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 +1101 -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": 1.4961074900378695,
|
| 4 |
+
"train_runtime": 199226.4751,
|
| 5 |
+
"train_samples": 5343672,
|
| 6 |
+
"train_samples_per_second": 268.221,
|
| 7 |
+
"train_steps_per_second": 0.419
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./exps/rocbart-base-chinese-v2/gec/run_2021/checkpoint-44110",
|
| 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 sha256:9421cef3fb607d1830da0ac4f988d7b91dc1108079d09777e14d0fbdb3c9b297
|
| 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": 1.4961074900378695,
|
| 4 |
+
"train_runtime": 199226.4751,
|
| 5 |
+
"train_samples": 5343672,
|
| 6 |
+
"train_samples_per_second": 268.221,
|
| 7 |
+
"train_steps_per_second": 0.419
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.999401161746212,
|
| 5 |
+
"global_step": 83490,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 2.9826326506168404e-06,
|
| 13 |
+
"loss": 1.509,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 2.9652653012336808e-06,
|
| 19 |
+
"loss": 1.5092,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 2.947897951850521e-06,
|
| 25 |
+
"loss": 1.5089,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 2.9305306024673614e-06,
|
| 31 |
+
"loss": 1.5082,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 2.9131632530842018e-06,
|
| 37 |
+
"loss": 1.5086,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 2.895795903701042e-06,
|
| 43 |
+
"loss": 1.5082,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.42,
|
| 48 |
+
"learning_rate": 2.8784285543178824e-06,
|
| 49 |
+
"loss": 1.5077,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.48,
|
| 54 |
+
"learning_rate": 2.8610612049347228e-06,
|
| 55 |
+
"loss": 1.5077,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.54,
|
| 60 |
+
"learning_rate": 2.843693855551563e-06,
|
| 61 |
+
"loss": 1.5067,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.6,
|
| 66 |
+
"learning_rate": 2.8263265061684034e-06,
|
| 67 |
+
"loss": 1.507,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.66,
|
| 72 |
+
"learning_rate": 2.8089591567852438e-06,
|
| 73 |
+
"loss": 1.5067,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.72,
|
| 78 |
+
"learning_rate": 2.791591807402084e-06,
|
| 79 |
+
"loss": 1.5067,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.78,
|
| 84 |
+
"learning_rate": 2.7742244580189245e-06,
|
| 85 |
+
"loss": 1.5061,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.84,
|
| 90 |
+
"learning_rate": 2.756857108635765e-06,
|
| 91 |
+
"loss": 1.5054,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.9,
|
| 96 |
+
"learning_rate": 2.739489759252605e-06,
|
| 97 |
+
"loss": 1.5058,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.96,
|
| 102 |
+
"learning_rate": 2.7221224098694455e-06,
|
| 103 |
+
"loss": 1.5052,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0,
|
| 108 |
+
"eval_loss": 1.5115793943405151,
|
| 109 |
+
"eval_runtime": 99.986,
|
| 110 |
+
"eval_samples_per_second": 300.042,
|
| 111 |
+
"eval_steps_per_second": 1.88,
|
| 112 |
+
"step": 8349
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.02,
|
| 116 |
+
"learning_rate": 2.704755060486286e-06,
|
| 117 |
+
"loss": 1.5046,
|
| 118 |
+
"step": 8500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.08,
|
| 122 |
+
"learning_rate": 2.687387711103126e-06,
|
| 123 |
+
"loss": 1.5045,
|
| 124 |
+
"step": 9000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.14,
|
| 128 |
+
"learning_rate": 2.6700203617199665e-06,
|
| 129 |
+
"loss": 1.5038,
|
| 130 |
+
"step": 9500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.2,
|
| 134 |
+
"learning_rate": 2.652653012336807e-06,
|
| 135 |
+
"loss": 1.5042,
|
| 136 |
+
"step": 10000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.26,
|
| 140 |
+
