Upload folder using huggingface_hub
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +628 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMultipleChoice"
|
| 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 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.31.0",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 31002
|
| 27 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19194dca7929b20a16025795d890b069a06c7a183c2feec2792dea524dfcb4ed
|
| 3 |
+
size 878931077
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68fec5a859f6258595f40b87df731d7b669a55c719d89bd16fd6e0006f510bee
|
| 3 |
+
size 439474993
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48bd856d73fe10ab713775bc695b232bacb465eb7f46a23484535a12015139f4
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd589488ba741dd3adccd2f9496ca3a9be7bdcffe51d84217c9577a41b2642c2
|
| 3 |
+
size 627
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": false,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8278950452804565,
|
| 3 |
+
"best_model_checkpoint": "beto-SemcorSDS-esp-mchoice/checkpoint-49572",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 49572,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.949568304688131e-05,
|
| 13 |
+
"loss": 1.0107,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 4.899136609376261e-05,
|
| 19 |
+
"loss": 0.8723,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 4.848704914064391e-05,
|
| 25 |
+
"loss": 0.8684,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 4.798273218752522e-05,
|
| 31 |
+
"loss": 0.8193,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 4.747841523440652e-05,
|
| 37 |
+
"loss": 0.8183,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"learning_rate": 4.697409828128783e-05,
|
| 43 |
+
"loss": 0.7922,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14,
|
| 48 |
+
"learning_rate": 4.6469781328169134e-05,
|
| 49 |
+
"loss": 0.7736,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16,
|
| 54 |
+
"learning_rate": 4.5965464375050435e-05,
|
| 55 |
+
"loss": 0.7731,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.18,
|
| 60 |
+
"learning_rate": 4.5461147421931735e-05,
|
| 61 |
+
"loss": 0.7645,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2,
|
| 66 |
+
"learning_rate": 4.495683046881304e-05,
|
| 67 |
+
"loss": 0.747,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.22,
|
| 72 |
+
"learning_rate": 4.4452513515694343e-05,
|
| 73 |
+
"loss": 0.7296,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 4.394819656257565e-05,
|
| 79 |
+
"loss": 0.6894,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.26,
|
| 84 |
+
"learning_rate": 4.344387960945696e-05,
|
| 85 |
+
"loss": 0.7093,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.28,
|
| 90 |
+
"learning_rate": 4.293956265633826e-05,
|
| 91 |
+
"loss": 0.7082,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.3,
|
| 96 |
+
"learning_rate": 4.243524570321956e-05,
|
| 97 |
+
"loss": 0.7191,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.32,
|
| 102 |
+
"learning_rate": 4.193092875010087e-05,
|
| 103 |
+
"loss": 0.7172,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.34,
|
| 108 |
+
"learning_rate": 4.142661179698217e-05,
|
| 109 |
+
"loss": 0.6845,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.36,
|
| 114 |
+
"learning_rate": 4.0922294843863475e-05,
|
| 115 |
+
"loss": 0.6957,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.38,
|
| 120 |
+
"learning_rate": 4.041797789074478e-05,
|
| 121 |
+
"loss": 0.6726,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4,
|
| 126 |
+
"learning_rate": 3.9913660937626076e-05,
|
| 127 |
+
"loss": 0.6653,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.42,
|
| 132 |
+
"learning_rate": 3.9409343984507384e-05,
|
| 133 |
+
"loss": 0.6952,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.44,
|
| 138 |
+
"learning_rate": 3.890502703138869e-05,
|
| 139 |
+
"loss": 0.6757,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.46,
|
| 144 |
+
"learning_rate": 3.840071007826999e-05,
|
| 145 |
+
"loss": 0.7029,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.48,
|
| 150 |
+
"learning_rate": 3.78963931251513e-05,
|
| 151 |
+
