Upload 10 files
Browse files- all_results.json +8 -0
- config.json +76 -0
- generation_config.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- train_results.json +8 -0
- trainer_state.json +633 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.5161892493331657,
|
| 4 |
+
"train_runtime": 101125.7197,
|
| 5 |
+
"train_samples": 2823058,
|
| 6 |
+
"train_samples_per_second": 279.163,
|
| 7 |
+
"train_steps_per_second": 0.436
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./exps/rocbart-base-chinese-v1",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 101,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 102,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 102,
|
| 27 |
+
"forced_eos_token_id": 102,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_length": 100,
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"tokenizer_class": "BertTokenizer",
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.31.0",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"vocab_size": 51271
|
| 76 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 101,
|
| 4 |
+
"decoder_start_token_id": 102,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 102,
|
| 7 |
+
"forced_eos_token_id": 102,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 4,
|
| 10 |
+
"pad_token_id": 0,
|
| 11 |
+
"transformers_version": "4.31.0"
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ce1b97e8bc176472ac0118985abccdd7b719d5db832aebc0afad3771eb6c42
|
| 3 |
+
size 561063609
|
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_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.5161892493331657,
|
| 4 |
+
"train_runtime": 101125.7197,
|
| 5 |
+
"train_samples": 2823058,
|
| 6 |
+
"train_samples_per_second": 279.163,
|
| 7 |
+
"train_steps_per_second": 0.436
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.999433267214508,
|
| 5 |
+
"global_step": 44110,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.9671276354568124e-06,
|
| 13 |
+
"loss": 1.5714,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 2.934255270913625e-06,
|
| 19 |
+
"loss": 1.5492,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 2.9013829063704375e-06,
|
| 25 |
+
"loss": 1.5441,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.45,
|
| 30 |
+
"learning_rate": 2.8685105418272502e-06,
|
| 31 |
+
"loss": 1.5406,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.57,
|
| 36 |
+
"learning_rate": 2.8356381772840626e-06,
|
| 37 |
+
"loss": 1.5376,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.68,
|
| 42 |
+
"learning_rate": 2.802765812740875e-06,
|
| 43 |
+
"loss": 1.5358,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.79,
|
| 48 |
+
"learning_rate": 2.7698934481976876e-06,
|
| 49 |
+
"loss": 1.5342,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.91,
|
| 54 |
+
"learning_rate": 2.7370210836545004e-06,
|
| 55 |
+
"loss": 1.5329,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.0,
|
| 60 |
+
"eval_loss": 1.5299354791641235,
|
| 61 |
+
"eval_runtime": 95.1335,
|
| 62 |
+
"eval_samples_per_second": 299.737,
|
| 63 |
+
"eval_steps_per_second": 1.882,
|
| 64 |
+
"step": 4411
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.02,
|
| 68 |
+
"learning_rate": 2.7041487191113127e-06,
|
| 69 |
+
"loss": 1.5308,
|
| 70 |
+
"step": 4500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.13,
|
| 74 |
+
"learning_rate": 2.6712763545681255e-06,
|
| 75 |
+
"loss": 1.5293,
|
| 76 |
+
"step": 5000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.25,
|
| 80 |
+
"learning_rate": 2.638403990024938e-06,
|
| 81 |
+
"loss": 1.5287,
|
| 82 |
+
"step": 5500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.36,
|
| 86 |
+
"learning_rate": 2.60553162548175e-06,
|
| 87 |
+
"loss": 1.5277,
|
| 88 |
+
"step": 6000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.47,
|
