Upload folder using huggingface_hub
Browse files- checkpoint-28000/config.json +75 -0
- checkpoint-28000/generation_config.json +13 -0
- checkpoint-28000/merges.txt +0 -0
- checkpoint-28000/model.safetensors +3 -0
- checkpoint-28000/optimizer.pt +3 -0
- checkpoint-28000/rng_state.pth +3 -0
- checkpoint-28000/scheduler.pt +3 -0
- checkpoint-28000/special_tokens_map.json +15 -0
- checkpoint-28000/tokenizer.json +0 -0
- checkpoint-28000/tokenizer_config.json +57 -0
- checkpoint-28000/trainer_state.json +537 -0
- checkpoint-28000/training_args.bin +3 -0
- checkpoint-28000/vocab.json +0 -0
- config.json +75 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-28000/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 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": 0,
|
| 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": 2,
|
| 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": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 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": 1,
|
| 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 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.44.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
checkpoint-28000/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.44.2"
|
| 13 |
+
}
|
checkpoint-28000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-28000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eb379ff69f0841bae403808b9e09ba0f61178a3691b911184daeb37e01d5ef7
|
| 3 |
+
size 557912620
|
checkpoint-28000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4496a306f07804ab73593846f344e540f81cb9983a62cada9793a2c76e8ae765
|
| 3 |
+
size 1115579898
|
checkpoint-28000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c11218fe0750100712655a1bd4d36f2d748ed6c55ac670a50fc4ff1688d6da
|
| 3 |
+
size 14244
|
checkpoint-28000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:804a3a1759941c27027c7ee1563007ee340be0b2328c340ddb1a3de21490700a
|
| 3 |
+
size 1064
|
checkpoint-28000/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 |
+
}
|
checkpoint-28000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-28000/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": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-28000/trainer_state.json
ADDED
|
@@ -0,0 +1,537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7608290314674377,
|
| 3 |
+
"best_model_checkpoint": "models/bart-base-summary-v1/checkpoint-28000",
|
| 4 |
+
"epoch": 9.431578947368422,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 28000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16842105263157894,
|
| 13 |
+
"grad_norm": 2.8360345363616943,
|
| 14 |
+
"learning_rate": 3.355795148247979e-06,
|
| 15 |
+
"loss": 2.661,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3368421052631579,
|
| 20 |
+
"grad_norm": 2.307560682296753,
|
| 21 |
+
"learning_rate": 6.718328840970351e-06,
|
| 22 |
+
"loss": 1.7672,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5052631578947369,
|
| 27 |
+
"grad_norm": 2.249586582183838,
|
| 28 |
+
"learning_rate": 1.0087601078167117e-05,
|
| 29 |
+
"loss": 1.5549,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.6736842105263158,
|
| 34 |
+
"grad_norm": 2.347072124481201,
|
| 35 |
+
"learning_rate": 1.3456873315363883e-05,
|
| 36 |
+
"loss": 1.4346,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.6736842105263158,
|
| 41 |
+
"eval_loss": 1.1874284744262695,
|
| 42 |
+
"eval_runtime": 12.0215,
|
| 43 |
+
"eval_samples_per_second": 415.922,
|
| 44 |
+
"eval_steps_per_second": 51.99,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.8421052631578947,
|
| 49 |
+
"grad_norm": 2.1872618198394775,
|
| 50 |
+
"learning_rate": 1.682614555256065e-05,
|
| 51 |
+
"loss": 1.3456,
|
| 52 |
+
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.0105263157894737,
|
| 56 |
+
"grad_norm": 2.077637195587158,
|
| 57 |
+
"learning_rate": 1.9978286912249178e-05,
|
| 58 |
+
"loss": 1.2792,
|
| 59 |
+
"step": 3000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.1789473684210527,
|
| 63 |
+
