Upload folder using huggingface_hub
Browse files- README.md +35 -0
- checkpoint-360/config.json +70 -0
- checkpoint-360/generation_config.json +16 -0
- checkpoint-360/merges.txt +0 -0
- checkpoint-360/model.safetensors +3 -0
- checkpoint-360/optimizer.pt +3 -0
- checkpoint-360/rng_state.pth +3 -0
- checkpoint-360/scheduler.pt +3 -0
- checkpoint-360/special_tokens_map.json +15 -0
- checkpoint-360/tokenizer.json +0 -0
- checkpoint-360/tokenizer_config.json +57 -0
- checkpoint-360/trainer_state.json +420 -0
- checkpoint-360/training_args.bin +3 -0
- checkpoint-360/vocab.json +0 -0
- config.json +70 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Feb05_21-02-32_r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774/events.out.tfevents.1707166953.r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774.57.0 +3 -0
- runs/Feb05_21-02-32_r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774/events.out.tfevents.1707169069.r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774.57.1 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +36 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- text2text-generation
|
| 6 |
+
widget:
|
| 7 |
+
- text: "I love AutoTrain"
|
| 8 |
+
datasets:
|
| 9 |
+
- autotrain-qtwrd-y9iny/autotrain-data
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Seq2Seq
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 0.20580817759037018
|
| 18 |
+
|
| 19 |
+
rouge1: 54.3657
|
| 20 |
+
|
| 21 |
+
rouge2: 43.8004
|
| 22 |
+
|
| 23 |
+
rougeL: 50.056
|
| 24 |
+
|
| 25 |
+
rougeLsum: 53.9699
|
| 26 |
+
|
| 27 |
+
gen_len: 116.6083
|
| 28 |
+
|
| 29 |
+
runtime: 450.7126
|
| 30 |
+
|
| 31 |
+
samples_per_second: 0.266
|
| 32 |
+
|
| 33 |
+
steps_per_second: 0.033
|
| 34 |
+
|
| 35 |
+
: 3.0
|
checkpoint-360/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": "4.37.0",
|
| 68 |
+
"use_cache": false,
|
| 69 |
+
"vocab_size": 50265
|
| 70 |
+
}
|
checkpoint-360/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "4.37.0",
|
| 15 |
+
"use_cache": false
|
| 16 |
+
}
|
checkpoint-360/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-360/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6139316961f7b3663f8c5521299563f94cb822e60c02b3c041bb50af76e1f5a3
|
| 3 |
+
size 1625426996
|
checkpoint-360/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bbf2f061917a398b4f9c6122351dec78c38ef479abab15488b0db442ab06f9
|
| 3 |
+
size 3250759951
|
checkpoint-360/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:365fa914b157eb3811a12e1df5686f71783495c5a5143bcd52ea5d86455f0317
|
| 3 |
+
size 14244
|
checkpoint-360/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb4d389cd2e1eb7be499408b73e5e5839d5839a5ed8cf9cf5528564656615d69
|
| 3 |
+
size 1064
|
checkpoint-360/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-360/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-360/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 |
+
}
|
checkpoint-360/trainer_state.json
ADDED
|
@@ -0,0 +1,420 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.20580817759037018,
|
| 3 |
+
"best_model_checkpoint": "autotrain-qtwrd-y9iny/checkpoint-360",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 360,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 5.555555555555556e-06,
|
| 14 |
+
"loss": 1.6662,
|
| 15 |
+
"step": 6
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1.388888888888889e-05,
|
| 20 |
+
"loss": 1.2219,
|
| 21 |
+
"step": 12
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 26 |
+
"loss": 0.5655,
|
| 27 |
+
"step": 18
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 3.055555555555556e-05,
|
| 32 |
+
"loss": 0.5646,
|
| 33 |
+
"step": 24
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 3.888888888888889e-05,
|
| 38 |
+
"loss": 0.5171,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.3,
|
| 43 |
+
"learning_rate": 4.722222222222222e-05,
|
| 44 |
+
"loss": 0.477,
|
| 45 |
+
"step": 36
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.35,
|
| 49 |
+
"learning_rate": 4.938271604938271e-05,
|
| 50 |
+
"loss": 0.2809,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"learning_rate": 4.845679012345679e-05,
|
| 56 |
+
"loss": 0.4842,
|
| 57 |
+
"step": 48