| 92 |
+
"learning_rate": 2.572659260938563e-06,
|
| 93 |
+
"loss": 1.5267,
|
| 94 |
+
"step": 6500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.59,
|
| 98 |
+
"learning_rate": 2.539786896395375e-06,
|
| 99 |
+
"loss": 1.5256,
|
| 100 |
+
"step": 7000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.7,
|
| 104 |
+
"learning_rate": 2.506914531852188e-06,
|
| 105 |
+
"loss": 1.525,
|
| 106 |
+
"step": 7500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.81,
|
| 110 |
+
"learning_rate": 2.4740421673090003e-06,
|
| 111 |
+
"loss": 1.5246,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.93,
|
| 116 |
+
"learning_rate": 2.4411698027658126e-06,
|
| 117 |
+
"loss": 1.5238,
|
| 118 |
+
"step": 8500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.0,
|
| 122 |
+
"eval_loss": 1.5252745151519775,
|
| 123 |
+
"eval_runtime": 95.3162,
|
| 124 |
+
"eval_samples_per_second": 299.162,
|
| 125 |
+
"eval_steps_per_second": 1.878,
|
| 126 |
+
"step": 8822
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.04,
|
| 130 |
+
"learning_rate": 2.4082974382226254e-06,
|
| 131 |
+
"loss": 1.5238,
|
| 132 |
+
"step": 9000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.15,
|
| 136 |
+
"learning_rate": 2.3754250736794377e-06,
|
| 137 |
+
"loss": 1.5222,
|
| 138 |
+
"step": 9500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.27,
|
| 142 |
+
"learning_rate": 2.34255270913625e-06,
|
| 143 |
+
"loss": 1.5216,
|
| 144 |
+
"step": 10000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.38,
|
| 148 |
+
"learning_rate": 2.3096803445930628e-06,
|
| 149 |
+
"loss": 1.5208,
|
| 150 |
+
"step": 10500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.49,
|
| 154 |
+
"learning_rate": 2.2768079800498755e-06,
|
| 155 |
+
"loss": 1.5204,
|
| 156 |
+
"step": 11000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.61,
|
| 160 |
+
"learning_rate": 2.243935615506688e-06,
|
| 161 |
+
"loss": 1.5202,
|
| 162 |
+
"step": 11500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.72,
|
| 166 |
+
"learning_rate": 2.2110632509635006e-06,
|
| 167 |
+
"loss": 1.5195,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.83,
|
| 172 |
+
"learning_rate": 2.178190886420313e-06,
|
| 173 |
+
"loss": 1.5193,
|
| 174 |
+
"step": 12500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.95,
|
| 178 |
+
"learning_rate": 2.1453185218771257e-06,
|
| 179 |
+
"loss": 1.5183,
|
| 180 |
+
"step": 13000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.0,
|
| 184 |
+
"eval_loss": 1.5211608409881592,
|
| 185 |
+
"eval_runtime": 96.0051,
|
| 186 |
+
"eval_samples_per_second": 297.015,
|
| 187 |
+
"eval_steps_per_second": 1.864,
|
| 188 |
+
"step": 13233
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.06,
|
| 192 |
+
"learning_rate": 2.112446157333938e-06,
|
| 193 |
+
"loss": 1.5179,
|
| 194 |
+
"step": 13500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.17,
|
| 198 |
+
"learning_rate": 2.0795737927907503e-06,
|
| 199 |
+
"loss": 1.5175,
|
| 200 |
+
"step": 14000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.29,
|
| 204 |
+
"learning_rate": 2.0467014282475627e-06,
|
| 205 |
+
"loss": 1.5173,
|
| 206 |
+
"step": 14500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.4,
|
| 210 |
+
"learning_rate": 2.0138290637043754e-06,
|
| 211 |
+
"loss": 1.5166,
|
| 212 |
+
"step": 15000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.51,
|
| 216 |
+
"learning_rate": 1.980956699161188e-06,
|
| 217 |
+
"loss": 1.5166,
|
| 218 |
+
"step": 15500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.63,
|
| 222 |
+
"learning_rate": 1.9480843346180005e-06,
|
| 223 |
+
"loss": 1.5163,
|
| 224 |
+
"step": 16000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.74,
|
| 228 |
+
"learning_rate": 1.9152119700748132e-06,
|
| 229 |
+
"loss": 1.5158,
|
| 230 |
+