"learning_rate": 2.635285662953647e-06,
|
| 141 |
+
"loss": 1.5039,
|
| 142 |
+
"step": 10500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.32,
|
| 146 |
+
"learning_rate": 2.6179183135704875e-06,
|
| 147 |
+
"loss": 1.5033,
|
| 148 |
+
"step": 11000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.38,
|
| 152 |
+
"learning_rate": 2.600550964187328e-06,
|
| 153 |
+
"loss": 1.5028,
|
| 154 |
+
"step": 11500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.44,
|
| 158 |
+
"learning_rate": 2.583183614804168e-06,
|
| 159 |
+
"loss": 1.5036,
|
| 160 |
+
"step": 12000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.5,
|
| 164 |
+
"learning_rate": 2.5658162654210085e-06,
|
| 165 |
+
"loss": 1.5032,
|
| 166 |
+
"step": 12500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.56,
|
| 170 |
+
"learning_rate": 2.548448916037849e-06,
|
| 171 |
+
"loss": 1.5029,
|
| 172 |
+
"step": 13000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.62,
|
| 176 |
+
"learning_rate": 2.5310815666546896e-06,
|
| 177 |
+
"loss": 1.5028,
|
| 178 |
+
"step": 13500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.68,
|
| 182 |
+
"learning_rate": 2.5137142172715295e-06,
|
| 183 |
+
"loss": 1.5024,
|
| 184 |
+
"step": 14000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.74,
|
| 188 |
+
"learning_rate": 2.49634686788837e-06,
|
| 189 |
+
"loss": 1.5022,
|
| 190 |
+
"step": 14500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.8,
|
| 194 |
+
"learning_rate": 2.47897951850521e-06,
|
| 195 |
+
"loss": 1.5022,
|
| 196 |
+
"step": 15000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.86,
|
| 200 |
+
"learning_rate": 2.4616121691220505e-06,
|
| 201 |
+
"loss": 1.5019,
|
| 202 |
+
"step": 15500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.92,
|
| 206 |
+
"learning_rate": 2.444244819738891e-06,
|
| 207 |
+
"loss": 1.502,
|
| 208 |
+
"step": 16000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.98,
|
| 212 |
+
"learning_rate": 2.426877470355731e-06,
|
| 213 |
+
"loss": 1.5019,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.0,
|
| 218 |
+
"eval_loss": 1.509125828742981,
|
| 219 |
+
"eval_runtime": 102.1448,
|
| 220 |
+
"eval_samples_per_second": 293.701,
|
| 221 |
+
"eval_steps_per_second": 1.841,
|
| 222 |
+
"step": 16699
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.04,
|
| 226 |
+
"learning_rate": 2.4095101209725715e-06,
|
| 227 |
+
"loss": 1.501,
|
| 228 |
+
"step": 17000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.1,
|
| 232 |
+
"learning_rate": 2.392142771589412e-06,
|
| 233 |
+
"loss": 1.5004,
|
| 234 |
+
"step": 17500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.16,
|
| 238 |
+
"learning_rate": 2.374775422206252e-06,
|
| 239 |
+
"loss": 1.5009,
|
| 240 |
+
"step": 18000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.22,
|
| 244 |
+
"learning_rate": 2.3574080728230925e-06,
|
| 245 |
+
"loss": 1.5004,
|
| 246 |
+
"step": 18500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.28,
|
| 250 |
+
"learning_rate": 2.340040723439933e-06,
|
| 251 |
+
"loss": 1.5004,
|
| 252 |
+
"step": 19000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.34,
|
| 256 |
+
"learning_rate": 2.3226733740567732e-06,
|
| 257 |
+
"loss": 1.5001,
|
| 258 |
+
"step": 19500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.4,
|
| 262 |
+
"learning_rate": 2.3053060246736136e-06,
|
| 263 |
+
"loss": 1.4998,
|
| 264 |
+
"step": 20000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.46,
|
| 268 |
+
"learning_rate": 2.2879386752904543e-06,
|
| 269 |
+
"loss": 1.4998,
|
| 270 |
+
"step": 20500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.52,
|
| 274 |
+
"learning_rate": 2.2705713259072942e-06,
|
| 275 |
+
"loss": 1.4998,
|
| 276 |
+
"step": 21000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.58,
|
| 280 |
+
"learning_rate": 2.2532039765241346e-06,
|
| 281 |
+
