Initial commit of fine-tuned model
Browse files- checkpoint-8000/config.json +77 -0
- checkpoint-8000/generation_config.json +16 -0
- checkpoint-8000/merges.txt +0 -0
- checkpoint-8000/model.safetensors +3 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/rng_state.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/special_tokens_map.json +51 -0
- checkpoint-8000/tokenizer.json +0 -0
- checkpoint-8000/tokenizer_config.json +57 -0
- checkpoint-8000/trainer_state.json +153 -0
- checkpoint-8000/training_args.bin +3 -0
- checkpoint-8000/vocab.json +0 -0
- checkpoint-8500/config.json +77 -0
- checkpoint-8500/generation_config.json +16 -0
- checkpoint-8500/merges.txt +0 -0
- checkpoint-8500/model.safetensors +3 -0
- checkpoint-8500/optimizer.pt +3 -0
- checkpoint-8500/rng_state.pth +3 -0
- checkpoint-8500/scheduler.pt +3 -0
- checkpoint-8500/special_tokens_map.json +51 -0
- checkpoint-8500/tokenizer.json +0 -0
- checkpoint-8500/tokenizer_config.json +57 -0
- checkpoint-8500/trainer_state.json +168 -0
- checkpoint-8500/training_args.bin +3 -0
- checkpoint-8500/vocab.json +0 -0
- checkpoint-8960/config.json +77 -0
- checkpoint-8960/generation_config.json +16 -0
- checkpoint-8960/merges.txt +0 -0
- checkpoint-8960/model.safetensors +3 -0
- checkpoint-8960/optimizer.pt +3 -0
- checkpoint-8960/rng_state.pth +3 -0
- checkpoint-8960/scheduler.pt +3 -0
- checkpoint-8960/special_tokens_map.json +51 -0
- checkpoint-8960/tokenizer.json +0 -0
- checkpoint-8960/tokenizer_config.json +57 -0
- checkpoint-8960/trainer_state.json +168 -0
- checkpoint-8960/training_args.bin +3 -0
- checkpoint-8960/vocab.json +0 -0
- config.json +77 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.json +0 -0
checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"extra_pos_embeddings": 2,
|
| 29 |
+
"force_bos_token_to_be_generated": true,
|
| 30 |
+
"forced_bos_token_id": 0,
|
| 31 |
+
"forced_eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 2.0,
|
| 46 |
+
"max_length": 142,
|
| 47 |
+
"max_position_embeddings": 1024,
|
| 48 |
+
"min_length": 56,
|
| 49 |
+
"model_type": "bart",
|
| 50 |
+
"no_repeat_ngram_size": 3,
|
| 51 |
+
"normalize_before": false,
|
| 52 |
+
"normalize_embedding": true,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"output_past": true,
|
| 56 |
+
"pad_token_id": 1,
|
| 57 |
+
"prefix": " ",
|
| 58 |
+
"replacing_rate": 0,
|
| 59 |
+
"scale_embedding": false,
|
| 60 |
+
"static_position_embeddings": false,
|
| 61 |
+
"student_decoder_layers": null,
|
| 62 |
+
"student_encoder_layers": null,
|
| 63 |
+
"task_specific_params": {
|
| 64 |
+
"summarization": {
|
| 65 |
+
"early_stopping": true,
|
| 66 |
+
"length_penalty": 2.0,
|
| 67 |
+
"max_length": 142,
|
| 68 |
+
"min_length": 56,
|
| 69 |
+
"no_repeat_ngram_size": 3,
|
| 70 |
+
"num_beams": 4
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.42.4",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 50264
|
| 77 |
+
}
|
checkpoint-8000/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 142,
|
| 11 |
+
"min_length": 56,
|
| 12 |
+
"no_repeat_ngram_size": 3,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.42.4"
|
| 16 |
+
}
|
checkpoint-8000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e4fcfa72dbe9bad2502c473350f403c767d5ec09a399f5bdd0dd19bcd1ac0f
|
| 3 |
+
size 1222284056
|
checkpoint-8000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b0eb7e3c6f59269c005c0169933c5c75e2b0bbbc8c2a53364ec4aa5c74e782a