"step": 16500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.85,
|
| 234 |
+
"learning_rate": 1.8823396055316256e-06,
|
| 235 |
+
"loss": 1.5156,
|
| 236 |
+
"step": 17000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.97,
|
| 240 |
+
"learning_rate": 1.8494672409884385e-06,
|
| 241 |
+
"loss": 1.5152,
|
| 242 |
+
"step": 17500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.0,
|
| 246 |
+
"eval_loss": 1.5186687707901,
|
| 247 |
+
"eval_runtime": 95.8953,
|
| 248 |
+
"eval_samples_per_second": 297.356,
|
| 249 |
+
"eval_steps_per_second": 1.867,
|
| 250 |
+
"step": 17645
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.08,
|
| 254 |
+
"learning_rate": 1.8165948764452506e-06,
|
| 255 |
+
"loss": 1.5147,
|
| 256 |
+
"step": 18000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.19,
|
| 260 |
+
"learning_rate": 1.7837225119020632e-06,
|
| 261 |
+
"loss": 1.5137,
|
| 262 |
+
"step": 18500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.31,
|
| 266 |
+
"learning_rate": 1.7508501473588757e-06,
|
| 267 |
+
"loss": 1.5138,
|
| 268 |
+
"step": 19000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 4.42,
|
| 272 |
+
"learning_rate": 1.717977782815688e-06,
|
| 273 |
+
"loss": 1.5134,
|
| 274 |
+
"step": 19500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.53,
|
| 278 |
+
"learning_rate": 1.6851054182725004e-06,
|
| 279 |
+
"loss": 1.5136,
|
| 280 |
+
"step": 20000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.65,
|
| 284 |
+
"learning_rate": 1.6522330537293131e-06,
|
| 285 |
+
"loss": 1.5135,
|
| 286 |
+
"step": 20500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.76,
|
| 290 |
+
"learning_rate": 1.6193606891861259e-06,
|
| 291 |
+
"loss": 1.5128,
|
| 292 |
+
"step": 21000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.87,
|
| 296 |
+
"learning_rate": 1.5864883246429384e-06,
|
| 297 |
+
"loss": 1.5133,
|
| 298 |
+
"step": 21500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.99,
|
| 302 |
+
"learning_rate": 1.5536159600997505e-06,
|
| 303 |
+
"loss": 1.5127,
|
| 304 |
+
"step": 22000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.0,
|
| 308 |
+
"eval_loss": 1.5171175003051758,
|
| 309 |
+
"eval_runtime": 94.991,
|
| 310 |
+
"eval_samples_per_second": 300.186,
|
| 311 |
+
"eval_steps_per_second": 1.884,
|
| 312 |
+
"step": 22056
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.1,
|
| 316 |
+
"learning_rate": 1.520743595556563e-06,
|
| 317 |
+
"loss": 1.5109,
|
| 318 |
+
"step": 22500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 5.21,
|
| 322 |
+
"learning_rate": 1.4878712310133756e-06,
|
| 323 |
+
"loss": 1.512,
|
| 324 |
+
"step": 23000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.33,
|
| 328 |
+
"learning_rate": 1.454998866470188e-06,
|
| 329 |
+
"loss": 1.5115,
|
| 330 |
+
"step": 23500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.44,
|
| 334 |
+
"learning_rate": 1.4221265019270007e-06,
|
| 335 |
+
"loss": 1.5113,
|
| 336 |
+
"step": 24000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.55,
|
| 340 |
+
"learning_rate": 1.3892541373838134e-06,
|
| 341 |
+
"loss": 1.511,
|
| 342 |
+
"step": 24500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 5.67,
|
| 346 |
+
"learning_rate": 1.3563817728406258e-06,
|
| 347 |
+
"loss": 1.5112,
|
| 348 |
+
"step": 25000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.78,
|
| 352 |
+
"learning_rate": 1.3235094082974385e-06,
|
| 353 |
+
"loss": 1.5106,
|
| 354 |
+
"step": 25500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.89,
|
| 358 |
+
"learning_rate": 1.2906370437542509e-06,
|
| 359 |
+
"loss": 1.5105,
|
| 360 |
+
"step": 26000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.0,
|
| 364 |
+
"eval_loss": 1.51548171043396,
|
| 365 |
+
"eval_runtime": 95.4859,
|
| 366 |
+
"eval_samples_per_second": 298.631,
|
| 367 |
+
