Upload folder using huggingface_hub
Browse files- config.json +69 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +212 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LED_Legal/checkpoint-2464",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"LEDForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attention_window": [
|
| 11 |
+
1024,
|
| 12 |
+
1024,
|
| 13 |
+
1024,
|
| 14 |
+
1024,
|
| 15 |
+
1024,
|
| 16 |
+
1024,
|
| 17 |
+
1024,
|
| 18 |
+
1024,
|
| 19 |
+
1024,
|
| 20 |
+
1024,
|
| 21 |
+
1024,
|
| 22 |
+
1024
|
| 23 |
+
],
|
| 24 |
+
"bos_token_id": 0,
|
| 25 |
+
"classif_dropout": 0.0,
|
| 26 |
+
"classifier_dropout": 0.0,
|
| 27 |
+
"d_model": 1024,
|
| 28 |
+
"decoder_attention_heads": 16,
|
| 29 |
+
"decoder_ffn_dim": 4096,
|
| 30 |
+
"decoder_layerdrop": 0.0,
|
| 31 |
+
"decoder_layers": 12,
|
| 32 |
+
"decoder_start_token_id": 2,
|
| 33 |
+
"dropout": 0.1,
|
| 34 |
+
"early_stopping": null,
|
| 35 |
+
"encoder_attention_heads": 16,
|
| 36 |
+
"encoder_ffn_dim": 4096,
|
| 37 |
+
"encoder_layerdrop": 0.0,
|
| 38 |
+
"encoder_layers": 12,
|
| 39 |
+
"eos_token_id": 2,
|
| 40 |
+
"gradient_checkpointing": false,
|
| 41 |
+
"id2label": {
|
| 42 |
+
"0": "LABEL_0",
|
| 43 |
+
"1": "LABEL_1",
|
| 44 |
+
"2": "LABEL_2"
|
| 45 |
+
},
|
| 46 |
+
"init_std": 0.02,
|
| 47 |
+
"is_encoder_decoder": true,
|
| 48 |
+
"label2id": {
|
| 49 |
+
"LABEL_0": 0,
|
| 50 |
+
"LABEL_1": 1,
|
| 51 |
+
"LABEL_2": 2
|
| 52 |
+
},
|
| 53 |
+
"length_penalty": null,
|
| 54 |
+
"max_decoder_position_embeddings": 1024,
|
| 55 |
+
"max_encoder_position_embeddings": 16384,
|
| 56 |
+
"max_length": null,
|
| 57 |
+
"min_length": null,
|
| 58 |
+
"model_type": "led",
|
| 59 |
+
"no_repeat_ngram_size": null,
|
| 60 |
+
"num_beams": null,
|
| 61 |
+
"num_hidden_layers": 12,
|
| 62 |
+
"output_past": false,
|
| 63 |
+
"pad_token_id": 1,
|
| 64 |
+
"prefix": " ",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.48.2",
|
| 67 |
+
"use_cache": true,
|
| 68 |
+
"vocab_size": 50265
|
| 69 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"length_penalty": 2.0,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"min_length": 100,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.2"
|
| 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 sha256:87fdb0b9f1f5f57ba581a0148710eeefde0d5bd6dd70357baf5c8c4b849e5b80
|
| 3 |
+
size 1839478364
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:690adafd3facfde869ce9addf2bfeb858f6f29dfe0154d9f208ad52b33b5942b
|
| 3 |
+
size 3678901863
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71a15ef88792665b655241190f3cbbc2ef54548c87f0f39c7c94d3e32025b2fd
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4c85b5a36bf713d51ab092ce307694364aaa468de20cd6099160b7c34e9d029
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 16384,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "LEDTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3770,
|
| 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 |
+
"eval_gen_len": 114.58,
|
| 14 |
+
"eval_loss": 2.4033706188201904,
|
| 15 |
+
"eval_rouge1": 0.3258037600187694,
|
| 16 |
+
"eval_rouge2": 0.08003474229428373,
|
| 17 |
+
"eval_rougeL": 0.20739237956049256,
|
| 18 |
+
"eval_rougeLsum": 0.2230784420688168,
|
| 19 |
+
"eval_runtime": 989.0997,
|
| 20 |
+
"eval_samples_per_second": 1.011,
