc": 0.2654659366009494,
|
| 24 |
+
"eval_precision": 0.6111111111111112,
|
| 25 |
+
"eval_recall": 0.3093145869947276,
|
| 26 |
+
"eval_runtime": 3.1397,
|
| 27 |
+
"eval_samples_per_second": 543.682,
|
| 28 |
+
"eval_steps_per_second": 17.199,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 2.549020290374756,
|
| 34 |
+
"learning_rate": 0.00018544520187681036,
|
| 35 |
+
"loss": 0.5455,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.7229056824838899,
|
| 41 |
+
"eval_f1": 0.4569460390355913,
|
| 42 |
+
"eval_loss": 0.5337331295013428,
|
| 43 |
+
"eval_mcc": 0.32023248430720136,
|
| 44 |
+
"eval_precision": 0.6589403973509934,
|
| 45 |
+
"eval_recall": 0.34973637961335674,
|
| 46 |
+
"eval_runtime": 3.1777,
|
| 47 |
+
"eval_samples_per_second": 537.185,
|
| 48 |
+
"eval_steps_per_second": 16.994,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 3.2418973445892334,
|
| 54 |
+
"learning_rate": 0.00015895303018012317,
|
| 55 |
+
"loss": 0.514,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.7311072056239016,
|
| 61 |
+
"eval_f1": 0.43122676579925656,
|
| 62 |
+
"eval_loss": 0.5188717246055603,
|
| 63 |
+
"eval_mcc": 0.3396283739174578,
|
| 64 |
+
"eval_precision": 0.7310924369747899,
|
| 65 |
+
"eval_recall": 0.30579964850615116,
|
| 66 |
+
"eval_runtime": 3.1525,
|
| 67 |
+
"eval_samples_per_second": 541.47,
|
| 68 |
+
"eval_steps_per_second": 17.129,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 4.082540988922119,
|
| 74 |
+
"learning_rate": 0.000132460858483436,
|
| 75 |
+
"loss": 0.5028,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.7281780902167545,
|
| 81 |
+
"eval_f1": 0.3796791443850267,
|
| 82 |
+
"eval_loss": 0.521298348903656,
|
| 83 |
+
"eval_mcc": 0.33395946974565643,
|
| 84 |
+
"eval_precision": 0.7932960893854749,
|
| 85 |
+
"eval_recall": 0.24956063268892795,
|
| 86 |
+
"eval_runtime": 3.1071,
|
| 87 |
+
"eval_samples_per_second": 549.395,
|
| 88 |
+
"eval_steps_per_second": 17.38,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 5.98746919631958,
|
| 94 |
+
"learning_rate": 0.00010596868678674878,
|
| 95 |
+
"loss": 0.4947,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.7492677211482133,
|
| 101 |
+
"eval_f1": 0.5668016194331983,
|
| 102 |
+
"eval_loss": 0.49519282579421997,
|
| 103 |
+
"eval_mcc": 0.4052305275875567,
|
| 104 |
+
"eval_precision": 0.6682577565632458,
|
| 105 |
+
"eval_recall": 0.492091388400703,
|
| 106 |
+
"eval_runtime": 3.1175,
|
| 107 |
+
"eval_samples_per_second": 547.552,
|
| 108 |
+
"eval_steps_per_second": 17.321,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 4.624367713928223,
|
| 114 |
+
"learning_rate": 7.947651509006158e-05,
|
| 115 |
+
"loss": 0.4792,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.7545401288810779,
|
| 121 |
+
"eval_f1": 0.6080449017773621,
|
| 122 |
+
"eval_loss": 0.49225014448165894,
|
| 123 |
+
"eval_mcc": 0.4323544910894334,
|
| 124 |
+
"eval_precision": 0.65,
|
| 125 |
+
"eval_recall": 0.5711775043936731,
|
| 126 |
+
"eval_runtime": 3.1259,
|
| 127 |
+
"eval_samples_per_second": 546.074,
|
| 128 |
+
"eval_steps_per_second": 17.275,
|
| 129 |
+
"step": 1284
|
| 130 |
+
}
|
| 131 |
+
],
|
| 132 |
+
"logging_steps": 500,
|
| 133 |
+
"max_steps": 1926,
|
| 134 |
+
"num_input_tokens_seen": 0,
|
| 135 |
+
"num_train_epochs": 9,
|
| 136 |
+
"save_steps": 500,
|
| 137 |
+
"total_flos": 3148653986640.0,
