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 +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +821 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large-cnn",
|
| 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:b1a046115e29d9fc4fc6f17d15acf273321331ea0487dfd2957837691e6cf87d
|
| 3 |
+
size 1625422896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e93e6668d0d71e4a8bacc823bd506fd598fec95d54d98bec19533846e92ce874
|
| 3 |
+
size 3250751759
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3598de065a7686e00443ba710bed5e60aa5e2573d27b288cce4c65b4b90af763
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d1882094b3a5d792444fca74f847dc6fea714ecc5e8e0806baac71db6ac44e5
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"model_max_length": 1024,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,821 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.6413997492305938,
|
| 5 |
+
"eval_steps": 720,
|
| 6 |
+
"global_step": 28800,
|
| 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": 0.535019040107727,
|
| 14 |
+
"learning_rate": 9.864353971540931e-05,
|
| 15 |
+
"loss": 0.3127,
|
| 16 |
+
"step": 720
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"eval_bertscore": 0.7034942507743835,
|
| 21 |
+
"eval_loss": 0.12081495672464371,
|
| 22 |
+
"eval_rouge1": 0.5240594026277678,
|
| 23 |
+
"eval_rouge2": 0.3067757525245376,
|
| 24 |
+
"eval_rougeL": 0.39633186458379827,
|
| 25 |
+
"eval_rougeLsum": 0.39613387865495875,
|
| 26 |
+
"eval_runtime": 80.0774,
|
| 27 |
+
"eval_samples_per_second": 0.674,
|
| 28 |
+
"eval_steps_per_second": 0.337,
|
| 29 |
+
"step": 720
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.08,
|
| 33 |
+
"grad_norm": 0.42372021079063416,
|
| 34 |
+
"learning_rate": 9.72756806048977e-05,
|
| 35 |
+
"loss": 0.1212,
|
| 36 |
+
"step": 1440
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.08,
|
| 40 |
+
"eval_bertscore": 0.7000990509986877,
|
| 41 |
+
"eval_loss": 0.11524277925491333,
|
| 42 |
+
"eval_rouge1": 0.5216793756151761,
|
| 43 |
+
"eval_rouge2": 0.2934274790368596,
|
| 44 |
+
"eval_rougeL": 0.3886043968581182,
|
| 45 |
+
"eval_rougeLsum": 0.38807827948983176,
|
| 46 |
+
"eval_runtime": 76.9989,
|
| 47 |
+
"eval_samples_per_second": 0.701,
|
| 48 |
+
"eval_steps_per_second": 0.351,
|
| 49 |
+
"step": 1440
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.12,
|
| 53 |
+
"grad_norm": 0.42828959226608276,
|
| 54 |
+
"learning_rate": 9.590782149438608e-05,
|
| 55 |
+
"loss": 0.1222,
|
| 56 |
+
"step": 2160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.12,
|
| 60 |
+
"eval_bertscore": 0.6457424163818359,
|
| 61 |
+
"eval_loss": 0.1191863939166069,
|
| 62 |
+
"eval_rouge1": 0.4637245182501467,
|
| 63 |
+
"eval_rouge2": 0.25286895940302717,
|
| 64 |
+
"eval_rougeL": 0.34111914002345234,
|
| 65 |
+
"eval_rougeLsum": 0.3407154814401842,
|
| 66 |
+
"eval_runtime": 103.8897,
|
| 67 |
+
"eval_samples_per_second": 0.52,
|
| 68 |
+
"eval_steps_per_second": 0.26,
|
| 69 |
+
"step": 2160
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.16,
|
| 73 |
+
"grad_norm": 0.44599342346191406,
|
| 74 |
+
"learning_rate": 9.453996238387447e-05,
|
| 75 |
+
"loss": 0.1172,
|
| 76 |
+
"step": 2880
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.16,
|
| 80 |
+
"eval_bertscore": 0.6841260194778442,
|
| 81 |
+
"eval_loss": 0.11394956707954407,
|
| 82 |
+
"eval_rouge1": 0.48661400042430136,
|
| 83 |
+
"eval_rouge2": 0.27298564925044316,
|
| 84 |
+
"eval_rougeL": 0.371859286615548,
|
| 85 |
+
"eval_rougeLsum": 0.37045985133751724,
|
| 86 |
+
"eval_runtime": 67.7701,
|
| 87 |
+
"eval_samples_per_second": 0.797,
|
| 88 |
+
"eval_steps_per_second": 0.398,
|
| 89 |
+
"step": 2880