"loss": 0.657,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.5,
|
| 156 |
+
"learning_rate": 3.73920761720326e-05,
|
| 157 |
+
"loss": 0.6924,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.52,
|
| 162 |
+
"learning_rate": 3.68877592189139e-05,
|
| 163 |
+
"loss": 0.6466,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.54,
|
| 168 |
+
"learning_rate": 3.638344226579521e-05,
|
| 169 |
+
"loss": 0.6479,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.56,
|
| 174 |
+
"learning_rate": 3.5879125312676515e-05,
|
| 175 |
+
"loss": 0.6381,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.59,
|
| 180 |
+
"learning_rate": 3.5374808359557816e-05,
|
| 181 |
+
"loss": 0.659,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.61,
|
| 186 |
+
"learning_rate": 3.4870491406439124e-05,
|
| 187 |
+
"loss": 0.6862,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.63,
|
| 192 |
+
"learning_rate": 3.4366174453320424e-05,
|
| 193 |
+
"loss": 0.6493,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.65,
|
| 198 |
+
"learning_rate": 3.3861857500201725e-05,
|
| 199 |
+
"loss": 0.6541,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.67,
|
| 204 |
+
"learning_rate": 3.335754054708303e-05,
|
| 205 |
+
"loss": 0.6269,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.69,
|
| 210 |
+
"learning_rate": 3.285322359396434e-05,
|
| 211 |
+
"loss": 0.6667,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.71,
|
| 216 |
+
"learning_rate": 3.234890664084564e-05,
|
| 217 |
+
"loss": 0.639,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.73,
|
| 222 |
+
"learning_rate": 3.184458968772695e-05,
|
| 223 |
+
"loss": 0.6136,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"learning_rate": 3.134027273460825e-05,
|
| 229 |
+
"loss": 0.6126,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.77,
|
| 234 |
+
"learning_rate": 3.083595578148955e-05,
|
| 235 |
+
"loss": 0.6108,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.79,
|
| 240 |
+
"learning_rate": 3.0331638828370857e-05,
|
| 241 |
+
"loss": 0.6087,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.81,
|
| 246 |
+
"learning_rate": 2.982732187525216e-05,
|
| 247 |
+
"loss": 0.6155,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.83,
|
| 252 |
+
"learning_rate": 2.932300492213346e-05,
|
| 253 |
+
"loss": 0.6204,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.85,
|
| 258 |
+
"learning_rate": 2.881868796901477e-05,
|
| 259 |
+
"loss": 0.6014,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.87,
|
| 264 |
+
"learning_rate": 2.8314371015896073e-05,
|
| 265 |
+
"loss": 0.5979,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.89,
|
| 270 |
+
"learning_rate": 2.7810054062777373e-05,
|
| 271 |
+
"loss": 0.6329,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.91,
|
| 276 |
+
"learning_rate": 2.730573710965868e-05,
|
| 277 |
+
"loss": 0.5963,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.93,
|
| 282 |
+
"learning_rate": 2.6801420156539985e-05,
|
| 283 |
+
"loss": 0.6109,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.95,
|
| 288 |
+
"learning_rate": 2.6297103203421285e-05,
|
| 289 |
+
"loss": 0.6187,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.97,
|
| 294 |
+
"learning_rate": 2.5792786250302593e-05,
|
| 295 |
+
"loss": 0.5924,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.99,
|
| 300 |
+
"learning_rate": 2.5288469297183897e-05,
|
| 301 |
+
"loss": 0.5883,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.0,
|
| 306 |
+
"eval_accuracy": 0.8021398186683655,
|
| 307 |
+
"eval_loss": 0.5718119144439697,
|
| 308 |
+
"eval_runtime": 299.0287,
|
| 309 |
+
"eval_samples_per_second": 69.077,
|
| 310 |
+
"eval_steps_per_second": 11.514,
|
| 311 |
+
"step": 24786
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.01,
|
| 315 |
+
"learning_rate": 2.4784152344065198e-05,
|
| 316 |
+
"loss": 0.5161,
|
| 317 |
+
"step": 25000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.03,
|
| 321 |
+
"learning_rate": 2.4279835390946505e-05,
|
| 322 |
+
"loss": 0.3989,
|
| 323 |
+
"step": 25500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.05,
|
| 327 |
+
"learning_rate": 2.3775518437827806e-05,
|
| 328 |
+
"loss": 0.4255,
|
| 329 |
+
