longformer doctype
Browse files- .gitattributes +2 -0
- all_results.json +8 -0
- config.json +56 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +385 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.0,
|
| 3 |
+
"train_loss": 1.4238887095158894,
|
| 4 |
+
"train_runtime": 60363.921,
|
| 5 |
+
"train_samples": 275219,
|
| 6 |
+
"train_samples_per_second": 31.915,
|
| 7 |
+
"train_steps_per_second": 1.995
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"add_bias_logits": false,
|
| 5 |
+
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"LongformerBartWithDoctypeForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"attention_window": [
|
| 12 |
+
64,
|
| 13 |
+
64,
|
| 14 |
+
64,
|
| 15 |
+
64
|
| 16 |
+
],
|
| 17 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"classif_dropout": 0.1,
|
| 20 |
+
"classifier_dropout": 0.1,
|
| 21 |
+
"d_model": 512,
|
| 22 |
+
"decoder_attention_heads": 4,
|
| 23 |
+
"decoder_ffn_dim": 2048,
|
| 24 |
+
"decoder_layerdrop": 0.0,
|
| 25 |
+
"decoder_layers": 4,
|
| 26 |
+
"decoder_start_token_id": 1,
|
| 27 |
+
"do_blenderbot_90_layernorm": false,
|
| 28 |
+
"doc_type_size": 4,
|
| 29 |
+
"dropout": 0.1,
|
| 30 |
+
"encoder_attention_heads": 4,
|
| 31 |
+
"encoder_ffn_dim": 2048,
|
| 32 |
+
"encoder_layerdrop": 0.0,
|
| 33 |
+
"encoder_layers": 4,
|
| 34 |
+
"eos_token_id": 1,
|
| 35 |
+
"extra_pos_embeddings": 2,
|
| 36 |
+
"force_bos_token_to_be_generated": false,
|
| 37 |
+
"forced_eos_token_id": 1,
|
| 38 |
+
"gradient_checkpointing": false,
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"kobart_version": 1.0,
|
| 42 |
+
"max_position_embeddings": 2048,
|
| 43 |
+
"max_target_positions": 2048,
|
| 44 |
+
"model_type": "bart",
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 3,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"static_position_embeddings": false,
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.11.0",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 30000
|
| 56 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aaa592ac16613e01d4ed2606deae7729e8a110465a43fa46e4a1f4daf673bff
|
| 3 |
+
size 261798381
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/3e6abf40f4fadbea9e7b539c182868d979838d8f7e6cdcdf2ed52ddcf01420c0.15447ae63ad4a2eba8bc7a5146360711dc32b315b4f1488b4806debf35315e9a", "name_or_path": "gogamza/kobart-base-v1", "tokenizer_class": "PreTrainedTokenizerFast"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.0,
|
| 3 |
+
"train_loss": 1.4238887095158894,
|
| 4 |
+
"train_runtime": 60363.921,
|
| 5 |
+
"train_samples": 275219,
|
| 6 |
+
"train_samples_per_second": 31.915,
|
| 7 |
+
"train_steps_per_second": 1.995
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.999985466172516,
|
| 5 |
+
"global_step": 120407,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 2e-05,
|
| 13 |
+
"loss": 9.0919,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 4e-05,
|
| 19 |
+
"loss": 7.6432,
|
| 20 |
+
"step": 4000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.35,
|
| 24 |
+
"learning_rate": 6e-05,
|
| 25 |
+
"loss": 6.7199,
|
| 26 |
+
"step": 6000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.47,
|
| 30 |
+
"learning_rate": 8e-05,
|
| 31 |
+
"loss": 6.1549,
|
| 32 |
+
"step": 8000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.58,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 5.5391,
|
| 38 |
+
"step": 10000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7,
|
| 42 |
+
"learning_rate": 9.818852065539323e-05,
|
| 43 |
+
"loss": 4.4909,
|
| 44 |
+
"step": 12000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.81,
|
| 48 |
+
"learning_rate": 9.637704131078646e-05,
|
| 49 |
+
"loss": 2.7203,
|
| 50 |
+
"step": 14000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.93,
|
| 54 |
+
"learning_rate": 9.456556196617969e-05,
|
| 55 |
+
"loss": 1.5493,
|
| 56 |
+
"step": 16000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.05,
|
| 60 |
+
"learning_rate": 9.275408262157291e-05,
|
| 61 |
+
"loss": 1.2876,
|
| 62 |
+
"step": 18000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.16,
|
| 66 |
+
"learning_rate": 9.094260327696614e-05,
|
| 67 |
+
"loss": 1.1713,
|
| 68 |
+
"step": 20000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.28,
|
| 72 |
+
"learning_rate": 8.913112393235937e-05,
|
| 73 |
+
"loss": 1.1049,
|
| 74 |