"loss": 1.4997,
|
| 282 |
+
"step": 21500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.63,
|
| 286 |
+
"learning_rate": 2.235836627140975e-06,
|
| 287 |
+
"loss": 1.4992,
|
| 288 |
+
"step": 22000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.69,
|
| 292 |
+
"learning_rate": 2.2184692777578152e-06,
|
| 293 |
+
"loss": 1.4991,
|
| 294 |
+
"step": 22500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.75,
|
| 298 |
+
"learning_rate": 2.2011019283746556e-06,
|
| 299 |
+
"loss": 1.499,
|
| 300 |
+
"step": 23000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.81,
|
| 304 |
+
"learning_rate": 2.183734578991496e-06,
|
| 305 |
+
"loss": 1.4987,
|
| 306 |
+
"step": 23500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.87,
|
| 310 |
+
"learning_rate": 2.1663672296083363e-06,
|
| 311 |
+
"loss": 1.4991,
|
| 312 |
+
"step": 24000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.93,
|
| 316 |
+
"learning_rate": 2.1489998802251766e-06,
|
| 317 |
+
"loss": 1.4986,
|
| 318 |
+
"step": 24500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.99,
|
| 322 |
+
"learning_rate": 2.131632530842017e-06,
|
| 323 |
+
"loss": 1.4989,
|
| 324 |
+
"step": 25000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.0,
|
| 328 |
+
"eval_loss": 1.5069462060928345,
|
| 329 |
+
"eval_runtime": 101.4916,
|
| 330 |
+
"eval_samples_per_second": 295.591,
|
| 331 |
+
"eval_steps_per_second": 1.852,
|
| 332 |
+
"step": 25048
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.05,
|
| 336 |
+
"learning_rate": 2.1142651814588573e-06,
|
| 337 |
+
"loss": 1.498,
|
| 338 |
+
"step": 25500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.11,
|
| 342 |
+
"learning_rate": 2.096897832075698e-06,
|
| 343 |
+
"loss": 1.4977,
|
| 344 |
+
"step": 26000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.17,
|
| 348 |
+
"learning_rate": 2.079530482692538e-06,
|
| 349 |
+
"loss": 1.4975,
|
| 350 |
+
"step": 26500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.23,
|
| 354 |
+
"learning_rate": 2.0621631333093783e-06,
|
| 355 |
+
"loss": 1.4974,
|
| 356 |
+
"step": 27000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.29,
|
| 360 |
+
"learning_rate": 2.044795783926219e-06,
|
| 361 |
+
"loss": 1.4976,
|
| 362 |
+
"step": 27500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.35,
|
| 366 |
+
"learning_rate": 2.027428434543059e-06,
|
| 367 |
+
"loss": 1.4978,
|
| 368 |
+
"step": 28000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.41,
|
| 372 |
+
"learning_rate": 2.0100610851598993e-06,
|
| 373 |
+
"loss": 1.4971,
|
| 374 |
+
"step": 28500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.47,
|
| 378 |
+
"learning_rate": 1.99269373577674e-06,
|
| 379 |
+
"loss": 1.4974,
|
| 380 |
+
"step": 29000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.53,
|
| 384 |
+
"learning_rate": 1.97532638639358e-06,
|
| 385 |
+
"loss": 1.4972,
|
| 386 |
+
"step": 29500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.59,
|
| 390 |
+
"learning_rate": 1.9579590370104203e-06,
|
| 391 |
+
"loss": 1.4969,
|
| 392 |
+
"step": 30000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.65,
|
| 396 |
+
"learning_rate": 1.940591687627261e-06,
|
| 397 |
+
"loss": 1.4967,
|
| 398 |
+
"step": 30500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.71,
|
| 402 |
+
"learning_rate": 1.923224338244101e-06,
|
| 403 |
+
"loss": 1.4969,
|
| 404 |
+
"step": 31000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.77,
|
| 408 |
+
"learning_rate": 1.9058569888609415e-06,
|
| 409 |
+
"loss": 1.497,
|
| 410 |
+
"step": 31500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.83,
|
| 414 |
+
"learning_rate": 1.888489639477782e-06,
|
| 415 |
+
"loss": 1.4967,
|
| 416 |
+
"step": 32000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.89,
|
| 420 |
+
"learning_rate": 1.871122290094622e-06,
|
| 421 |
+
"loss": 1.4965,