"grad_norm": 2.0131642818450928,
|
| 64 |
+
"learning_rate": 1.9603923330338425e-05,
|
| 65 |
+
"loss": 1.2074,
|
| 66 |
+
"step": 3500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.3473684210526315,
|
| 70 |
+
"grad_norm": 2.1782569885253906,
|
| 71 |
+
"learning_rate": 1.9229559748427674e-05,
|
| 72 |
+
"loss": 1.1684,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.3473684210526315,
|
| 77 |
+
"eval_loss": 1.0076570510864258,
|
| 78 |
+
"eval_runtime": 11.7862,
|
| 79 |
+
"eval_samples_per_second": 424.225,
|
| 80 |
+
"eval_steps_per_second": 53.028,
|
| 81 |
+
"step": 4000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.5157894736842106,
|
| 85 |
+
"grad_norm": 2.0057213306427,
|
| 86 |
+
"learning_rate": 1.8855196166516924e-05,
|
| 87 |
+
"loss": 1.1353,
|
| 88 |
+
"step": 4500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.6842105263157894,
|
| 92 |
+
"grad_norm": 2.027010440826416,
|
| 93 |
+
"learning_rate": 1.848083258460617e-05,
|
| 94 |
+
"loss": 1.1059,
|
| 95 |
+
"step": 5000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.8526315789473684,
|
| 99 |
+
"grad_norm": 1.936415672302246,
|
| 100 |
+
"learning_rate": 1.810646900269542e-05,
|
| 101 |
+
"loss": 1.0878,
|
| 102 |
+
"step": 5500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.0210526315789474,
|
| 106 |
+
"grad_norm": 1.950352668762207,
|
| 107 |
+
"learning_rate": 1.7732105420784667e-05,
|
| 108 |
+
"loss": 1.0663,
|
| 109 |
+
"step": 6000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.0210526315789474,
|
| 113 |
+
"eval_loss": 0.9253098368644714,
|
| 114 |
+
"eval_runtime": 11.7756,
|
| 115 |
+
"eval_samples_per_second": 424.607,
|
| 116 |
+
"eval_steps_per_second": 53.076,
|
| 117 |
+
"step": 6000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.1894736842105265,
|
| 121 |
+
"grad_norm": 1.8735631704330444,
|
| 122 |
+
"learning_rate": 1.7357741838873916e-05,
|
| 123 |
+
"loss": 1.0237,
|
| 124 |
+
"step": 6500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.3578947368421055,
|
| 128 |
+
"grad_norm": 1.7945765256881714,
|
| 129 |
+
"learning_rate": 1.6983378256963163e-05,
|
| 130 |
+
"loss": 1.0127,
|
| 131 |
+
"step": 7000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.526315789473684,
|
| 135 |
+
"grad_norm": 2.2172329425811768,
|
| 136 |
+
"learning_rate": 1.6609014675052412e-05,
|
| 137 |
+
"loss": 1.0038,
|
| 138 |
+
"step": 7500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.694736842105263,
|
| 142 |
+
"grad_norm": 1.7735260725021362,
|
| 143 |
+
"learning_rate": 1.623465109314166e-05,
|
| 144 |
+
"loss": 0.988,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.694736842105263,
|
| 149 |
+
"eval_loss": 0.8785091638565063,
|
| 150 |
+
"eval_runtime": 11.813,
|
| 151 |
+
"eval_samples_per_second": 423.262,
|
| 152 |
+
"eval_steps_per_second": 52.908,
|
| 153 |
+
"step": 8000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.863157894736842,
|
| 157 |
+
"grad_norm": 1.850122094154358,
|
| 158 |
+
"learning_rate": 1.586028751123091e-05,
|
| 159 |
+
"loss": 0.9798,
|
| 160 |
+
"step": 8500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 3.031578947368421,
|
| 164 |
+
"grad_norm": 1.89518404006958,
|
| 165 |
+
"learning_rate": 1.5485923929320158e-05,
|
| 166 |
+
"loss": 0.9645,
|
| 167 |
+
"step": 9000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.2,
|
| 171 |
+
"grad_norm": 1.878665566444397,
|
| 172 |
+
"learning_rate": 1.5112309074573225e-05,
|
| 173 |
+
"loss": 0.9366,
|
| 174 |
+
"step": 9500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.3684210526315788,
|
| 178 |
+
"grad_norm": 1.7754616737365723,
|
| 179 |
+
"learning_rate": 1.4737945492662475e-05,
|
| 180 |
+
"loss": 0.9317,
|
| 181 |
+
"step": 10000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 3.3684210526315788,
|
| 185 |
+
"eval_loss": 0.8507896661758423,
|
| 186 |
+
"eval_runtime": 11.8019,
|
| 187 |
+
"eval_samples_per_second": 423.66,
|
| 188 |
+
"eval_steps_per_second": 52.958,
|
| 189 |
+
"step": 10000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.536842105263158,
