Upload folder using huggingface_hub
Browse files- config.json +70 -0
- generation_config.json +15 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- trainer_state.json +501 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/workspace/Finetune/Shorts/bart/20240321-045013/checkpoint-28800",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"force_bos_token_to_be_generated": true,
|
| 28 |
+
"forced_bos_token_id": 0,
|
| 29 |
+
"forced_eos_token_id": 2,
|
| 30 |
+
"gradient_checkpointing": false,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1",
|
| 34 |
+
"2": "LABEL_2"
|
| 35 |
+
},
|
| 36 |
+
"init_std": 0.02,
|
| 37 |
+
"is_encoder_decoder": true,
|
| 38 |
+
"label2id": {
|
| 39 |
+
"LABEL_0": 0,
|
| 40 |
+
"LABEL_1": 1,
|
| 41 |
+
"LABEL_2": 2
|
| 42 |
+
},
|
| 43 |
+
"length_penalty": 2.0,
|
| 44 |
+
"max_length": 142,
|
| 45 |
+
"max_position_embeddings": 1024,
|
| 46 |
+
"min_length": 56,
|
| 47 |
+
"model_type": "bart",
|
| 48 |
+
"no_repeat_ngram_size": 3,
|
| 49 |
+
"normalize_before": false,
|
| 50 |
+
"num_beams": 4,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"output_past": true,
|
| 53 |
+
"pad_token_id": 1,
|
| 54 |
+
"prefix": " ",
|
| 55 |
+
"scale_embedding": false,
|
| 56 |
+
"task_specific_params": {
|
| 57 |
+
"summarization": {
|
| 58 |
+
"early_stopping": true,
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"no_repeat_ngram_size": 3,
|
| 63 |
+
"num_beams": 4
|
| 64 |
+
}
|
| 65 |
+
},
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.39.0",
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 50264
|
| 70 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 0,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"length_penalty": 2.0,
|
| 9 |
+
"max_length": 142,
|
| 10 |
+
"min_length": 56,
|
| 11 |
+
"no_repeat_ngram_size": 3,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 1,
|
| 14 |
+
"transformers_version": "4.39.0"
|
| 15 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:164b5494ac7dc63ddd647f8c38f8282e5bab9fd22022d2076c188a5d2a5b1cfe
|
| 3 |
+
size 1625422896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88054f4b96e2c48d52f7e14d9dd88d01981d1c768ba436efeaceade549897e7f
|
| 3 |
+
size 3250751759
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6f76dc88a49fbe8084c46058a6690efc16d635806e103f2dda5d02d870b82e5
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:420fc5f51a05e0274a48344decd52036c9e49d1a1fff581ca68f3034646a3c19
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"max_length": 1024,
|
| 52 |
+
"model_max_length": 1024,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
+
"pad_token": "<pad>",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
+
"sep_token": "</s>",
|
| 58 |
+
"stride": 0,
|
| 59 |
+
"tokenizer_class": "BartTokenizer",
|
| 60 |
+
"trim_offsets": true,
|
| 61 |
+
"truncation_side": "right",
|
| 62 |
+
"truncation_strategy": "longest_first",
|
| 63 |
+
"unk_token": "<unk>"
|
| 64 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9848398495383563,
|
| 5 |
+
"eval_steps": 720,
|
| 6 |
+
"global_step": 17280,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 0.3646579682826996,
|
| 14 |
+
"learning_rate": 9.795674104471232e-05,
|
| 15 |
+
"loss": 0.0784,
|
| 16 |
+
"step": 720
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"eval_bertscore": 0.7196829915046692,
|
| 21 |
+
"eval_loss": 0.10667099058628082,
|
| 22 |