|
| 422 |
+
"step": 32500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.95,
|
| 426 |
+
"learning_rate": 1.8537549407114627e-06,
|
| 427 |
+
"loss": 1.4969,
|
| 428 |
+
"step": 33000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.0,
|
| 432 |
+
"eval_loss": 1.5056320428848267,
|
| 433 |
+
"eval_runtime": 101.7674,
|
| 434 |
+
"eval_samples_per_second": 294.79,
|
| 435 |
+
"eval_steps_per_second": 1.847,
|
| 436 |
+
"step": 33398
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 4.01,
|
| 440 |
+
"learning_rate": 1.8363875913283029e-06,
|
| 441 |
+
"loss": 1.4962,
|
| 442 |
+
"step": 33500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 4.07,
|
| 446 |
+
"learning_rate": 1.8190202419451432e-06,
|
| 447 |
+
"loss": 1.4956,
|
| 448 |
+
"step": 34000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.13,
|
| 452 |
+
"learning_rate": 1.8016528925619838e-06,
|
| 453 |
+
"loss": 1.4955,
|
| 454 |
+
"step": 34500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 4.19,
|
| 458 |
+
"learning_rate": 1.7842855431788235e-06,
|
| 459 |
+
"loss": 1.4955,
|
| 460 |
+
"step": 35000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 4.25,
|
| 464 |
+
"learning_rate": 1.7669181937956644e-06,
|
| 465 |
+
"loss": 1.4953,
|
| 466 |
+
"step": 35500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 4.31,
|
| 470 |
+
"learning_rate": 1.7495508444125048e-06,
|
| 471 |
+
"loss": 1.4954,
|
| 472 |
+
"step": 36000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 4.37,
|
| 476 |
+
"learning_rate": 1.7321834950293447e-06,
|
| 477 |
+
"loss": 1.4952,
|
| 478 |
+
"step": 36500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 4.43,
|
| 482 |
+
"learning_rate": 1.714816145646185e-06,
|
| 483 |
+
"loss": 1.4956,
|
| 484 |
+
"step": 37000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 4.49,
|
| 488 |
+
"learning_rate": 1.6974487962630258e-06,
|
| 489 |
+
"loss": 1.4953,
|
| 490 |
+
"step": 37500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.55,
|
| 494 |
+
"learning_rate": 1.6800814468798657e-06,
|
| 495 |
+
"loss": 1.4951,
|
| 496 |
+
"step": 38000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 4.61,
|
| 500 |
+
"learning_rate": 1.6627140974967064e-06,
|
| 501 |
+
"loss": 1.4953,
|
| 502 |
+
"step": 38500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 4.67,
|
| 506 |
+
"learning_rate": 1.645346748113547e-06,
|
| 507 |
+
"loss": 1.4954,
|
| 508 |
+
"step": 39000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.73,
|
| 512 |
+
"learning_rate": 1.6279793987303871e-06,
|
| 513 |
+
"loss": 1.495,
|
| 514 |
+
"step": 39500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.79,
|
| 518 |
+
"learning_rate": 1.6106120493472275e-06,
|
| 519 |
+
"loss": 1.4951,
|
| 520 |
+
"step": 40000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.85,
|
| 524 |
+
"learning_rate": 1.5932446999640674e-06,
|
| 525 |
+
"loss": 1.4946,
|
| 526 |
+
"step": 40500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.91,
|
| 530 |
+
"learning_rate": 1.5758773505809081e-06,
|
| 531 |
+
"loss": 1.4948,
|
| 532 |
+
"step": 41000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.97,
|
| 536 |
+
"learning_rate": 1.5585100011977485e-06,
|
| 537 |
+
"loss": 1.4946,
|
| 538 |
+
"step": 41500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 5.0,
|
| 542 |
+
"eval_loss": 1.504227638244629,
|
| 543 |
+
"eval_runtime": 101.5567,
|
| 544 |
+
"eval_samples_per_second": 295.402,
|
| 545 |
+
"eval_steps_per_second": 1.851,
|
| 546 |
+
"step": 41747
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 5.03,
|
| 550 |
+
"learning_rate": 1.5411426518145884e-06,
|
| 551 |
+
"loss": 1.4944,
|
| 552 |
+
"step": 42000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 5.09,
|
| 556 |
+
"learning_rate": 1.5237753024314291e-06,
|
| 557 |
+
"loss": 1.494,
|
| 558 |
+