|
| 193 |
+
"grad_norm": 1.9295374155044556,
|
| 194 |
+
"learning_rate": 1.4363581910751723e-05,
|
| 195 |
+
"loss": 0.9223,
|
| 196 |
+
"step": 10500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.705263157894737,
|
| 200 |
+
"grad_norm": 1.8295032978057861,
|
| 201 |
+
"learning_rate": 1.3989218328840973e-05,
|
| 202 |
+
"loss": 0.9177,
|
| 203 |
+
"step": 11000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.873684210526316,
|
| 207 |
+
"grad_norm": 1.687798023223877,
|
| 208 |
+
"learning_rate": 1.3614854746930219e-05,
|
| 209 |
+
"loss": 0.9163,
|
| 210 |
+
"step": 11500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.042105263157895,
|
| 214 |
+
"grad_norm": 1.712350845336914,
|
| 215 |
+
"learning_rate": 1.3240491165019469e-05,
|
| 216 |
+
"loss": 0.9007,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 4.042105263157895,
|
| 221 |
+
"eval_loss": 0.8287107348442078,
|
| 222 |
+
"eval_runtime": 11.8057,
|
| 223 |
+
"eval_samples_per_second": 423.525,
|
| 224 |
+
"eval_steps_per_second": 52.941,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.2105263157894735,
|
| 229 |
+
"grad_norm": 1.898863434791565,
|
| 230 |
+
"learning_rate": 1.2866876310272537e-05,
|
| 231 |
+
"loss": 0.8817,
|
| 232 |
+
"step": 12500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.378947368421053,
|
| 236 |
+
"grad_norm": 1.781389832496643,
|
| 237 |
+
"learning_rate": 1.2492512728361785e-05,
|
| 238 |
+
"loss": 0.8752,
|
| 239 |
+
"step": 13000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.5473684210526315,
|
| 243 |
+
"grad_norm": 1.86565101146698,
|
| 244 |
+
"learning_rate": 1.2118149146451035e-05,
|
| 245 |
+
"loss": 0.8751,
|
| 246 |
+
"step": 13500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.715789473684211,
|
| 250 |
+
"grad_norm": 1.7370086908340454,
|
| 251 |
+
"learning_rate": 1.1743785564540281e-05,
|
| 252 |
+
"loss": 0.8724,
|
| 253 |
+
"step": 14000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 4.715789473684211,
|
| 257 |
+
"eval_loss": 0.8084099888801575,
|
| 258 |
+
"eval_runtime": 11.7759,
|
| 259 |
+
"eval_samples_per_second": 424.596,
|
| 260 |
+
"eval_steps_per_second": 53.074,
|
| 261 |
+
"step": 14000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.88421052631579,
|
| 265 |
+
"grad_norm": 1.718099594116211,
|
| 266 |
+
"learning_rate": 1.1369421982629531e-05,
|
| 267 |
+
"loss": 0.87,
|
| 268 |
+
"step": 14500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.052631578947368,
|
| 272 |
+
"grad_norm": 1.727287769317627,
|
| 273 |
+
"learning_rate": 1.099505840071878e-05,
|
| 274 |
+
"loss": 0.8601,
|
| 275 |
+
"step": 15000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.221052631578948,
|
| 279 |
+
"grad_norm": 1.7727770805358887,
|
| 280 |
+
"learning_rate": 1.0621443545971848e-05,
|
| 281 |
+
"loss": 0.8401,
|
| 282 |
+
"step": 15500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.389473684210526,
|
| 286 |
+
"grad_norm": 1.6627490520477295,
|
| 287 |
+
"learning_rate": 1.0247079964061098e-05,
|
| 288 |
+
"loss": 0.8422,
|
| 289 |
+
"step": 16000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.389473684210526,
|
| 293 |
+
"eval_loss": 0.7975589632987976,
|
| 294 |
+
"eval_runtime": 11.7734,
|
| 295 |
+
"eval_samples_per_second": 424.686,
|
| 296 |
+
"eval_steps_per_second": 53.086,
|
| 297 |
+
"step": 16000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.557894736842105,
|
| 301 |
+
"grad_norm": 1.753895878791809,
|
| 302 |
+
"learning_rate": 9.872716382150344e-06,
|
| 303 |
+
"loss": 0.8364,
|
| 304 |
+
"step": 16500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 5.726315789473684,
|
| 308 |
+
"grad_norm": 1.7738673686981201,
|
| 309 |
+
"learning_rate": 9.498352800239594e-06,
|
| 310 |
+
"loss": 0.8361,
|
| 311 |
+
"step": 17000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 5.894736842105263,
|
| 315 |
+
"grad_norm": 1.815612554550171,
|
| 316 |
+
"learning_rate": 9.123989218328842e-06,
|
| 317 |
+
"loss": 0.8325,
|
| 318 |
+
