Upload folder using huggingface_hub
Browse files- checkpoint-1800/config.json +24 -0
- checkpoint-1800/model.safetensors +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/rng_state.pth +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/special_tokens_map.json +7 -0
- checkpoint-1800/tokenizer.json +0 -0
- checkpoint-1800/tokenizer_config.json +56 -0
- checkpoint-1800/trainer_state.json +367 -0
- checkpoint-1800/training_args.bin +3 -0
- checkpoint-1800/vocab.txt +0 -0
- checkpoint-1896/config.json +24 -0
- checkpoint-1896/model.safetensors +3 -0
- checkpoint-1896/optimizer.pt +3 -0
- checkpoint-1896/rng_state.pth +3 -0
- checkpoint-1896/scheduler.pt +3 -0
- checkpoint-1896/special_tokens_map.json +7 -0
- checkpoint-1896/tokenizer.json +0 -0
- checkpoint-1896/tokenizer_config.json +56 -0
- checkpoint-1896/trainer_state.json +374 -0
- checkpoint-1896/training_args.bin +3 -0
- checkpoint-1896/vocab.txt +0 -0
- config.json +24 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- vocab.txt +0 -0
checkpoint-1800/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
checkpoint-1800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92361523a2e2174ac5ae3cd0c48c4f1b189d2433258d2b82f2db5832295380ad
|
| 3 |
+
size 267832560
|
checkpoint-1800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a1a0d7919108a852ac69c7b31dab6a468d19c1cc4f55a15572fe165501f701a
|
| 3 |
+
size 535727290
|
checkpoint-1800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2abe76ba90e9be52369dd6eb49ba256054c772c6d349b4e19d582552b44d0b4e
|
| 3 |
+
size 14244
|
checkpoint-1800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:608f2f562aa9c61ea2f62642beff17b896a1118a0c36c2c98d8f987840a869d0
|
| 3 |
+
size 1064
|
checkpoint-1800/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 |
+
}
|
checkpoint-1800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1800/trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.848101265822785,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 1800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07911392405063292,
|
| 14 |
+
"grad_norm": 3.0736875534057617,
|
| 15 |
+
"learning_rate": 1.94831223628692e-05,
|
| 16 |
+
"loss": 0.4829,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.15822784810126583,
|
| 21 |
+
"grad_norm": 4.341821670532227,
|
| 22 |
+
"learning_rate": 1.8955696202531647e-05,
|
| 23 |
+
"loss": 0.2281,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.23734177215189872,
|
| 28 |
+
"grad_norm": 6.131030082702637,
|
| 29 |
+
"learning_rate": 1.8428270042194095e-05,
|
| 30 |
+
"loss": 0.2278,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.31645569620253167,
|
| 35 |
+
"grad_norm": 6.115195274353027,
|
| 36 |
+
"learning_rate": 1.7900843881856543e-05,
|
| 37 |
+
"loss": 0.2047,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.31645569620253167,
|
| 42 |
+
"eval_accuracy": 0.9299841772151899,
|
| 43 |
+
"eval_loss": 0.1906946450471878,
|
| 44 |
+
"eval_runtime": 21.5532,
|
| 45 |
+
"eval_samples_per_second": 117.291,
|
| 46 |
+
"eval_steps_per_second": 1.856,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.39556962025316456,
|
| 51 |
+
"grad_norm": 5.020113945007324,
|
| 52 |
+
"learning_rate": 1.7373417721518987e-05,
|
| 53 |
+
"loss": 0.1944,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.47468354430379744,
|
| 58 |
+
