com1
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.txt +5 -0
- trainer_state.json +865 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "kykim/bert-kor-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"embedding_size": 768,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"model_type": "bert",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pooler_fc_size": 768,
|
| 23 |
+
"pooler_num_attention_heads": 12,
|
| 24 |
+
"pooler_num_fc_layers": 3,
|
| 25 |
+
"pooler_size_per_head": 128,
|
| 26 |
+
"pooler_type": "first_token_transform",
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.12.2",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 42000
|
| 33 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b1e25e5ea76e0285921a674a586a382d957279182de1ff351d32e6bbd09b841
|
| 3 |
+
size 602629988
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "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 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "kykim/bert-kor-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 10.0
|
| 2 |
+
train_loss = 1.6471780081788416
|
| 3 |
+
train_runtime = 2443.9537
|
| 4 |
+
train_samples_per_second = 91.692
|
| 5 |
+
train_steps_per_second = 2.868
|
trainer_state.json
ADDED
|
@@ -0,0 +1,865 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 7010,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.964336661911555e-05,
|
| 13 |
+
"loss": 2.1394,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 4.92867332382311e-05,
|
| 19 |
+
"loss": 1.9883,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.21,
|
| 24 |
+
"learning_rate": 4.893009985734665e-05,
|
| 25 |
+
"loss": 1.9832,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.29,
|
| 30 |
+
"learning_rate": 4.85734664764622e-05,
|
| 31 |
+
"loss": 1.9561,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.36,
|
| 36 |
+
"learning_rate": 4.821683309557775e-05,
|
| 37 |
+
"loss": 1.9404,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.43,
|
| 42 |
+
"learning_rate": 4.7860199714693296e-05,
|
| 43 |
+
"loss": 1.9088,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5,
|
| 48 |
+
"learning_rate": 4.7503566333808845e-05,
|
| 49 |
+
"loss": 1.8832,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.57,
|
| 54 |
+
"learning_rate": 4.7146932952924393e-05,
|
| 55 |
+
"loss": 1.8853,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.64,
|
| 60 |
+
"learning_rate": 4.679029957203995e-05,
|
| 61 |
+
"loss": 1.8799,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.71,
|
| 66 |
+
"learning_rate": 4.64336661911555e-05,
|
| 67 |
+
"loss": 1.825,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.78,
|
| 72 |
+
"learning_rate": 4.607703281027104e-05,
|
| 73 |
+
"loss": 1.8531,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.86,
|
| 78 |
+
"learning_rate": 4.572039942938659e-05,
|
| 79 |
+
"loss": 1.847,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.93,
|
| 84 |
+
"learning_rate": 4.5363766048502145e-05,
|
| 85 |
+
"loss": 1.8485,
|
| 86 |
+
"step": 650
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"learning_rate": 4.5007132667617693e-05,
|
| 91 |
+
"loss": 1.83,
|
| 92 |
+
"step": 700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.07,
|
| 96 |
+
"learning_rate": 4.4650499286733236e-05,
|
| 97 |
+
"loss": 1.8062,
|
| 98 |
+
"step": 750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.14,
|
| 102 |
+
"learning_rate": 4.429386590584879e-05,
|
| 103 |
+