+
"eval_rouge1": 0.5424204681399662,
|
| 23 |
+
"eval_rouge2": 0.3232621307936826,
|
| 24 |
+
"eval_rougeL": 0.4168316330799737,
|
| 25 |
+
"eval_rougeLsum": 0.41874171810922023,
|
| 26 |
+
"eval_runtime": 50.0749,
|
| 27 |
+
"eval_samples_per_second": 1.078,
|
| 28 |
+
"eval_steps_per_second": 0.28,
|
| 29 |
+
"step": 720
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.08,
|
| 33 |
+
"grad_norm": NaN,
|
| 34 |
+
"learning_rate": 9.590778262232482e-05,
|
| 35 |
+
"loss": 0.0858,
|
| 36 |
+
"step": 1440
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.08,
|
| 40 |
+
"eval_bertscore": 0.6401040554046631,
|
| 41 |
+
"eval_loss": 0.18695296347141266,
|
| 42 |
+
"eval_rouge1": 0.4271646967472444,
|
| 43 |
+
"eval_rouge2": 0.1659738534008396,
|
| 44 |
+
"eval_rougeL": 0.28939047028045584,
|
| 45 |
+
"eval_rougeLsum": 0.28900025002813623,
|
| 46 |
+
"eval_runtime": 43.3827,
|
| 47 |
+
"eval_samples_per_second": 1.245,
|
| 48 |
+
"eval_steps_per_second": 0.323,
|
| 49 |
+
"step": 1440
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.12,
|
| 53 |
+
"grad_norm": 0.3369450867176056,
|
| 54 |
+
"learning_rate": 9.38559744663874e-05,
|
| 55 |
+
"loss": 0.0887,
|
| 56 |
+
"step": 2160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.12,
|
| 60 |
+
"eval_bertscore": 0.7218716740608215,
|
| 61 |
+
"eval_loss": 0.1099499836564064,
|
| 62 |
+
"eval_rouge1": 0.5524760977800962,
|
| 63 |
+
"eval_rouge2": 0.330958882130141,
|
| 64 |
+
"eval_rougeL": 0.4259051117722474,
|
| 65 |
+
"eval_rougeLsum": 0.42919968644337714,
|
| 66 |
+
"eval_runtime": 47.1009,
|
| 67 |
+
"eval_samples_per_second": 1.146,
|
| 68 |
+
"eval_steps_per_second": 0.297,
|
| 69 |
+
"step": 2160
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.16,
|
| 73 |
+
"grad_norm": 0.36330386996269226,
|
| 74 |
+
"learning_rate": 9.180416631044998e-05,
|
| 75 |
+
"loss": 0.0933,
|
| 76 |
+
"step": 2880
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.16,
|
| 80 |
+
"eval_bertscore": 0.7138540744781494,
|
| 81 |
+
"eval_loss": 0.1120433360338211,
|
| 82 |
+
"eval_rouge1": 0.5390251173909333,
|
| 83 |
+
"eval_rouge2": 0.31146103356099275,
|
| 84 |
+
"eval_rougeL": 0.41387331131584476,
|
| 85 |
+
"eval_rougeLsum": 0.4135311998867288,
|
| 86 |
+
"eval_runtime": 46.0195,
|
| 87 |
+
"eval_samples_per_second": 1.173,
|
| 88 |
+
"eval_steps_per_second": 0.304,
|
| 89 |
+
"step": 2880
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"grad_norm": 0.35335826873779297,
|
| 94 |
+
"learning_rate": 8.975235815451256e-05,
|
| 95 |
+
"loss": 0.0862,
|
| 96 |
+
"step": 3600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.21,
|
| 100 |
+
"eval_bertscore": 0.7312328219413757,
|
| 101 |
+
"eval_loss": 0.10742145031690598,
|
| 102 |
+
"eval_rouge1": 0.5669051469800668,
|
| 103 |
+
"eval_rouge2": 0.3520718989284114,
|
| 104 |
+
"eval_rougeL": 0.44425293679893696,
|
| 105 |
+
"eval_rougeLsum": 0.44695777725182906,
|
| 106 |
+
"eval_runtime": 45.6563,
|
| 107 |
+
"eval_samples_per_second": 1.183,
|
| 108 |
+
"eval_steps_per_second": 0.307,
|
| 109 |
+
"step": 3600
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.25,
|
| 113 |
+
"grad_norm": 0.37303468585014343,
|
| 114 |
+
"learning_rate": 8.770339973212504e-05,
|
| 115 |
+
"loss": 0.0911,
|
| 116 |
+
"step": 4320
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.25,
|
| 120 |
+
"eval_bertscore": 0.7096375226974487,
|