"grad_norm": 0.6651616096496582,
|
| 59 |
+
"learning_rate": 1.6845991561181435e-05,
|
| 60 |
+
"loss": 0.1724,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.5537974683544303,
|
| 65 |
+
"grad_norm": 2.898188829421997,
|
| 66 |
+
"learning_rate": 1.6318565400843886e-05,
|
| 67 |
+
"loss": 0.1649,
|
| 68 |
+
"step": 350
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6329113924050633,
|
| 72 |
+
"grad_norm": 3.437992572784424,
|
| 73 |
+
"learning_rate": 1.579113924050633e-05,
|
| 74 |
+
"loss": 0.1756,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6329113924050633,
|
| 79 |
+
"eval_accuracy": 0.9438291139240507,
|
| 80 |
+
"eval_loss": 0.15072669088840485,
|
| 81 |
+
"eval_runtime": 21.8255,
|
| 82 |
+
"eval_samples_per_second": 115.828,
|
| 83 |
+
"eval_steps_per_second": 1.833,
|
| 84 |
+
"step": 400
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.7120253164556962,
|
| 88 |
+
"grad_norm": 3.6517462730407715,
|
| 89 |
+
"learning_rate": 1.5263713080168778e-05,
|
| 90 |
+
"loss": 0.1751,
|
| 91 |
+
"step": 450
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.7911392405063291,
|
| 95 |
+
"grad_norm": 3.4184911251068115,
|
| 96 |
+
"learning_rate": 1.4736286919831224e-05,
|
| 97 |
+
"loss": 0.1717,
|
| 98 |
+
"step": 500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.870253164556962,
|
| 102 |
+
"grad_norm": 7.792496204376221,
|
| 103 |
+
"learning_rate": 1.4208860759493672e-05,
|
| 104 |
+
"loss": 0.1422,
|
| 105 |
+
"step": 550
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9493670886075949,
|
| 109 |
+
"grad_norm": 5.846955299377441,
|
| 110 |
+
"learning_rate": 1.3681434599156118e-05,
|
| 111 |
+
"loss": 0.154,
|
| 112 |
+
"step": 600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9493670886075949,
|
| 116 |
+
"eval_accuracy": 0.9438291139240507,
|
| 117 |
+
"eval_loss": 0.15628908574581146,
|
| 118 |
+
"eval_runtime": 21.8985,
|
| 119 |
+
"eval_samples_per_second": 115.442,
|
| 120 |
+
"eval_steps_per_second": 1.827,
|
| 121 |
+
"step": 600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0284810126582278,
|
| 125 |
+
"grad_norm": 0.5277347564697266,
|
| 126 |
+
"learning_rate": 1.3154008438818566e-05,
|
| 127 |
+
"loss": 0.1269,
|
| 128 |
+
"step": 650
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.1075949367088607,
|
| 132 |
+
"grad_norm": 1.5498286485671997,
|
| 133 |
+
"learning_rate": 1.2626582278481014e-05,
|
| 134 |
+
"loss": 0.1419,
|
| 135 |
+
"step": 700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1867088607594938,
|
| 139 |
+
"grad_norm": 4.222334861755371,
|
| 140 |
+
"learning_rate": 1.209915611814346e-05,
|
| 141 |
+
"loss": 0.1092,
|
| 142 |
+
"step": 750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.2658227848101267,
|
| 146 |
+
"grad_norm": 7.636617660522461,
|
| 147 |
+
"learning_rate": 1.1571729957805908e-05,
|
| 148 |
+
"loss": 0.0975,
|
| 149 |
+
"step": 800
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2658227848101267,
|
| 153 |
+
"eval_accuracy": 0.9560917721518988,
|
| 154 |
+
"eval_loss": 0.15132202208042145,
|
| 155 |
+
"eval_runtime": 21.7326,
|
| 156 |
+
"eval_samples_per_second": 116.323,
|
| 157 |
+
"eval_steps_per_second": 1.841,
|
| 158 |
+
"step": 800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3449367088607596,
|
| 162 |
+
"grad_norm": 2.144458770751953,
|
| 163 |
+
"learning_rate": 1.1044303797468354e-05,