"step": 17500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 6.063157894736842,
|
| 322 |
+
"grad_norm": 1.816428542137146,
|
| 323 |
+
"learning_rate": 8.74962563641809e-06,
|
| 324 |
+
"loss": 0.8238,
|
| 325 |
+
"step": 18000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 6.063157894736842,
|
| 329 |
+
"eval_loss": 0.7852381467819214,
|
| 330 |
+
"eval_runtime": 11.9756,
|
| 331 |
+
"eval_samples_per_second": 417.515,
|
| 332 |
+
"eval_steps_per_second": 52.189,
|
| 333 |
+
"step": 18000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.231578947368421,
|
| 337 |
+
"grad_norm": 1.736885905265808,
|
| 338 |
+
"learning_rate": 8.37601078167116e-06,
|
| 339 |
+
"loss": 0.8135,
|
| 340 |
+
"step": 18500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 6.4,
|
| 344 |
+
"grad_norm": 1.9003022909164429,
|
| 345 |
+
"learning_rate": 8.001647199760408e-06,
|
| 346 |
+
"loss": 0.81,
|
| 347 |
+
"step": 19000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 6.568421052631579,
|
| 351 |
+
"grad_norm": 1.7985416650772095,
|
| 352 |
+
"learning_rate": 7.627283617849657e-06,
|
| 353 |
+
"loss": 0.8118,
|
| 354 |
+
"step": 19500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 6.7368421052631575,
|
| 358 |
+
"grad_norm": 1.7737785577774048,
|
| 359 |
+
"learning_rate": 7.252920035938904e-06,
|
| 360 |
+
"loss": 0.8105,
|
| 361 |
+
"step": 20000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 6.7368421052631575,
|
| 365 |
+
"eval_loss": 0.7769207954406738,
|
| 366 |
+
"eval_runtime": 11.7906,
|
| 367 |
+
"eval_samples_per_second": 424.066,
|
| 368 |
+
"eval_steps_per_second": 53.008,
|
| 369 |
+
"step": 20000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.905263157894737,
|
| 373 |
+
"grad_norm": 1.8330082893371582,
|
| 374 |
+
"learning_rate": 6.8793051811919745e-06,
|
| 375 |
+
"loss": 0.8055,
|
| 376 |
+
"step": 20500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 7.073684210526316,
|
| 380 |
+
"grad_norm": 1.733942985534668,
|
| 381 |
+
"learning_rate": 6.5049415992812226e-06,
|
| 382 |
+
"loss": 0.8011,
|
| 383 |
+
"step": 21000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.242105263157895,
|
| 387 |
+
"grad_norm": 1.7954128980636597,
|
| 388 |
+
"learning_rate": 6.130578017370471e-06,
|
| 389 |
+
"loss": 0.7906,
|
| 390 |
+
"step": 21500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 7.410526315789474,
|
| 394 |
+
"grad_norm": 1.7851158380508423,
|
| 395 |
+
"learning_rate": 5.7562144354597195e-06,
|
| 396 |
+
"loss": 0.7917,
|
| 397 |
+
"step": 22000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 7.410526315789474,
|
| 401 |
+
"eval_loss": 0.7711201310157776,
|
| 402 |
+
"eval_runtime": 11.7828,
|
| 403 |
+
"eval_samples_per_second": 424.347,
|
| 404 |
+
"eval_steps_per_second": 53.043,
|
| 405 |
+
"step": 22000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 7.578947368421053,
|
| 409 |
+
"grad_norm": 1.695130705833435,
|
| 410 |
+
"learning_rate": 5.3818508535489676e-06,
|
| 411 |
+
"loss": 0.7864,
|
| 412 |
+
"step": 22500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 7.747368421052632,
|
| 416 |
+
"grad_norm": 1.779215931892395,
|
| 417 |
+
"learning_rate": 5.007487271638215e-06,
|
| 418 |
+
"loss": 0.7882,
|
| 419 |
+
"step": 23000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.91578947368421,
|
| 423 |
+
"grad_norm": 1.6731973886489868,
|
| 424 |
+
"learning_rate": 4.633123689727464e-06,
|
| 425 |
+
"loss": 0.7879,
|
| 426 |
+
"step": 23500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 8.08421052631579,
|
| 430 |
+
"grad_norm": 1.685503602027893,
|
| 431 |
+
"learning_rate": 4.258760107816712e-06,
|
| 432 |
+
"loss": 0.7799,
|
| 433 |
+
"step": 24000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 8.08421052631579,
|
| 437 |
+
"eval_loss": 0.7651861310005188,
|
| 438 |
+
"eval_runtime": 11.8098,
|
| 439 |
+
"eval_samples_per_second": 423.378,
|
| 440 |
+
"eval_steps_per_second": 52.922,
|
| 441 |
+
"step": 24000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.25263157894737,
|
| 445 |
+