"step": 42500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 5.15,
|
| 562 |
+
"learning_rate": 1.5064079530482697e-06,
|
| 563 |
+
"loss": 1.4942,
|
| 564 |
+
"step": 43000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 5.21,
|
| 568 |
+
"learning_rate": 1.4890406036651098e-06,
|
| 569 |
+
"loss": 1.4938,
|
| 570 |
+
"step": 43500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 5.27,
|
| 574 |
+
"learning_rate": 1.4716732542819497e-06,
|
| 575 |
+
"loss": 1.4939,
|
| 576 |
+
"step": 44000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 5.33,
|
| 580 |
+
"learning_rate": 1.4543059048987905e-06,
|
| 581 |
+
"loss": 1.4938,
|
| 582 |
+
"step": 44500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.39,
|
| 586 |
+
"learning_rate": 1.4369385555156308e-06,
|
| 587 |
+
"loss": 1.4937,
|
| 588 |
+
"step": 45000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 5.45,
|
| 592 |
+
"learning_rate": 1.4195712061324707e-06,
|
| 593 |
+
"loss": 1.494,
|
| 594 |
+
"step": 45500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 5.51,
|
| 598 |
+
"learning_rate": 1.4022038567493115e-06,
|
| 599 |
+
"loss": 1.4936,
|
| 600 |
+
"step": 46000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 5.57,
|
| 604 |
+
"learning_rate": 1.3848365073661518e-06,
|
| 605 |
+
"loss": 1.4936,
|
| 606 |
+
"step": 46500
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 5.63,
|
| 610 |
+
"learning_rate": 1.3674691579829922e-06,
|
| 611 |
+
"loss": 1.4934,
|
| 612 |
+
"step": 47000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 5.69,
|
| 616 |
+
"learning_rate": 1.350101808599832e-06,
|
| 617 |
+
"loss": 1.4936,
|
| 618 |
+
"step": 47500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.75,
|
| 622 |
+
"learning_rate": 1.3327344592166729e-06,
|
| 623 |
+
"loss": 1.4933,
|
| 624 |
+
"step": 48000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.81,
|
| 628 |
+
"learning_rate": 1.3153671098335132e-06,
|
| 629 |
+
"loss": 1.4934,
|
| 630 |
+
"step": 48500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 5.87,
|
| 634 |
+
"learning_rate": 1.297999760450353e-06,
|
| 635 |
+
"loss": 1.493,
|
| 636 |
+
"step": 49000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 5.93,
|
| 640 |
+
"learning_rate": 1.2806324110671939e-06,
|
| 641 |
+
"loss": 1.4932,
|
| 642 |
+
"step": 49500
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 5.99,
|
| 646 |
+
"learning_rate": 1.2632650616840342e-06,
|
| 647 |
+
"loss": 1.4933,
|
| 648 |
+
"step": 50000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 6.0,
|
| 652 |
+
"eval_loss": 1.5031880140304565,
|
| 653 |
+
"eval_runtime": 101.923,
|
| 654 |
+
"eval_samples_per_second": 294.34,
|
| 655 |
+
"eval_steps_per_second": 1.845,
|
| 656 |
+
"step": 50097
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.05,
|
| 660 |
+
"learning_rate": 1.2458977123008745e-06,
|
| 661 |
+
"loss": 1.4928,
|
| 662 |
+
"step": 50500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.11,
|
| 666 |
+
"learning_rate": 1.2285303629177145e-06,
|
| 667 |
+
"loss": 1.4928,
|
| 668 |
+
"step": 51000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.17,
|
| 672 |
+
"learning_rate": 1.2111630135345552e-06,
|
| 673 |
+
"loss": 1.4927,
|
| 674 |
+
"step": 51500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.23,
|
| 678 |
+
"learning_rate": 1.1937956641513955e-06,
|
| 679 |
+
"loss": 1.4926,
|
| 680 |
+
"step": 52000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 6.29,
|
| 684 |
+
"learning_rate": 1.1764283147682355e-06,
|
| 685 |
+
"loss": 1.4929,
|
| 686 |
+
"step": 52500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.35,
|
| 690 |
+
"learning_rate": 1.1590609653850762e-06,
|
| 691 |
+
"loss": 1.4927,
|
| 692 |
+
"step": 53000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.41,
|
| 696 |
+
"learning_rate": 1.1416936160019166e-06,
|
| 697 |
+
"loss": 1.4924,
|