|
| 164 |
+
"loss": 0.103,
|
| 165 |
+
"step": 850
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.4240506329113924,
|
| 169 |
+
"grad_norm": 0.4628768265247345,
|
| 170 |
+
"learning_rate": 1.0516877637130802e-05,
|
| 171 |
+
"loss": 0.0927,
|
| 172 |
+
"step": 900
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.5031645569620253,
|
| 176 |
+
"grad_norm": 4.971005916595459,
|
| 177 |
+
"learning_rate": 9.98945147679325e-06,
|
| 178 |
+
"loss": 0.0893,
|
| 179 |
+
"step": 950
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.5822784810126582,
|
| 183 |
+
"grad_norm": 4.186551570892334,
|
| 184 |
+
"learning_rate": 9.462025316455697e-06,
|
| 185 |
+
"loss": 0.0987,
|
| 186 |
+
"step": 1000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5822784810126582,
|
| 190 |
+
"eval_accuracy": 0.9545094936708861,
|
| 191 |
+
"eval_loss": 0.1511051058769226,
|
| 192 |
+
"eval_runtime": 21.7262,
|
| 193 |
+
"eval_samples_per_second": 116.357,
|
| 194 |
+
"eval_steps_per_second": 1.841,
|
| 195 |
+
"step": 1000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6613924050632911,
|
| 199 |
+
"grad_norm": 2.5125277042388916,
|
| 200 |
+
"learning_rate": 8.934599156118145e-06,
|
| 201 |
+
"loss": 0.0865,
|
| 202 |
+
"step": 1050
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.740506329113924,
|
| 206 |
+
"grad_norm": 15.021677017211914,
|
| 207 |
+
"learning_rate": 8.407172995780591e-06,
|
| 208 |
+
"loss": 0.0937,
|
| 209 |
+
"step": 1100
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.8196202531645569,
|
| 213 |
+
"grad_norm": 6.045713901519775,
|
| 214 |
+
"learning_rate": 7.879746835443039e-06,
|
| 215 |
+
"loss": 0.0776,
|
| 216 |
+
"step": 1150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.8987341772151898,
|
| 220 |
+
"grad_norm": 2.6441538333892822,
|
| 221 |
+
"learning_rate": 7.352320675105486e-06,
|
| 222 |
+
"loss": 0.0972,
|
| 223 |
+
"step": 1200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.8987341772151898,
|
| 227 |
+
"eval_accuracy": 0.9533227848101266,
|
| 228 |
+
"eval_loss": 0.152543842792511,
|
| 229 |
+
"eval_runtime": 21.691,
|
| 230 |
+
"eval_samples_per_second": 116.546,
|
| 231 |
+
"eval_steps_per_second": 1.844,
|
| 232 |
+
"step": 1200
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.9778481012658227,
|
| 236 |
+
"grad_norm": 12.360393524169922,
|
| 237 |
+
"learning_rate": 6.8248945147679335e-06,
|
| 238 |
+
"loss": 0.0984,
|
| 239 |
+
"step": 1250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.0569620253164556,
|
| 243 |
+
"grad_norm": 1.6513817310333252,
|
| 244 |
+
"learning_rate": 6.2974683544303804e-06,
|
| 245 |
+
"loss": 0.0616,
|
| 246 |
+
"step": 1300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.1360759493670884,
|
| 250 |
+
"grad_norm": 0.32455408573150635,
|
| 251 |
+
"learning_rate": 5.770042194092827e-06,
|
| 252 |
+
"loss": 0.0525,
|
| 253 |
+
"step": 1350
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.2151898734177213,
|
| 257 |
+
"grad_norm": 0.3913777470588684,
|
| 258 |
+
"learning_rate": 5.242616033755274e-06,
|
| 259 |
+
"loss": 0.0498,
|
| 260 |
+
"step": 1400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.2151898734177213,
|
| 264 |
+
"eval_accuracy": 0.9580696202531646,
|
| 265 |
+
"eval_loss": 0.16716444492340088,
|
| 266 |
+
"eval_runtime": 21.651,
|
| 267 |
+