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.45,
|
| 61 |
+
"learning_rate": 4.7530864197530866e-05,
|
| 62 |
+
"loss": 0.4148,
|
| 63 |
+
"step": 54
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.5,
|
| 67 |
+
"learning_rate": 4.6604938271604945e-05,
|
| 68 |
+
"loss": 0.5962,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.55,
|
| 73 |
+
"learning_rate": 4.567901234567901e-05,
|
| 74 |
+
"loss": 0.2418,
|
| 75 |
+
"step": 66
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.6,
|
| 79 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 80 |
+
"loss": 0.3418,
|
| 81 |
+
"step": 72
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.65,
|
| 85 |
+
"learning_rate": 4.3827160493827164e-05,
|
| 86 |
+
"loss": 0.263,
|
| 87 |
+
"step": 78
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7,
|
| 91 |
+
"learning_rate": 4.290123456790124e-05,
|
| 92 |
+
"loss": 0.3013,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.75,
|
| 97 |
+
"learning_rate": 4.197530864197531e-05,
|
| 98 |
+
"loss": 0.1821,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.8,
|
| 103 |
+
"learning_rate": 4.104938271604938e-05,
|
| 104 |
+
"loss": 0.2559,
|
| 105 |
+
"step": 96
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.85,
|
| 109 |
+
"learning_rate": 4.012345679012346e-05,
|
| 110 |
+
"loss": 0.696,
|
| 111 |
+
"step": 102
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.9,
|
| 115 |
+
"learning_rate": 3.9197530864197535e-05,
|
| 116 |
+
"loss": 0.4992,
|
| 117 |
+
"step": 108
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.95,
|
| 121 |
+
"learning_rate": 3.82716049382716e-05,
|
| 122 |
+
"loss": 0.3305,
|
| 123 |
+
"step": 114
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"learning_rate": 3.734567901234568e-05,
|
| 128 |
+
"loss": 0.1607,
|
| 129 |
+
"step": 120
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_gen_len": 118.7,
|
| 134 |
+
"eval_loss": 0.2715524733066559,
|
| 135 |
+
"eval_rouge1": 48.1918,
|
| 136 |
+
"eval_rouge2": 37.1255,
|
| 137 |
+
"eval_rougeL": 43.0239,
|
| 138 |
+
"eval_rougeLsum": 47.9099,
|
| 139 |
+
"eval_runtime": 451.4323,
|
| 140 |
+
"eval_samples_per_second": 0.266,
|
| 141 |
+
"eval_steps_per_second": 0.033,
|
| 142 |
+
"step": 120
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.05,
|
| 146 |
+
"learning_rate": 3.6419753086419754e-05,
|
| 147 |
+
"loss": 0.1584,
|
| 148 |
+
"step": 126
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.1,
|
| 152 |
+
"learning_rate": 3.5493827160493834e-05,
|
| 153 |
+
"loss": 0.2017,
|
| 154 |
+
"step": 132
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.15,
|
| 158 |
+
"learning_rate": 3.45679012345679e-05,
|
| 159 |
+
"loss": 0.3175,
|
| 160 |
+
"step": 138
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.2,
|
| 164 |
+
"learning_rate": 3.364197530864198e-05,
|
| 165 |
+
"loss": 0.348,
|
| 166 |
+
"step": 144
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.25,
|
| 170 |
+
"learning_rate": 3.271604938271605e-05,
|
| 171 |
+
"loss": 0.2901,
|
| 172 |
+
"step": 150
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.3,
|
| 176 |
+
"learning_rate": 3.1790123456790125e-05,
|
| 177 |
+
"loss": 0.1567,
|
| 178 |
+
"step": 156
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.35,
|
| 182 |
+
"learning_rate": 3.08641975308642e-05,
|
| 183 |
+
"loss": 0.236,
|
| 184 |
+
"step": 162
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4,
|
| 188 |
+
"learning_rate": 2.993827160493827e-05,
|
| 189 |
+
"loss": 0.2284,
|
| 190 |
+
"step": 168
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.45,
|
| 194 |
+
"learning_rate": 2.9012345679012347e-05,
|
| 195 |
+
"loss": 0.2008,
|
| 196 |
+
"step": 174
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5,
|
| 200 |
+
"learning_rate": 2.8086419753086424e-05,
|
| 201 |
+
"loss": 0.1082,
|
| 202 |
+
"step": 180
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.55,
|
| 206 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 207 |
+
"loss": 0.3563,
|
| 208 |
+
"step": 186
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6,
|
| 212 |
+
"learning_rate": 2.623456790123457e-05,
|
| 213 |
+
"loss": 0.1463,
|
| 214 |
+
"step": 192
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.65,