"loss": 1.806,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.21,
|
| 108 |
+
"learning_rate": 4.393723252496434e-05,
|
| 109 |
+
"loss": 1.7829,
|
| 110 |
+
"step": 850
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.28,
|
| 114 |
+
"learning_rate": 4.358059914407989e-05,
|
| 115 |
+
"loss": 1.7775,
|
| 116 |
+
"step": 900
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.36,
|
| 120 |
+
"learning_rate": 4.322396576319544e-05,
|
| 121 |
+
"loss": 1.7954,
|
| 122 |
+
"step": 950
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.43,
|
| 126 |
+
"learning_rate": 4.286733238231099e-05,
|
| 127 |
+
"loss": 1.794,
|
| 128 |
+
"step": 1000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.5,
|
| 132 |
+
"learning_rate": 4.2510699001426536e-05,
|
| 133 |
+
"loss": 1.7848,
|
| 134 |
+
"step": 1050
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.57,
|
| 138 |
+
"learning_rate": 4.2154065620542085e-05,
|
| 139 |
+
"loss": 1.7733,
|
| 140 |
+
"step": 1100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.64,
|
| 144 |
+
"learning_rate": 4.1797432239657633e-05,
|
| 145 |
+
"loss": 1.7579,
|
| 146 |
+
"step": 1150
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.71,
|
| 150 |
+
"learning_rate": 4.144079885877318e-05,
|
| 151 |
+
"loss": 1.7667,
|
| 152 |
+
"step": 1200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.78,
|
| 156 |
+
"learning_rate": 4.108416547788873e-05,
|
| 157 |
+
"loss": 1.7709,
|
| 158 |
+
"step": 1250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.85,
|
| 162 |
+
"learning_rate": 4.072753209700429e-05,
|
| 163 |
+
"loss": 1.7481,
|
| 164 |
+
"step": 1300
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.93,
|
| 168 |
+
"learning_rate": 4.037089871611983e-05,
|
| 169 |
+
"loss": 1.7354,
|
| 170 |
+
"step": 1350
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.0,
|
| 174 |
+
"learning_rate": 4.001426533523538e-05,
|
| 175 |
+
"loss": 1.7537,
|
| 176 |
+
"step": 1400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.07,
|
| 180 |
+
"learning_rate": 3.965763195435093e-05,
|
| 181 |
+
"loss": 1.7301,
|
| 182 |
+
"step": 1450
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.14,
|
| 186 |
+
"learning_rate": 3.930099857346648e-05,
|
| 187 |
+
"loss": 1.7135,
|
| 188 |
+
"step": 1500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.21,
|
| 192 |
+
"learning_rate": 3.8944365192582024e-05,
|
| 193 |
+
"loss": 1.7132,
|
| 194 |
+
"step": 1550
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.28,
|
| 198 |
+
"learning_rate": 3.858773181169757e-05,
|
| 199 |
+
"loss": 1.7312,
|
| 200 |
+
"step": 1600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.35,
|
| 204 |
+
"learning_rate": 3.823109843081313e-05,
|
| 205 |
+
"loss": 1.7184,
|
| 206 |
+
"step": 1650
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.43,
|
| 210 |
+
"learning_rate": 3.787446504992868e-05,
|
| 211 |
+
"loss": 1.7202,
|
| 212 |
+
"step": 1700
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.5,
|
| 216 |
+
"learning_rate": 3.751783166904422e-05,
|
| 217 |
+
"loss": 1.7139,
|
| 218 |
+
"step": 1750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.57,
|
| 222 |
+
"learning_rate": 3.716119828815977e-05,
|
| 223 |
+
"loss": 1.721,
|
| 224 |
+
"step": 1800
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.64,
|
| 228 |
+
"learning_rate": 3.6804564907275324e-05,
|
| 229 |
+
"loss": 1.7021,
|
| 230 |
+
"step": 1850
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.71,
|
| 234 |
+
"learning_rate": 3.644793152639087e-05,