"eval_steps_per_second": 1.875,
|
| 368 |
+
"step": 26467
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.01,
|
| 372 |
+
"learning_rate": 1.2577646792110636e-06,
|
| 373 |
+
"loss": 1.511,
|
| 374 |
+
"step": 26500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.12,
|
| 378 |
+
"learning_rate": 1.224892314667876e-06,
|
| 379 |
+
"loss": 1.5103,
|
| 380 |
+
"step": 27000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 6.23,
|
| 384 |
+
"learning_rate": 1.1920199501246883e-06,
|
| 385 |
+
"loss": 1.5095,
|
| 386 |
+
"step": 27500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 6.35,
|
| 390 |
+
"learning_rate": 1.159147585581501e-06,
|
| 391 |
+
"loss": 1.5096,
|
| 392 |
+
"step": 28000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.46,
|
| 396 |
+
"learning_rate": 1.1262752210383133e-06,
|
| 397 |
+
"loss": 1.5099,
|
| 398 |
+
"step": 28500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.57,
|
| 402 |
+
"learning_rate": 1.0934028564951257e-06,
|
| 403 |
+
"loss": 1.5096,
|
| 404 |
+
"step": 29000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.69,
|
| 408 |
+
"learning_rate": 1.0605304919519384e-06,
|
| 409 |
+
"loss": 1.5091,
|
| 410 |
+
"step": 29500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.8,
|
| 414 |
+
"learning_rate": 1.0276581274087507e-06,
|
| 415 |
+
"loss": 1.5096,
|
| 416 |
+
"step": 30000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 6.91,
|
| 420 |
+
"learning_rate": 9.947857628655633e-07,
|
| 421 |
+
"loss": 1.5087,
|
| 422 |
+
"step": 30500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.0,
|
| 426 |
+
"eval_loss": 1.5147736072540283,
|
| 427 |
+
"eval_runtime": 95.3411,
|
| 428 |
+
"eval_samples_per_second": 299.084,
|
| 429 |
+
"eval_steps_per_second": 1.877,
|
| 430 |
+
"step": 30878
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 7.03,
|
| 434 |
+
"learning_rate": 9.61913398322376e-07,
|
| 435 |
+
"loss": 1.5093,
|
| 436 |
+
"step": 31000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 7.14,
|
| 440 |
+
"learning_rate": 9.290410337791883e-07,
|
| 441 |
+
"loss": 1.5085,
|
| 442 |
+
"step": 31500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 7.25,
|
| 446 |
+
"learning_rate": 8.96168669236001e-07,
|
| 447 |
+
"loss": 1.5082,
|
| 448 |
+
"step": 32000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 7.37,
|
| 452 |
+
"learning_rate": 8.632963046928134e-07,
|
| 453 |
+
"loss": 1.5082,
|
| 454 |
+
"step": 32500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 7.48,
|
| 458 |
+
"learning_rate": 8.304239401496259e-07,
|
| 459 |
+
"loss": 1.5082,
|
| 460 |
+
"step": 33000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 7.59,
|
| 464 |
+
"learning_rate": 7.975515756064386e-07,
|
| 465 |
+
"loss": 1.5084,
|
| 466 |
+
"step": 33500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 7.71,
|
| 470 |
+
"learning_rate": 7.64679211063251e-07,
|
| 471 |
+
"loss": 1.5083,
|
| 472 |
+
"step": 34000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 7.82,
|
| 476 |
+
"learning_rate": 7.318068465200634e-07,
|
| 477 |
+
"loss": 1.5084,
|
| 478 |
+
"step": 34500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.93,
|
| 482 |
+
"learning_rate": 6.989344819768761e-07,
|
| 483 |
+
"loss": 1.5078,
|
| 484 |
+
"step": 35000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 8.0,
|
| 488 |
+
"eval_loss": 1.5141184329986572,
|
| 489 |
+
"eval_runtime": 95.3059,
|
| 490 |
+
"eval_samples_per_second": 299.195,
|
| 491 |
+
"eval_steps_per_second": 1.878,
|
| 492 |
+
"step": 35290
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 8.05,
|
| 496 |
+
"learning_rate": 6.660621174336885e-07,
|
| 497 |
+
"loss": 1.5083,
|
| 498 |
+
"step": 35500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 8.16,
|
| 502 |
+
"learning_rate": 6.331897528905012e-07,
|
| 503 |
+
"loss": 1.5078,
|
| 504 |