| 698 |
+
"step": 53500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 6.47,
|
| 702 |
+
"learning_rate": 1.124326266618757e-06,
|
| 703 |
+
"loss": 1.4924,
|
| 704 |
+
"step": 54000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.53,
|
| 708 |
+
"learning_rate": 1.1069589172355968e-06,
|
| 709 |
+
"loss": 1.4921,
|
| 710 |
+
"step": 54500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 6.59,
|
| 714 |
+
"learning_rate": 1.0895915678524376e-06,
|
| 715 |
+
"loss": 1.4922,
|
| 716 |
+
"step": 55000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.65,
|
| 720 |
+
"learning_rate": 1.072224218469278e-06,
|
| 721 |
+
"loss": 1.4925,
|
| 722 |
+
"step": 55500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 6.71,
|
| 726 |
+
"learning_rate": 1.0548568690861182e-06,
|
| 727 |
+
"loss": 1.4925,
|
| 728 |
+
"step": 56000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 6.77,
|
| 732 |
+
"learning_rate": 1.0374895197029584e-06,
|
| 733 |
+
"loss": 1.4922,
|
| 734 |
+
"step": 56500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.83,
|
| 738 |
+
"learning_rate": 1.020122170319799e-06,
|
| 739 |
+
"loss": 1.4924,
|
| 740 |
+
"step": 57000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.89,
|
| 744 |
+
"learning_rate": 1.0027548209366393e-06,
|
| 745 |
+
"loss": 1.492,
|
| 746 |
+
"step": 57500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 6.95,
|
| 750 |
+
"learning_rate": 9.853874715534794e-07,
|
| 751 |
+
"loss": 1.4923,
|
| 752 |
+
"step": 58000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 7.0,
|
| 756 |
+
"eval_loss": 1.502358317375183,
|
| 757 |
+
"eval_runtime": 100.8628,
|
| 758 |
+
"eval_samples_per_second": 297.434,
|
| 759 |
+
"eval_steps_per_second": 1.864,
|
| 760 |
+
"step": 58446
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 7.01,
|
| 764 |
+
"learning_rate": 9.6802012217032e-07,
|
| 765 |
+
"loss": 1.4919,
|
| 766 |
+
"step": 58500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 7.07,
|
| 770 |
+
"learning_rate": 9.506527727871603e-07,
|
| 771 |
+
"loss": 1.4919,
|
| 772 |
+
"step": 59000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 7.13,
|
| 776 |
+
"learning_rate": 9.332854234040007e-07,
|
| 777 |
+
"loss": 1.4917,
|
| 778 |
+
"step": 59500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 7.19,
|
| 782 |
+
"learning_rate": 9.159180740208407e-07,
|
| 783 |
+
"loss": 1.4917,
|
| 784 |
+
"step": 60000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 7.25,
|
| 788 |
+
"learning_rate": 8.985507246376812e-07,
|
| 789 |
+
"loss": 1.4914,
|
| 790 |
+
"step": 60500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 7.31,
|
| 794 |
+
"learning_rate": 8.811833752545216e-07,
|
| 795 |
+
"loss": 1.4917,
|
| 796 |
+
"step": 61000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 7.37,
|
| 800 |
+
"learning_rate": 8.638160258713617e-07,
|
| 801 |
+
"loss": 1.4917,
|
| 802 |
+
"step": 61500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 7.43,
|
| 806 |
+
"learning_rate": 8.464486764882022e-07,
|
| 807 |
+
"loss": 1.4914,
|
| 808 |
+
"step": 62000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 7.49,
|
| 812 |
+
"learning_rate": 8.290813271050427e-07,
|
| 813 |
+
"loss": 1.4917,
|
| 814 |
+
"step": 62500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 7.55,
|
| 818 |
+
"learning_rate": 8.11713977721883e-07,
|
| 819 |
+
"loss": 1.4914,
|
| 820 |
+
"step": 63000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 7.61,
|
| 824 |
+
"learning_rate": 7.943466283387231e-07,
|
| 825 |
+
"loss": 1.4915,
|
| 826 |
+
"step": 63500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 7.67,
|
| 830 |
+
"learning_rate": 7.769792789555636e-07,
|
| 831 |
+
"loss": 1.4915,
|
| 832 |
+
"step": 64000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 7.73,
|
| 836 |
+
"learning_rate": 7.596119295724041e-07,
|
| 837 |