"grad_norm": 1.9109100103378296,
|
| 446 |
+
"learning_rate": 3.88439652590596e-06,
|
| 447 |
+
"loss": 0.7761,
|
| 448 |
+
"step": 24500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 8.421052631578947,
|
| 452 |
+
"grad_norm": 1.7145105600357056,
|
| 453 |
+
"learning_rate": 3.5100329439952087e-06,
|
| 454 |
+
"loss": 0.7737,
|
| 455 |
+
"step": 25000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 8.589473684210526,
|
| 459 |
+
"grad_norm": 1.7552852630615234,
|
| 460 |
+
"learning_rate": 3.1356693620844567e-06,
|
| 461 |
+
"loss": 0.7765,
|
| 462 |
+
"step": 25500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 8.757894736842106,
|
| 466 |
+
"grad_norm": 1.7488547563552856,
|
| 467 |
+
"learning_rate": 2.761305780173705e-06,
|
| 468 |
+
"loss": 0.7716,
|
| 469 |
+
"step": 26000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 8.757894736842106,
|
| 473 |
+
"eval_loss": 0.7634322047233582,
|
| 474 |
+
"eval_runtime": 12.0663,
|
| 475 |
+
"eval_samples_per_second": 414.379,
|
| 476 |
+
"eval_steps_per_second": 51.797,
|
| 477 |
+
"step": 26000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 8.926315789473684,
|
| 481 |
+
"grad_norm": 1.7470569610595703,
|
| 482 |
+
"learning_rate": 2.3869421982629533e-06,
|
| 483 |
+
"loss": 0.7712,
|
| 484 |
+
"step": 26500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 9.094736842105263,
|
| 488 |
+
"grad_norm": 1.717542290687561,
|
| 489 |
+
"learning_rate": 2.013327343516023e-06,
|
| 490 |
+
"loss": 0.7681,
|
| 491 |
+
"step": 27000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.263157894736842,
|
| 495 |
+
"grad_norm": 1.7589292526245117,
|
| 496 |
+
"learning_rate": 1.6397124887690927e-06,
|
| 497 |
+
"loss": 0.7637,
|
| 498 |
+
"step": 27500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 9.431578947368422,
|
| 502 |
+
"grad_norm": 1.8123559951782227,
|
| 503 |
+
"learning_rate": 1.265348906858341e-06,
|
| 504 |
+
"loss": 0.7663,
|
| 505 |
+
"step": 28000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 9.431578947368422,
|
| 509 |
+
"eval_loss": 0.7608290314674377,
|
| 510 |
+
"eval_runtime": 11.8041,
|
| 511 |
+
"eval_samples_per_second": 423.582,
|
| 512 |
+
"eval_steps_per_second": 52.948,
|
| 513 |
+
"step": 28000
|
| 514 |
+
}
|
| 515 |
+
],
|
| 516 |
+
"logging_steps": 500,
|
| 517 |
+
"max_steps": 29680,
|
| 518 |
+
"num_input_tokens_seen": 0,
|
| 519 |
+
"num_train_epochs": 10,
|
| 520 |
+
"save_steps": 2000,
|
| 521 |
+
"stateful_callbacks": {
|
| 522 |
+
"TrainerControl": {
|
| 523 |
+
"args": {
|
| 524 |
+
"should_epoch_stop": false,
|
| 525 |
+
"should_evaluate": false,
|
| 526 |
+
"should_log": false,
|
| 527 |
+
"should_save": true,
|
| 528 |
+
"should_training_stop": false
|
| 529 |
+
},
|
| 530 |
+
"attributes": {}
|
| 531 |
+
}
|
| 532 |
+
},
|
| 533 |
+
"total_flos": 5.413865017946112e+17,
|
| 534 |
+
"train_batch_size": 8,
|
| 535 |
+
"trial_name": null,
|
| 536 |
+
"trial_params": null
|
| 537 |
+
}
|
checkpoint-28000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8694dd337e7b3fbd2dfddfe02df545dcf78839ed25090937d7dc2158d5a1bb12
|
| 3 |
+
size 5176
|
checkpoint-28000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 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": 0,
|
| 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": 2,
|
| 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": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 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": 1,
|
| 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 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.44.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.44.2"
|
| 13 |
+
}
|
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 sha256:1eb379ff69f0841bae403808b9e09ba0f61178a3691b911184daeb37e01d5ef7
|
| 3 |
+
size 557912620
|
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": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8694dd337e7b3fbd2dfddfe02df545dcf78839ed25090937d7dc2158d5a1bb12
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|