|
| 235 |
+
"loss": 1.722,
|
| 236 |
+
"step": 1900
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.78,
|
| 240 |
+
"learning_rate": 3.609129814550642e-05,
|
| 241 |
+
"loss": 1.6787,
|
| 242 |
+
"step": 1950
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.85,
|
| 246 |
+
"learning_rate": 3.573466476462197e-05,
|
| 247 |
+
"loss": 1.7017,
|
| 248 |
+
"step": 2000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.92,
|
| 252 |
+
"learning_rate": 3.537803138373752e-05,
|
| 253 |
+
"loss": 1.7102,
|
| 254 |
+
"step": 2050
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.0,
|
| 258 |
+
"learning_rate": 3.502139800285307e-05,
|
| 259 |
+
"loss": 1.6821,
|
| 260 |
+
"step": 2100
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.07,
|
| 264 |
+
"learning_rate": 3.466476462196862e-05,
|
| 265 |
+
"loss": 1.6934,
|
| 266 |
+
"step": 2150
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.14,
|
| 270 |
+
"learning_rate": 3.430813124108417e-05,
|
| 271 |
+
"loss": 1.6817,
|
| 272 |
+
"step": 2200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.21,
|
| 276 |
+
"learning_rate": 3.3951497860199716e-05,
|
| 277 |
+
"loss": 1.6769,
|
| 278 |
+
"step": 2250
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.28,
|
| 282 |
+
"learning_rate": 3.3594864479315264e-05,
|
| 283 |
+
"loss": 1.6836,
|
| 284 |
+
"step": 2300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.35,
|
| 288 |
+
"learning_rate": 3.323823109843081e-05,
|
| 289 |
+
"loss": 1.6666,
|
| 290 |
+
"step": 2350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.42,
|
| 294 |
+
"learning_rate": 3.288159771754636e-05,
|
| 295 |
+
"loss": 1.6788,
|
| 296 |
+
"step": 2400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.5,
|
| 300 |
+
"learning_rate": 3.252496433666191e-05,
|
| 301 |
+
"loss": 1.6446,
|
| 302 |
+
"step": 2450
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.57,
|
| 306 |
+
"learning_rate": 3.216833095577747e-05,
|
| 307 |
+
"loss": 1.6658,
|
| 308 |
+
"step": 2500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.64,
|
| 312 |
+
"learning_rate": 3.1811697574893016e-05,
|
| 313 |
+
"loss": 1.6523,
|
| 314 |
+
"step": 2550
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.71,
|
| 318 |
+
"learning_rate": 3.145506419400856e-05,
|
| 319 |
+
"loss": 1.6794,
|
| 320 |
+
"step": 2600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.78,
|
| 324 |
+
"learning_rate": 3.1098430813124107e-05,
|
| 325 |
+
"loss": 1.6551,
|
| 326 |
+
"step": 2650
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.85,
|
| 330 |
+
"learning_rate": 3.074179743223966e-05,
|
| 331 |
+
"loss": 1.6595,
|
| 332 |
+
"step": 2700
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.92,
|
| 336 |
+
"learning_rate": 3.0385164051355208e-05,
|
| 337 |
+
"loss": 1.6518,
|
| 338 |
+
"step": 2750
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.99,
|
| 342 |
+
"learning_rate": 3.0028530670470757e-05,
|
| 343 |
+
"loss": 1.6226,
|
| 344 |
+
"step": 2800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.07,
|
| 348 |
+
"learning_rate": 2.967189728958631e-05,
|
| 349 |
+
"loss": 1.6458,
|
| 350 |
+
"step": 2850
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.14,
|
| 354 |
+
"learning_rate": 2.9315263908701858e-05,
|
| 355 |
+
"loss": 1.6407,
|
| 356 |
+
"step": 2900
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.21,
|
| 360 |
+
"learning_rate": 2.8958630527817403e-05,
|
| 361 |
+
"loss": 1.6321,
|
| 362 |
+
"step": 2950