+
"loss": 1.4912,
|
| 838 |
+
"step": 64500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 7.78,
|
| 842 |
+
"learning_rate": 7.422445801892441e-07,
|
| 843 |
+
"loss": 1.4913,
|
| 844 |
+
"step": 65000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 7.84,
|
| 848 |
+
"learning_rate": 7.248772308060845e-07,
|
| 849 |
+
"loss": 1.4913,
|
| 850 |
+
"step": 65500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 7.9,
|
| 854 |
+
"learning_rate": 7.07509881422925e-07,
|
| 855 |
+
"loss": 1.4912,
|
| 856 |
+
"step": 66000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 7.96,
|
| 860 |
+
"learning_rate": 6.901425320397654e-07,
|
| 861 |
+
"loss": 1.4914,
|
| 862 |
+
"step": 66500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 8.0,
|
| 866 |
+
"eval_loss": 1.5018346309661865,
|
| 867 |
+
"eval_runtime": 100.3999,
|
| 868 |
+
"eval_samples_per_second": 298.805,
|
| 869 |
+
"eval_steps_per_second": 1.873,
|
| 870 |
+
"step": 66796
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 8.02,
|
| 874 |
+
"learning_rate": 6.727751826566056e-07,
|
| 875 |
+
"loss": 1.4912,
|
| 876 |
+
"step": 67000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 8.08,
|
| 880 |
+
"learning_rate": 6.554078332734459e-07,
|
| 881 |
+
"loss": 1.4909,
|
| 882 |
+
"step": 67500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 8.14,
|
| 886 |
+
"learning_rate": 6.380404838902863e-07,
|
| 887 |
+
"loss": 1.4912,
|
| 888 |
+
"step": 68000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 8.2,
|
| 892 |
+
"learning_rate": 6.206731345071265e-07,
|
| 893 |
+
"loss": 1.4909,
|
| 894 |
+
"step": 68500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 8.26,
|
| 898 |
+
"learning_rate": 6.033057851239669e-07,
|
| 899 |
+
"loss": 1.4911,
|
| 900 |
+
"step": 69000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 8.32,
|
| 904 |
+
"learning_rate": 5.859384357408073e-07,
|
| 905 |
+
"loss": 1.4908,
|
| 906 |
+
"step": 69500
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 8.38,
|
| 910 |
+
"learning_rate": 5.685710863576478e-07,
|
| 911 |
+
"loss": 1.491,
|
| 912 |
+
"step": 70000
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 8.44,
|
| 916 |
+
"learning_rate": 5.512037369744878e-07,
|
| 917 |
+
"loss": 1.491,
|
| 918 |
+
"step": 70500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 8.5,
|
| 922 |
+
"learning_rate": 5.338363875913284e-07,
|
| 923 |
+
"loss": 1.491,
|
| 924 |
+
"step": 71000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 8.56,
|
| 928 |
+
"learning_rate": 5.164690382081687e-07,
|
| 929 |
+
"loss": 1.4911,
|
| 930 |
+
"step": 71500
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 8.62,
|
| 934 |
+
"learning_rate": 4.991016888250091e-07,
|
| 935 |
+
"loss": 1.4908,
|
| 936 |
+
"step": 72000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 8.68,
|
| 940 |
+
"learning_rate": 4.817343394418493e-07,
|
| 941 |
+
"loss": 1.4907,
|
| 942 |
+
"step": 72500
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 8.74,
|
| 946 |
+
"learning_rate": 4.643669900586897e-07,
|
| 947 |
+
"loss": 1.4907,
|
| 948 |
+
"step": 73000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 8.8,
|
| 952 |
+
"learning_rate": 4.4699964067553015e-07,
|
| 953 |
+
"loss": 1.4906,
|
| 954 |
+
"step": 73500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 8.86,
|
| 958 |
+
"learning_rate": 4.296322912923702e-07,
|
| 959 |
+
"loss": 1.4907,
|
| 960 |
+
"step": 74000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 8.92,
|
| 964 |
+
"learning_rate": 4.1226494190921066e-07,
|
| 965 |
+
"loss": 1.491,
|
| 966 |
+
"step": 74500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 8.98,
|
| 970 |
+
"learning_rate": 3.948975925260511e-07,
|
| 971 |
+
"loss": 1.4907,
|
| 972 |
+
"step": 75000
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 9.0,
|
| 976 |
+
"eval_loss": 1.5016120672225952,