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"grad_norm": 0.4306412935256958,
|
| 94 |
+
"learning_rate": 9.317210327336284e-05,
|
| 95 |
+
"loss": 0.1265,
|
| 96 |
+
"step": 3600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.21,
|
| 100 |
+
"eval_bertscore": 0.5902894139289856,
|
| 101 |
+
"eval_loss": 0.1217198297381401,
|
| 102 |
+
"eval_rouge1": 0.3684193429088964,
|
| 103 |
+
"eval_rouge2": 0.19503224358227592,
|
| 104 |
+
"eval_rougeL": 0.29399973276202795,
|
| 105 |
+
"eval_rougeLsum": 0.29348115386759427,
|
| 106 |
+
"eval_runtime": 58.6683,
|
| 107 |
+
"eval_samples_per_second": 0.92,
|
| 108 |
+
"eval_steps_per_second": 0.46,
|
| 109 |
+
"step": 3600
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.25,
|
| 113 |
+
"grad_norm": 0.4569800794124603,
|
| 114 |
+
"learning_rate": 9.180424416285122e-05,
|
| 115 |
+
"loss": 0.1201,
|
| 116 |
+
"step": 4320
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.25,
|
| 120 |
+
"eval_bertscore": 0.6664375066757202,
|
| 121 |
+
"eval_loss": 0.11453992873430252,
|
| 122 |
+
"eval_rouge1": 0.4849966834372761,
|
| 123 |
+
"eval_rouge2": 0.27797369581531306,
|
| 124 |
+
"eval_rougeL": 0.3629296708263681,
|
| 125 |
+
"eval_rougeLsum": 0.3623800251579623,
|
| 126 |
+
"eval_runtime": 81.2927,
|
| 127 |
+
"eval_samples_per_second": 0.664,
|
| 128 |
+
"eval_steps_per_second": 0.332,
|
| 129 |
+
"step": 4320
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.29,
|
| 133 |
+
"grad_norm": 0.4236726462841034,
|
| 134 |
+
"learning_rate": 9.043638505233961e-05,
|
| 135 |
+
"loss": 0.1171,
|
| 136 |
+
"step": 5040
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.29,
|
| 140 |
+
"eval_bertscore": 0.6511832475662231,
|
| 141 |
+
"eval_loss": 0.1140449047088623,
|
| 142 |
+
"eval_rouge1": 0.4622762558490229,
|
| 143 |
+
"eval_rouge2": 0.2720739144786822,
|
| 144 |
+
"eval_rougeL": 0.35563312683133363,
|
| 145 |
+
"eval_rougeLsum": 0.3553109181928958,
|
| 146 |
+
"eval_runtime": 96.9669,
|
| 147 |
+
"eval_samples_per_second": 0.557,
|
| 148 |
+
"eval_steps_per_second": 0.278,
|
| 149 |
+
"step": 5040
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.33,
|
| 153 |
+
"grad_norm": 0.4153118431568146,
|
| 154 |
+
"learning_rate": 8.9068525941828e-05,
|
| 155 |
+
"loss": 0.1182,
|
| 156 |
+
"step": 5760
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.33,
|
| 160 |
+
"eval_bertscore": 0.7056278586387634,
|
| 161 |
+
"eval_loss": 0.11447593569755554,
|
| 162 |
+
"eval_rouge1": 0.535980541670685,
|
| 163 |
+
"eval_rouge2": 0.3085487182685619,
|
| 164 |
+
"eval_rougeL": 0.3952747177668595,
|
| 165 |
+
"eval_rougeLsum": 0.39487374036594847,
|
| 166 |
+
"eval_runtime": 78.3273,
|
| 167 |
+
"eval_samples_per_second": 0.689,
|
| 168 |
+
"eval_steps_per_second": 0.345,
|
| 169 |
+
"step": 5760
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.37,
|
| 173 |
+
"grad_norm": 0.30859124660491943,
|
| 174 |
+
"learning_rate": 8.770066683131638e-05,
|
| 175 |
+
"loss": 0.1161,
|
| 176 |
+
"step": 6480
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.37,
|
| 180 |
+
"eval_bertscore": 0.717333197593689,
|
| 181 |
+
"eval_loss": 0.11316747963428497,
|
| 182 |
+
"eval_rouge1": 0.5395779598124536,
|
| 183 |
+
"eval_rouge2": 0.3235379995103774,
|
| 184 |
+
"eval_rougeL": 0.40115447322823283,
|
| 185 |
+
"eval_rougeLsum": 0.40261399344054405,
|
| 186 |
+
"eval_runtime": 77.4572,
|
| 187 |
+
"eval_samples_per_second": 0.697,
|
| 188 |
+
"eval_steps_per_second": 0.349,
|
| 189 |
+
"step": 6480
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.41,
|
| 193 |
+
"grad_norm": 0.3857922852039337,
|
| 194 |
+
"learning_rate": 8.633280772080476e-05,
|
| 195 |
+
"loss": 0.1151,
|
| 196 |
+