| 121 |
+
"eval_loss": 0.11186981201171875,
|
| 122 |
+
"eval_rouge1": 0.5333109271513738,
|
| 123 |
+
"eval_rouge2": 0.30338933797823264,
|
| 124 |
+
"eval_rougeL": 0.4003430978893555,
|
| 125 |
+
"eval_rougeLsum": 0.4005552066640774,
|
| 126 |
+
"eval_runtime": 43.9874,
|
| 127 |
+
"eval_samples_per_second": 1.228,
|
| 128 |
+
"eval_steps_per_second": 0.318,
|
| 129 |
+
"step": 4320
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.29,
|
| 133 |
+
"grad_norm": 0.30176717042922974,
|
| 134 |
+
"learning_rate": 8.565159157618762e-05,
|
| 135 |
+
"loss": 0.0893,
|
| 136 |
+
"step": 5040
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.29,
|
| 140 |
+
"eval_bertscore": 0.7181953191757202,
|
| 141 |
+
"eval_loss": 0.10768043249845505,
|
| 142 |
+
"eval_rouge1": 0.5493961807050101,
|
| 143 |
+
"eval_rouge2": 0.3304637891082364,
|
| 144 |
+
"eval_rougeL": 0.42184528341938216,
|
| 145 |
+
"eval_rougeLsum": 0.4241212110511772,
|
| 146 |
+
"eval_runtime": 45.8651,
|
| 147 |
+
"eval_samples_per_second": 1.177,
|
| 148 |
+
"eval_steps_per_second": 0.305,
|
| 149 |
+
"step": 5040
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.33,
|
| 153 |
+
"grad_norm": 0.35905396938323975,
|
| 154 |
+
"learning_rate": 8.35997834202502e-05,
|
| 155 |
+
"loss": 0.0895,
|
| 156 |
+
"step": 5760
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.33,
|
| 160 |
+
"eval_bertscore": 0.7235485315322876,
|
| 161 |
+
"eval_loss": 0.10892420262098312,
|
| 162 |
+
"eval_rouge1": 0.5464214086441583,
|
| 163 |
+
"eval_rouge2": 0.33055059501726136,
|
| 164 |
+
"eval_rougeL": 0.4309761675921166,
|
| 165 |
+
"eval_rougeLsum": 0.43243067509302885,
|
| 166 |
+
"eval_runtime": 46.6469,
|
| 167 |
+
"eval_samples_per_second": 1.158,
|
| 168 |
+
"eval_steps_per_second": 0.3,
|
| 169 |
+
"step": 5760
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.37,
|
| 173 |
+
"grad_norm": 0.4224866032600403,
|
| 174 |
+
"learning_rate": 8.154797526431279e-05,
|
| 175 |
+
"loss": 0.0904,
|
| 176 |
+
"step": 6480
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.37,
|
| 180 |
+
"eval_bertscore": 0.7329062819480896,
|
| 181 |
+
"eval_loss": 0.10619346052408218,
|
| 182 |
+
"eval_rouge1": 0.564360420431112,
|
| 183 |
+
"eval_rouge2": 0.3430202743146231,
|
| 184 |
+
"eval_rougeL": 0.43258159937823415,
|
| 185 |
+
"eval_rougeLsum": 0.4342682613180943,
|
| 186 |
+
"eval_runtime": 43.9471,
|
| 187 |
+
"eval_samples_per_second": 1.229,
|
| 188 |
+
"eval_steps_per_second": 0.319,
|
| 189 |
+
"step": 6480
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.41,
|
| 193 |
+
"grad_norm": 0.326298326253891,
|
| 194 |
+
"learning_rate": 7.949616710837537e-05,
|
| 195 |
+
"loss": 0.088,
|
| 196 |
+
"step": 7200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.41,
|
| 200 |
+
"eval_bertscore": 0.7319415807723999,
|
| 201 |
+
"eval_loss": 0.10810621827840805,
|
| 202 |
+
"eval_rouge1": 0.567691068841891,
|
| 203 |
+
"eval_rouge2": 0.3516256462902142,
|
| 204 |
+
"eval_rougeL": 0.42838027396990275,
|
| 205 |
+
"eval_rougeLsum": 0.4324782503340911,
|
| 206 |
+
"eval_runtime": 46.4934,
|
| 207 |
+
"eval_samples_per_second": 1.161,
|
| 208 |
+
"eval_steps_per_second": 0.301,
|
| 209 |
+
"step": 7200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.45,
|
| 213 |
+
"grad_norm": 0.38782864809036255,
|
| 214 |
+
"learning_rate": 7.744720868598786e-05,
|
| 215 |
+
"loss": 0.099,
|
