Upload folder using huggingface_hub
Browse files- config.json +35 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +327 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0,
|
| 19 |
+
"LABEL_1": 1,
|
| 20 |
+
"LABEL_2": 2
|
| 21 |
+
},
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "distilbert",
|
| 24 |
+
"n_heads": 12,
|
| 25 |
+
"n_layers": 6,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"problem_type": "single_label_classification",
|
| 28 |
+
"qa_dropout": 0.1,
|
| 29 |
+
"seq_classif_dropout": 0.2,
|
| 30 |
+
"sinusoidal_pos_embds": false,
|
| 31 |
+
"tie_weights_": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.42.4",
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aac8fda2a47f12e1ef697c13cc8d54d91c63374403f85e867a224467c9a892a8
|
| 3 |
+
size 267835644
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf558659b14f74f697bb6e9a0ab6ee031aaa319646d660768c4e27d56081142
|
| 3 |
+
size 535733434
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fabdeb0e8b13a28b4d97ae9c33181267a3e2285aa4ea9fa8fcc79447bbbdb41
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba158a766417be853d755a747fbf87c5dc53c613f82bc2485f065540fb7ee23
|
| 3 |
+
size 1064
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 21460,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11649580615097857,
|
| 13 |
+
"grad_norm": 2.5263092517852783,
|
| 14 |
+
"learning_rate": 4.883504193849022e-05,
|
| 15 |
+
"loss": 0.612,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.23299161230195714,
|
| 20 |
+
"grad_norm": 2.820680856704712,
|
| 21 |
+
"learning_rate": 4.767008387698043e-05,
|
| 22 |
+
"loss": 0.4835,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3494874184529357,
|
| 27 |
+
"grad_norm": 2.4191653728485107,
|
| 28 |
+
"learning_rate": 4.650512581547065e-05,
|
| 29 |
+
"loss": 0.4403,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4659832246039143,
|
| 34 |
+
"grad_norm": 2.0218257904052734,
|
| 35 |
+
"learning_rate": 4.534016775396086e-05,
|
| 36 |
+
"loss": 0.4163,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5824790307548928,
|
| 41 |
+
"grad_norm": 2.193092107772827,
|
| 42 |
+
"learning_rate": 4.4175209692451076e-05,
|
| 43 |
+
"loss": 0.4056,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6989748369058714,
|
| 48 |
+
"grad_norm": 2.5563910007476807,
|
| 49 |
+
"learning_rate": 4.3010251630941286e-05,
|
| 50 |
+
"loss": 0.3903,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8154706430568499,
|
| 55 |
+
"grad_norm": 2.4142184257507324,
|
| 56 |
+
"learning_rate": 4.1845293569431504e-05,
|
| 57 |
+
"loss": 0.3818,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.9319664492078286,
|
| 62 |
+
"grad_norm": 2.6781787872314453,
|
| 63 |
+
"learning_rate": 4.068033550792172e-05,
|
| 64 |
+
"loss": 0.3752,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.048462255358807,
|
| 69 |
+
"grad_norm": 3.981492757797241,
|
| 70 |
+
"learning_rate": 3.951537744641193e-05,
|
| 71 |
+
"loss": 0.3407,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.1649580615097856,
|
| 76 |
+
"grad_norm": 2.2366013526916504,
|
| 77 |
+
"learning_rate": 3.835041938490215e-05,
|
| 78 |
+
"loss": 0.3079,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.281453867660764,
|
| 83 |
+
"grad_norm": 2.7982800006866455,
|
| 84 |
+
"learning_rate": 3.718546132339236e-05,
|
| 85 |
+
"loss": 0.3003,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.3979496738117427,
|
| 90 |
