Commit
·
214bf03
1
Parent(s):
11be5b4
Upload 14 files
Browse filesuploaded best model
- added_tokens.json +1 -0
- config.json +59 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +601 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<highlight_start>": 50265, "<highlight_end>": 50266}
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models/led-base-16384/4096__global_on_highlights_pretrained_CNNDM_full_and_duc/checkpoint-9400",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LEDForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_window": [
|
| 10 |
+
1024,
|
| 11 |
+
1024,
|
| 12 |
+
1024,
|
| 13 |
+
1024,
|
| 14 |
+
1024,
|
| 15 |
+
1024
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 768,
|
| 21 |
+
"decoder_attention_heads": 12,
|
| 22 |
+
"decoder_ffn_dim": 3072,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 2,
|
| 26 |
+
"dropout": 0.1,
|
| 27 |
+
"early_stopping": "True",
|
| 28 |
+
"encoder_attention_heads": 12,
|
| 29 |
+
"encoder_ffn_dim": 3072,
|
| 30 |
+
"encoder_layerdrop": 0.0,
|
| 31 |
+
"encoder_layers": 6,
|
| 32 |
+
"eos_token_id": 2,
|
| 33 |
+
"gradient_checkpointing": false,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1",
|
| 37 |
+
"2": "LABEL_2"
|
| 38 |
+
},
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1,
|
| 44 |
+
"LABEL_2": 2
|
| 45 |
+
},
|
| 46 |
+
"length_penalty": 2.0,
|
| 47 |
+
"max_decoder_position_embeddings": 1024,
|
| 48 |
+
"max_encoder_position_embeddings": 16384,
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"min_length": 100,
|
| 51 |
+
"model_type": "led",
|
| 52 |
+
"no_repeat_ngram_size": 3,
|
| 53 |
+
"num_hidden_layers": 6,
|
| 54 |
+
"pad_token_id": 1,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.19.0.dev0",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50267
|
| 59 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46506a719ba29caa4a3dded2787845c946fcf79a272431a39d50927935a418ca
|
| 3 |
+
size 1294939621
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f339237b4f895edf3e887cc49bdde3a6a03ca3e66e17477d7a6492493da60562
|
| 3 |
+
size 647684657
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e787ae7bc9e34655bb9c021296096b5c493fd665973ba89ec7f4b7db5881df1
|
| 3 |
+
size 14503
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f30aff976137ec8a8f02bc3ed293492299fd63571aec46a1b1426491c85fe082
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd5ace93702a8e7be1611d4d27fac30ab7761fed42cc13c688a67c93dff8301b
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<highlight_start>", "<highlight_end>"]}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 16384, "special_tokens_map_file": "/home/nlp/sloboda1/.cache/huggingface/transformers/05da652a7fca41c1c18027c1201e473217bb373e370d1283e3de49d5880cbf0c.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "models/led-base-16384/4096__global_on_highlights_pretrained_CNNDM_full_and_duc/checkpoint-9400", "tokenizer_class": "LEDTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,601 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 62.7436,
|
| 3 |
+
"best_model_checkpoint": "models/led-base-16384/finetune_led_4096_global_on_highlights_pretrained_CNNDM_full_and_duc/checkpoint-1300",
|
| 4 |
+
"epoch": 5.439330543933054,
|
| 5 |
+
"global_step": 1300,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 4.895397489539749e-05,
|
| 13 |
+
"loss": 1.6206,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.42,
|
| 18 |
+
"learning_rate": 4.7907949790794984e-05,
|
| 19 |
+
"loss": 1.5797,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.42,
|
| 24 |
+
"eval_gen_len": 126.07751937984496,
|
| 25 |
+
"eval_gold_content__rouge1": 58.3427,
|
| 26 |
+
"eval_gold_content__rouge1_precision": 59.85,
|
| 27 |
+
"eval_gold_content__rouge1_recall": 57.438,
|
| 28 |
+
"eval_gold_content__rouge2": 33.9535,
|
| 29 |
+
"eval_gold_content__rouge2_precision": 34.901,
|
| 30 |
+
"eval_gold_content__rouge2_recall": 33.41,
|
| 31 |
+
"eval_gold_content__rougeL": 43.3591,
|
| 32 |
+
"eval_gold_content__rougeL_precision": 44.5351,
|
| 33 |
+
"eval_gold_content__rougeL_recall": 42.6937,
|
| 34 |
+
"eval_gold_content__rougeLsum": 43.5008,
|
| 35 |
+
"eval_gold_content__rougeLsum_precision": 44.6304,
|