"step": 7200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.41,
|
| 200 |
+
"eval_bertscore": 0.7019616365432739,
|
| 201 |
+
"eval_loss": 0.11000501364469528,
|
| 202 |
+
"eval_rouge1": 0.5236493302484355,
|
| 203 |
+
"eval_rouge2": 0.3068191529551719,
|
| 204 |
+
"eval_rougeL": 0.4036664284755191,
|
| 205 |
+
"eval_rougeLsum": 0.4040689187486951,
|
| 206 |
+
"eval_runtime": 76.1117,
|
| 207 |
+
"eval_samples_per_second": 0.709,
|
| 208 |
+
"eval_steps_per_second": 0.355,
|
| 209 |
+
"step": 7200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.45,
|
| 213 |
+
"grad_norm": 0.3432803452014923,
|
| 214 |
+
"learning_rate": 8.496494861029315e-05,
|
| 215 |
+
"loss": 0.1144,
|
| 216 |
+
"step": 7920
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.45,
|
| 220 |
+
"eval_bertscore": 0.7042035460472107,
|
| 221 |
+
"eval_loss": 0.11131834983825684,
|
| 222 |
+
"eval_rouge1": 0.5294383728708514,
|
| 223 |
+
"eval_rouge2": 0.3003098501119716,
|
| 224 |
+
"eval_rougeL": 0.3967273111533241,
|
| 225 |
+
"eval_rougeLsum": 0.39619485281011757,
|
| 226 |
+
"eval_runtime": 77.3811,
|
| 227 |
+
"eval_samples_per_second": 0.698,
|
| 228 |
+
"eval_steps_per_second": 0.349,
|
| 229 |
+
"step": 7920
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.49,
|
| 233 |
+
"grad_norm": 0.3402859568595886,
|
| 234 |
+
"learning_rate": 8.359708949978152e-05,
|
| 235 |
+
"loss": 0.1126,
|
| 236 |
+
"step": 8640
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.49,
|
| 240 |
+
"eval_bertscore": 0.71971595287323,
|
| 241 |
+
"eval_loss": 0.11067274957895279,
|
| 242 |
+
"eval_rouge1": 0.551885774991056,
|
| 243 |
+
"eval_rouge2": 0.33499475588298316,
|
| 244 |
+
"eval_rougeL": 0.4160407628361842,
|
| 245 |
+
"eval_rougeLsum": 0.4164543392695917,
|
| 246 |
+
"eval_runtime": 77.4902,
|
| 247 |
+
"eval_samples_per_second": 0.697,
|
| 248 |
+
"eval_steps_per_second": 0.348,
|
| 249 |
+
"step": 8640
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.53,
|
| 253 |
+
"grad_norm": 0.4391550123691559,
|
| 254 |
+
"learning_rate": 8.223113019359007e-05,
|
| 255 |
+
"loss": 0.1116,
|
| 256 |
+
"step": 9360
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.53,
|
| 260 |
+
"eval_bertscore": 0.7158631086349487,
|
| 261 |
+
"eval_loss": 0.1099533885717392,
|
| 262 |
+
"eval_rouge1": 0.5557272797557176,
|
| 263 |
+
"eval_rouge2": 0.332779980249166,
|
| 264 |
+
"eval_rougeL": 0.4155444723963883,
|
| 265 |
+
"eval_rougeLsum": 0.41657130732656783,
|
| 266 |
+
"eval_runtime": 80.0828,
|
| 267 |
+
"eval_samples_per_second": 0.674,
|
| 268 |
+
"eval_steps_per_second": 0.337,
|
| 269 |
+
"step": 9360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.57,
|
| 273 |
+
"grad_norm": 0.3907322287559509,
|
| 274 |
+
"learning_rate": 8.086327108307846e-05,
|
| 275 |
+
"loss": 0.1141,
|
| 276 |
+
"step": 10080
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.57,
|
| 280 |
+
"eval_bertscore": 0.7130799293518066,
|
| 281 |
+
"eval_loss": 0.11258435994386673,
|
| 282 |
+
"eval_rouge1": 0.5457292777447704,
|
| 283 |
+
"eval_rouge2": 0.3214033358835623,
|
| 284 |
+
"eval_rougeL": 0.40814606110656115,
|
| 285 |
+
"eval_rougeLsum": 0.4086806368595041,
|
| 286 |
+
"eval_runtime": 73.8407,
|
| 287 |
+
"eval_samples_per_second": 0.731,
|
| 288 |
+
"eval_steps_per_second": 0.366,
|
| 289 |
+
"step": 10080
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.62,
|
| 293 |
+
"grad_norm": 0.38848328590393066,
|
| 294 |
+
"learning_rate": 7.949541197256683e-05,
|
| 295 |
+
"loss": 0.1132,
|
| 296 |
+
"step": 10800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.62,
|
| 300 |
+
"eval_bertscore": 0.7245057225227356,
|
| 301 |
+
"eval_loss": 0.11034353822469711,
|
| 302 |
+
