Initial commit from mrm8488
Browse files- config.json +58 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +580 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"MBartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"encoder_attention_heads": 16,
|
| 22 |
+
"encoder_ffn_dim": 4096,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 2,
|
| 26 |
+
"gradient_checkpointing": false,
|
| 27 |
+
"id2label": {
|
| 28 |
+
"0": "LABEL_0",
|
| 29 |
+
"1": "LABEL_1",
|
| 30 |
+
"2": "LABEL_2"
|
| 31 |
+
},
|
| 32 |
+
"init_std": 0.02,
|
| 33 |
+
"is_encoder_decoder": true,
|
| 34 |
+
"label2id": {
|
| 35 |
+
"LABEL_0": 0,
|
| 36 |
+
"LABEL_1": 1,
|
| 37 |
+
"LABEL_2": 2
|
| 38 |
+
},
|
| 39 |
+
"max_length": 1024,
|
| 40 |
+
"max_position_embeddings": 1024,
|
| 41 |
+
"model_type": "mbart",
|
| 42 |
+
"normalize_before": true,
|
| 43 |
+
"normalize_embedding": true,
|
| 44 |
+
"num_beams": 5,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"output_past": true,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"scale_embedding": true,
|
| 49 |
+
"static_position_embeddings": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"translation_en_to_ro": {
|
| 52 |
+
"decoder_start_token_id": 250020
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"transformers_version": "4.3.0.dev0",
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 250027
|
| 58 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b97145c58822ae9628103d632fd7300f14260d20b8d1699fc7114f9650dcf158
|
| 3 |
+
size 2444606128
|
sentencepiece.bpe.model
ADDED
|
Binary file (5.07 MB). View file
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "tokenizer_file": null, "model_max_length": 1024, "name_or_path": "facebook/mbart-large-cc25"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,580 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.37524950099800397,
|
| 5 |
+
"global_step": 47000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9966733200266135e-05,
|
| 13 |
+
"loss": 1.8086,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 4.993346640053227e-05,
|
| 19 |
+
"loss": 2.1136,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 4.99001996007984e-05,
|
| 25 |
+
"loss": 1.0008,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02,
|
| 30 |
+
"learning_rate": 4.986693280106454e-05,
|
| 31 |
+
"loss": 0.8661,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 4.983366600133067e-05,
|
| 37 |
+
"loss": 0.8234,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 4.980039920159681e-05,
|
| 43 |
+
"loss": 0.811,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"learning_rate": 4.9767132401862945e-05,
|
| 49 |
+
"loss": 0.7938,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.03,
|
| 54 |
+
"learning_rate": 4.973386560212908e-05,
|
| 55 |
+
"loss": 0.7741,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.04,
|
| 60 |
+
"learning_rate": 4.970059880239521e-05,
|
| 61 |
+
"loss": 0.795,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.04,
|
| 66 |
+
"learning_rate": 4.966733200266135e-05,
|
| 67 |
+
"loss": 0.745,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.04,
|
| 72 |
+
"learning_rate": 4.963406520292748e-05,
|
| 73 |
+
"loss": 0.7542,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.05,
|
| 78 |
+
"learning_rate": 4.9600798403193615e-05,
|
| 79 |
+
"loss": 0.749,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05,
|
| 84 |
+
"learning_rate": 4.956753160345975e-05,
|
| 85 |
+
"loss": 0.7411,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06,
|
| 90 |
+
"learning_rate": 4.953426480372588e-05,
|
| 91 |
+
"loss": 0.737,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.06,
|
| 96 |
+
"learning_rate": 4.950099800399202e-05,
|
| 97 |
+
"loss": 0.7304,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.06,
|
| 102 |
+
"learning_rate": 4.946773120425816e-05,
|
| 103 |
+
"loss": 0.7227,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.07,
|
| 108 |
+
"learning_rate": 4.943446440452429e-05,
|
| 109 |
+
"loss": 0.7153,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.07,
|
| 114 |
+
"learning_rate": 4.9401197604790424e-05,
|
| 115 |
+
"loss": 0.7292,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.08,
|
| 120 |
+
"learning_rate": 4.936793080505656e-05,
|
| 121 |
+
"loss": 0.698,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08,
|
| 126 |
+
"learning_rate": 4.933466400532269e-05,
|
| 127 |
+
"loss": 0.7148,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08,
|
| 132 |
+
"learning_rate": 4.930139720558882e-05,
|
| 133 |
+
"loss": 0.6963,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.09,
|
| 138 |
+
"learning_rate": 4.9268130405854955e-05,
|
| 139 |
+
"loss": 0.7101,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.09,
|
| 144 |
+
"learning_rate": 4.9234863606121094e-05,
|
| 145 |
+
"loss": 0.6888,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.1,
|
| 150 |
+
"learning_rate": 4.920159680638723e-05,
|
| 151 |
+