"eval_samples_per_second": 116.761,
|
| 268 |
+
"eval_steps_per_second": 1.847,
|
| 269 |
+
"step": 1400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2943037974683547,
|
| 273 |
+
"grad_norm": 0.17981760203838348,
|
| 274 |
+
"learning_rate": 4.715189873417722e-06,
|
| 275 |
+
"loss": 0.0555,
|
| 276 |
+
"step": 1450
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.3734177215189876,
|
| 280 |
+
"grad_norm": 8.692523956298828,
|
| 281 |
+
"learning_rate": 4.187763713080169e-06,
|
| 282 |
+
"loss": 0.063,
|
| 283 |
+
"step": 1500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.4525316455696204,
|
| 287 |
+
"grad_norm": 4.8722100257873535,
|
| 288 |
+
"learning_rate": 3.6603375527426164e-06,
|
| 289 |
+
"loss": 0.0421,
|
| 290 |
+
"step": 1550
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.5316455696202533,
|
| 294 |
+
"grad_norm": 0.40789884328842163,
|
| 295 |
+
"learning_rate": 3.132911392405064e-06,
|
| 296 |
+
"loss": 0.0691,
|
| 297 |
+
"step": 1600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.5316455696202533,
|
| 301 |
+
"eval_accuracy": 0.9560917721518988,
|
| 302 |
+
"eval_loss": 0.1713864654302597,
|
| 303 |
+
"eval_runtime": 21.7194,
|
| 304 |
+
"eval_samples_per_second": 116.394,
|
| 305 |
+
"eval_steps_per_second": 1.842,
|
| 306 |
+
"step": 1600
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.6107594936708862,
|
| 310 |
+
"grad_norm": 0.035212136805057526,
|
| 311 |
+
"learning_rate": 2.6054852320675107e-06,
|
| 312 |
+
"loss": 0.0488,
|
| 313 |
+
"step": 1650
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.689873417721519,
|
| 317 |
+
"grad_norm": 0.17139802873134613,
|
| 318 |
+
"learning_rate": 2.0780590717299577e-06,
|
| 319 |
+
"loss": 0.043,
|
| 320 |
+
"step": 1700
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.768987341772152,
|
| 324 |
+
"grad_norm": 2.1545848846435547,
|
| 325 |
+
"learning_rate": 1.550632911392405e-06,
|
| 326 |
+
"loss": 0.0428,
|
| 327 |
+
"step": 1750
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.848101265822785,
|
| 331 |
+
"grad_norm": 0.045621346682310104,
|
| 332 |
+
"learning_rate": 1.0232067510548524e-06,
|
| 333 |
+
"loss": 0.0296,
|
| 334 |
+
"step": 1800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.848101265822785,
|
| 338 |
+
"eval_accuracy": 0.9572784810126582,
|
| 339 |
+
"eval_loss": 0.17169879376888275,
|
| 340 |
+
"eval_runtime": 22.181,
|
| 341 |
+
"eval_samples_per_second": 113.972,
|
| 342 |
+
"eval_steps_per_second": 1.803,
|
| 343 |
+
"step": 1800
|
| 344 |
+
}
|
| 345 |
+
],
|
| 346 |
+
"logging_steps": 50,
|
| 347 |
+
"max_steps": 1896,
|
| 348 |
+
"num_input_tokens_seen": 0,
|
| 349 |
+
"num_train_epochs": 3,
|
| 350 |
+
"save_steps": 200,
|
| 351 |
+
"stateful_callbacks": {
|
| 352 |
+
"TrainerControl": {
|
| 353 |
+
"args": {
|
| 354 |
+
"should_epoch_stop": false,
|
| 355 |
+
"should_evaluate": false,
|
| 356 |
+
"should_log": false,
|
| 357 |
+
"should_save": true,
|
| 358 |
+
"should_training_stop": false
|
| 359 |
+
},
|
| 360 |
+
"attributes": {}
|
| 361 |
+
}
|
| 362 |
+
},
|
| 363 |
+
"total_flos": 7628002684207104.0,
|
| 364 |
+
"train_batch_size": 32,
|
| 365 |
+
"trial_name": null,
|
| 366 |
+
"trial_params": null
|
| 367 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268993dc03cb72c869ff0efb186a5fffad48027344a07450746f7b8d3fe16e12
|
| 3 |
+
size 5240
|