"eval_rouge1": 0.5603983140826179,
|
| 303 |
+
"eval_rouge2": 0.3445987526625777,
|
| 304 |
+
"eval_rougeL": 0.43423536113182604,
|
| 305 |
+
"eval_rougeLsum": 0.43398163455334016,
|
| 306 |
+
"eval_runtime": 77.732,
|
| 307 |
+
"eval_samples_per_second": 0.695,
|
| 308 |
+
"eval_steps_per_second": 0.347,
|
| 309 |
+
"step": 10800
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.66,
|
| 313 |
+
"grad_norm": 0.37145286798477173,
|
| 314 |
+
"learning_rate": 7.812945266637537e-05,
|
| 315 |
+
"loss": 0.112,
|
| 316 |
+
"step": 11520
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.66,
|
| 320 |
+
"eval_bertscore": 0.7207842469215393,
|
| 321 |
+
"eval_loss": 0.11157318204641342,
|
| 322 |
+
"eval_rouge1": 0.5554178283606811,
|
| 323 |
+
"eval_rouge2": 0.3317069905744905,
|
| 324 |
+
"eval_rougeL": 0.4209451268922738,
|
| 325 |
+
"eval_rougeLsum": 0.42120272115590573,
|
| 326 |
+
"eval_runtime": 81.6277,
|
| 327 |
+
"eval_samples_per_second": 0.662,
|
| 328 |
+
"eval_steps_per_second": 0.331,
|
| 329 |
+
"step": 11520
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.7,
|
| 333 |
+
"grad_norm": 0.32327908277511597,
|
| 334 |
+
"learning_rate": 7.676349336018391e-05,
|
| 335 |
+
"loss": 0.1118,
|
| 336 |
+
"step": 12240
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.7,
|
| 340 |
+
"eval_bertscore": 0.7193225622177124,
|
| 341 |
+
"eval_loss": 0.11037024855613708,
|
| 342 |
+
"eval_rouge1": 0.5534709029702873,
|
| 343 |
+
"eval_rouge2": 0.33508595975393674,
|
| 344 |
+
"eval_rougeL": 0.4220660586810759,
|
| 345 |
+
"eval_rougeLsum": 0.42394444829473793,
|
| 346 |
+
"eval_runtime": 79.4778,
|
| 347 |
+
"eval_samples_per_second": 0.679,
|
| 348 |
+
"eval_steps_per_second": 0.34,
|
| 349 |
+
"step": 12240
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.74,
|
| 353 |
+
"grad_norm": 0.296165406703949,
|
| 354 |
+
"learning_rate": 7.539563424967229e-05,
|
| 355 |
+
"loss": 0.1096,
|
| 356 |
+
"step": 12960
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.74,
|
| 360 |
+
"eval_bertscore": 0.7183234691619873,
|
| 361 |
+
"eval_loss": 0.10668845474720001,
|
| 362 |
+
"eval_rouge1": 0.5527080110711662,
|
| 363 |
+
"eval_rouge2": 0.3304597058226536,
|
| 364 |
+
"eval_rougeL": 0.4176676998826935,
|
| 365 |
+
"eval_rougeLsum": 0.41906982236369805,
|
| 366 |
+
"eval_runtime": 74.609,
|
| 367 |
+
"eval_samples_per_second": 0.724,
|
| 368 |
+
"eval_steps_per_second": 0.362,
|
| 369 |
+
"step": 12960
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.78,
|
| 373 |
+
"grad_norm": 0.3004627525806427,
|
| 374 |
+
"learning_rate": 7.402777513916068e-05,
|
| 375 |
+
"loss": 0.1105,
|
| 376 |
+
"step": 13680
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.78,
|
| 380 |
+
"eval_bertscore": 0.7093863487243652,
|
| 381 |
+
"eval_loss": 0.1068594753742218,
|
| 382 |
+
"eval_rouge1": 0.5386027107080774,
|
| 383 |
+
"eval_rouge2": 0.3174670612173311,
|
| 384 |
+
"eval_rougeL": 0.4089464604886982,
|
| 385 |
+
"eval_rougeLsum": 0.40954043741634194,
|
| 386 |
+
"eval_runtime": 76.1174,
|
| 387 |
+
"eval_samples_per_second": 0.709,
|
| 388 |
+
"eval_steps_per_second": 0.355,
|
| 389 |
+
"step": 13680
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.82,
|
| 393 |
+
"grad_norm": 0.4122227132320404,
|
| 394 |
+
"learning_rate": 7.265991602864905e-05,
|
| 395 |
+
"loss": 0.1094,
|
| 396 |
+
"step": 14400
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.82,
|
| 400 |
+
"eval_bertscore": 0.7156451344490051,
|
| 401 |
+
"eval_loss": 0.10706545412540436,
|
| 402 |
+
"eval_rouge1": 0.5522097394348282,
|
| 403 |
+
"eval_rouge2": 0.3376815877629147,
|
| 404 |
+
"eval_rougeL": 0.41094798705443536,
|
| 405 |
+
"eval_rougeLsum": 0.41185755780524297,