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.28,
|
| 366 |
+
"learning_rate": 2.8601997146932952e-05,
|
| 367 |
+
"loss": 1.6502,
|
| 368 |
+
"step": 3000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.35,
|
| 372 |
+
"learning_rate": 2.8245363766048504e-05,
|
| 373 |
+
"loss": 1.6438,
|
| 374 |
+
"step": 3050
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.42,
|
| 378 |
+
"learning_rate": 2.7888730385164053e-05,
|
| 379 |
+
"loss": 1.6428,
|
| 380 |
+
"step": 3100
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.49,
|
| 384 |
+
"learning_rate": 2.75320970042796e-05,
|
| 385 |
+
"loss": 1.633,
|
| 386 |
+
"step": 3150
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.56,
|
| 390 |
+
"learning_rate": 2.7175463623395154e-05,
|
| 391 |
+
"loss": 1.6245,
|
| 392 |
+
"step": 3200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.64,
|
| 396 |
+
"learning_rate": 2.68188302425107e-05,
|
| 397 |
+
"loss": 1.6337,
|
| 398 |
+
"step": 3250
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.71,
|
| 402 |
+
"learning_rate": 2.646219686162625e-05,
|
| 403 |
+
"loss": 1.6511,
|
| 404 |
+
"step": 3300
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.78,
|
| 408 |
+
"learning_rate": 2.6105563480741794e-05,
|
| 409 |
+
"loss": 1.6104,
|
| 410 |
+
"step": 3350
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.85,
|
| 414 |
+
"learning_rate": 2.574893009985735e-05,
|
| 415 |
+
"loss": 1.614,
|
| 416 |
+
"step": 3400
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.92,
|
| 420 |
+
"learning_rate": 2.5392296718972895e-05,
|
| 421 |
+
"loss": 1.6038,
|
| 422 |
+
"step": 3450
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.99,
|
| 426 |
+
"learning_rate": 2.5035663338088444e-05,
|
| 427 |
+
"loss": 1.6365,
|
| 428 |
+
"step": 3500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.06,
|
| 432 |
+
"learning_rate": 2.4679029957203993e-05,
|
| 433 |
+
"loss": 1.6022,
|
| 434 |
+
"step": 3550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.14,
|
| 438 |
+
"learning_rate": 2.4322396576319545e-05,
|
| 439 |
+
"loss": 1.6039,
|
| 440 |
+
"step": 3600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.21,
|
| 444 |
+
"learning_rate": 2.396576319543509e-05,
|
| 445 |
+
"loss": 1.5874,
|
| 446 |
+
"step": 3650
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.28,
|
| 450 |
+
"learning_rate": 2.3609129814550643e-05,
|
| 451 |
+
"loss": 1.5715,
|
| 452 |
+
"step": 3700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 5.35,
|
| 456 |
+
"learning_rate": 2.3252496433666192e-05,
|
| 457 |
+
"loss": 1.601,
|
| 458 |
+
"step": 3750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.42,
|
| 462 |
+
"learning_rate": 2.289586305278174e-05,
|
| 463 |
+
"loss": 1.5898,
|
| 464 |
+
"step": 3800
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.49,
|
| 468 |
+
"learning_rate": 2.253922967189729e-05,
|
| 469 |
+
"loss": 1.6232,
|
| 470 |
+
"step": 3850
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 5.56,
|
| 474 |
+
"learning_rate": 2.218259629101284e-05,
|
| 475 |
+
"loss": 1.6,
|
| 476 |
+
"step": 3900
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.63,
|
| 480 |
+
"learning_rate": 2.1825962910128388e-05,
|
| 481 |
+
"loss": 1.5911,
|
| 482 |
+
"step": 3950
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.71,
|
| 486 |
+
"learning_rate": 2.146932952924394e-05,
|
| 487 |
+
"loss": 1.5976,
|
| 488 |
+
"step": 4000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.78,
|
| 492 |
+