checkpoint-1800/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1896/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
checkpoint-1896/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d930f19a93192dfa853d23448a377774cecc9585085bd3bdbf685058964f0e6
|
| 3 |
+
size 267832560
|
checkpoint-1896/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db2ded89bfb23607d512e8a8c69691b3318732c7768dd2760478e6e6a977f83
|
| 3 |
+
size 535727290
|
checkpoint-1896/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89c925c2febcdddfb5e1d94d480e5902242b7a5fa7cd199d13d7369ee8c76e96
|
| 3 |
+
size 14244
|
checkpoint-1896/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:390a197240414e3c06b30b37efc4c9f73bc2faa2335ea640c697ebbac4f13d0a
|
| 3 |
+
size 1064
|
checkpoint-1896/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 |
+
}
|
checkpoint-1896/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1896/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1896/trainer_state.json
ADDED
|
@@ -0,0 +1,374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 1896,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07911392405063292,
|
| 14 |
+
"grad_norm": 3.0736875534057617,
|
| 15 |
+
"learning_rate": 1.94831223628692e-05,
|
| 16 |
+
"loss": 0.4829,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.15822784810126583,
|
| 21 |
+
"grad_norm": 4.341821670532227,
|
| 22 |
+
"learning_rate": 1.8955696202531647e-05,
|
| 23 |
+
"loss": 0.2281,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.23734177215189872,
|
| 28 |
+
"grad_norm": 6.131030082702637,
|
| 29 |
+
"learning_rate": 1.8428270042194095e-05,
|
| 30 |
+
"loss": 0.2278,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.31645569620253167,
|
| 35 |
+
"grad_norm": 6.115195274353027,
|
| 36 |
+
"learning_rate": 1.7900843881856543e-05,
|
| 37 |
+
"loss": 0.2047,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.31645569620253167,
|
| 42 |
+
"eval_accuracy": 0.9299841772151899,
|
| 43 |
+
"eval_loss": 0.1906946450471878,
|
| 44 |
+
"eval_runtime": 21.5532,
|
| 45 |
+
"eval_samples_per_second": 117.291,
|
| 46 |
+
"eval_steps_per_second": 1.856,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.39556962025316456,
|
| 51 |
+
"grad_norm": 5.020113945007324,
|
| 52 |
+
"learning_rate": 1.7373417721518987e-05,
|
| 53 |
+
"loss": 0.1944,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.47468354430379744,
|
| 58 |
+
"grad_norm": 0.6651616096496582,
|
| 59 |
+
"learning_rate": 1.6845991561181435e-05,
|
| 60 |
+
"loss": 0.1724,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.5537974683544303,
|
| 65 |
+
"grad_norm": 2.898188829421997,
|
| 66 |
+
"learning_rate": 1.6318565400843886e-05,
|
| 67 |
+
"loss": 0.1649,
|
| 68 |
+
"step": 350
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6329113924050633,
|
| 72 |
+
"grad_norm": 3.437992572784424,
|
| 73 |
+
"learning_rate": 1.579113924050633e-05,
|
| 74 |
+
"loss": 0.1756,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6329113924050633,
|
| 79 |
+
"eval_accuracy": 0.9438291139240507,
|
| 80 |
+
"eval_loss": 0.15072669088840485,
|
| 81 |
+
"eval_runtime": 21.8255,
|
| 82 |
+
"eval_samples_per_second": 115.828,
|
| 83 |
+
"eval_steps_per_second": 1.833,
|
| 84 |
+
"step": 400
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.7120253164556962,
|
| 88 |
+
"grad_norm": 3.6517462730407715,