|
| 406 |
+
"eval_runtime": 79.5068,
|
| 407 |
+
"eval_samples_per_second": 0.679,
|
| 408 |
+
"eval_steps_per_second": 0.34,
|
| 409 |
+
"step": 14400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.86,
|
| 413 |
+
"grad_norm": 0.3019055128097534,
|
| 414 |
+
"learning_rate": 7.129205691813743e-05,
|
| 415 |
+
"loss": 0.1047,
|
| 416 |
+
"step": 15120
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.86,
|
| 420 |
+
"eval_bertscore": 0.723181962966919,
|
| 421 |
+
"eval_loss": 0.10513070970773697,
|
| 422 |
+
"eval_rouge1": 0.5597833953895566,
|
| 423 |
+
"eval_rouge2": 0.3368159976094224,
|
| 424 |
+
"eval_rougeL": 0.4251112326345452,
|
| 425 |
+
"eval_rougeLsum": 0.4271018761152323,
|
| 426 |
+
"eval_runtime": 72.9275,
|
| 427 |
+
"eval_samples_per_second": 0.74,
|
| 428 |
+
"eval_steps_per_second": 0.37,
|
| 429 |
+
"step": 15120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9,
|
| 433 |
+
"grad_norm": 0.39543616771698,
|
| 434 |
+
"learning_rate": 6.992609761194597e-05,
|
| 435 |
+
"loss": 0.106,
|
| 436 |
+
"step": 15840
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9,
|
| 440 |
+
"eval_bertscore": 0.7264233231544495,
|
| 441 |
+
"eval_loss": 0.10471142083406448,
|
| 442 |
+
"eval_rouge1": 0.5607444186855683,
|
| 443 |
+
"eval_rouge2": 0.32933852525922336,
|
| 444 |
+
"eval_rougeL": 0.4164104876659622,
|
| 445 |
+
"eval_rougeLsum": 0.4178921783444509,
|
| 446 |
+
"eval_runtime": 79.4632,
|
| 447 |
+
"eval_samples_per_second": 0.68,
|
| 448 |
+
"eval_steps_per_second": 0.34,
|
| 449 |
+
"step": 15840
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.94,
|
| 453 |
+
"grad_norm": 0.17296220362186432,
|
| 454 |
+
"learning_rate": 6.855823850143436e-05,
|
| 455 |
+
"loss": 0.1085,
|
| 456 |
+
"step": 16560
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.94,
|
| 460 |
+
"eval_bertscore": 0.7186797261238098,
|
| 461 |
+
"eval_loss": 0.10288402438163757,
|
| 462 |
+
"eval_rouge1": 0.5499937534452628,
|
| 463 |
+
"eval_rouge2": 0.33202955320606253,
|
| 464 |
+
"eval_rougeL": 0.41109499153735635,
|
| 465 |
+
"eval_rougeLsum": 0.4129325173744952,
|
| 466 |
+
"eval_runtime": 74.2816,
|
| 467 |
+
"eval_samples_per_second": 0.727,
|
| 468 |
+
"eval_steps_per_second": 0.363,
|
| 469 |
+
"step": 16560
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.98,
|
| 473 |
+
"grad_norm": 0.34968239068984985,
|
| 474 |
+
"learning_rate": 6.719037939092274e-05,
|
| 475 |
+
"loss": 0.1064,
|
| 476 |
+
"step": 17280
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.98,
|
| 480 |
+
"eval_bertscore": 0.715437650680542,
|
| 481 |
+
"eval_loss": 0.10678575932979584,
|
| 482 |
+
"eval_rouge1": 0.5487884139639068,
|
| 483 |
+
"eval_rouge2": 0.3287484312214649,
|
| 484 |
+
"eval_rougeL": 0.4115546192599129,
|
| 485 |
+
"eval_rougeLsum": 0.4129129108454481,
|
| 486 |
+
"eval_runtime": 77.9977,
|
| 487 |
+
"eval_samples_per_second": 0.692,
|
| 488 |
+
"eval_steps_per_second": 0.346,
|
| 489 |
+
"step": 17280
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.03,
|
| 493 |
+
"grad_norm": 0.22770258784294128,
|
| 494 |
+
"learning_rate": 6.582252028041113e-05,
|
| 495 |
+
"loss": 0.094,
|
| 496 |
+
"step": 18000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.03,
|
| 500 |
+
"eval_bertscore": 0.7268933653831482,
|
| 501 |
+
"eval_loss": 0.10910864919424057,
|
| 502 |
+
"eval_rouge1": 0.5644640432420631,
|
| 503 |
+
"eval_rouge2": 0.34856910757450765,
|
| 504 |
+
"eval_rougeL": 0.4334348850734425,
|
| 505 |
+
"eval_rougeLsum": 0.4322774316283801,
|
| 506 |
+
"eval_runtime": 70.7723,
|
| 507 |
+
"eval_samples_per_second": 0.763,
|
| 508 |
+
"eval_steps_per_second": 0.382,
|
| 509 |
+