|
| 21 |
+
"eval_steps_per_second": 0.064,
|
| 22 |
+
"step": 377
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.3262599469496021,
|
| 26 |
+
"grad_norm": 3.424102306365967,
|
| 27 |
+
"learning_rate": 2.8726803935335058e-06,
|
| 28 |
+
"loss": 2.5193,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_gen_len": 113.452,
|
| 34 |
+
"eval_loss": 2.340730905532837,
|
| 35 |
+
"eval_rouge1": 0.32476949134280386,
|
| 36 |
+
"eval_rouge2": 0.07874634827290394,
|
| 37 |
+
"eval_rougeL": 0.21000147880278136,
|
| 38 |
+
"eval_rougeLsum": 0.22603538175456714,
|
| 39 |
+
"eval_runtime": 997.6459,
|
| 40 |
+
"eval_samples_per_second": 1.002,
|
| 41 |
+
"eval_steps_per_second": 0.063,
|
| 42 |
+
"step": 754
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.6525198938992043,
|
| 46 |
+
"grad_norm": 3.1680996417999268,
|
| 47 |
+
"learning_rate": 2.510489126644959e-06,
|
| 48 |
+
"loss": 2.3392,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"eval_gen_len": 112.564,
|
| 54 |
+
"eval_loss": 2.3039560317993164,
|
| 55 |
+
"eval_rouge1": 0.32059271290891156,
|
| 56 |
+
"eval_rouge2": 0.07500377265811553,
|
| 57 |
+
"eval_rougeL": 0.20560349340841416,
|
| 58 |
+
"eval_rougeLsum": 0.21866034362863596,
|
| 59 |
+
"eval_runtime": 1134.6335,
|
| 60 |
+
"eval_samples_per_second": 0.881,
|
| 61 |
+
"eval_steps_per_second": 0.056,
|
| 62 |
+
"step": 1131
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.9787798408488064,
|
| 66 |
+
"grad_norm": 3.4218506813049316,
|
| 67 |
+
"learning_rate": 1.976582554006042e-06,
|
| 68 |
+
"loss": 2.2626,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_gen_len": 113.102,
|
| 74 |
+
"eval_loss": 2.2713050842285156,
|
| 75 |
+
"eval_rouge1": 0.3188878832812406,
|
| 76 |
+
"eval_rouge2": 0.07552561950583175,
|
| 77 |
+
"eval_rougeL": 0.20580794751959977,
|
| 78 |
+
"eval_rougeLsum": 0.21840355661823818,
|
| 79 |
+
"eval_runtime": 1342.8107,
|
| 80 |
+
"eval_samples_per_second": 0.745,
|
| 81 |
+
"eval_steps_per_second": 0.047,
|
| 82 |
+
"step": 1508
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.0,
|
| 86 |
+
"eval_gen_len": 108.076,
|
| 87 |
+
"eval_loss": 2.2622933387756348,
|
| 88 |
+
"eval_rouge1": 0.3220955459492587,
|
| 89 |
+
"eval_rouge2": 0.07576255906806914,
|
| 90 |
+
"eval_rougeL": 0.2069475588748002,
|
| 91 |
+
"eval_rougeLsum": 0.21979050526677296,
|
| 92 |
+
"eval_runtime": 1537.4132,
|
| 93 |
+
"eval_samples_per_second": 0.65,
|
| 94 |
+
"eval_steps_per_second": 0.041,
|
| 95 |
+
"step": 1885
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 5.305039787798409,
|
| 99 |
+
"grad_norm": 3.1164140701293945,
|
| 100 |
+
"learning_rate": 1.3602064545876772e-06,
|
| 101 |
+
"loss": 2.209,
|
| 102 |
+
"step": 2000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 6.0,
|
| 106 |
+
"eval_gen_len": 111.277,
|
| 107 |
+
"eval_loss": 2.247816801071167,
|
| 108 |
+
"eval_rouge1": 0.31907757245587076,
|
| 109 |
+
"eval_rouge2": 0.07415047575742183,
|
| 110 |
+
"eval_rougeL": 0.20518250100183638,
|
| 111 |
+
"eval_rougeLsum": 0.21723476148216042,
|
| 112 |
+
"eval_runtime": 1624.5789,
|
| 113 |
+
"eval_samples_per_second": 0.616,
|
| 114 |
+
"eval_steps_per_second": 0.039,
|
| 115 |
+
"step": 2262
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 6.63129973474801,
|
| 119 |
+
"grad_norm": 3.0489401817321777,