"learning_rate": 2.111269614835949e-05,
|
| 493 |
+
"loss": 1.5734,
|
| 494 |
+
"step": 4050
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.85,
|
| 498 |
+
"learning_rate": 2.0756062767475038e-05,
|
| 499 |
+
"loss": 1.6059,
|
| 500 |
+
"step": 4100
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 5.92,
|
| 504 |
+
"learning_rate": 2.0399429386590586e-05,
|
| 505 |
+
"loss": 1.5414,
|
| 506 |
+
"step": 4150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.99,
|
| 510 |
+
"learning_rate": 2.0042796005706135e-05,
|
| 511 |
+
"loss": 1.5934,
|
| 512 |
+
"step": 4200
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.06,
|
| 516 |
+
"learning_rate": 1.9686162624821684e-05,
|
| 517 |
+
"loss": 1.5541,
|
| 518 |
+
"step": 4250
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.13,
|
| 522 |
+
"learning_rate": 1.9329529243937233e-05,
|
| 523 |
+
"loss": 1.5748,
|
| 524 |
+
"step": 4300
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.21,
|
| 528 |
+
"learning_rate": 1.8972895863052782e-05,
|
| 529 |
+
"loss": 1.5502,
|
| 530 |
+
"step": 4350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.28,
|
| 534 |
+
"learning_rate": 1.861626248216833e-05,
|
| 535 |
+
"loss": 1.5512,
|
| 536 |
+
"step": 4400
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.35,
|
| 540 |
+
"learning_rate": 1.8259629101283883e-05,
|
| 541 |
+
"loss": 1.5841,
|
| 542 |
+
"step": 4450
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 6.42,
|
| 546 |
+
"learning_rate": 1.790299572039943e-05,
|
| 547 |
+
"loss": 1.6056,
|
| 548 |
+
"step": 4500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.49,
|
| 552 |
+
"learning_rate": 1.754636233951498e-05,
|
| 553 |
+
"loss": 1.5843,
|
| 554 |
+
"step": 4550
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.56,
|
| 558 |
+
"learning_rate": 1.718972895863053e-05,
|
| 559 |
+
"loss": 1.5775,
|
| 560 |
+
"step": 4600
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.63,
|
| 564 |
+
"learning_rate": 1.683309557774608e-05,
|
| 565 |
+
"loss": 1.567,
|
| 566 |
+
"step": 4650
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 6.7,
|
| 570 |
+
"learning_rate": 1.6476462196861628e-05,
|
| 571 |
+
"loss": 1.5395,
|
| 572 |
+
"step": 4700
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 6.78,
|
| 576 |
+
"learning_rate": 1.6119828815977176e-05,
|
| 577 |
+
"loss": 1.6035,
|
| 578 |
+
"step": 4750
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.85,
|
| 582 |
+
"learning_rate": 1.5763195435092725e-05,
|
| 583 |
+
"loss": 1.5744,
|
| 584 |
+
"step": 4800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.92,
|
| 588 |
+
"learning_rate": 1.5406562054208274e-05,
|
| 589 |
+
"loss": 1.5538,
|
| 590 |
+
"step": 4850
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.99,
|
| 594 |
+
"learning_rate": 1.5049928673323823e-05,
|
| 595 |
+
"loss": 1.5561,
|
| 596 |
+
"step": 4900
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 7.06,
|
| 600 |
+
"learning_rate": 1.4693295292439374e-05,
|
| 601 |
+
"loss": 1.5545,
|
| 602 |
+
"step": 4950
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 7.13,
|
| 606 |
+
"learning_rate": 1.433666191155492e-05,
|
| 607 |
+
"loss": 1.5433,
|
| 608 |
+
"step": 5000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 7.2,
|
| 612 |
+
"learning_rate": 1.3980028530670471e-05,
|
| 613 |
+
"loss": 1.536,
|
| 614 |
+
"step": 5050
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 7.28,
|
| 618 |
+
"learning_rate": 1.362339514978602e-05,
|
| 619 |
+
"loss": 1.5689,
