Upload folder using huggingface_hub
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +460 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "intfloat/e5-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.43.0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d367f30a69ad20043c232a7f4259940d6ccd1f0582427aad105c0914e3521ab
|
| 3 |
+
size 871298443
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f703e4b1eab330619fe51bed587b754b4aa0c8813db6f34d95d6e1ee7706ab7
|
| 3 |
+
size 437996607
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5346963d01ff2275ef2a2e1ac1b2e38c936c49b438bcc2a76e36b0eb9e31cd6
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b1391659994bec3070ae72c750ae8996cd6c94db4778d7ae30afc081ddb2d5f
|
| 3 |
+
size 1465
|
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": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 615,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24390243902439024,
|
| 13 |
+
"grad_norm": 399.5959777832031,
|
| 14 |
+
"learning_rate": 1.2195121951219514e-06,
|
| 15 |
+
"loss": 20.1185,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4878048780487805,
|
| 20 |
+
"grad_norm": 488.2876892089844,
|
| 21 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 22 |
+
"loss": 17.8526,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.7317073170731707,
|
| 27 |
+
"grad_norm": 234.39358520507812,
|
| 28 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 29 |
+
"loss": 14.6449,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.975609756097561,
|
| 34 |
+
"grad_norm": 132.1689910888672,
|
| 35 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 36 |
+
"loss": 12.2963,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.2195121951219512,
|
| 41 |
+
"grad_norm": 108.00102996826172,
|
| 42 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 43 |
+
"loss": 10.2374,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.4634146341463414,
|
| 48 |
+
"grad_norm": 72.84204864501953,
|
| 49 |
+
"learning_rate": 7.317073170731707e-06,
|
| 50 |
+
"loss": 8.1356,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.7073170731707317,
|
| 55 |
+
"grad_norm": 59.829524993896484,
|
| 56 |
+
"learning_rate": 8.536585365853658e-06,
|
| 57 |
+
"loss": 6.7279,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.951219512195122,
|
| 62 |
+
"grad_norm": 42.48904800415039,
|
| 63 |
+
"learning_rate": 9.756097560975611e-06,
|
| 64 |
+
"loss": 6.0069,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.1951219512195124,
|
| 69 |
+
"grad_norm": 37.831233978271484,
|
| 70 |
+
"learning_rate": 9.89159891598916e-06,
|
| 71 |
+
"loss": 5.2742,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.4390243902439024,
|
| 76 |
+
"grad_norm": 27.763004302978516,
|
| 77 |
+
"learning_rate": 9.756097560975611e-06,
|
| 78 |
+
"loss": 4.8932,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.682926829268293,
|
| 83 |
+
"grad_norm": 18.03118896484375,
|
| 84 |
+
"learning_rate": 9.620596205962061e-06,
|
| 85 |
+
"loss": 4.6851,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.926829268292683,
|
| 90 |
+
"grad_norm": 18.090776443481445,
|
| 91 |
+
"learning_rate": 9.485094850948512e-06,
|
| 92 |
+
"loss": 4.5649,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.1707317073170733,
|
| 97 |
+
"grad_norm": 15.51219654083252,
|
| 98 |
+
"learning_rate": 9.34959349593496e-06,
|
| 99 |
+
"loss": 4.492,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.4146341463414633,
|
| 104 |
+
"grad_norm": 14.675006866455078,
|
| 105 |
+
"learning_rate": 9.21409214092141e-06,
|
| 106 |
+
"loss": 4.406,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.658536585365854,
|
| 111 |
+
"grad_norm": 14.471592903137207,
|
| 112 |
+
"learning_rate": 9.07859078590786e-06,
|
| 113 |
+
"loss": 4.4155,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.902439024390244,
|
| 118 |
+
"grad_norm": 13.054672241210938,
|
| 119 |
+
"learning_rate": 8.94308943089431e-06,
|
| 120 |
+
"loss": 4.3375,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.146341463414634,
|
| 125 |
+
"grad_norm": 12.959569931030273,
|
| 126 |
+
"learning_rate": 8.80758807588076e-06,
|
| 127 |
+
"loss": 4.266,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.390243902439025,
|
| 132 |
+
"grad_norm": 13.852252960205078,
|
| 133 |
+
"learning_rate": 8.67208672086721e-06,
|
| 134 |
+
"loss": 4.2173,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.634146341463414,
|
| 139 |
+
"grad_norm": 13.482157707214355,
|
| 140 |
+
"learning_rate": 8.536585365853658e-06,
|
| 141 |
+