|
| 3 |
+
size 2444380155
|
checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e3a3d0fb34f09937b081a09f2e5cb797f53eff47deca2f80172ab23568cc363
|
| 3 |
+
size 14244
|
checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9532630c96738824825ac7a6bbe822276d93800a9c086f542d8dcbb22223023
|
| 3 |
+
size 1064
|
checkpoint-8000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-8000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8000/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-8000/trainer_state.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.928571428571429,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.934483289718628,
|
| 14 |
+
"learning_rate": 4.5e-05,
|
| 15 |
+
"loss": 1.344,
|
| 16 |
+
"step": 896
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.1773991584777832,
|
| 21 |
+
"eval_runtime": 45.1328,
|
| 22 |
+
"eval_samples_per_second": 17.659,
|
| 23 |
+
"eval_steps_per_second": 2.216,
|
| 24 |
+
"step": 896
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"grad_norm": 3.3010060787200928,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9285,
|
| 31 |
+
"step": 1792
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 1.191049575805664,
|
| 36 |
+
"eval_runtime": 45.2481,
|
| 37 |
+
"eval_samples_per_second": 17.614,
|
| 38 |
+
"eval_steps_per_second": 2.21,
|
| 39 |
+
"step": 1792
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"grad_norm": 3.7312071323394775,
|
| 44 |
+
"learning_rate": 3.5e-05,
|
| 45 |
+
"loss": 0.6776,
|
| 46 |
+
"step": 2688
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_loss": 1.2539539337158203,
|
| 51 |
+
"eval_runtime": 45.1707,
|
| 52 |
+
"eval_samples_per_second": 17.644,
|
| 53 |
+
"eval_steps_per_second": 2.214,
|
| 54 |
+
"step": 2688
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"grad_norm": 2.9814953804016113,
|
| 59 |
+
"learning_rate": 3e-05,
|
| 60 |
+
"loss": 0.4907,
|
| 61 |
+
"step": 3584
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 4.0,
|
| 65 |
+
"eval_loss": 1.3984911441802979,
|
| 66 |
+
"eval_runtime": 45.1857,
|
| 67 |
+
"eval_samples_per_second": 17.638,
|
| 68 |
+
"eval_steps_per_second": 2.213,
|
| 69 |
+
"step": 3584
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"grad_norm": 3.6583733558654785,
|
| 74 |
+
"learning_rate": 2.5e-05,
|
| 75 |
+
"loss": 0.3517,
|
| 76 |
+
"step": 4480
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.0,
|
| 80 |
+
"eval_loss": 1.5196635723114014,
|
| 81 |
+
"eval_runtime": 45.2303,
|
| 82 |
+
"eval_samples_per_second": 17.621,
|
| 83 |
+
"eval_steps_per_second": 2.211,
|
| 84 |
+
"step": 4480
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"grad_norm": 3.3650012016296387,
|
| 89 |
+
"learning_rate": 2e-05,
|
| 90 |
+
"loss": 0.2463,
|
| 91 |
+
"step": 5376
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"eval_loss": 1.6338224411010742,
|
| 96 |
+
"eval_runtime": 45.23,
|
| 97 |
+
"eval_samples_per_second": 17.621,
|
| 98 |
+
"eval_steps_per_second": 2.211,
|
| 99 |
+
"step": 5376
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"grad_norm": 2.788938283920288,
|
| 104 |
+
"learning_rate": 1.5e-05,
|
| 105 |
+
"loss": 0.1731,
|
| 106 |
+
"step": 6272
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 7.0,
|
| 110 |
+
"eval_loss": 1.7133498191833496,
|
| 111 |
+
"eval_runtime": 45.1963,
|
| 112 |
+
"eval_samples_per_second": 17.634,