|
| 218 |
+
"learning_rate": 2.5308641975308646e-05,
|
| 219 |
+
"loss": 0.1531,
|
| 220 |
+
"step": 198
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.7,
|
| 224 |
+
"learning_rate": 2.438271604938272e-05,
|
| 225 |
+
"loss": 0.1886,
|
| 226 |
+
"step": 204
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.75,
|
| 230 |
+
"learning_rate": 2.345679012345679e-05,
|
| 231 |
+
"loss": 0.1699,
|
| 232 |
+
"step": 210
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.8,
|
| 236 |
+
"learning_rate": 2.2530864197530865e-05,
|
| 237 |
+
"loss": 0.2024,
|
| 238 |
+
"step": 216
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.85,
|
| 242 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 243 |
+
"loss": 0.12,
|
| 244 |
+
"step": 222
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.9,
|
| 248 |
+
"learning_rate": 2.0679012345679014e-05,
|
| 249 |
+
"loss": 0.1441,
|
| 250 |
+
"step": 228
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.95,
|
| 254 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 255 |
+
"loss": 0.1217,
|
| 256 |
+
"step": 234
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.0,
|
| 260 |
+
"learning_rate": 1.8827160493827163e-05,
|
| 261 |
+
"loss": 0.2564,
|
| 262 |
+
"step": 240
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.0,
|
| 266 |
+
"eval_gen_len": 115.3167,
|
| 267 |
+
"eval_loss": 0.2248244434595108,
|
| 268 |
+
"eval_rouge1": 52.3593,
|
| 269 |
+
"eval_rouge2": 39.8513,
|
| 270 |
+
"eval_rougeL": 47.1605,
|
| 271 |
+
"eval_rougeLsum": 52.1913,
|
| 272 |
+
"eval_runtime": 451.0124,
|
| 273 |
+
"eval_samples_per_second": 0.266,
|
| 274 |
+
"eval_steps_per_second": 0.033,
|
| 275 |
+
"step": 240
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.05,
|
| 279 |
+
"learning_rate": 1.7901234567901236e-05,
|
| 280 |
+
"loss": 0.1657,
|
| 281 |
+
"step": 246
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.1,
|
| 285 |
+
"learning_rate": 1.697530864197531e-05,
|
| 286 |
+
"loss": 0.0853,
|
| 287 |
+
"step": 252
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.15,
|
| 291 |
+
"learning_rate": 1.604938271604938e-05,
|
| 292 |
+
"loss": 0.2708,
|
| 293 |
+
"step": 258
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.2,
|
| 297 |
+
"learning_rate": 1.5123456790123458e-05,
|
| 298 |
+
"loss": 0.0697,
|
| 299 |
+
"step": 264
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.25,
|
| 303 |
+
"learning_rate": 1.419753086419753e-05,
|
| 304 |
+
"loss": 0.2495,
|
| 305 |
+
"step": 270
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.3,
|
| 309 |
+
"learning_rate": 1.3271604938271605e-05,
|
| 310 |
+
"loss": 0.1598,
|
| 311 |
+
"step": 276
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.35,
|
| 315 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 316 |
+
"loss": 0.0863,
|
| 317 |
+
"step": 282
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.4,
|
| 321 |
+
"learning_rate": 1.1419753086419753e-05,
|
| 322 |
+
"loss": 0.067,
|
| 323 |
+
"step": 288
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.45,
|
| 327 |
+
"learning_rate": 1.0493827160493827e-05,
|
| 328 |
+
"loss": 0.1219,
|
| 329 |
+
"step": 294
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.5,
|
| 333 |
+
"learning_rate": 9.5679012345679e-06,
|
| 334 |
+
"loss": 0.1327,
|
| 335 |
+
"step": 300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.55,
|
| 339 |
+
"learning_rate": 8.641975308641975e-06,
|
| 340 |
+
"loss": 0.0823,
|
| 341 |
+
"step": 306
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.6,
|
| 345 |
+
"learning_rate": 7.71604938271605e-06,
|
| 346 |
+
"loss": 0.0862,
|
| 347 |
+
"step": 312
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.65,
|
| 351 |
+
"learning_rate": 6.790123456790123e-06,
|
| 352 |
+
"loss": 0.0591,
|
| 353 |
+
"step": 318
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.7,
|
| 357 |
+
"learning_rate": 5.864197530864198e-06,
|
| 358 |
+
"loss": 0.0881,
|
| 359 |
+
"step": 324
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.75,
|
| 363 |
+
"learning_rate": 4.938271604938272e-06,
|
| 364 |
+
"loss": 0.0518,
|
| 365 |
+
"step": 330
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.8,
|
| 369 |
+