|
| 620 |
+
"step": 5100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.35,
|
| 624 |
+
"learning_rate": 1.326676176890157e-05,
|
| 625 |
+
"loss": 1.5497,
|
| 626 |
+
"step": 5150
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 7.42,
|
| 630 |
+
"learning_rate": 1.291012838801712e-05,
|
| 631 |
+
"loss": 1.5449,
|
| 632 |
+
"step": 5200
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.49,
|
| 636 |
+
"learning_rate": 1.2553495007132669e-05,
|
| 637 |
+
"loss": 1.5663,
|
| 638 |
+
"step": 5250
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.56,
|
| 642 |
+
"learning_rate": 1.2196861626248217e-05,
|
| 643 |
+
"loss": 1.5725,
|
| 644 |
+
"step": 5300
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.63,
|
| 648 |
+
"learning_rate": 1.1840228245363768e-05,
|
| 649 |
+
"loss": 1.5291,
|
| 650 |
+
"step": 5350
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.7,
|
| 654 |
+
"learning_rate": 1.1483594864479317e-05,
|
| 655 |
+
"loss": 1.5607,
|
| 656 |
+
"step": 5400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 7.77,
|
| 660 |
+
"learning_rate": 1.1126961483594866e-05,
|
| 661 |
+
"loss": 1.5361,
|
| 662 |
+
"step": 5450
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 7.85,
|
| 666 |
+
"learning_rate": 1.0770328102710415e-05,
|
| 667 |
+
"loss": 1.5743,
|
| 668 |
+
"step": 5500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 7.92,
|
| 672 |
+
"learning_rate": 1.0413694721825964e-05,
|
| 673 |
+
"loss": 1.5484,
|
| 674 |
+
"step": 5550
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.99,
|
| 678 |
+
"learning_rate": 1.0057061340941512e-05,
|
| 679 |
+
"loss": 1.5238,
|
| 680 |
+
"step": 5600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 8.06,
|
| 684 |
+
"learning_rate": 9.700427960057063e-06,
|
| 685 |
+
"loss": 1.5493,
|
| 686 |
+
"step": 5650
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 8.13,
|
| 690 |
+
"learning_rate": 9.343794579172612e-06,
|
| 691 |
+
"loss": 1.5216,
|
| 692 |
+
"step": 5700
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 8.2,
|
| 696 |
+
"learning_rate": 8.98716119828816e-06,
|
| 697 |
+
"loss": 1.5233,
|
| 698 |
+
"step": 5750
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 8.27,
|
| 702 |
+
"learning_rate": 8.63052781740371e-06,
|
| 703 |
+
"loss": 1.5664,
|
| 704 |
+
"step": 5800
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.35,
|
| 708 |
+
"learning_rate": 8.273894436519259e-06,
|
| 709 |
+
"loss": 1.557,
|
| 710 |
+
"step": 5850
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 8.42,
|
| 714 |
+
"learning_rate": 7.917261055634807e-06,
|
| 715 |
+
"loss": 1.5289,
|
| 716 |
+
"step": 5900
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 8.49,
|
| 720 |
+
"learning_rate": 7.560627674750358e-06,
|
| 721 |
+
"loss": 1.5276,
|
| 722 |
+
"step": 5950
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 8.56,
|
| 726 |
+
"learning_rate": 7.203994293865907e-06,
|
| 727 |
+
"loss": 1.579,
|
| 728 |
+
"step": 6000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.63,
|
| 732 |
+
"learning_rate": 6.847360912981456e-06,
|
| 733 |
+
"loss": 1.5147,
|
| 734 |
+
"step": 6050
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.7,
|
| 738 |
+
"learning_rate": 6.490727532097005e-06,
|
| 739 |
+
"loss": 1.5442,
|
| 740 |
+
"step": 6100
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 8.77,
|
| 744 |
+
"learning_rate": 6.1340941512125535e-06,
|
| 745 |
+
"loss": 1.5118,
|
| 746 |
+
"step": 6150