|
| 113 |
+
"eval_steps_per_second": 2.213,
|
| 114 |
+
"step": 6272
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"grad_norm": 1.9669969081878662,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 0.1241,
|
| 121 |
+
"step": 7168
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_loss": 1.7768992185592651,
|
| 126 |
+
"eval_runtime": 45.2465,
|
| 127 |
+
"eval_samples_per_second": 17.615,
|
| 128 |
+
"eval_steps_per_second": 2.21,
|
| 129 |
+
"step": 7168
|
| 130 |
+
}
|
| 131 |
+
],
|
| 132 |
+
"logging_steps": 500,
|
| 133 |
+
"max_steps": 8960,
|
| 134 |
+
"num_input_tokens_seen": 0,
|
| 135 |
+
"num_train_epochs": 10,
|
| 136 |
+
"save_steps": 500,
|
| 137 |
+
"stateful_callbacks": {
|
| 138 |
+
"TrainerControl": {
|
| 139 |
+
"args": {
|
| 140 |
+
"should_epoch_stop": false,
|
| 141 |
+
"should_evaluate": false,
|
| 142 |
+
"should_log": false,
|
| 143 |
+
"should_save": true,
|
| 144 |
+
"should_training_stop": false
|
| 145 |
+
},
|
| 146 |
+
"attributes": {}
|
| 147 |
+
}
|
| 148 |
+
},
|
| 149 |
+
"total_flos": 4.9533186736128e+16,
|
| 150 |
+
"train_batch_size": 8,
|
| 151 |
+
"trial_name": null,
|
| 152 |
+
"trial_params": null
|
| 153 |
+
}
|
checkpoint-8000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:969e2e6a2dd189d7886d7b9eff22362746cca61f8f7ed129d2a784d8e3e14965
|
| 3 |
+
size 5048
|
checkpoint-8000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8500/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"extra_pos_embeddings": 2,
|
| 29 |
+
"force_bos_token_to_be_generated": true,
|
| 30 |
+
"forced_bos_token_id": 0,
|
| 31 |
+
"forced_eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 2.0,
|
| 46 |
+
"max_length": 142,
|
| 47 |
+
"max_position_embeddings": 1024,
|
| 48 |
+
"min_length": 56,
|
| 49 |
+
"model_type": "bart",
|
| 50 |
+
"no_repeat_ngram_size": 3,
|
| 51 |
+
"normalize_before": false,
|
| 52 |
+
"normalize_embedding": true,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"output_past": true,
|
| 56 |
+
"pad_token_id": 1,
|
| 57 |
+
"prefix": " ",
|
| 58 |
+
"replacing_rate": 0,
|
| 59 |
+
"scale_embedding": false,
|
| 60 |
+
"static_position_embeddings": false,
|
| 61 |
+
"student_decoder_layers": null,
|
| 62 |
+
"student_encoder_layers": null,
|
| 63 |
+
"task_specific_params": {
|
| 64 |
+
"summarization": {
|
| 65 |
+
"early_stopping": true,
|
| 66 |
+
"length_penalty": 2.0,
|
| 67 |
+
"max_length": 142,
|
| 68 |
+
"min_length": 56,
|
| 69 |
+
"no_repeat_ngram_size": 3,
|
| 70 |
+
"num_beams": 4
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.42.4",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 50264
|
| 77 |
+
}
|
checkpoint-8500/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 142,
|
| 11 |
+
"min_length": 56,
|
| 12 |
+
"no_repeat_ngram_size": 3,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.42.4"
|
| 16 |
+
}
|
checkpoint-8500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81574555a42f3cb0e7a2973391d267f2edb24d58521e102bb2477bd0cc80e84c
|
| 3 |
+
size 1222284056
|
checkpoint-8500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8cfa6aeb4160375f2a319f9497c08da9c2b700aa054fb81c11bebf755cb7180
|
| 3 |
+
size 2444380155
|
checkpoint-8500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d2561b35c7a0c38a6729ae98412a296e6234c151eb0ec5dc40f4cd7802e60de
|
| 3 |
+
size 14244
|