"loss": 4.2434,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.878048780487805,
|
| 146 |
+
"grad_norm": 12.567044258117676,
|
| 147 |
+
"learning_rate": 8.401084010840109e-06,
|
| 148 |
+
"loss": 4.194,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.121951219512195,
|
| 153 |
+
"grad_norm": 14.015665054321289,
|
| 154 |
+
"learning_rate": 8.265582655826559e-06,
|
| 155 |
+
"loss": 4.0342,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.365853658536586,
|
| 160 |
+
"grad_norm": 16.776611328125,
|
| 161 |
+
"learning_rate": 8.130081300813009e-06,
|
| 162 |
+
"loss": 4.2782,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.609756097560975,
|
| 167 |
+
"grad_norm": 12.224383354187012,
|
| 168 |
+
"learning_rate": 7.99457994579946e-06,
|
| 169 |
+
"loss": 4.1003,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.853658536585366,
|
| 174 |
+
"grad_norm": 13.62357234954834,
|
| 175 |
+
"learning_rate": 7.859078590785908e-06,
|
| 176 |
+
"loss": 4.0503,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.097560975609756,
|
| 181 |
+
"grad_norm": 13.351895332336426,
|
| 182 |
+
"learning_rate": 7.723577235772358e-06,
|
| 183 |
+
"loss": 3.9835,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.341463414634147,
|
| 188 |
+
"grad_norm": 14.620662689208984,
|
| 189 |
+
"learning_rate": 7.5880758807588085e-06,
|
| 190 |
+
"loss": 4.0102,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.585365853658536,
|
| 195 |
+
"grad_norm": 15.941452026367188,
|
| 196 |
+
"learning_rate": 7.452574525745257e-06,
|
| 197 |
+
"loss": 3.9992,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.829268292682927,
|
| 202 |
+
"grad_norm": 11.67154598236084,
|
| 203 |
+
"learning_rate": 7.317073170731707e-06,
|
| 204 |
+
"loss": 4.015,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.073170731707317,
|
| 209 |
+
"grad_norm": 12.082201957702637,
|
| 210 |
+
"learning_rate": 7.181571815718158e-06,
|
| 211 |
+
"loss": 3.9566,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.317073170731708,
|
| 216 |
+
"grad_norm": 14.346577644348145,
|
| 217 |
+
"learning_rate": 7.046070460704607e-06,
|
| 218 |
+
"loss": 3.9484,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.560975609756097,
|
| 223 |
+
"grad_norm": 13.629508018493652,
|
| 224 |
+
"learning_rate": 6.910569105691057e-06,
|
| 225 |
+
"loss": 3.8996,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.804878048780488,
|
| 230 |
+
"grad_norm": 12.285475730895996,
|
| 231 |
+
"learning_rate": 6.775067750677508e-06,
|
| 232 |
+
"loss": 3.8117,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.048780487804878,
|
| 237 |
+
"grad_norm": 13.470380783081055,
|
| 238 |
+
"learning_rate": 6.639566395663957e-06,
|
| 239 |
+
"loss": 3.7927,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.292682926829269,
|
| 244 |
+
"grad_norm": 12.478575706481934,
|
| 245 |
+
"learning_rate": 6.504065040650407e-06,
|
| 246 |
+
"loss": 3.851,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.536585365853659,
|
| 251 |
+
"grad_norm": 13.219705581665039,
|
| 252 |
+
"learning_rate": 6.368563685636857e-06,
|
| 253 |
+
"loss": 3.9406,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.78048780487805,
|
| 258 |
+
"grad_norm": 12.26967716217041,
|
| 259 |
+
"learning_rate": 6.233062330623306e-06,
|
| 260 |
+
"loss": 3.8733,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.024390243902438,
|
| 265 |
+
"grad_norm": 14.403388023376465,
|
| 266 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 267 |
+
"loss": 3.6919,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.268292682926829,
|
| 272 |
+
"grad_norm": 12.453432083129883,
|
| 273 |
+
"learning_rate": 5.962059620596207e-06,
|
| 274 |
+
"loss": 3.7806,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 9.512195121951219,
|
| 279 |
+
"grad_norm": 12.452446937561035,
|
| 280 |
+
"learning_rate": 5.826558265582656e-06,
|
| 281 |
+
"loss": 3.6793,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.75609756097561,
|
| 286 |
+
"grad_norm": 12.078032493591309,
|
| 287 |
+
"learning_rate": 5.691056910569106e-06,
|
| 288 |
+
"loss": 3.9065,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 10.0,
|
| 293 |
+
"grad_norm": 15.963644027709961,
|
| 294 |
+
"learning_rate": 5.555555555555557e-06,
|
| 295 |
+
"loss": 3.7498,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 10.24390243902439,
|
| 300 |
+
"grad_norm": 12.582329750061035,
|
| 301 |
+
"learning_rate": 5.420054200542005e-06,
|
| 302 |
+
"loss": 3.85,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 10.487804878048781,
|
| 307 |
+