"loss": 0.702,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.1,
|
| 156 |
+
"learning_rate": 4.916833000665336e-05,
|
| 157 |
+
"loss": 0.6865,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.1,
|
| 162 |
+
"learning_rate": 4.91350632069195e-05,
|
| 163 |
+
"loss": 0.6816,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.11,
|
| 168 |
+
"learning_rate": 4.910179640718563e-05,
|
| 169 |
+
"loss": 0.6926,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11,
|
| 174 |
+
"learning_rate": 4.9068529607451764e-05,
|
| 175 |
+
"loss": 0.6917,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.12,
|
| 180 |
+
"learning_rate": 4.9035262807717903e-05,
|
| 181 |
+
"loss": 0.6714,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.12,
|
| 186 |
+
"learning_rate": 4.9001996007984036e-05,
|
| 187 |
+
"loss": 0.6793,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.12,
|
| 192 |
+
"learning_rate": 4.896872920825017e-05,
|
| 193 |
+
"loss": 0.6826,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.13,
|
| 198 |
+
"learning_rate": 4.89354624085163e-05,
|
| 199 |
+
"loss": 0.6739,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.13,
|
| 204 |
+
"learning_rate": 4.8902195608782434e-05,
|
| 205 |
+
"loss": 0.697,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.14,
|
| 210 |
+
"learning_rate": 4.886892880904857e-05,
|
| 211 |
+
"loss": 0.6696,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.14,
|
| 216 |
+
"learning_rate": 4.8835662009314706e-05,
|
| 217 |
+
"loss": 0.6911,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.14,
|
| 222 |
+
"learning_rate": 4.8802395209580846e-05,
|
| 223 |
+
"loss": 0.6642,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.15,
|
| 228 |
+
"learning_rate": 4.876912840984698e-05,
|
| 229 |
+
"loss": 0.6697,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.15,
|
| 234 |
+
"learning_rate": 4.873586161011311e-05,
|
| 235 |
+
"loss": 0.6635,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.16,
|
| 240 |
+
"learning_rate": 4.8702594810379244e-05,
|
| 241 |
+
"loss": 0.6824,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.16,
|
| 246 |
+
"learning_rate": 4.8669328010645376e-05,
|
| 247 |
+
"loss": 0.6601,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.16,
|
| 252 |
+
"learning_rate": 4.863606121091151e-05,
|
| 253 |
+
"loss": 0.6871,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.17,
|
| 258 |
+
"learning_rate": 4.860279441117765e-05,
|
| 259 |
+
"loss": 0.661,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.17,
|
| 264 |
+
"learning_rate": 4.856952761144378e-05,
|
| 265 |
+
"loss": 0.6658,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.18,
|
| 270 |
+
"learning_rate": 4.8536260811709914e-05,
|
| 271 |
+
"loss": 0.6607,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.18,
|
| 276 |
+
"learning_rate": 4.8502994011976046e-05,
|
| 277 |
+
"loss": 0.6447,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.18,
|
| 282 |
+
"learning_rate": 4.8469727212242186e-05,
|
| 283 |
+
"loss": 0.6603,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.19,
|
| 288 |
+
"learning_rate": 4.843646041250832e-05,
|
| 289 |
+
"loss": 0.6559,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19,
|
| 294 |
+
"learning_rate": 4.840319361277446e-05,
|
| 295 |
+
"loss": 0.6563,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2,
|
| 300 |
+
"learning_rate": 4.836992681304059e-05,
|
| 301 |
+
"loss": 0.6681,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.2,
|
| 306 |
+
"learning_rate": 4.833666001330672e-05,
|
| 307 |
+
"loss": 0.6412,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.2,
|
| 312 |
+
"learning_rate": 4.8303393213572856e-05,
|
| 313 |
+
"loss": 0.6553,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.21,
|
| 318 |
+
"learning_rate": 4.827012641383899e-05,
|
| 319 |
+
"loss": 0.655,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.21,
|
| 324 |
+
"learning_rate": 4.823685961410512e-05,
|
| 325 |
+
"loss": 0.6623,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.22,
|
| 330 |
+
"learning_rate": 4.820359281437126e-05,
|
| 331 |
+
"loss": 0.6574,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.22,
|
| 336 |
+
"learning_rate": 4.817032601463739e-05,
|
| 337 |
+
"loss": 0.6492,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22,
|
| 342 |
+
"learning_rate": 4.813705921490353e-05,
|
| 343 |
+
"loss": 0.6371,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.23,
|
| 348 |
+
"learning_rate": 4.8103792415169665e-05,
|
| 349 |
+
"loss": 0.6509,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.23,
|
| 354 |
+
"learning_rate": 4.80705256154358e-05,
|
| 355 |
+
"loss": 0.6443,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.24,
|
| 360 |
+
"learning_rate": 4.803725881570193e-05,
|
| 361 |
+
"loss": 0.634,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.24,
|
| 366 |
+
"learning_rate": 4.800399201596807e-05,
|
| 367 |
+
"loss": 0.6575,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.24,