checkpoint-8500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ba980037a926daa469432ced043fb0007aba3439310f606e1d0d9b14540f616
|
| 3 |
+
size 1064
|
checkpoint-8500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-8500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8500/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-8500/trainer_state.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.486607142857142,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.934483289718628,
|
| 14 |
+
"learning_rate": 4.5e-05,
|
| 15 |
+
"loss": 1.344,
|
| 16 |
+
"step": 896
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.1773991584777832,
|
| 21 |
+
"eval_runtime": 45.1328,
|
| 22 |
+
"eval_samples_per_second": 17.659,
|
| 23 |
+
"eval_steps_per_second": 2.216,
|
| 24 |
+
"step": 896
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"grad_norm": 3.3010060787200928,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9285,
|
| 31 |
+
"step": 1792
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 1.191049575805664,
|
| 36 |
+
"eval_runtime": 45.2481,
|
| 37 |
+
"eval_samples_per_second": 17.614,
|
| 38 |
+
"eval_steps_per_second": 2.21,
|
| 39 |
+
"step": 1792
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"grad_norm": 3.7312071323394775,
|
| 44 |
+
"learning_rate": 3.5e-05,
|
| 45 |
+
"loss": 0.6776,
|
| 46 |
+
"step": 2688
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_loss": 1.2539539337158203,
|
| 51 |
+
"eval_runtime": 45.1707,
|
| 52 |
+
"eval_samples_per_second": 17.644,
|
| 53 |
+
"eval_steps_per_second": 2.214,
|
| 54 |
+
"step": 2688
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"grad_norm": 2.9814953804016113,
|
| 59 |
+
"learning_rate": 3e-05,
|
| 60 |
+
"loss": 0.4907,
|
| 61 |
+
"step": 3584
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 4.0,
|
| 65 |
+
"eval_loss": 1.3984911441802979,
|
| 66 |
+
"eval_runtime": 45.1857,
|
| 67 |
+
"eval_samples_per_second": 17.638,
|
| 68 |
+
"eval_steps_per_second": 2.213,
|
| 69 |
+
"step": 3584
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"grad_norm": 3.6583733558654785,
|
| 74 |
+
"learning_rate": 2.5e-05,
|
| 75 |
+
"loss": 0.3517,
|
| 76 |
+
"step": 4480
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.0,
|
| 80 |
+
"eval_loss": 1.5196635723114014,
|
| 81 |
+
"eval_runtime": 45.2303,
|
| 82 |
+
"eval_samples_per_second": 17.621,
|
| 83 |
+
"eval_steps_per_second": 2.211,
|
| 84 |
+
"step": 4480
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"grad_norm": 3.3650012016296387,
|
| 89 |
+
"learning_rate": 2e-05,
|
| 90 |
+
"loss": 0.2463,
|
| 91 |
+
"step": 5376
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"eval_loss": 1.6338224411010742,
|
| 96 |
+
"eval_runtime": 45.23,
|
| 97 |
+
"eval_samples_per_second": 17.621,
|
| 98 |
+
"eval_steps_per_second": 2.211,
|
| 99 |
+
"step": 5376
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"grad_norm": 2.788938283920288,
|
| 104 |
+
"learning_rate": 1.5e-05,
|
| 105 |
+
"loss": 0.1731,
|
| 106 |
+
"step": 6272
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 7.0,
|
| 110 |
+
"eval_loss": 1.7133498191833496,
|
| 111 |
+
"eval_runtime": 45.1963,
|
| 112 |
+
"eval_samples_per_second": 17.634,
|
| 113 |
+
"eval_steps_per_second": 2.213,
|
| 114 |
+
"step": 6272
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"grad_norm": 1.9669969081878662,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 0.1241,
|
| 121 |
+
"step": 7168