|
| 89 |
+
"learning_rate": 1.5263713080168778e-05,
|
| 90 |
+
"loss": 0.1751,
|
| 91 |
+
"step": 450
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.7911392405063291,
|
| 95 |
+
"grad_norm": 3.4184911251068115,
|
| 96 |
+
"learning_rate": 1.4736286919831224e-05,
|
| 97 |
+
"loss": 0.1717,
|
| 98 |
+
"step": 500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.870253164556962,
|
| 102 |
+
"grad_norm": 7.792496204376221,
|
| 103 |
+
"learning_rate": 1.4208860759493672e-05,
|
| 104 |
+
"loss": 0.1422,
|
| 105 |
+
"step": 550
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9493670886075949,
|
| 109 |
+
"grad_norm": 5.846955299377441,
|
| 110 |
+
"learning_rate": 1.3681434599156118e-05,
|
| 111 |
+
"loss": 0.154,
|
| 112 |
+
"step": 600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9493670886075949,
|
| 116 |
+
"eval_accuracy": 0.9438291139240507,
|
| 117 |
+
"eval_loss": 0.15628908574581146,
|
| 118 |
+
"eval_runtime": 21.8985,
|
| 119 |
+
"eval_samples_per_second": 115.442,
|
| 120 |
+
"eval_steps_per_second": 1.827,
|
| 121 |
+
"step": 600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0284810126582278,
|
| 125 |
+
"grad_norm": 0.5277347564697266,
|
| 126 |
+
"learning_rate": 1.3154008438818566e-05,
|
| 127 |
+
"loss": 0.1269,
|
| 128 |
+
"step": 650
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.1075949367088607,
|
| 132 |
+
"grad_norm": 1.5498286485671997,
|
| 133 |
+
"learning_rate": 1.2626582278481014e-05,
|
| 134 |
+
"loss": 0.1419,
|
| 135 |
+
"step": 700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.1867088607594938,
|
| 139 |
+
"grad_norm": 4.222334861755371,
|
| 140 |
+
"learning_rate": 1.209915611814346e-05,
|
| 141 |
+
"loss": 0.1092,
|
| 142 |
+
"step": 750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.2658227848101267,
|
| 146 |
+
"grad_norm": 7.636617660522461,
|
| 147 |
+
"learning_rate": 1.1571729957805908e-05,
|
| 148 |
+
"loss": 0.0975,
|
| 149 |
+
"step": 800
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.2658227848101267,
|
| 153 |
+
"eval_accuracy": 0.9560917721518988,
|
| 154 |
+
"eval_loss": 0.15132202208042145,
|
| 155 |
+
"eval_runtime": 21.7326,
|
| 156 |
+
"eval_samples_per_second": 116.323,
|
| 157 |
+
"eval_steps_per_second": 1.841,
|
| 158 |
+
"step": 800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3449367088607596,
|
| 162 |
+
"grad_norm": 2.144458770751953,
|
| 163 |
+
"learning_rate": 1.1044303797468354e-05,
|
| 164 |
+
"loss": 0.103,
|
| 165 |
+
"step": 850
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.4240506329113924,
|
| 169 |
+
"grad_norm": 0.4628768265247345,
|
| 170 |
+
"learning_rate": 1.0516877637130802e-05,
|
| 171 |
+
"loss": 0.0927,
|
| 172 |
+
"step": 900
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.5031645569620253,
|
| 176 |
+
"grad_norm": 4.971005916595459,
|
| 177 |
+
"learning_rate": 9.98945147679325e-06,
|
| 178 |
+
"loss": 0.0893,
|
| 179 |
+
"step": 950
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.5822784810126582,
|
| 183 |
+
"grad_norm": 4.186551570892334,
|
| 184 |
+
"learning_rate": 9.462025316455697e-06,
|
| 185 |
+
"loss": 0.0987,
|
| 186 |
+
"step": 1000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5822784810126582,
|
| 190 |
+
"eval_accuracy": 0.9545094936708861,
|
| 191 |
+
"eval_loss": 0.1511051058769226,
|
| 192 |
+
"eval_runtime": 21.7262,