|
| 138 |
+
"train_batch_size": 32,
|
| 139 |
+
"trial_name": null,
|
| 140 |
+
"trial_params": {
|
| 141 |
+
"alpha": 0.9926400370862213,
|
| 142 |
+
"learning_rate": 0.00023842954527018476,
|
| 143 |
+
"num_train_epochs": 9,
|
| 144 |
+
"temperature": 23
|
| 145 |
+
}
|
| 146 |
+
}
|
run-23/checkpoint-1284/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af146dad23da6bdb3233b97634c1ec6cd3215ed9e511d41e8ad3a40f344164c7
|
| 3 |
+
size 5048
|
run-23/checkpoint-1284/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-23/checkpoint-1498/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "negative",
|
| 13 |
+
"1": "positive"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 512,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"negative": "0",
|
| 19 |
+
"positive": "1"
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 2,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
run-23/checkpoint-1498/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ae476f7f8d03c3164f421d2391c3ca209062edfcb2bc1c23e6f822b2b5e62f
|
| 3 |
+
size 17549312
|
run-23/checkpoint-1498/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a581d985d902b76fe6b95b9b9bd590582096bde5933d3939386cdae23d7748d
|
| 3 |
+
size 35123898
|
run-23/checkpoint-1498/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
|
| 3 |
+
size 14308
|
run-23/checkpoint-1498/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7067b9bb434d76147b5fff58b2bc3d66b23a76cc2d8598110ee2b031cf18d9a
|
| 3 |
+
size 1064
|
run-23/checkpoint-1498/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-23/checkpoint-1498/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-23/checkpoint-1498/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-23/checkpoint-1498/trainer_state.json
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7562975981253661,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-1498",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1498,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 8.174213409423828,
|
| 14 |
+
"learning_rate": 0.00021193737357349756,
|
| 15 |
+
"loss": 0.6053,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7041593438781488,
|
| 21 |
+
"eval_f1": 0.4107351225204201,
|
| 22 |
+
"eval_loss": 0.5531450510025024,
|
| 23 |
+
"eval_mcc": 0.2654659366009494,
|
| 24 |
+
"eval_precision": 0.6111111111111112,
|
| 25 |
+
"eval_recall": 0.3093145869947276,
|
| 26 |
+
"eval_runtime": 3.1397,
|
| 27 |
+
"eval_samples_per_second": 543.682,
|
| 28 |
+
"eval_steps_per_second": 17.199,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 2.549020290374756,
|
| 34 |
+
"learning_rate": 0.00018544520187681036,
|
| 35 |
+
"loss": 0.5455,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.7229056824838899,
|
| 41 |
+
"eval_f1": 0.4569460390355913,
|
| 42 |
+
"eval_loss": 0.5337331295013428,
|
| 43 |
+
"eval_mcc": 0.32023248430720136,
|
| 44 |
+
"eval_precision": 0.6589403973509934,
|
| 45 |
+
"eval_recall": 0.34973637961335674,
|
| 46 |
+
"eval_runtime": 3.1777,
|
| 47 |
+
"eval_samples_per_second": 537.185,
|
| 48 |
+
"eval_steps_per_second": 16.994,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 3.2418973445892334,
|
| 54 |
+
"learning_rate": 0.00015895303018012317,
|
| 55 |
+
"loss": 0.514,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.7311072056239016,
|
| 61 |
+
"eval_f1": 0.43122676579925656,
|
| 62 |
+