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_loss": 1.7768992185592651,
|
| 126 |
+
"eval_runtime": 45.2465,
|
| 127 |
+
"eval_samples_per_second": 17.615,
|
| 128 |
+
"eval_steps_per_second": 2.21,
|
| 129 |
+
"step": 7168
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.0,
|
| 133 |
+
"grad_norm": 2.556154489517212,
|
| 134 |
+
"learning_rate": 5e-06,
|
| 135 |
+
"loss": 0.091,
|
| 136 |
+
"step": 8064
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"eval_loss": 1.8283599615097046,
|
| 141 |
+
"eval_runtime": 45.1614,
|
| 142 |
+
"eval_samples_per_second": 17.648,
|
| 143 |
+
"eval_steps_per_second": 2.214,
|
| 144 |
+
"step": 8064
|
| 145 |
+
}
|
| 146 |
+
],
|
| 147 |
+
"logging_steps": 500,
|
| 148 |
+
"max_steps": 8960,
|
| 149 |
+
"num_input_tokens_seen": 0,
|
| 150 |
+
"num_train_epochs": 10,
|
| 151 |
+
"save_steps": 500,
|
| 152 |
+
"stateful_callbacks": {
|
| 153 |
+
"TrainerControl": {
|
| 154 |
+
"args": {
|
| 155 |
+
"should_epoch_stop": false,
|
| 156 |
+
"should_evaluate": false,
|
| 157 |
+
"should_log": false,
|
| 158 |
+
"should_save": true,
|
| 159 |
+
"should_training_stop": false
|
| 160 |
+
},
|
| 161 |
+
"attributes": {}
|
| 162 |
+
}
|
| 163 |
+
},
|
| 164 |
+
"total_flos": 5.2629010907136e+16,
|
| 165 |
+
"train_batch_size": 8,
|
| 166 |
+
"trial_name": null,
|
| 167 |
+
"trial_params": null
|
| 168 |
+
}
|
checkpoint-8500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:969e2e6a2dd189d7886d7b9eff22362746cca61f8f7ed129d2a784d8e3e14965
|
| 3 |
+
size 5048
|
checkpoint-8500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8960/config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"extra_pos_embeddings": 2,
|
| 29 |
+
"force_bos_token_to_be_generated": true,
|
| 30 |
+
"forced_bos_token_id": 0,
|
| 31 |
+
"forced_eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 2.0,
|
| 46 |
+
"max_length": 142,
|
| 47 |
+
"max_position_embeddings": 1024,
|
| 48 |
+
"min_length": 56,
|
| 49 |
+
"model_type": "bart",
|
| 50 |
+
"no_repeat_ngram_size": 3,
|
| 51 |
+
"normalize_before": false,
|
| 52 |
+
"normalize_embedding": true,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"output_past": true,
|
| 56 |
+
"pad_token_id": 1,
|
| 57 |
+
"prefix": " ",
|
| 58 |
+
"replacing_rate": 0,
|
| 59 |
+
"scale_embedding": false,
|
| 60 |
+
"static_position_embeddings": false,
|
| 61 |
+
"student_decoder_layers": null,
|
| 62 |
+
"student_encoder_layers": null,
|
| 63 |
+
"task_specific_params": {
|
| 64 |
+
"summarization": {
|
| 65 |
+
"early_stopping": true,
|
| 66 |
+
"length_penalty": 2.0,
|
| 67 |
+
"max_length": 142,
|
| 68 |
+
"min_length": 56,
|
| 69 |
+
"no_repeat_ngram_size": 3,
|
| 70 |
+
"num_beams": 4
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.42.4",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 50264
|
| 77 |
+
}
|
checkpoint-8960/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 142,
|
| 11 |
+
"min_length": 56,
|
| 12 |
+
"no_repeat_ngram_size": 3,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.42.4"
|
| 16 |
+
}
|
checkpoint-8960/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8960/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aef3280005f74825b3f858277ef1fc26287db9f410c50ab8471ad4213e9325a
|
| 3 |
+
size 1222284056
|
checkpoint-8960/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c9d8436ec5bd0671b6551c3bcceee4b4266bd9bb750b71971eb3e9c9cdbdc49
|
| 3 |
+
size 2444380155