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.84,
|
| 750 |
+
"learning_rate": 5.777460770328103e-06,
|
| 751 |
+
"loss": 1.525,
|
| 752 |
+
"step": 6200
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 8.92,
|
| 756 |
+
"learning_rate": 5.420827389443652e-06,
|
| 757 |
+
"loss": 1.5131,
|
| 758 |
+
"step": 6250
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 8.99,
|
| 762 |
+
"learning_rate": 5.064194008559201e-06,
|
| 763 |
+
"loss": 1.5268,
|
| 764 |
+
"step": 6300
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 9.06,
|
| 768 |
+
"learning_rate": 4.707560627674751e-06,
|
| 769 |
+
"loss": 1.5325,
|
| 770 |
+
"step": 6350
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 9.13,
|
| 774 |
+
"learning_rate": 4.3509272467903e-06,
|
| 775 |
+
"loss": 1.5153,
|
| 776 |
+
"step": 6400
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 9.2,
|
| 780 |
+
"learning_rate": 3.9942938659058485e-06,
|
| 781 |
+
"loss": 1.5342,
|
| 782 |
+
"step": 6450
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 9.27,
|
| 786 |
+
"learning_rate": 3.6376604850213982e-06,
|
| 787 |
+
"loss": 1.5422,
|
| 788 |
+
"step": 6500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 9.34,
|
| 792 |
+
"learning_rate": 3.2810271041369475e-06,
|
| 793 |
+
"loss": 1.5243,
|
| 794 |
+
"step": 6550
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 9.42,
|
| 798 |
+
"learning_rate": 2.924393723252497e-06,
|
| 799 |
+
"loss": 1.5273,
|
| 800 |
+
"step": 6600
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 9.49,
|
| 804 |
+
"learning_rate": 2.5677603423680457e-06,
|
| 805 |
+
"loss": 1.5353,
|
| 806 |
+
"step": 6650
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 9.56,
|
| 810 |
+
"learning_rate": 2.211126961483595e-06,
|
| 811 |
+
"loss": 1.537,
|
| 812 |
+
"step": 6700
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 9.63,
|
| 816 |
+
"learning_rate": 1.8544935805991443e-06,
|
| 817 |
+
"loss": 1.5333,
|
| 818 |
+
"step": 6750
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.7,
|
| 822 |
+
"learning_rate": 1.4978601997146932e-06,
|
| 823 |
+
"loss": 1.5402,
|
| 824 |
+
"step": 6800
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.77,
|
| 828 |
+
"learning_rate": 1.1412268188302427e-06,
|
| 829 |
+
"loss": 1.5236,
|
| 830 |
+
"step": 6850
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 9.84,
|
| 834 |
+
"learning_rate": 7.845934379457918e-07,
|
| 835 |
+
"loss": 1.5204,
|
| 836 |
+
"step": 6900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 9.91,
|
| 840 |
+
"learning_rate": 4.27960057061341e-07,
|
| 841 |
+
"loss": 1.5038,
|
| 842 |
+
"step": 6950
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 9.99,
|
| 846 |
+
"learning_rate": 7.132667617689017e-08,
|
| 847 |
+
"loss": 1.5403,
|
| 848 |
+
"step": 7000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 10.0,
|
| 852 |
+
"step": 7010,
|
| 853 |
+
"total_flos": 7384869485936640.0,
|
| 854 |
+
"train_loss": 1.6471780081788416,
|
| 855 |
+
"train_runtime": 2443.9537,
|
| 856 |
+
"train_samples_per_second": 91.692,
|
| 857 |
+
"train_steps_per_second": 2.868
|
| 858 |
+
}
|
| 859 |
+
],
|
| 860 |
+
"max_steps": 7010,
|
| 861 |
+
"num_train_epochs": 10,
|
| 862 |
+
"total_flos": 7384869485936640.0,
|
| 863 |
+
"trial_name": null,
|
| 864 |
+
"trial_params": null
|
| 865 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4330f3214a77045d82fd2e8b9dc7a7c8c94b92d56475e3e3fe27593324cd3c88
|
| 3 |
+
size 2799
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|