|
| 193 |
+
"eval_samples_per_second": 116.357,
|
| 194 |
+
"eval_steps_per_second": 1.841,
|
| 195 |
+
"step": 1000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.6613924050632911,
|
| 199 |
+
"grad_norm": 2.5125277042388916,
|
| 200 |
+
"learning_rate": 8.934599156118145e-06,
|
| 201 |
+
"loss": 0.0865,
|
| 202 |
+
"step": 1050
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.740506329113924,
|
| 206 |
+
"grad_norm": 15.021677017211914,
|
| 207 |
+
"learning_rate": 8.407172995780591e-06,
|
| 208 |
+
"loss": 0.0937,
|
| 209 |
+
"step": 1100
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.8196202531645569,
|
| 213 |
+
"grad_norm": 6.045713901519775,
|
| 214 |
+
"learning_rate": 7.879746835443039e-06,
|
| 215 |
+
"loss": 0.0776,
|
| 216 |
+
"step": 1150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.8987341772151898,
|
| 220 |
+
"grad_norm": 2.6441538333892822,
|
| 221 |
+
"learning_rate": 7.352320675105486e-06,
|
| 222 |
+
"loss": 0.0972,
|
| 223 |
+
"step": 1200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.8987341772151898,
|
| 227 |
+
"eval_accuracy": 0.9533227848101266,
|
| 228 |
+
"eval_loss": 0.152543842792511,
|
| 229 |
+
"eval_runtime": 21.691,
|
| 230 |
+
"eval_samples_per_second": 116.546,
|
| 231 |
+
"eval_steps_per_second": 1.844,
|
| 232 |
+
"step": 1200
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.9778481012658227,
|
| 236 |
+
"grad_norm": 12.360393524169922,
|
| 237 |
+
"learning_rate": 6.8248945147679335e-06,
|
| 238 |
+
"loss": 0.0984,
|
| 239 |
+
"step": 1250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.0569620253164556,
|
| 243 |
+
"grad_norm": 1.6513817310333252,
|
| 244 |
+
"learning_rate": 6.2974683544303804e-06,
|
| 245 |
+
"loss": 0.0616,
|
| 246 |
+
"step": 1300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.1360759493670884,
|
| 250 |
+
"grad_norm": 0.32455408573150635,
|
| 251 |
+
"learning_rate": 5.770042194092827e-06,
|
| 252 |
+
"loss": 0.0525,
|
| 253 |
+
"step": 1350
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.2151898734177213,
|
| 257 |
+
"grad_norm": 0.3913777470588684,
|
| 258 |
+
"learning_rate": 5.242616033755274e-06,
|
| 259 |
+
"loss": 0.0498,
|
| 260 |
+
"step": 1400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.2151898734177213,
|
| 264 |
+
"eval_accuracy": 0.9580696202531646,
|
| 265 |
+
"eval_loss": 0.16716444492340088,
|
| 266 |
+
"eval_runtime": 21.651,
|
| 267 |
+
"eval_samples_per_second": 116.761,
|
| 268 |
+
"eval_steps_per_second": 1.847,
|
| 269 |
+
"step": 1400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.2943037974683547,
|
| 273 |
+
"grad_norm": 0.17981760203838348,
|
| 274 |
+
"learning_rate": 4.715189873417722e-06,
|
| 275 |
+
"loss": 0.0555,
|
| 276 |
+
"step": 1450
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.3734177215189876,
|
| 280 |
+
"grad_norm": 8.692523956298828,
|
| 281 |
+
"learning_rate": 4.187763713080169e-06,
|
| 282 |
+
"loss": 0.063,
|
| 283 |
+
"step": 1500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.4525316455696204,
|
| 287 |
+
"grad_norm": 4.8722100257873535,
|
| 288 |
+
"learning_rate": 3.6603375527426164e-06,
|
| 289 |
+
"loss": 0.0421,
|
| 290 |
+
"step": 1550
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.5316455696202533,
|
| 294 |
+
"grad_norm": 0.40789884328842163,
|
| 295 |
+
"learning_rate": 3.132911392405064e-06,