"grad_norm": 12.392144203186035,
|
| 308 |
+
"learning_rate": 5.2845528455284555e-06,
|
| 309 |
+
"loss": 3.8093,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 10.731707317073171,
|
| 314 |
+
"grad_norm": 13.39164924621582,
|
| 315 |
+
"learning_rate": 5.149051490514906e-06,
|
| 316 |
+
"loss": 3.829,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 10.975609756097562,
|
| 321 |
+
"grad_norm": 11.60807991027832,
|
| 322 |
+
"learning_rate": 5.013550135501355e-06,
|
| 323 |
+
"loss": 3.8262,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.21951219512195,
|
| 328 |
+
"grad_norm": 11.956347465515137,
|
| 329 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 330 |
+
"loss": 3.6282,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.463414634146341,
|
| 335 |
+
"grad_norm": 12.04183292388916,
|
| 336 |
+
"learning_rate": 4.742547425474256e-06,
|
| 337 |
+
"loss": 3.7594,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 11.707317073170731,
|
| 342 |
+
"grad_norm": 11.708353042602539,
|
| 343 |
+
"learning_rate": 4.607046070460705e-06,
|
| 344 |
+
"loss": 3.6854,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.951219512195122,
|
| 349 |
+
"grad_norm": 12.383793830871582,
|
| 350 |
+
"learning_rate": 4.471544715447155e-06,
|
| 351 |
+
"loss": 3.8401,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 12.195121951219512,
|
| 356 |
+
"grad_norm": 13.459123611450195,
|
| 357 |
+
"learning_rate": 4.336043360433605e-06,
|
| 358 |
+
"loss": 3.6459,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 12.439024390243903,
|
| 363 |
+
"grad_norm": 12.854645729064941,
|
| 364 |
+
"learning_rate": 4.200542005420054e-06,
|
| 365 |
+
"loss": 3.5457,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 12.682926829268293,
|
| 370 |
+
"grad_norm": 12.653203964233398,
|
| 371 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 372 |
+
"loss": 3.8569,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 12.926829268292684,
|
| 377 |
+
"grad_norm": 11.430753707885742,
|
| 378 |
+
"learning_rate": 3.929539295392954e-06,
|
| 379 |
+
"loss": 3.7373,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 13.170731707317072,
|
| 384 |
+
"grad_norm": 12.394974708557129,
|
| 385 |
+
"learning_rate": 3.7940379403794043e-06,
|
| 386 |
+
"loss": 3.5982,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 13.414634146341463,
|
| 391 |
+
"grad_norm": 12.253921508789062,
|
| 392 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 393 |
+
"loss": 3.7153,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 13.658536585365853,
|
| 398 |
+
"grad_norm": 12.761003494262695,
|
| 399 |
+
"learning_rate": 3.5230352303523035e-06,
|
| 400 |
+
"loss": 3.5524,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 13.902439024390244,
|
| 405 |
+
"grad_norm": 15.800996780395508,
|
| 406 |
+
"learning_rate": 3.387533875338754e-06,
|
| 407 |
+
"loss": 3.8582,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.146341463414634,
|
| 412 |
+
"grad_norm": 14.060684204101562,
|
| 413 |
+
"learning_rate": 3.2520325203252037e-06,
|
| 414 |
+
"loss": 3.5614,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.390243902439025,
|
| 419 |
+
"grad_norm": 12.352811813354492,
|
| 420 |
+
"learning_rate": 3.116531165311653e-06,
|
| 421 |
+
"loss": 3.5614,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 14.634146341463415,
|
| 426 |
+
"grad_norm": 12.797225952148438,
|
| 427 |
+
"learning_rate": 2.9810298102981034e-06,
|
| 428 |
+
"loss": 3.6201,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.878048780487806,
|
| 433 |
+
"grad_norm": 13.079516410827637,
|
| 434 |
+
"learning_rate": 2.845528455284553e-06,
|
| 435 |
+
"loss": 3.8288,
|
| 436 |
+
"step": 610
|
| 437 |
+
}
|
| 438 |
+
],
|
| 439 |
+
"logging_steps": 10,
|
| 440 |
+
"max_steps": 820,
|
| 441 |
+
"num_input_tokens_seen": 0,
|
| 442 |
+
"num_train_epochs": 20,
|
| 443 |
+
"save_steps": 500,
|
| 444 |
+
"stateful_callbacks": {
|
| 445 |
+
"TrainerControl": {
|
| 446 |
+
"args": {
|
| 447 |
+
"should_epoch_stop": false,
|
| 448 |
+
"should_evaluate": false,
|
| 449 |
+
"should_log": false,
|
| 450 |
+
"should_save": true,
|
| 451 |
+
"should_training_stop": false
|
| 452 |
+
},
|
| 453 |
+
"attributes": {}
|
| 454 |
+
}
|
| 455 |
+
},
|
| 456 |
+
"total_flos": 0.0,
|
| 457 |
+
"train_batch_size": 64,
|
| 458 |
+
"trial_name": null,
|
| 459 |
+
"trial_params": null
|
| 460 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe825e666f042761ddcc69346ffb80a22be6d1eecef756242bed6d10060e586a
|
| 3 |
+
size 5713
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|