|
| 120 |
+
"learning_rate": 7.677498585764536e-07,
|
| 121 |
+
"loss": 2.1706,
|
| 122 |
+
"step": 2500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_gen_len": 108.655,
|
| 127 |
+
"eval_loss": 2.2410194873809814,
|
| 128 |
+
"eval_rouge1": 0.32212385903573537,
|
| 129 |
+
"eval_rouge2": 0.07536919970473052,
|
| 130 |
+
"eval_rougeL": 0.20648069011418652,
|
| 131 |
+
"eval_rougeLsum": 0.21908203834574824,
|
| 132 |
+
"eval_runtime": 1614.3024,
|
| 133 |
+
"eval_samples_per_second": 0.619,
|
| 134 |
+
"eval_steps_per_second": 0.039,
|
| 135 |
+
"step": 2639
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 7.957559681697613,
|
| 139 |
+
"grad_norm": 3.88566517829895,
|
| 140 |
+
"learning_rate": 3.005855977799911e-07,
|
| 141 |
+
"loss": 2.1506,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"eval_gen_len": 108.303,
|
| 147 |
+
"eval_loss": 2.2375478744506836,
|
| 148 |
+
"eval_rouge1": 0.32285486927261353,
|
| 149 |
+
"eval_rouge2": 0.0742826049179253,
|
| 150 |
+
"eval_rougeL": 0.20526480763464744,
|
| 151 |
+
"eval_rougeLsum": 0.21783648885941626,
|
| 152 |
+
"eval_runtime": 1614.4824,
|
| 153 |
+
"eval_samples_per_second": 0.619,
|
| 154 |
+
"eval_steps_per_second": 0.039,
|
| 155 |
+
"step": 3016
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 9.0,
|
| 159 |
+
"eval_gen_len": 108.217,
|
| 160 |
+
"eval_loss": 2.236407995223999,
|
| 161 |
+
"eval_rouge1": 0.32342426871285435,
|
| 162 |
+
"eval_rouge2": 0.0748472633333527,
|
| 163 |
+
"eval_rougeL": 0.20594698388820035,
|
| 164 |
+
"eval_rougeLsum": 0.21901668088377402,
|
| 165 |
+
"eval_runtime": 1593.8828,
|
| 166 |
+
"eval_samples_per_second": 0.627,
|
| 167 |
+
"eval_steps_per_second": 0.04,
|
| 168 |
+
"step": 3393
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.283819628647215,
|
| 172 |
+
"grad_norm": 3.319697141647339,
|
| 173 |
+
"learning_rate": 3.89306660307448e-08,
|
| 174 |
+
"loss": 2.1426,
|
| 175 |
+
"step": 3500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 10.0,
|
| 179 |
+
"eval_gen_len": 108.113,
|
| 180 |
+
"eval_loss": 2.2360377311706543,
|
| 181 |
+
"eval_rouge1": 0.3225991249221293,
|
| 182 |
+
"eval_rouge2": 0.07423068760947925,
|
| 183 |
+
"eval_rougeL": 0.20558156696804017,
|
| 184 |
+
"eval_rougeLsum": 0.21800338685798093,
|
| 185 |
+
"eval_runtime": 1476.193,
|
| 186 |
+
"eval_samples_per_second": 0.677,
|
| 187 |
+
"eval_steps_per_second": 0.043,
|
| 188 |
+
"step": 3770
|
| 189 |
+
}
|
| 190 |
+
],
|
| 191 |
+
"logging_steps": 500,
|
| 192 |
+
"max_steps": 3770,
|
| 193 |
+
"num_input_tokens_seen": 0,
|
| 194 |
+
"num_train_epochs": 10,
|
| 195 |
+
"save_steps": 500,
|
| 196 |
+
"stateful_callbacks": {
|
| 197 |
+
"TrainerControl": {
|
| 198 |
+
"args": {
|
| 199 |
+
"should_epoch_stop": false,
|
| 200 |
+
"should_evaluate": false,
|
| 201 |
+
"should_log": false,
|
| 202 |
+
"should_save": true,
|
| 203 |
+
"should_training_stop": true
|
| 204 |
+
},
|
| 205 |
+
"attributes": {}
|
| 206 |
+
}
|
| 207 |
+
},
|
| 208 |
+
"total_flos": 1.4448339676299264e+17,
|
| 209 |
+
"train_batch_size": 16,
|
| 210 |
+
"trial_name": null,
|
| 211 |
+
"trial_params": null
|
| 212 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40719d02bfded9b6b2c03c346ab1ad7facb5af9d8ed51859dfcb336d64f58404
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|