|
| 977 |
+
"eval_runtime": 100.2408,
|
| 978 |
+
"eval_samples_per_second": 299.279,
|
| 979 |
+
"eval_steps_per_second": 1.875,
|
| 980 |
+
"step": 75145
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 9.04,
|
| 984 |
+
"learning_rate": 3.775302431428916e-07,
|
| 985 |
+
"loss": 1.4908,
|
| 986 |
+
"step": 75500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 9.1,
|
| 990 |
+
"learning_rate": 3.601628937597316e-07,
|
| 991 |
+
"loss": 1.4906,
|
| 992 |
+
"step": 76000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.16,
|
| 996 |
+
"learning_rate": 3.4279554437657206e-07,
|
| 997 |
+
"loss": 1.4906,
|
| 998 |
+
"step": 76500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 9.22,
|
| 1002 |
+
"learning_rate": 3.254281949934125e-07,
|
| 1003 |
+
"loss": 1.4903,
|
| 1004 |
+
"step": 77000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 9.28,
|
| 1008 |
+
"learning_rate": 3.0806084561025263e-07,
|
| 1009 |
+
"loss": 1.4905,
|
| 1010 |
+
"step": 77500
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 9.34,
|
| 1014 |
+
"learning_rate": 2.90693496227093e-07,
|
| 1015 |
+
"loss": 1.4907,
|
| 1016 |
+
"step": 78000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 9.4,
|
| 1020 |
+
"learning_rate": 2.7332614684393346e-07,
|
| 1021 |
+
"loss": 1.4905,
|
| 1022 |
+
"step": 78500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 9.46,
|
| 1026 |
+
"learning_rate": 2.5595879746077385e-07,
|
| 1027 |
+
"loss": 1.4904,
|
| 1028 |
+
"step": 79000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 9.52,
|
| 1032 |
+
"learning_rate": 2.38591448077614e-07,
|
| 1033 |
+
"loss": 1.4905,
|
| 1034 |
+
"step": 79500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 9.58,
|
| 1038 |
+
"learning_rate": 2.2122409869445442e-07,
|
| 1039 |
+
"loss": 1.4906,
|
| 1040 |
+
"step": 80000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 9.64,
|
| 1044 |
+
"learning_rate": 2.0385674931129484e-07,
|
| 1045 |
+
"loss": 1.4904,
|
| 1046 |
+
"step": 80500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 9.7,
|
| 1050 |
+
"learning_rate": 1.8648939992813496e-07,
|
| 1051 |
+
"loss": 1.4903,
|
| 1052 |
+
"step": 81000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 9.76,
|
| 1056 |
+
"learning_rate": 1.6912205054497538e-07,
|
| 1057 |
+
"loss": 1.4906,
|
| 1058 |
+
"step": 81500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 9.82,
|
| 1062 |
+
"learning_rate": 1.5175470116181582e-07,
|
| 1063 |
+
"loss": 1.4908,
|
| 1064 |
+
"step": 82000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 9.88,
|
| 1068 |
+
"learning_rate": 1.3438735177865624e-07,
|
| 1069 |
+
"loss": 1.49,
|
| 1070 |
+
"step": 82500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 9.94,
|
| 1074 |
+
"learning_rate": 1.1702000239549635e-07,
|
| 1075 |
+
"loss": 1.4905,
|
| 1076 |
+
"step": 83000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 10.0,
|
| 1080 |
+
"eval_loss": 1.5012842416763306,
|
| 1081 |
+
"eval_runtime": 100.3947,
|
| 1082 |
+
"eval_samples_per_second": 298.821,
|
| 1083 |
+
"eval_steps_per_second": 1.873,
|
| 1084 |
+
"step": 83490
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 10.0,
|
| 1088 |
+
"step": 83490,
|
| 1089 |
+
"total_flos": 1.463646111228887e+18,
|
| 1090 |
+
"train_loss": 1.4961074900378695,
|
| 1091 |
+
"train_runtime": 199226.4751,
|
| 1092 |
+
"train_samples_per_second": 268.221,
|
| 1093 |
+
"train_steps_per_second": 0.419
|
| 1094 |
+
}
|
| 1095 |
+
],
|
| 1096 |
+
"max_steps": 83490,
|
| 1097 |
+
"num_train_epochs": 10,
|
| 1098 |
+
"total_flos": 1.463646111228887e+18,
|
| 1099 |
+
"trial_name": null,
|
| 1100 |
+
"trial_params": null
|
| 1101 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5653bb3db359b57cbf329e7a11a0a6d4cc78ee136ae7b9b94550a9bb939922bc
|
| 3 |
+
size 4207
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|