+
"step": 22000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.4,
|
| 78 |
+
"learning_rate": 8.73196445877526e-05,
|
| 79 |
+
"loss": 1.0576,
|
| 80 |
+
"step": 24000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.51,
|
| 84 |
+
"learning_rate": 8.550816524314582e-05,
|
| 85 |
+
"loss": 1.0238,
|
| 86 |
+
"step": 26000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.63,
|
| 90 |
+
"learning_rate": 8.369668589853905e-05,
|
| 91 |
+
"loss": 0.9882,
|
| 92 |
+
"step": 28000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.74,
|
| 96 |
+
"learning_rate": 8.188520655393228e-05,
|
| 97 |
+
"loss": 0.9338,
|
| 98 |
+
"step": 30000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.86,
|
| 102 |
+
"learning_rate": 8.00737272093255e-05,
|
| 103 |
+
"loss": 0.895,
|
| 104 |
+
"step": 32000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.98,
|
| 108 |
+
"learning_rate": 7.826224786471873e-05,
|
| 109 |
+
"loss": 0.8748,
|
| 110 |
+
"step": 34000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.09,
|
| 114 |
+
"learning_rate": 7.645076852011194e-05,
|
| 115 |
+
"loss": 0.8617,
|
| 116 |
+
"step": 36000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.21,
|
| 120 |
+
"learning_rate": 7.463928917550518e-05,
|
| 121 |
+
"loss": 0.8464,
|
| 122 |
+
"step": 38000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.33,
|
| 126 |
+
"learning_rate": 7.282780983089841e-05,
|
| 127 |
+
"loss": 0.8373,
|
| 128 |
+
"step": 40000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.44,
|
| 132 |
+
"learning_rate": 7.101633048629164e-05,
|
| 133 |
+
"loss": 0.8292,
|
| 134 |
+
"step": 42000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.56,
|
| 138 |
+
"learning_rate": 6.920485114168485e-05,
|
| 139 |
+
"loss": 0.8215,
|
| 140 |
+
"step": 44000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.67,
|
| 144 |
+
"learning_rate": 6.739337179707809e-05,
|
| 145 |
+
"loss": 0.8139,
|
| 146 |
+
"step": 46000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.79,
|
| 150 |
+
"learning_rate": 6.558189245247132e-05,
|
| 151 |
+
"loss": 0.8065,
|
| 152 |
+
"step": 48000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.91,
|
| 156 |
+
"learning_rate": 6.377041310786455e-05,
|
| 157 |
+
"loss": 0.8003,
|
| 158 |
+
"step": 50000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.02,
|
| 162 |
+
"learning_rate": 6.195893376325776e-05,
|
| 163 |
+
"loss": 0.7953,
|
| 164 |
+
"step": 52000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.14,
|
| 168 |
+
"learning_rate": 6.0147454418650995e-05,
|
| 169 |
+
"loss": 0.7864,
|
| 170 |
+
"step": 54000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.26,
|
| 174 |
+
"learning_rate": 5.833597507404422e-05,
|
| 175 |
+
"loss": 0.7826,
|
| 176 |
+
"step": 56000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.37,
|
| 180 |
+
"learning_rate": 5.652449572943744e-05,
|
| 181 |
+
"loss": 0.7781,
|
| 182 |
+
"step": 58000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.49,
|
| 186 |
+
"learning_rate": 5.4713016384830676e-05,
|
| 187 |
+
"loss": 0.7744,
|
| 188 |
+
"step": 60000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.6,
|
| 192 |
+
"learning_rate": 5.2901537040223903e-05,
|
| 193 |
+
"loss": 0.7678,
|
| 194 |
+
"step": 62000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.72,
|
| 198 |
+
"learning_rate": 5.109005769561713e-05,
|
| 199 |
+
"loss": 0.7646,
|
| 200 |
+
"step": 64000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.84,
|
| 204 |
+
"learning_rate": 4.927857835101036e-05,
|
| 205 |
+
"loss": 0.7621,
|
| 206 |
+
"step": 66000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.95,
|
| 210 |
+
"learning_rate": 4.746709900640358e-05,
|
| 211 |
+
"loss": 0.7588,
|
| 212 |
+
"step": 68000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.07,
|
| 216 |
+
"learning_rate": 4.565561966179681e-05,
|
| 217 |
+
"loss": 0.7535,
|
| 218 |
+
"step": 70000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.19,
|
| 222 |
+
"learning_rate": 4.384414031719003e-05,
|
| 223 |
+
"loss": 0.7494,
|
| 224 |
+
"step": 72000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.3,
|
| 228 |
+
"learning_rate": 4.203266097258326e-05,
|
| 229 |
+
"loss": 0.7466,
|
| 230 |
+
"step": 74000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.42,
|
| 234 |
+
"learning_rate": 4.022118162797649e-05,