| 216 |
+
"step": 7920
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.45,
|
| 220 |
+
"eval_bertscore": 0.7281920909881592,
|
| 221 |
+
"eval_loss": 0.1160830408334732,
|
| 222 |
+
"eval_rouge1": 0.5638078274676868,
|
| 223 |
+
"eval_rouge2": 0.33447827597228297,
|
| 224 |
+
"eval_rougeL": 0.42103610080157494,
|
| 225 |
+
"eval_rougeLsum": 0.421241459135431,
|
| 226 |
+
"eval_runtime": 43.8757,
|
| 227 |
+
"eval_samples_per_second": 1.231,
|
| 228 |
+
"eval_steps_per_second": 0.319,
|
| 229 |
+
"step": 7920
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.49,
|
| 233 |
+
"grad_norm": 0.3241174519062042,
|
| 234 |
+
"learning_rate": 7.539540053005044e-05,
|
| 235 |
+
"loss": 0.0872,
|
| 236 |
+
"step": 8640
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.49,
|
| 240 |
+
"eval_bertscore": 0.7242642045021057,
|
| 241 |
+
"eval_loss": 0.10293756425380707,
|
| 242 |
+
"eval_rouge1": 0.5632532860588884,
|
| 243 |
+
"eval_rouge2": 0.34322756987289393,
|
| 244 |
+
"eval_rougeL": 0.42262041814568485,
|
| 245 |
+
"eval_rougeLsum": 0.423440338568295,
|
| 246 |
+
"eval_runtime": 46.2455,
|
| 247 |
+
"eval_samples_per_second": 1.168,
|
| 248 |
+
"eval_steps_per_second": 0.303,
|
| 249 |
+
"step": 8640
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.53,
|
| 253 |
+
"grad_norm": 0.3583599030971527,
|
| 254 |
+
"learning_rate": 7.334359237411302e-05,
|
| 255 |
+
"loss": 0.0873,
|
| 256 |
+
"step": 9360
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.53,
|
| 260 |
+
"eval_bertscore": 0.6995793581008911,
|
| 261 |
+
"eval_loss": 0.1057819277048111,
|
| 262 |
+
"eval_rouge1": 0.5146289688453939,
|
| 263 |
+
"eval_rouge2": 0.31515963367438793,
|
| 264 |
+
"eval_rougeL": 0.3849697348906047,
|
| 265 |
+
"eval_rougeLsum": 0.3853863269798617,
|
| 266 |
+
"eval_runtime": 41.7431,
|
| 267 |
+
"eval_samples_per_second": 1.294,
|
| 268 |
+
"eval_steps_per_second": 0.335,
|
| 269 |
+
"step": 9360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.57,
|
| 273 |
+
"grad_norm": 0.2910310626029968,
|
| 274 |
+
"learning_rate": 7.12917842181756e-05,
|
| 275 |
+
"loss": 0.0867,
|
| 276 |
+
"step": 10080
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.57,
|
| 280 |
+
"eval_bertscore": 0.6976329684257507,
|
| 281 |
+
"eval_loss": 0.1045340821146965,
|
| 282 |
+
"eval_rouge1": 0.5207467825430098,
|
| 283 |
+
"eval_rouge2": 0.3033279665805546,
|
| 284 |
+
"eval_rougeL": 0.3864676775585604,
|
| 285 |
+
"eval_rougeLsum": 0.38810836905339663,
|
| 286 |
+
"eval_runtime": 42.5457,
|
| 287 |
+
"eval_samples_per_second": 1.269,
|
| 288 |
+
"eval_steps_per_second": 0.329,
|
| 289 |
+
"step": 10080
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.62,
|
| 293 |
+
"grad_norm": 0.3698158860206604,
|
| 294 |
+
"learning_rate": 6.92428257957881e-05,
|
| 295 |
+
"loss": 0.0877,
|
| 296 |
+
"step": 10800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.62,
|
| 300 |
+
"eval_bertscore": 0.6928555369377136,
|
| 301 |
+
"eval_loss": 0.10213906317949295,
|
| 302 |
+
"eval_rouge1": 0.5052125219715984,
|
| 303 |
+
"eval_rouge2": 0.2901105424948756,
|
| 304 |
+
"eval_rougeL": 0.38512895532246294,
|
| 305 |
+
"eval_rougeLsum": 0.38700266390157023,
|
| 306 |
+
"eval_runtime": 43.2036,
|
| 307 |
+
"eval_samples_per_second": 1.25,
|
| 308 |
+
"eval_steps_per_second": 0.324,
|
| 309 |
+
"step": 10800
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.66,