|
| 372 |
+
"learning_rate": 4.79707252162342e-05,
|
| 373 |
+
"loss": 0.6518,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.25,
|
| 378 |
+
"learning_rate": 4.7937458416500335e-05,
|
| 379 |
+
"loss": 0.6584,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.25,
|
| 384 |
+
"learning_rate": 4.790419161676647e-05,
|
| 385 |
+
"loss": 0.6374,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.26,
|
| 390 |
+
"learning_rate": 4.78709248170326e-05,
|
| 391 |
+
"loss": 0.6481,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.26,
|
| 396 |
+
"learning_rate": 4.783765801729873e-05,
|
| 397 |
+
"loss": 0.6438,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.26,
|
| 402 |
+
"learning_rate": 4.780439121756487e-05,
|
| 403 |
+
"loss": 0.6349,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.27,
|
| 408 |
+
"learning_rate": 4.777112441783101e-05,
|
| 409 |
+
"loss": 0.63,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.27,
|
| 414 |
+
"learning_rate": 4.7737857618097145e-05,
|
| 415 |
+
"loss": 0.6447,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.28,
|
| 420 |
+
"learning_rate": 4.770459081836328e-05,
|
| 421 |
+
"loss": 0.6462,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.28,
|
| 426 |
+
"learning_rate": 4.767132401862941e-05,
|
| 427 |
+
"loss": 0.6317,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.28,
|
| 432 |
+
"learning_rate": 4.763805721889554e-05,
|
| 433 |
+
"loss": 0.641,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.29,
|
| 438 |
+
"learning_rate": 4.7604790419161675e-05,
|
| 439 |
+
"loss": 0.6407,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.29,
|
| 444 |
+
"learning_rate": 4.7571523619427815e-05,
|
| 445 |
+
"loss": 0.6353,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.3,
|
| 450 |
+
"learning_rate": 4.753825681969395e-05,
|
| 451 |
+
"loss": 0.6284,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.3,
|
| 456 |
+
"learning_rate": 4.750499001996008e-05,
|
| 457 |
+
"loss": 0.6333,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3,
|
| 462 |
+
"learning_rate": 4.747172322022622e-05,
|
| 463 |
+
"loss": 0.6202,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.31,
|
| 468 |
+
"learning_rate": 4.743845642049235e-05,
|
| 469 |
+
"loss": 0.6277,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.31,
|
| 474 |
+
"learning_rate": 4.7405189620758485e-05,
|
| 475 |
+
"loss": 0.6416,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.32,
|
| 480 |
+
"learning_rate": 4.7371922821024624e-05,
|
| 481 |
+
"loss": 0.6256,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.32,
|
| 486 |
+
"learning_rate": 4.733865602129076e-05,
|
| 487 |
+
"loss": 0.628,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.32,
|
| 492 |
+
"learning_rate": 4.730538922155689e-05,
|
| 493 |
+
"loss": 0.6328,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.33,
|
| 498 |
+
"learning_rate": 4.727212242182302e-05,
|
| 499 |
+
"loss": 0.6379,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.33,
|
| 504 |
+
"learning_rate": 4.7238855622089155e-05,
|
| 505 |
+
"loss": 0.6279,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.34,
|
| 510 |
+
"learning_rate": 4.720558882235529e-05,
|
| 511 |
+
"loss": 0.6298,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.34,
|
| 516 |
+
"learning_rate": 4.717232202262143e-05,
|
| 517 |
+
"loss": 0.6369,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.34,
|
| 522 |
+
"learning_rate": 4.713905522288756e-05,
|
| 523 |
+
"loss": 0.6135,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.35,
|
| 528 |
+
"learning_rate": 4.71057884231537e-05,
|
| 529 |
+
"loss": 0.6188,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.35,
|
| 534 |
+
"learning_rate": 4.707252162341983e-05,
|
| 535 |
+
"loss": 0.638,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.36,
|
| 540 |
+
"learning_rate": 4.7039254823685964e-05,
|
| 541 |
+
"loss": 0.638,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.36,
|
| 546 |
+
"learning_rate": 4.70059880239521e-05,
|
| 547 |
+
"loss": 0.6346,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36,
|
| 552 |
+
"learning_rate": 4.697272122421823e-05,
|
| 553 |
+
"loss": 0.6261,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.37,
|
| 558 |
+
"learning_rate": 4.693945442448437e-05,
|
| 559 |
+
"loss": 0.6294,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.37,
|
| 564 |
+
"learning_rate": 4.69061876247505e-05,
|
| 565 |
+
"loss": 0.6438,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.38,
|
| 570 |
+
"learning_rate": 4.6872920825016634e-05,
|
| 571 |
+
"loss": 0.6299,
|
| 572 |
+
"step": 47000
|
| 573 |
+
}
|
| 574 |
+
],
|
| 575 |
+
"max_steps": 751500,
|
| 576 |
+
"num_train_epochs": 6,
|
| 577 |
+
"total_flos": 57057686327623680,
|
| 578 |
+
"trial_name": null,
|
| 579 |
+
"trial_params": null
|
| 580 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee44e2d0ee2b71554c29517318b2f412b308cd8397f598a958b30fe625e2f01
|
| 3 |
+
size 2159
|