+
"step": 36000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 8.27,
|
| 508 |
+
"learning_rate": 6.003173883473137e-07,
|
| 509 |
+
"loss": 1.5077,
|
| 510 |
+
"step": 36500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 8.39,
|
| 514 |
+
"learning_rate": 5.67445023804126e-07,
|
| 515 |
+
"loss": 1.5079,
|
| 516 |
+
"step": 37000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 8.5,
|
| 520 |
+
"learning_rate": 5.345726592609387e-07,
|
| 521 |
+
"loss": 1.5073,
|
| 522 |
+
"step": 37500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 8.61,
|
| 526 |
+
"learning_rate": 5.017002947177512e-07,
|
| 527 |
+
"loss": 1.5072,
|
| 528 |
+
"step": 38000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 8.73,
|
| 532 |
+
"learning_rate": 4.688279301745635e-07,
|
| 533 |
+
"loss": 1.5073,
|
| 534 |
+
"step": 38500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 8.84,
|
| 538 |
+
"learning_rate": 4.3595556563137624e-07,
|
| 539 |
+
"loss": 1.5072,
|
| 540 |
+
"step": 39000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 8.95,
|
| 544 |
+
"learning_rate": 4.030832010881886e-07,
|
| 545 |
+
"loss": 1.5071,
|
| 546 |
+
"step": 39500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 9.0,
|
| 550 |
+
"eval_loss": 1.5136668682098389,
|
| 551 |
+
"eval_runtime": 95.2932,
|
| 552 |
+
"eval_samples_per_second": 299.234,
|
| 553 |
+
"eval_steps_per_second": 1.878,
|
| 554 |
+
"step": 39701
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 9.07,
|
| 558 |
+
"learning_rate": 3.70210836545001e-07,
|
| 559 |
+
"loss": 1.5066,
|
| 560 |
+
"step": 40000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 9.18,
|
| 564 |
+
"learning_rate": 3.3733847200181375e-07,
|
| 565 |
+
"loss": 1.5074,
|
| 566 |
+
"step": 40500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 9.29,
|
| 570 |
+
"learning_rate": 3.044661074586261e-07,
|
| 571 |
+
"loss": 1.5069,
|
| 572 |
+
"step": 41000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 9.41,
|
| 576 |
+
"learning_rate": 2.7159374291543883e-07,
|
| 577 |
+
"loss": 1.5069,
|
| 578 |
+
"step": 41500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 9.52,
|
| 582 |
+
"learning_rate": 2.387213783722512e-07,
|
| 583 |
+
"loss": 1.5067,
|
| 584 |
+
"step": 42000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 9.63,
|
| 588 |
+
"learning_rate": 2.0584901382906362e-07,
|
| 589 |
+
"loss": 1.5067,
|
| 590 |
+
"step": 42500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 9.75,
|
| 594 |
+
"learning_rate": 1.7297664928587634e-07,
|
| 595 |
+
"loss": 1.5066,
|
| 596 |
+
"step": 43000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 9.86,
|
| 600 |
+
"learning_rate": 1.4010428474268872e-07,
|
| 601 |
+
"loss": 1.5072,
|
| 602 |
+
"step": 43500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 9.97,
|
| 606 |
+
"learning_rate": 1.0723192019950112e-07,
|
| 607 |
+
"loss": 1.507,
|
| 608 |
+
"step": 44000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 10.0,
|
| 612 |
+
"eval_loss": 1.5134241580963135,
|
| 613 |
+
"eval_runtime": 95.477,
|
| 614 |
+
"eval_samples_per_second": 298.658,
|
| 615 |
+
"eval_steps_per_second": 1.875,
|
| 616 |
+
"step": 44110
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 10.0,
|
| 620 |
+
"step": 44110,
|
| 621 |
+
"total_flos": 7.740642541156762e+17,
|
| 622 |
+
"train_loss": 1.5161892493331657,
|
| 623 |
+
"train_runtime": 101125.7197,
|
| 624 |
+
"train_samples_per_second": 279.163,
|
| 625 |
+
"train_steps_per_second": 0.436
|
| 626 |
+
}
|
| 627 |
+
],
|
| 628 |
+
"max_steps": 44110,
|
| 629 |
+
"num_train_epochs": 10,
|
| 630 |
+
"total_flos": 7.740642541156762e+17,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27da7fda07f67a865cfe5af5a2f9265d566f5bc7cdc350b1313c194072a25965
|
| 3 |
+
size 4207
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|