"step": 26000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.07,
|
| 333 |
+
"learning_rate": 2.327120148470911e-05,
|
| 334 |
+
"loss": 0.4015,
|
| 335 |
+
"step": 26500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.09,
|
| 339 |
+
"learning_rate": 2.2766884531590417e-05,
|
| 340 |
+
"loss": 0.4222,
|
| 341 |
+
"step": 27000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.11,
|
| 345 |
+
"learning_rate": 2.2262567578471718e-05,
|
| 346 |
+
"loss": 0.4449,
|
| 347 |
+
"step": 27500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.13,
|
| 351 |
+
"learning_rate": 2.1758250625353022e-05,
|
| 352 |
+
"loss": 0.4148,
|
| 353 |
+
"step": 28000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.15,
|
| 357 |
+
"learning_rate": 2.1253933672234326e-05,
|
| 358 |
+
"loss": 0.4286,
|
| 359 |
+
"step": 28500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.17,
|
| 363 |
+
"learning_rate": 2.074961671911563e-05,
|
| 364 |
+
"loss": 0.4623,
|
| 365 |
+
"step": 29000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.19,
|
| 369 |
+
"learning_rate": 2.0245299765996934e-05,
|
| 370 |
+
"loss": 0.4258,
|
| 371 |
+
"step": 29500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.21,
|
| 375 |
+
"learning_rate": 1.9740982812878238e-05,
|
| 376 |
+
"loss": 0.4439,
|
| 377 |
+
"step": 30000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.23,
|
| 381 |
+
"learning_rate": 1.9236665859759542e-05,
|
| 382 |
+
"loss": 0.4485,
|
| 383 |
+
"step": 30500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.25,
|
| 387 |
+
"learning_rate": 1.8732348906640846e-05,
|
| 388 |
+
"loss": 0.4374,
|
| 389 |
+
"step": 31000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.27,
|
| 393 |
+
"learning_rate": 1.822803195352215e-05,
|
| 394 |
+
"loss": 0.4199,
|
| 395 |
+
"step": 31500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.29,
|
| 399 |
+
"learning_rate": 1.7723715000403454e-05,
|
| 400 |
+
"loss": 0.4585,
|
| 401 |
+
"step": 32000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.31,
|
| 405 |
+
"learning_rate": 1.7219398047284758e-05,
|
| 406 |
+
"loss": 0.4371,
|
| 407 |
+
"step": 32500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.33,
|
| 411 |
+
"learning_rate": 1.6715081094166062e-05,
|
| 412 |
+
"loss": 0.4205,
|
| 413 |
+
"step": 33000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.35,
|
| 417 |
+
"learning_rate": 1.6210764141047366e-05,
|
| 418 |
+
"loss": 0.4491,
|
| 419 |
+
"step": 33500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.37,
|
| 423 |
+
"learning_rate": 1.570644718792867e-05,
|
| 424 |
+
"loss": 0.4186,
|
| 425 |
+
"step": 34000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.39,
|
| 429 |
+
"learning_rate": 1.5202130234809974e-05,
|
| 430 |
+
"loss": 0.4236,
|
| 431 |
+
"step": 34500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.41,
|
| 435 |
+
"learning_rate": 1.4697813281691278e-05,
|
| 436 |
+
"loss": 0.4114,
|
| 437 |
+
"step": 35000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.43,
|
| 441 |
+
"learning_rate": 1.419349632857258e-05,
|
| 442 |
+
"loss": 0.4206,
|
| 443 |
+
"step": 35500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.45,
|
| 447 |
+
"learning_rate": 1.3689179375453886e-05,
|
| 448 |
+
"loss": 0.4212,
|
| 449 |
+
"step": 36000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.47,
|
| 453 |
+
"learning_rate": 1.318486242233519e-05,
|
| 454 |
+
"loss": 0.4327,
|
| 455 |
+
"step": 36500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.49,
|
| 459 |
+
"learning_rate": 1.2680545469216493e-05,
|
| 460 |
+
"loss": 0.4082,
|
| 461 |
+
"step": 37000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.51,
|
| 465 |
+
"learning_rate": 1.2176228516097797e-05,
|
| 466 |
+
"loss": 0.4307,
|
| 467 |
+
"step": 37500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.53,
|
| 471 |
+
"learning_rate": 1.1671911562979101e-05,
|
| 472 |
+
"loss": 0.4021,
|
| 473 |
+
"step": 38000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.55,
|
| 477 |
+
"learning_rate": 1.1167594609860407e-05,
|
| 478 |
+
"loss": 0.4307,
|
| 479 |
+
"step": 38500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.57,
|
| 483 |
+
"learning_rate": 1.0663277656741709e-05,