"step": 18000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.07,
|
| 513 |
+
"grad_norm": 0.2036217600107193,
|
| 514 |
+
"learning_rate": 6.44546611698995e-05,
|
| 515 |
+
"loss": 0.0864,
|
| 516 |
+
"step": 18720
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.07,
|
| 520 |
+
"eval_bertscore": 0.7298507690429688,
|
| 521 |
+
"eval_loss": 0.1051657572388649,
|
| 522 |
+
"eval_rouge1": 0.5693416283658175,
|
| 523 |
+
"eval_rouge2": 0.3547090481291705,
|
| 524 |
+
"eval_rougeL": 0.4367412765285528,
|
| 525 |
+
"eval_rougeLsum": 0.4370252833034207,
|
| 526 |
+
"eval_runtime": 74.7048,
|
| 527 |
+
"eval_samples_per_second": 0.723,
|
| 528 |
+
"eval_steps_per_second": 0.361,
|
| 529 |
+
"step": 18720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.11,
|
| 533 |
+
"grad_norm": 0.3400803804397583,
|
| 534 |
+
"learning_rate": 6.308680205938788e-05,
|
| 535 |
+
"loss": 0.0846,
|
| 536 |
+
"step": 19440
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.11,
|
| 540 |
+
"eval_bertscore": 0.7288545966148376,
|
| 541 |
+
"eval_loss": 0.1069113239645958,
|
| 542 |
+
"eval_rouge1": 0.5633722381222108,
|
| 543 |
+
"eval_rouge2": 0.337377454492796,
|
| 544 |
+
"eval_rougeL": 0.4349115421710151,
|
| 545 |
+
"eval_rougeLsum": 0.43561356852158567,
|
| 546 |
+
"eval_runtime": 73.5552,
|
| 547 |
+
"eval_samples_per_second": 0.734,
|
| 548 |
+
"eval_steps_per_second": 0.367,
|
| 549 |
+
"step": 19440
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.15,
|
| 553 |
+
"grad_norm": 0.3360745310783386,
|
| 554 |
+
"learning_rate": 6.172084275319642e-05,
|
| 555 |
+
"loss": 0.0875,
|
| 556 |
+
"step": 20160
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.15,
|
| 560 |
+
"eval_bertscore": 0.715953528881073,
|
| 561 |
+
"eval_loss": 0.10425002127885818,
|
| 562 |
+
"eval_rouge1": 0.5548398737384996,
|
| 563 |
+
"eval_rouge2": 0.33589277481599067,
|
| 564 |
+
"eval_rougeL": 0.42137114864331937,
|
| 565 |
+
"eval_rougeLsum": 0.4231469615029759,
|
| 566 |
+
"eval_runtime": 78.0304,
|
| 567 |
+
"eval_samples_per_second": 0.692,
|
| 568 |
+
"eval_steps_per_second": 0.346,
|
| 569 |
+
"step": 20160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.19,
|
| 573 |
+
"grad_norm": 0.4246189594268799,
|
| 574 |
+
"learning_rate": 6.03529836426848e-05,
|
| 575 |
+
"loss": 0.0868,
|
| 576 |
+
"step": 20880
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.19,
|
| 580 |
+
"eval_bertscore": 0.7299396395683289,
|
| 581 |
+
"eval_loss": 0.10365325212478638,
|
| 582 |
+
"eval_rouge1": 0.5715394315498017,
|
| 583 |
+
"eval_rouge2": 0.34427400662165897,
|
| 584 |
+
"eval_rougeL": 0.433027526044127,
|
| 585 |
+
"eval_rougeLsum": 0.4347450430032858,
|
| 586 |
+
"eval_runtime": 74.0473,
|
| 587 |
+
"eval_samples_per_second": 0.729,
|
| 588 |
+
"eval_steps_per_second": 0.365,
|
| 589 |
+
"step": 20880
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.23,
|
| 593 |
+
"grad_norm": 0.2776849865913391,
|
| 594 |
+
"learning_rate": 5.898512453217319e-05,
|
| 595 |
+
"loss": 0.0854,
|
| 596 |
+
"step": 21600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.23,
|
| 600 |
+
"eval_bertscore": 0.7214290499687195,
|
| 601 |
+
"eval_loss": 0.10122980922460556,
|
| 602 |
+
"eval_rouge1": 0.5565823263453793,
|
| 603 |
+
"eval_rouge2": 0.3393375143994867,
|
| 604 |
+
"eval_rougeL": 0.4156140884756716,
|
| 605 |
+
"eval_rougeLsum": 0.41819540905867203,
|
| 606 |
+
"eval_runtime": 73.2235,
|
| 607 |
+
"eval_samples_per_second": 0.737,
|
| 608 |
+
"eval_steps_per_second": 0.369,
|
| 609 |
+
"step": 21600
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.27,
|
| 613 |
+
"grad_norm": 0.3710538446903229,
|
| 614 |
+
"learning_rate": 5.761726542166157e-05,
|
| 615 |
+
"loss": 0.0845,
|
| 616 |