|
| 296 |
+
"loss": 0.0691,
|
| 297 |
+
"step": 1600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.5316455696202533,
|
| 301 |
+
"eval_accuracy": 0.9560917721518988,
|
| 302 |
+
"eval_loss": 0.1713864654302597,
|
| 303 |
+
"eval_runtime": 21.7194,
|
| 304 |
+
"eval_samples_per_second": 116.394,
|
| 305 |
+
"eval_steps_per_second": 1.842,
|
| 306 |
+
"step": 1600
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.6107594936708862,
|
| 310 |
+
"grad_norm": 0.035212136805057526,
|
| 311 |
+
"learning_rate": 2.6054852320675107e-06,
|
| 312 |
+
"loss": 0.0488,
|
| 313 |
+
"step": 1650
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.689873417721519,
|
| 317 |
+
"grad_norm": 0.17139802873134613,
|
| 318 |
+
"learning_rate": 2.0780590717299577e-06,
|
| 319 |
+
"loss": 0.043,
|
| 320 |
+
"step": 1700
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.768987341772152,
|
| 324 |
+
"grad_norm": 2.1545848846435547,
|
| 325 |
+
"learning_rate": 1.550632911392405e-06,
|
| 326 |
+
"loss": 0.0428,
|
| 327 |
+
"step": 1750
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.848101265822785,
|
| 331 |
+
"grad_norm": 0.045621346682310104,
|
| 332 |
+
"learning_rate": 1.0232067510548524e-06,
|
| 333 |
+
"loss": 0.0296,
|
| 334 |
+
"step": 1800
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.848101265822785,
|
| 338 |
+
"eval_accuracy": 0.9572784810126582,
|
| 339 |
+
"eval_loss": 0.17169879376888275,
|
| 340 |
+
"eval_runtime": 22.181,
|
| 341 |
+
"eval_samples_per_second": 113.972,
|
| 342 |
+
"eval_steps_per_second": 1.803,
|
| 343 |
+
"step": 1800
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.9272151898734178,
|
| 347 |
+
"grad_norm": 0.16637776792049408,
|
| 348 |
+
"learning_rate": 4.957805907172996e-07,
|
| 349 |
+
"loss": 0.0432,
|
| 350 |
+
"step": 1850
|
| 351 |
+
}
|
| 352 |
+
],
|
| 353 |
+
"logging_steps": 50,
|
| 354 |
+
"max_steps": 1896,
|
| 355 |
+
"num_input_tokens_seen": 0,
|
| 356 |
+
"num_train_epochs": 3,
|
| 357 |
+
"save_steps": 200,
|
| 358 |
+
"stateful_callbacks": {
|
| 359 |
+
"TrainerControl": {
|
| 360 |
+
"args": {
|
| 361 |
+
"should_epoch_stop": false,
|
| 362 |
+
"should_evaluate": false,
|
| 363 |
+
"should_log": false,
|
| 364 |
+
"should_save": true,
|
| 365 |
+
"should_training_stop": true
|
| 366 |
+
},
|
| 367 |
+
"attributes": {}
|
| 368 |
+
}
|
| 369 |
+
},
|
| 370 |
+
"total_flos": 8033882793689088.0,
|
| 371 |
+
"train_batch_size": 32,
|
| 372 |
+
"trial_name": null,
|
| 373 |
+
"trial_params": null
|
| 374 |
+
}
|
checkpoint-1896/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268993dc03cb72c869ff0efb186a5fffad48027344a07450746f7b8d3fe16e12
|
| 3 |
+
size 5240
|
checkpoint-1896/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"max_position_embeddings": 512,
|
| 12 |
+
"model_type": "distilbert",
|
| 13 |
+
"n_heads": 12,
|
| 14 |
+
"n_layers": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"problem_type": "single_label_classification",
|
| 17 |
+
"qa_dropout": 0.1,
|
| 18 |
+
"seq_classif_dropout": 0.2,
|
| 19 |
+
"sinusoidal_pos_embds": false,
|
| 20 |
+
"tie_weights_": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.51.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d930f19a93192dfa853d23448a377774cecc9585085bd3bdbf685058964f0e6
|
| 3 |
+
size 267832560
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|