|
checkpoint-8960/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f6fe9acc20773616ddd83462119037dc64fa1352c36bce5ee39368d63631ad
|
| 3 |
+
size 14244
|
checkpoint-8960/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:582a9ccfc35d10c0270e3c2c15beffc96824c6588b34f83b318c0620f149c996
|
| 3 |
+
size 1064
|
checkpoint-8960/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-8960/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8960/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-8960/trainer_state.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8960,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.934483289718628,
|
| 14 |
+
"learning_rate": 4.5e-05,
|
| 15 |
+
"loss": 1.344,
|
| 16 |
+
"step": 896
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 1.1773991584777832,
|
| 21 |
+
"eval_runtime": 45.1328,
|
| 22 |
+
"eval_samples_per_second": 17.659,
|
| 23 |
+
"eval_steps_per_second": 2.216,
|
| 24 |
+
"step": 896
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"grad_norm": 3.3010060787200928,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.9285,
|
| 31 |
+
"step": 1792
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 1.191049575805664,
|
| 36 |
+
"eval_runtime": 45.2481,
|
| 37 |
+
"eval_samples_per_second": 17.614,
|
| 38 |
+
"eval_steps_per_second": 2.21,
|
| 39 |
+
"step": 1792
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"grad_norm": 3.7312071323394775,
|
| 44 |
+
"learning_rate": 3.5e-05,
|
| 45 |
+
"loss": 0.6776,
|
| 46 |
+
"step": 2688
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.0,
|
| 50 |
+
"eval_loss": 1.2539539337158203,
|
| 51 |
+
"eval_runtime": 45.1707,
|
| 52 |
+
"eval_samples_per_second": 17.644,
|
| 53 |
+
"eval_steps_per_second": 2.214,
|
| 54 |
+
"step": 2688
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"grad_norm": 2.9814953804016113,
|
| 59 |
+
"learning_rate": 3e-05,
|
| 60 |
+
"loss": 0.4907,
|
| 61 |
+
"step": 3584
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 4.0,
|
| 65 |
+
"eval_loss": 1.3984911441802979,
|
| 66 |
+
"eval_runtime": 45.1857,
|
| 67 |
+
"eval_samples_per_second": 17.638,
|
| 68 |
+
"eval_steps_per_second": 2.213,
|
| 69 |
+
"step": 3584
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"grad_norm": 3.6583733558654785,
|
| 74 |
+
"learning_rate": 2.5e-05,
|
| 75 |
+
"loss": 0.3517,
|
| 76 |
+
"step": 4480
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.0,
|
| 80 |
+
"eval_loss": 1.5196635723114014,
|
| 81 |
+
"eval_runtime": 45.2303,
|
| 82 |
+
"eval_samples_per_second": 17.621,
|
| 83 |
+
"eval_steps_per_second": 2.211,
|
| 84 |
+
"step": 4480
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"grad_norm": 3.3650012016296387,
|
| 89 |
+
"learning_rate": 2e-05,
|
| 90 |
+
"loss": 0.2463,
|
| 91 |
+
"step": 5376
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"eval_loss": 1.6338224411010742,
|
| 96 |
+
"eval_runtime": 45.23,
|
| 97 |
+
"eval_samples_per_second": 17.621,
|
| 98 |
+
"eval_steps_per_second": 2.211,
|
| 99 |
+
"step": 5376
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"grad_norm": 2.788938283920288,
|
| 104 |
+
"learning_rate": 1.5e-05,
|
| 105 |
+
"loss": 0.1731,
|
| 106 |
+
"step": 6272
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 7.0,
|
| 110 |
+
"eval_loss": 1.7133498191833496,
|
| 111 |
+
"eval_runtime": 45.1963,
|
| 112 |
+
"eval_samples_per_second": 17.634,
|
| 113 |
+