+
"step": 22320
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.27,
|
| 620 |
+
"eval_bertscore": 0.7201518416404724,
|
| 621 |
+
"eval_loss": 0.10378885269165039,
|
| 622 |
+
"eval_rouge1": 0.5441295123980776,
|
| 623 |
+
"eval_rouge2": 0.33155064058257405,
|
| 624 |
+
"eval_rougeL": 0.42094247090226844,
|
| 625 |
+
"eval_rougeLsum": 0.42274633038817555,
|
| 626 |
+
"eval_runtime": 76.6313,
|
| 627 |
+
"eval_samples_per_second": 0.705,
|
| 628 |
+
"eval_steps_per_second": 0.352,
|
| 629 |
+
"step": 22320
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.31,
|
| 633 |
+
"grad_norm": 0.5819060206413269,
|
| 634 |
+
"learning_rate": 5.624940631114996e-05,
|
| 635 |
+
"loss": 0.0861,
|
| 636 |
+
"step": 23040
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.31,
|
| 640 |
+
"eval_bertscore": 0.7142701148986816,
|
| 641 |
+
"eval_loss": 0.10384026169776917,
|
| 642 |
+
"eval_rouge1": 0.5458184588249984,
|
| 643 |
+
"eval_rouge2": 0.3290922169442115,
|
| 644 |
+
"eval_rougeL": 0.4214855047650181,
|
| 645 |
+
"eval_rougeLsum": 0.4239018723206239,
|
| 646 |
+
"eval_runtime": 79.4541,
|
| 647 |
+
"eval_samples_per_second": 0.68,
|
| 648 |
+
"eval_steps_per_second": 0.34,
|
| 649 |
+
"step": 23040
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.35,
|
| 653 |
+
"grad_norm": 0.2952657639980316,
|
| 654 |
+
"learning_rate": 5.488154720063834e-05,
|
| 655 |
+
"loss": 0.0862,
|
| 656 |
+
"step": 23760
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.35,
|
| 660 |
+
"eval_bertscore": 0.7302463054656982,
|
| 661 |
+
"eval_loss": 0.10171066224575043,
|
| 662 |
+
"eval_rouge1": 0.564237466077122,
|
| 663 |
+
"eval_rouge2": 0.346632021192653,
|
| 664 |
+
"eval_rougeL": 0.44007571581541377,
|
| 665 |
+
"eval_rougeLsum": 0.4408434182223313,
|
| 666 |
+
"eval_runtime": 70.4368,
|
| 667 |
+
"eval_samples_per_second": 0.767,
|
| 668 |
+
"eval_steps_per_second": 0.383,
|
| 669 |
+
"step": 23760
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.4,
|
| 673 |
+
"grad_norm": 0.3152740001678467,
|
| 674 |
+
"learning_rate": 5.351368809012672e-05,
|
| 675 |
+
"loss": 0.0858,
|
| 676 |
+
"step": 24480
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.4,
|
| 680 |
+
"eval_bertscore": 0.7205690741539001,
|
| 681 |
+
"eval_loss": 0.10222817957401276,
|
| 682 |
+
"eval_rouge1": 0.561963492920594,
|
| 683 |
+
"eval_rouge2": 0.3366175149143015,
|
| 684 |
+
"eval_rougeL": 0.4370056834486044,
|
| 685 |
+
"eval_rougeLsum": 0.4383325343921459,
|
| 686 |
+
"eval_runtime": 70.7631,
|
| 687 |
+
"eval_samples_per_second": 0.763,
|
| 688 |
+
"eval_steps_per_second": 0.382,
|
| 689 |
+
"step": 24480
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.44,
|
| 693 |
+
"grad_norm": 0.3384862542152405,
|
| 694 |
+
"learning_rate": 5.214772878393526e-05,
|
| 695 |
+
"loss": 0.0868,
|
| 696 |
+
"step": 25200
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.44,
|
| 700 |
+
"eval_bertscore": 0.7201054096221924,
|
| 701 |
+
"eval_loss": 0.10058918595314026,
|
| 702 |
+
"eval_rouge1": 0.5506843793300468,
|
| 703 |
+
"eval_rouge2": 0.3305447880283259,
|
| 704 |
+
"eval_rougeL": 0.4221671281003694,
|
| 705 |
+
"eval_rougeLsum": 0.42405735392085775,
|
| 706 |
+
"eval_runtime": 73.3661,
|
| 707 |
+
"eval_samples_per_second": 0.736,
|
| 708 |
+
"eval_steps_per_second": 0.368,
|
| 709 |
+
"step": 25200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.48,
|
| 713 |
+
"grad_norm": 0.2858143150806427,
|
| 714 |
+
"learning_rate": 5.078176947774379e-05,
|
| 715 |
+
"loss": 0.0851,
|
| 716 |
+
"step": 25920
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.48,
|
| 720 |
+
"eval_bertscore": 0.7324591875076294,
|
| 721 |
+
"eval_loss": 0.10030569136142731,