+
"grad_norm": 2.147766590118408,
|
| 91 |
+
"learning_rate": 3.602050326188258e-05,
|
| 92 |
+
"loss": 0.3042,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.5144454799627214,
|
| 97 |
+
"grad_norm": 3.3207345008850098,
|
| 98 |
+
"learning_rate": 3.485554520037279e-05,
|
| 99 |
+
"loss": 0.2994,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.6309412861136998,
|
| 104 |
+
"grad_norm": 2.8516502380371094,
|
| 105 |
+
"learning_rate": 3.3690587138863e-05,
|
| 106 |
+
"loss": 0.3019,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.7474370922646785,
|
| 111 |
+
"grad_norm": 2.4767708778381348,
|
| 112 |
+
"learning_rate": 3.2525629077353216e-05,
|
| 113 |
+
"loss": 0.3029,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.8639328984156571,
|
| 118 |
+
"grad_norm": 2.9029157161712646,
|
| 119 |
+
"learning_rate": 3.1360671015843426e-05,
|
| 120 |
+
"loss": 0.2971,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.9804287045666356,
|
| 125 |
+
"grad_norm": 3.0262856483459473,
|
| 126 |
+
"learning_rate": 3.0195712954333644e-05,
|
| 127 |
+
"loss": 0.2926,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.096924510717614,
|
| 132 |
+
"grad_norm": 2.862046957015991,
|
| 133 |
+
"learning_rate": 2.9030754892823857e-05,
|
| 134 |
+
"loss": 0.2322,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.213420316868593,
|
| 139 |
+
"grad_norm": 2.759274482727051,
|
| 140 |
+
"learning_rate": 2.786579683131407e-05,
|
| 141 |
+
"loss": 0.2295,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.3299161230195713,
|
| 146 |
+
"grad_norm": 3.3560988903045654,
|
| 147 |
+
"learning_rate": 2.670083876980429e-05,
|
| 148 |
+
"loss": 0.2288,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.4464119291705497,
|
| 153 |
+
"grad_norm": 2.7938876152038574,
|
| 154 |
+
"learning_rate": 2.5535880708294503e-05,
|
| 155 |
+
"loss": 0.228,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.562907735321528,
|
| 160 |
+
"grad_norm": 3.100569486618042,
|
| 161 |
+
"learning_rate": 2.4370922646784717e-05,
|
| 162 |
+
"loss": 0.2288,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.679403541472507,
|
| 167 |
+
"grad_norm": 2.6765120029449463,
|
| 168 |
+
"learning_rate": 2.320596458527493e-05,
|
| 169 |
+
"loss": 0.2307,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.7958993476234855,
|
| 174 |
+
"grad_norm": 2.7146239280700684,
|
| 175 |
+
"learning_rate": 2.2041006523765145e-05,
|
| 176 |
+
"loss": 0.2275,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.9123951537744643,
|
| 181 |
+
"grad_norm": 3.6457717418670654,
|
| 182 |
+
"learning_rate": 2.087604846225536e-05,
|
| 183 |
+
"loss": 0.2328,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.0288909599254428,
|
| 188 |
+
"grad_norm": 3.6852147579193115,
|
| 189 |
+
"learning_rate": 1.9711090400745573e-05,
|
| 190 |
+
"loss": 0.2172,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.145386766076421,
|
| 195 |
+
"grad_norm": 3.0440313816070557,
|
| 196 |
+
"learning_rate": 1.854613233923579e-05,
|
| 197 |
+
"loss": 0.1749,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.2618825722273996,
|
| 202 |
+
"grad_norm": 2.364924192428589,
|
| 203 |
+
"learning_rate": 1.7381174277726004e-05,
|
| 204 |
+
"loss": 0.1767,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.3783783783783785,
|
| 209 |
+
"grad_norm": 2.6927711963653564,
|
| 210 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 211 |
+