"learning_rate": 4.012345679012345e-06,
|
| 370 |
+
"loss": 0.0701,
|
| 371 |
+
"step": 336
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.85,
|
| 375 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 376 |
+
"loss": 0.0682,
|
| 377 |
+
"step": 342
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.9,
|
| 381 |
+
"learning_rate": 2.1604938271604937e-06,
|
| 382 |
+
"loss": 0.06,
|
| 383 |
+
"step": 348
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.95,
|
| 387 |
+
"learning_rate": 1.234567901234568e-06,
|
| 388 |
+
"loss": 0.1058,
|
| 389 |
+
"step": 354
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"learning_rate": 3.08641975308642e-07,
|
| 394 |
+
"loss": 0.088,
|
| 395 |
+
"step": 360
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.0,
|
| 399 |
+
"eval_gen_len": 116.6083,
|
| 400 |
+
"eval_loss": 0.20580817759037018,
|
| 401 |
+
"eval_rouge1": 54.3657,
|
| 402 |
+
"eval_rouge2": 43.8004,
|
| 403 |
+
"eval_rougeL": 50.056,
|
| 404 |
+
"eval_rougeLsum": 53.9699,
|
| 405 |
+
"eval_runtime": 450.9703,
|
| 406 |
+
"eval_samples_per_second": 0.266,
|
| 407 |
+
"eval_steps_per_second": 0.033,
|
| 408 |
+
"step": 360
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"logging_steps": 6,
|
| 412 |
+
"max_steps": 360,
|
| 413 |
+
"num_input_tokens_seen": 0,
|
| 414 |
+
"num_train_epochs": 3,
|
| 415 |
+
"save_steps": 500,
|
| 416 |
+
"total_flos": 3000639907577856.0,
|
| 417 |
+
"train_batch_size": 4,
|
| 418 |
+
"trial_name": null,
|
| 419 |
+
"trial_params": null
|
| 420 |
+
}
|
checkpoint-360/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a069c8bea62138487a2ca8a1c187260270aa7f29a979fb313cd3e0031da2992
|
| 3 |
+
size 4920
|
checkpoint-360/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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": "4.37.0",
|
| 68 |
+
"use_cache": false,
|
| 69 |
+
"vocab_size": 50265
|
| 70 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "4.37.0",
|
| 15 |
+
"use_cache": false
|
| 16 |
+
}
|
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 sha256:6139316961f7b3663f8c5521299563f94cb822e60c02b3c041bb50af76e1f5a3
|
| 3 |
+
size 1625426996
|
runs/Feb05_21-02-32_r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774/events.out.tfevents.1707166953.r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774.57.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8b141822bbc84e6a84d5d2b302ce5fe196992a2570c100b88305bcb791c4d8e
|
| 3 |
+
size 16812
|
runs/Feb05_21-02-32_r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774/events.out.tfevents.1707169069.r-pruhtopia-toc-generation-5fv7gfun-9f108-4r774.57.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56c611b0a85e2eb11beb8d08dace6e71f39018f15332bf33a4a6c2e1cf562252
|
| 3 |
+
size 613
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a069c8bea62138487a2ca8a1c187260270aa7f29a979fb313cd3e0031da2992
|
| 3 |
+
size 4920
|
training_params.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-qtwrd-y9iny/autotrain-data",
|
| 3 |
+
"model": "facebook/bart-large-cnn",
|
| 4 |
+
"username": "pruhtopia",
|
| 5 |
+
"seed": 42,
|
| 6 |
+
"train_split": "train",
|
| 7 |
+
"valid_split": "validation",
|
| 8 |
+
"project_name": "autotrain-qtwrd-y9iny",
|
| 9 |
+
"push_to_hub": true,
|
| 10 |
+
"text_column": "autotrain_text",
|
| 11 |
+
"target_column": "autotrain_label",
|
| 12 |
+
"repo_id": "pruhtopia/autotrain-qtwrd-y9iny",
|
| 13 |
+
"lr": 5e-05,
|
| 14 |
+
"epochs": 3,
|
| 15 |
+
"max_seq_length": 1024,
|
| 16 |
+
"max_target_length": 512,
|
| 17 |
+
"batch_size": 4,
|
| 18 |
+
"warmup_ratio": 0.1,
|
| 19 |
+
"gradient_accumulation": 1,
|
| 20 |
+
"optimizer": "adamw_torch",
|
| 21 |
+
"scheduler": "linear",
|
| 22 |
+
"weight_decay": 0.0,
|
| 23 |
+
"max_grad_norm": 1.0,
|
| 24 |
+
"logging_steps": -1,
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"auto_find_batch_size": false,
|
| 27 |
+
"mixed_precision": "fp16",
|
| 28 |
+
"save_total_limit": 1,
|
| 29 |
+
"save_strategy": "epoch",
|
| 30 |
+
"peft": false,
|
| 31 |
+
"quantization": null,
|
| 32 |
+
"lora_r": 16,
|
| 33 |
+
"lora_alpha": 32,
|
| 34 |
+
"lora_dropout": 0.05,
|
| 35 |
+
"target_modules": []
|
| 36 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|