|
| 484 |
+
"loss": 0.4307,
|
| 485 |
+
"step": 39000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.59,
|
| 489 |
+
"learning_rate": 1.0158960703623013e-05,
|
| 490 |
+
"loss": 0.3856,
|
| 491 |
+
"step": 39500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.61,
|
| 495 |
+
"learning_rate": 9.654643750504317e-06,
|
| 496 |
+
"loss": 0.4156,
|
| 497 |
+
"step": 40000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.63,
|
| 501 |
+
"learning_rate": 9.150326797385621e-06,
|
| 502 |
+
"loss": 0.398,
|
| 503 |
+
"step": 40500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.65,
|
| 507 |
+
"learning_rate": 8.646009844266925e-06,
|
| 508 |
+
"loss": 0.4467,
|
| 509 |
+
"step": 41000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.67,
|
| 513 |
+
"learning_rate": 8.141692891148229e-06,
|
| 514 |
+
"loss": 0.3962,
|
| 515 |
+
"step": 41500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.69,
|
| 519 |
+
"learning_rate": 7.637375938029533e-06,
|
| 520 |
+
"loss": 0.405,
|
| 521 |
+
"step": 42000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.71,
|
| 525 |
+
"learning_rate": 7.133058984910837e-06,
|
| 526 |
+
"loss": 0.4219,
|
| 527 |
+
"step": 42500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.73,
|
| 531 |
+
"learning_rate": 6.628742031792141e-06,
|
| 532 |
+
"loss": 0.4234,
|
| 533 |
+
"step": 43000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.76,
|
| 537 |
+
"learning_rate": 6.124425078673445e-06,
|
| 538 |
+
"loss": 0.3794,
|
| 539 |
+
"step": 43500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.78,
|
| 543 |
+
"learning_rate": 5.6201081255547485e-06,
|
| 544 |
+
"loss": 0.3924,
|
| 545 |
+
"step": 44000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.8,
|
| 549 |
+
"learning_rate": 5.1157911724360525e-06,
|
| 550 |
+
"loss": 0.4233,
|
| 551 |
+
"step": 44500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.82,
|
| 555 |
+
"learning_rate": 4.611474219317357e-06,
|
| 556 |
+
"loss": 0.3938,
|
| 557 |
+
"step": 45000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.84,
|
| 561 |
+
"learning_rate": 4.107157266198661e-06,
|
| 562 |
+
"loss": 0.378,
|
| 563 |
+
"step": 45500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.86,
|
| 567 |
+
"learning_rate": 3.602840313079964e-06,
|
| 568 |
+
"loss": 0.3797,
|
| 569 |
+
"step": 46000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.88,
|
| 573 |
+
"learning_rate": 3.0985233599612687e-06,
|
| 574 |
+
"loss": 0.3882,
|
| 575 |
+
"step": 46500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.9,
|
| 579 |
+
"learning_rate": 2.5942064068425727e-06,
|
| 580 |
+
"loss": 0.3475,
|
| 581 |
+
"step": 47000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.92,
|
| 585 |
+
"learning_rate": 2.0898894537238767e-06,
|
| 586 |
+
"loss": 0.4292,
|
| 587 |
+
"step": 47500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.94,
|
| 591 |
+
"learning_rate": 1.5855725006051804e-06,
|
| 592 |
+
"loss": 0.3869,
|
| 593 |
+
"step": 48000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.96,
|
| 597 |
+
"learning_rate": 1.0812555474864844e-06,
|
| 598 |
+
"loss": 0.3847,
|
| 599 |
+
"step": 48500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.98,
|
| 603 |
+
"learning_rate": 5.769385943677882e-07,
|
| 604 |
+
"loss": 0.3832,
|
| 605 |
+
"step": 49000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.0,
|
| 609 |
+
"learning_rate": 7.262164124909223e-08,
|
| 610 |
+
"loss": 0.4131,
|
| 611 |
+
"step": 49500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.0,
|
| 615 |
+
"eval_accuracy": 0.8278950452804565,
|
| 616 |
+
"eval_loss": 0.6946226954460144,
|
| 617 |
+
"eval_runtime": 292.3668,
|
| 618 |
+
"eval_samples_per_second": 70.651,
|
| 619 |
+
"eval_steps_per_second": 11.776,
|
| 620 |
+
"step": 49572
|
| 621 |
+
}
|
| 622 |
+
],
|
| 623 |
+
"max_steps": 49572,
|
| 624 |
+
"num_train_epochs": 2,
|
| 625 |
+
"total_flos": 6.135635110010184e+16,
|
| 626 |
+
"trial_name": null,
|
| 627 |
+
"trial_params": null
|
| 628 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b916eb7567cfb2d89693c8b8f9aa413e2dc4c08e1dc93829c371741e4f5b7534
|
| 3 |
+
size 3963
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|