"loss": 0.172,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.494874184529357,
|
| 216 |
+
"grad_norm": 3.143772602081299,
|
| 217 |
+
"learning_rate": 1.5051258154706432e-05,
|
| 218 |
+
"loss": 0.1787,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.6113699906803354,
|
| 223 |
+
"grad_norm": 2.1713764667510986,
|
| 224 |
+
"learning_rate": 1.3886300093196648e-05,
|
| 225 |
+
"loss": 0.1724,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.7278657968313142,
|
| 230 |
+
"grad_norm": 4.549355506896973,
|
| 231 |
+
"learning_rate": 1.2721342031686858e-05,
|
| 232 |
+
"loss": 0.1744,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.8443616029822927,
|
| 237 |
+
"grad_norm": 1.8248041868209839,
|
| 238 |
+
"learning_rate": 1.1556383970177074e-05,
|
| 239 |
+
"loss": 0.1781,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.960857409133271,
|
| 244 |
+
"grad_norm": 3.255676507949829,
|
| 245 |
+
"learning_rate": 1.039142590866729e-05,
|
| 246 |
+
"loss": 0.1752,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 4.0773532152842495,
|
| 251 |
+
"grad_norm": 4.369929790496826,
|
| 252 |
+
"learning_rate": 9.226467847157502e-06,
|
| 253 |
+
"loss": 0.1491,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.193849021435228,
|
| 258 |
+
"grad_norm": 3.5270001888275146,
|
| 259 |
+
"learning_rate": 8.061509785647716e-06,
|
| 260 |
+
"loss": 0.1355,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.310344827586207,
|
| 265 |
+
"grad_norm": 3.747748613357544,
|
| 266 |
+
"learning_rate": 6.896551724137932e-06,
|
| 267 |
+
"loss": 0.1402,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 4.426840633737186,
|
| 272 |
+
"grad_norm": 2.4927761554718018,
|
| 273 |
+
"learning_rate": 5.731593662628146e-06,
|
| 274 |
+
"loss": 0.1341,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.543336439888164,
|
| 279 |
+
"grad_norm": 3.129467010498047,
|
| 280 |
+
"learning_rate": 4.56663560111836e-06,
|
| 281 |
+
"loss": 0.1349,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.659832246039143,
|
| 286 |
+
"grad_norm": 5.417072772979736,
|
| 287 |
+
"learning_rate": 3.401677539608574e-06,
|
| 288 |
+
"loss": 0.1322,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.776328052190121,
|
| 293 |
+
"grad_norm": 3.4678492546081543,
|
| 294 |
+
"learning_rate": 2.2367194780987884e-06,
|
| 295 |
+
"loss": 0.1402,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.8928238583410995,
|
| 300 |
+
"grad_norm": 3.649914026260376,
|
| 301 |
+
"learning_rate": 1.0717614165890028e-06,
|
| 302 |
+
"loss": 0.1375,
|
| 303 |
+
"step": 21000
|
| 304 |
+
}
|
| 305 |
+
],
|
| 306 |
+
"logging_steps": 500,
|
| 307 |
+
"max_steps": 21460,
|
| 308 |
+
"num_input_tokens_seen": 0,
|
| 309 |
+
"num_train_epochs": 5,
|
| 310 |
+
"save_steps": 500,
|
| 311 |
+
"stateful_callbacks": {
|
| 312 |
+
"TrainerControl": {
|
| 313 |
+
"args": {
|
| 314 |
+
"should_epoch_stop": false,
|
| 315 |
+
"should_evaluate": false,
|
| 316 |
+
"should_log": false,
|
| 317 |
+
"should_save": true,
|
| 318 |
+
"should_training_stop": true
|
| 319 |
+
},
|
| 320 |
+
"attributes": {}
|
| 321 |
+
}
|
| 322 |
+
},
|
| 323 |
+
"total_flos": 9.096814400558976e+16,
|
| 324 |
+
"train_batch_size": 128,
|
| 325 |
+
"trial_name": null,
|
| 326 |
+
"trial_params": null
|
| 327 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f177736d4d7559abc264e7ed5c33e0b74bfd7063d6b0273ab798cf8e6bf51aae
|
| 3 |
+
size 5112
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|