"eval_steps_per_second": 2.213,
|
| 114 |
+
"step": 6272
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"grad_norm": 1.9669969081878662,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 0.1241,
|
| 121 |
+
"step": 7168
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_loss": 1.7768992185592651,
|
| 126 |
+
"eval_runtime": 45.2465,
|
| 127 |
+
"eval_samples_per_second": 17.615,
|
| 128 |
+
"eval_steps_per_second": 2.21,
|
| 129 |
+
"step": 7168
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.0,
|
| 133 |
+
"grad_norm": 2.556154489517212,
|
| 134 |
+
"learning_rate": 5e-06,
|
| 135 |
+
"loss": 0.091,
|
| 136 |
+
"step": 8064
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"eval_loss": 1.8283599615097046,
|
| 141 |
+
"eval_runtime": 45.1614,
|
| 142 |
+
"eval_samples_per_second": 17.648,
|
| 143 |
+
"eval_steps_per_second": 2.214,
|
| 144 |
+
"step": 8064
|
| 145 |
+
}
|
| 146 |
+
],
|
| 147 |
+
"logging_steps": 500,
|
| 148 |
+
"max_steps": 8960,
|
| 149 |
+
"num_input_tokens_seen": 0,
|
| 150 |
+
"num_train_epochs": 10,
|
| 151 |
+
"save_steps": 500,
|
| 152 |
+
"stateful_callbacks": {
|
| 153 |
+
"TrainerControl": {
|
| 154 |
+
"args": {
|
| 155 |
+
"should_epoch_stop": false,
|
| 156 |
+
"should_evaluate": false,
|
| 157 |
+
"should_log": false,
|
| 158 |
+
"should_save": true,
|
| 159 |
+
"should_training_stop": true
|
| 160 |
+
},
|
| 161 |
+
"attributes": {}
|
| 162 |
+
}
|
| 163 |
+
},
|
| 164 |
+
"total_flos": 5.547716914446336e+16,
|
| 165 |
+
"train_batch_size": 8,
|
| 166 |
+
"trial_name": null,
|
| 167 |
+
"trial_params": null
|
| 168 |
+
}
|
checkpoint-8960/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:969e2e6a2dd189d7886d7b9eff22362746cca61f8f7ed129d2a784d8e3e14965
|
| 3 |
+
size 5048
|
checkpoint-8960/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"extra_pos_embeddings": 2,
|
| 29 |
+
"force_bos_token_to_be_generated": true,
|
| 30 |
+
"forced_bos_token_id": 0,
|
| 31 |
+
"forced_eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"length_penalty": 2.0,
|
| 46 |
+
"max_length": 142,
|
| 47 |
+
"max_position_embeddings": 1024,
|
| 48 |
+
"min_length": 56,
|
| 49 |
+
"model_type": "bart",
|
| 50 |
+
"no_repeat_ngram_size": 3,
|
| 51 |
+
"normalize_before": false,
|
| 52 |
+
"normalize_embedding": true,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"output_past": true,
|
| 56 |
+
"pad_token_id": 1,
|
| 57 |
+
"prefix": " ",
|
| 58 |
+
"replacing_rate": 0,
|
| 59 |
+
"scale_embedding": false,
|
| 60 |
+
"static_position_embeddings": false,
|
| 61 |
+
"student_decoder_layers": null,
|
| 62 |
+
"student_encoder_layers": null,
|
| 63 |
+
"task_specific_params": {
|
| 64 |
+
"summarization": {
|
| 65 |
+
"early_stopping": true,
|
| 66 |
+
"length_penalty": 2.0,
|
| 67 |
+
"max_length": 142,
|
| 68 |
+
"min_length": 56,
|
| 69 |
+
"no_repeat_ngram_size": 3,
|
| 70 |
+
"num_beams": 4
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.42.4",
|
| 75 |
+
"use_cache": true,
|
| 76 |
+
"vocab_size": 50264
|
| 77 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 142,
|
| 11 |
+
"min_length": 56,
|
| 12 |
+
"no_repeat_ngram_size": 3,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.42.4"
|
| 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 sha256:3aef3280005f74825b3f858277ef1fc26287db9f410c50ab8471ad4213e9325a
|
| 3 |
+
size 1222284056
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|