|
| 313 |
+
"grad_norm": 0.31327977776527405,
|
| 314 |
+
"learning_rate": 6.719101763985067e-05,
|
| 315 |
+
"loss": 0.0863,
|
| 316 |
+
"step": 11520
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.66,
|
| 320 |
+
"eval_bertscore": 0.7075583338737488,
|
| 321 |
+
"eval_loss": 0.10120192915201187,
|
| 322 |
+
"eval_rouge1": 0.5255501659415194,
|
| 323 |
+
"eval_rouge2": 0.313837826701734,
|
| 324 |
+
"eval_rougeL": 0.40085373784140194,
|
| 325 |
+
"eval_rougeLsum": 0.40434970576567464,
|
| 326 |
+
"eval_runtime": 42.8949,
|
| 327 |
+
"eval_samples_per_second": 1.259,
|
| 328 |
+
"eval_steps_per_second": 0.326,
|
| 329 |
+
"step": 11520
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.7,
|
| 333 |
+
"grad_norm": 0.3461964428424835,
|
| 334 |
+
"learning_rate": 6.514205921746318e-05,
|
| 335 |
+
"loss": 0.0872,
|
| 336 |
+
"step": 12240
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.7,
|
| 340 |
+
"eval_bertscore": 0.7073290348052979,
|
| 341 |
+
"eval_loss": 0.10406655818223953,
|
| 342 |
+
"eval_rouge1": 0.5477131085772904,
|
| 343 |
+
"eval_rouge2": 0.33149979593857803,
|
| 344 |
+
"eval_rougeL": 0.40632334489545124,
|
| 345 |
+
"eval_rougeLsum": 0.4095457087623684,
|
| 346 |
+
"eval_runtime": 44.6457,
|
| 347 |
+
"eval_samples_per_second": 1.21,
|
| 348 |
+
"eval_steps_per_second": 0.314,
|
| 349 |
+
"step": 12240
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.74,
|
| 353 |
+
"grad_norm": 0.5959820747375488,
|
| 354 |
+
"learning_rate": 6.309025106152576e-05,
|
| 355 |
+
"loss": 0.0865,
|
| 356 |
+
"step": 12960
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.74,
|
| 360 |
+
"eval_bertscore": 0.7051340937614441,
|
| 361 |
+
"eval_loss": 0.10186685621738434,
|
| 362 |
+
"eval_rouge1": 0.5286009039113435,
|
| 363 |
+
"eval_rouge2": 0.30974761597035483,
|
| 364 |
+
"eval_rougeL": 0.39408942231662314,
|
| 365 |
+
"eval_rougeLsum": 0.39582462237360283,
|
| 366 |
+
"eval_runtime": 41.0675,
|
| 367 |
+
"eval_samples_per_second": 1.315,
|
| 368 |
+
"eval_steps_per_second": 0.341,
|
| 369 |
+
"step": 12960
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.78,
|
| 373 |
+
"grad_norm": 0.3375673294067383,
|
| 374 |
+
"learning_rate": 6.104129263913825e-05,
|
| 375 |
+
"loss": 0.0882,
|
| 376 |
+
"step": 13680
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.78,
|
| 380 |
+
"eval_bertscore": 0.7006374001502991,
|
| 381 |
+
"eval_loss": 0.10748545080423355,
|
| 382 |
+
"eval_rouge1": 0.5293328711395651,
|
| 383 |
+
"eval_rouge2": 0.30648192947303854,
|
| 384 |
+
"eval_rougeL": 0.38835230184676583,
|
| 385 |
+
"eval_rougeLsum": 0.3893932601411799,
|
| 386 |
+
"eval_runtime": 42.4292,
|
| 387 |
+
"eval_samples_per_second": 1.273,
|
| 388 |
+
"eval_steps_per_second": 0.33,
|
| 389 |
+
"step": 13680
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.82,
|
| 393 |
+
"grad_norm": 0.2677787244319916,
|
| 394 |
+
"learning_rate": 5.899233421675073e-05,
|
| 395 |
+
"loss": 0.0974,
|
| 396 |
+
"step": 14400
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.82,
|
| 400 |
+
"eval_bertscore": 0.7165916562080383,
|
| 401 |
+
"eval_loss": 0.1007571741938591,
|
| 402 |
+
"eval_rouge1": 0.5513926515300362,
|
| 403 |
+
"eval_rouge2": 0.33911911389049787,
|
| 404 |
+
"eval_rougeL": 0.416442801833816,
|
| 405 |
+
"eval_rougeLsum": 0.4183281343761722,
|
| 406 |
+
"eval_runtime": 44.5976,
|
| 407 |
+