|
| 235 |
+
"loss": 0.7426,
|
| 236 |
+
"step": 76000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.53,
|
| 240 |
+
"learning_rate": 3.8409702283369714e-05,
|
| 241 |
+
"loss": 0.7402,
|
| 242 |
+
"step": 78000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.65,
|
| 246 |
+
"learning_rate": 3.659822293876294e-05,
|
| 247 |
+
"loss": 0.7386,
|
| 248 |
+
"step": 80000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.77,
|
| 252 |
+
"learning_rate": 3.478674359415617e-05,
|
| 253 |
+
"loss": 0.7348,
|
| 254 |
+
"step": 82000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.88,
|
| 258 |
+
"learning_rate": 3.2975264249549395e-05,
|
| 259 |
+
"loss": 0.7331,
|
| 260 |
+
"step": 84000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.0,
|
| 264 |
+
"learning_rate": 3.116378490494262e-05,
|
| 265 |
+
"loss": 0.7307,
|
| 266 |
+
"step": 86000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.12,
|
| 270 |
+
"learning_rate": 2.9352305560335853e-05,
|
| 271 |
+
"loss": 0.7258,
|
| 272 |
+
"step": 88000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.23,
|
| 276 |
+
"learning_rate": 2.7540826215729077e-05,
|
| 277 |
+
"loss": 0.7234,
|
| 278 |
+
"step": 90000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.35,
|
| 282 |
+
"learning_rate": 2.57293468711223e-05,
|
| 283 |
+
"loss": 0.7208,
|
| 284 |
+
"step": 92000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.46,
|
| 288 |
+
"learning_rate": 2.391786752651553e-05,
|
| 289 |
+
"loss": 0.7179,
|
| 290 |
+
"step": 94000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.58,
|
| 294 |
+
"learning_rate": 2.2106388181908758e-05,
|
| 295 |
+
"loss": 0.7188,
|
| 296 |
+
"step": 96000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 5.7,
|
| 300 |
+
"learning_rate": 2.0294908837301985e-05,
|
| 301 |
+
"loss": 0.7158,
|
| 302 |
+
"step": 98000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.81,
|
| 306 |
+
"learning_rate": 1.8483429492695212e-05,
|
| 307 |
+
"loss": 0.7146,
|
| 308 |
+
"step": 100000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.93,
|
| 312 |
+
"learning_rate": 1.6671950148088436e-05,
|
| 313 |
+
"loss": 0.7125,
|
| 314 |
+
"step": 102000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.05,
|
| 318 |
+
"learning_rate": 1.4860470803481663e-05,
|
| 319 |
+
"loss": 0.7092,
|
| 320 |
+
"step": 104000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.16,
|
| 324 |
+
"learning_rate": 1.304899145887489e-05,
|
| 325 |
+
"loss": 0.7061,
|
| 326 |
+
"step": 106000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.28,
|
| 330 |
+
"learning_rate": 1.1237512114268117e-05,
|
| 331 |
+
"loss": 0.7064,
|
| 332 |
+
"step": 108000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.39,
|
| 336 |
+
"learning_rate": 9.426032769661344e-06,
|
| 337 |
+
"loss": 0.7034,
|
| 338 |
+
"step": 110000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.51,
|
| 342 |
+
"learning_rate": 7.614553425054572e-06,
|
| 343 |
+
"loss": 0.7027,
|
| 344 |
+
"step": 112000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.63,
|
| 348 |
+
"learning_rate": 5.803074080447798e-06,
|
| 349 |
+
"loss": 0.7015,
|
| 350 |
+
"step": 114000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.74,
|
| 354 |
+
"learning_rate": 3.991594735841025e-06,
|
| 355 |
+
"loss": 0.7004,
|
| 356 |
+
"step": 116000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.86,
|
| 360 |
+
"learning_rate": 2.1801153912342513e-06,
|
| 361 |
+
"loss": 0.7,
|
| 362 |
+
"step": 118000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.98,
|
| 366 |
+
"learning_rate": 3.6863604662747836e-07,
|
| 367 |
+
"loss": 0.6989,
|
| 368 |
+
"step": 120000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 7.0,
|
| 372 |
+
"step": 120407,
|
| 373 |
+
"total_flos": 3.3047861122616525e+17,
|
| 374 |
+
"train_loss": 1.4238887095158894,
|
| 375 |
+
"train_runtime": 60363.921,
|
| 376 |
+
"train_samples_per_second": 31.915,
|
| 377 |
+
"train_steps_per_second": 1.995
|
| 378 |
+
}
|
| 379 |
+
],
|
| 380 |
+
"max_steps": 120407,
|
| 381 |
+
"num_train_epochs": 7,
|
| 382 |
+
"total_flos": 3.3047861122616525e+17,
|
| 383 |
+
"trial_name": null,
|
| 384 |
+
"trial_params": null
|
| 385 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507321ad1730b8b97d072cbf06c525731560134d2ba2bcdd11e90f6fe653f3b6
|
| 3 |
+
size 5743
|