"eval_loss": 0.5188717246055603,
|
| 63 |
+
"eval_mcc": 0.3396283739174578,
|
| 64 |
+
"eval_precision": 0.7310924369747899,
|
| 65 |
+
"eval_recall": 0.30579964850615116,
|
| 66 |
+
"eval_runtime": 3.1525,
|
| 67 |
+
"eval_samples_per_second": 541.47,
|
| 68 |
+
"eval_steps_per_second": 17.129,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 4.082540988922119,
|
| 74 |
+
"learning_rate": 0.000132460858483436,
|
| 75 |
+
"loss": 0.5028,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.7281780902167545,
|
| 81 |
+
"eval_f1": 0.3796791443850267,
|
| 82 |
+
"eval_loss": 0.521298348903656,
|
| 83 |
+
"eval_mcc": 0.33395946974565643,
|
| 84 |
+
"eval_precision": 0.7932960893854749,
|
| 85 |
+
"eval_recall": 0.24956063268892795,
|
| 86 |
+
"eval_runtime": 3.1071,
|
| 87 |
+
"eval_samples_per_second": 549.395,
|
| 88 |
+
"eval_steps_per_second": 17.38,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 5.98746919631958,
|
| 94 |
+
"learning_rate": 0.00010596868678674878,
|
| 95 |
+
"loss": 0.4947,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.7492677211482133,
|
| 101 |
+
"eval_f1": 0.5668016194331983,
|
| 102 |
+
"eval_loss": 0.49519282579421997,
|
| 103 |
+
"eval_mcc": 0.4052305275875567,
|
| 104 |
+
"eval_precision": 0.6682577565632458,
|
| 105 |
+
"eval_recall": 0.492091388400703,
|
| 106 |
+
"eval_runtime": 3.1175,
|
| 107 |
+
"eval_samples_per_second": 547.552,
|
| 108 |
+
"eval_steps_per_second": 17.321,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 4.624367713928223,
|
| 114 |
+
"learning_rate": 7.947651509006158e-05,
|
| 115 |
+
"loss": 0.4792,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.7545401288810779,
|
| 121 |
+
"eval_f1": 0.6080449017773621,
|
| 122 |
+
"eval_loss": 0.49225014448165894,
|
| 123 |
+
"eval_mcc": 0.4323544910894334,
|
| 124 |
+
"eval_precision": 0.65,
|
| 125 |
+
"eval_recall": 0.5711775043936731,
|
| 126 |
+
"eval_runtime": 3.1259,
|
| 127 |
+
"eval_samples_per_second": 546.074,
|
| 128 |
+
"eval_steps_per_second": 17.275,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 3.617922067642212,
|
| 134 |
+
"learning_rate": 5.298434339337439e-05,
|
| 135 |
+
"loss": 0.4667,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.7562975981253661,
|
| 141 |
+
"eval_f1": 0.5315315315315315,
|
| 142 |
+
"eval_loss": 0.4943116009235382,
|
| 143 |
+
"eval_mcc": 0.4133753055226225,
|
| 144 |
+
"eval_precision": 0.7398119122257053,
|
| 145 |
+
"eval_recall": 0.4147627416520211,
|
| 146 |
+
"eval_runtime": 3.1423,
|
| 147 |
+
"eval_samples_per_second": 543.239,
|
| 148 |
+
"eval_steps_per_second": 17.185,
|
| 149 |
+
"step": 1498
|
| 150 |
+
}
|
| 151 |
+
],
|
| 152 |
+
"logging_steps": 500,
|
| 153 |
+
"max_steps": 1926,
|
| 154 |
+
"num_input_tokens_seen": 0,
|
| 155 |
+
"num_train_epochs": 9,
|
| 156 |
+
"save_steps": 500,
|
| 157 |
+
"total_flos": 3673429651080.0,
|
| 158 |
+
"train_batch_size": 32,
|
| 159 |
+
"trial_name": null,
|
| 160 |
+
"trial_params": {
|
| 161 |
+
"alpha": 0.9926400370862213,
|
| 162 |
+
"learning_rate": 0.00023842954527018476,
|
| 163 |
+
"num_train_epochs": 9,
|
| 164 |
+
"temperature": 23
|
| 165 |
+
}
|
| 166 |
+
}
|
run-23/checkpoint-1498/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af146dad23da6bdb3233b97634c1ec6cd3215ed9e511d41e8ad3a40f344164c7
|
| 3 |
+
size 5048
|
run-23/checkpoint-1498/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|