"eval_samples_per_second": 1.211,
|
| 408 |
+
"eval_steps_per_second": 0.314,
|
| 409 |
+
"step": 14400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.86,
|
| 413 |
+
"grad_norm": 0.37346717715263367,
|
| 414 |
+
"learning_rate": 5.694052606081331e-05,
|
| 415 |
+
"loss": 0.0873,
|
| 416 |
+
"step": 15120
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.86,
|
| 420 |
+
"eval_bertscore": 0.7286005616188049,
|
| 421 |
+
"eval_loss": 0.10275202244520187,
|
| 422 |
+
"eval_rouge1": 0.568867460495994,
|
| 423 |
+
"eval_rouge2": 0.3456103655679248,
|
| 424 |
+
"eval_rougeL": 0.43306516695459163,
|
| 425 |
+
"eval_rougeLsum": 0.43448984907617605,
|
| 426 |
+
"eval_runtime": 45.9446,
|
| 427 |
+
"eval_samples_per_second": 1.175,
|
| 428 |
+
"eval_steps_per_second": 0.305,
|
| 429 |
+
"step": 15120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9,
|
| 433 |
+
"grad_norm": 0.42003852128982544,
|
| 434 |
+
"learning_rate": 5.4888717904875894e-05,
|
| 435 |
+
"loss": 0.0884,
|
| 436 |
+
"step": 15840
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9,
|
| 440 |
+
"eval_bertscore": 0.6985941529273987,
|
| 441 |
+
"eval_loss": 0.10138168185949326,
|
| 442 |
+
"eval_rouge1": 0.5142689394504161,
|
| 443 |
+
"eval_rouge2": 0.29174269779985657,
|
| 444 |
+
"eval_rougeL": 0.38750085273888524,
|
| 445 |
+
"eval_rougeLsum": 0.38942879459463353,
|
| 446 |
+
"eval_runtime": 45.3145,
|
| 447 |
+
"eval_samples_per_second": 1.192,
|
| 448 |
+
"eval_steps_per_second": 0.309,
|
| 449 |
+
"step": 15840
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.94,
|
| 453 |
+
"grad_norm": 0.2986052334308624,
|
| 454 |
+
"learning_rate": 5.283690974893848e-05,
|
| 455 |
+
"loss": 0.0843,
|
| 456 |
+
"step": 16560
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.94,
|
| 460 |
+
"eval_bertscore": 0.7196215391159058,
|
| 461 |
+
"eval_loss": 0.09988830983638763,
|
| 462 |
+
"eval_rouge1": 0.5568270207411694,
|
| 463 |
+
"eval_rouge2": 0.3344249967035061,
|
| 464 |
+
"eval_rougeL": 0.42228876150966843,
|
| 465 |
+
"eval_rougeLsum": 0.4241723819280844,
|
| 466 |
+
"eval_runtime": 43.9057,
|
| 467 |
+
"eval_samples_per_second": 1.23,
|
| 468 |
+
"eval_steps_per_second": 0.319,
|
| 469 |
+
"step": 16560
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.98,
|
| 473 |
+
"grad_norm": 0.42629748582839966,
|
| 474 |
+
"learning_rate": 5.078510159300106e-05,
|
| 475 |
+
"loss": 0.0841,
|
| 476 |
+
"step": 17280
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.98,
|
| 480 |
+
"eval_bertscore": 0.7275723814964294,
|
| 481 |
+
"eval_loss": 0.09897469729185104,
|
| 482 |
+
"eval_rouge1": 0.5719705231392143,
|
| 483 |
+
"eval_rouge2": 0.3548031109092683,
|
| 484 |
+
"eval_rougeL": 0.44224082293068945,
|
| 485 |
+
"eval_rougeLsum": 0.4454366319399464,
|
| 486 |
+
"eval_runtime": 44.0423,
|
| 487 |
+
"eval_samples_per_second": 1.226,
|
| 488 |
+
"eval_steps_per_second": 0.318,
|
| 489 |
+
"step": 17280
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"logging_steps": 720,
|
| 493 |
+
"max_steps": 35092,
|
| 494 |
+
"num_input_tokens_seen": 0,
|
| 495 |
+
"num_train_epochs": 2,
|
| 496 |
+
"save_steps": 2880,
|
| 497 |
+
"total_flos": 1.4979027009798144e+17,
|
| 498 |
+
"train_batch_size": 2,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6038e6e47917cfd3e4900c1fc5e4329e758274af20de40703038ad34b8794df8
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|