|
| 722 |
+
"eval_rouge1": 0.5711881175991272,
|
| 723 |
+
"eval_rouge2": 0.35036140380824915,
|
| 724 |
+
"eval_rougeL": 0.44736244718696055,
|
| 725 |
+
"eval_rougeLsum": 0.44882200145887735,
|
| 726 |
+
"eval_runtime": 73.2375,
|
| 727 |
+
"eval_samples_per_second": 0.737,
|
| 728 |
+
"eval_steps_per_second": 0.369,
|
| 729 |
+
"step": 25920
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.52,
|
| 733 |
+
"grad_norm": 0.34586507081985474,
|
| 734 |
+
"learning_rate": 4.941391036723218e-05,
|
| 735 |
+
"loss": 0.0839,
|
| 736 |
+
"step": 26640
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.52,
|
| 740 |
+
"eval_bertscore": 0.7323827147483826,
|
| 741 |
+
"eval_loss": 0.10078810900449753,
|
| 742 |
+
"eval_rouge1": 0.5643411922408847,
|
| 743 |
+
"eval_rouge2": 0.35335509416724475,
|
| 744 |
+
"eval_rougeL": 0.4412030311945061,
|
| 745 |
+
"eval_rougeLsum": 0.4423071630624772,
|
| 746 |
+
"eval_runtime": 78.0237,
|
| 747 |
+
"eval_samples_per_second": 0.692,
|
| 748 |
+
"eval_steps_per_second": 0.346,
|
| 749 |
+
"step": 26640
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.56,
|
| 753 |
+
"grad_norm": 0.35009488463401794,
|
| 754 |
+
"learning_rate": 4.804605125672056e-05,
|
| 755 |
+
"loss": 0.0843,
|
| 756 |
+
"step": 27360
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.56,
|
| 760 |
+
"eval_bertscore": 0.7391833662986755,
|
| 761 |
+
"eval_loss": 0.09879420697689056,
|
| 762 |
+
"eval_rouge1": 0.5744063451356638,
|
| 763 |
+
"eval_rouge2": 0.3631199161982914,
|
| 764 |
+
"eval_rougeL": 0.44665302719291095,
|
| 765 |
+
"eval_rougeLsum": 0.44897406269269213,
|
| 766 |
+
"eval_runtime": 80.5403,
|
| 767 |
+
"eval_samples_per_second": 0.67,
|
| 768 |
+
"eval_steps_per_second": 0.335,
|
| 769 |
+
"step": 27360
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.6,
|
| 773 |
+
"grad_norm": 0.3002821207046509,
|
| 774 |
+
"learning_rate": 4.667819214620894e-05,
|
| 775 |
+
"loss": 0.085,
|
| 776 |
+
"step": 28080
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.6,
|
| 780 |
+
"eval_bertscore": 0.7407130002975464,
|
| 781 |
+
"eval_loss": 0.09699860215187073,
|
| 782 |
+
"eval_rouge1": 0.5762741233248756,
|
| 783 |
+
"eval_rouge2": 0.3544722421313946,
|
| 784 |
+
"eval_rougeL": 0.4384246085216507,
|
| 785 |
+
"eval_rougeLsum": 0.4390526517186611,
|
| 786 |
+
"eval_runtime": 78.2681,
|
| 787 |
+
"eval_samples_per_second": 0.69,
|
| 788 |
+
"eval_steps_per_second": 0.345,
|
| 789 |
+
"step": 28080
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.64,
|
| 793 |
+
"grad_norm": 0.241718590259552,
|
| 794 |
+
"learning_rate": 4.5310333035697325e-05,
|
| 795 |
+
"loss": 0.0845,
|
| 796 |
+
"step": 28800
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.64,
|
| 800 |
+
"eval_bertscore": 0.7392789125442505,
|
| 801 |
+
"eval_loss": 0.09867523610591888,
|
| 802 |
+
"eval_rouge1": 0.580719658129176,
|
| 803 |
+
"eval_rouge2": 0.3694474172593357,
|
| 804 |
+
"eval_rougeL": 0.456964934995113,
|
| 805 |
+
"eval_rougeLsum": 0.45917370226539334,
|
| 806 |
+
"eval_runtime": 80.3113,
|
| 807 |
+
"eval_samples_per_second": 0.672,
|
| 808 |
+
"eval_steps_per_second": 0.336,
|
| 809 |
+
"step": 28800
|
| 810 |
+
}
|
| 811 |
+
],
|
| 812 |
+
"logging_steps": 720,
|
| 813 |
+
"max_steps": 52638,
|
| 814 |
+
"num_input_tokens_seen": 0,
|
| 815 |
+
"num_train_epochs": 3,
|
| 816 |
+
"save_steps": 2880,
|
| 817 |
+
"total_flos": 2.496482830587003e+17,
|
| 818 |
+
"train_batch_size": 2,
|
| 819 |
+
"trial_name": null,
|
| 820 |
+
"trial_params": null
|
| 821 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8b0fe275c173c3356b48c1b740a2f996b54b571a59ced80218c8b705d57d7cd
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|