| 36 |
+
"eval_gold_content__rougeLsum_recall": 42.8334,
|
| 37 |
+
"eval_gold_rouge1": 61.89,
|
| 38 |
+
"eval_gold_rouge1_precision": 63.1594,
|
| 39 |
+
"eval_gold_rouge1_recall": 61.1538,
|
| 40 |
+
"eval_gold_rouge2": 36.4056,
|
| 41 |
+
"eval_gold_rouge2_precision": 37.1918,
|
| 42 |
+
"eval_gold_rouge2_recall": 35.9234,
|
| 43 |
+
"eval_gold_rougeL": 43.5642,
|
| 44 |
+
"eval_gold_rougeL_precision": 44.4054,
|
| 45 |
+
"eval_gold_rougeL_recall": 43.0498,
|
| 46 |
+
"eval_gold_rougeLsum": 58.5201,
|
| 47 |
+
"eval_gold_rougeLsum_precision": 59.7136,
|
| 48 |
+
"eval_gold_rougeLsum_recall": 57.7912,
|
| 49 |
+
"eval_loss": 2.1532697677612305,
|
| 50 |
+
"eval_runtime": 308.7055,
|
| 51 |
+
"eval_samples_per_second": 0.418,
|
| 52 |
+
"eval_steps_per_second": 0.418,
|
| 53 |
+
"step": 100
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.63,
|
| 57 |
+
"learning_rate": 4.686192468619247e-05,
|
| 58 |
+
"loss": 1.5908,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.84,
|
| 63 |
+
"learning_rate": 4.581589958158996e-05,
|
| 64 |
+
"loss": 1.5953,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.84,
|
| 69 |
+
"eval_gen_len": 133.74418604651163,
|
| 70 |
+
"eval_gold_content__rouge1": 58.4517,
|
| 71 |
+
"eval_gold_content__rouge1_precision": 58.1392,
|
| 72 |
+
"eval_gold_content__rouge1_recall": 59.3081,
|
| 73 |
+
"eval_gold_content__rouge2": 34.4547,
|
| 74 |
+
"eval_gold_content__rouge2_precision": 34.347,
|
| 75 |
+
"eval_gold_content__rouge2_recall": 34.8401,
|
| 76 |
+
"eval_gold_content__rougeL": 43.6875,
|
| 77 |
+
"eval_gold_content__rougeL_precision": 43.5151,
|
| 78 |
+
"eval_gold_content__rougeL_recall": 44.2304,
|
| 79 |
+
"eval_gold_content__rougeLsum": 43.6718,
|
| 80 |
+
"eval_gold_content__rougeLsum_precision": 43.5039,
|
| 81 |
+
"eval_gold_content__rougeLsum_recall": 44.2415,
|
| 82 |
+
"eval_gold_rouge1": 62.0262,
|
| 83 |
+
"eval_gold_rouge1_precision": 61.4937,
|
| 84 |
+
"eval_gold_rouge1_recall": 63.0726,
|
| 85 |
+
"eval_gold_rouge2": 36.8819,
|
| 86 |
+
"eval_gold_rouge2_precision": 36.6756,
|
| 87 |
+
"eval_gold_rouge2_recall": 37.3674,
|
| 88 |
+
"eval_gold_rougeL": 43.6689,
|
| 89 |
+
"eval_gold_rougeL_precision": 43.3582,
|
| 90 |
+
"eval_gold_rougeL_recall": 44.3137,
|
| 91 |
+
"eval_gold_rougeLsum": 58.5109,
|
| 92 |
+
"eval_gold_rougeLsum_precision": 58.0665,
|
| 93 |
+
"eval_gold_rougeLsum_recall": 59.4408,
|
| 94 |
+
"eval_loss": 2.1124985218048096,
|
| 95 |
+
"eval_runtime": 327.1737,
|
| 96 |
+
"eval_samples_per_second": 0.394,
|
| 97 |
+
"eval_steps_per_second": 0.394,
|
| 98 |
+
"step": 200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.05,
|
| 102 |
+
"learning_rate": 4.476987447698745e-05,
|
| 103 |
+
"loss": 1.5117,
|
| 104 |
+
"step": 250
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.26,
|
| 108 |
+
"learning_rate": 4.372384937238494e-05,
|
| 109 |
+
"loss": 1.2453,
|
| 110 |
+
"step": 300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.26,
|
| 114 |
+
"eval_gen_len": 127.17054263565892,
|
| 115 |
+
"eval_gold_content__rouge1": 58.3354,
|
| 116 |
+
"eval_gold_content__rouge1_precision": 58.9279,
|
| 117 |
+
"eval_gold_content__rouge1_recall": 58.2257,
|
| 118 |
+
"eval_gold_content__rouge2": 34.017,
|
| 119 |
+
"eval_gold_content__rouge2_precision": 34.5263,
|
| 120 |
+
"eval_gold_content__rouge2_recall": 33.778,
|
| 121 |
+
"eval_gold_content__rougeL": 43.6636,
|
| 122 |
+
"eval_gold_content__rougeL_precision": 44.2381,
|
| 123 |
+
"eval_gold_content__rougeL_recall": 43.4675,
|
| 124 |
+
"eval_gold_content__rougeLsum": 43.6821,
|
| 125 |
+
"eval_gold_content__rougeLsum_precision": 44.3055,
|
| 126 |
+
"eval_gold_content__rougeLsum_recall": 43.4534,
|
| 127 |
+
"eval_gold_rouge1": 61.767,
|
| 128 |
+
"eval_gold_rouge1_precision": 62.401,
|
| 129 |
+
"eval_gold_rouge1_recall": 61.667,
|
| 130 |
+
"eval_gold_rouge2": 36.1801,
|
| 131 |
+
"eval_gold_rouge2_precision": 36.6528,
|
| 132 |
+
"eval_gold_rouge2_recall": 35.9826,
|
| 133 |
+
"eval_gold_rougeL": 43.7391,
|
| 134 |
+
"eval_gold_rougeL_precision": 44.2889,
|
| 135 |
+
"eval_gold_rougeL_recall": 43.5425,
|
| 136 |
+
"eval_gold_rougeLsum": 58.1127,
|
| 137 |
+
"eval_gold_rougeLsum_precision": 58.7827,
|
| 138 |
+
"eval_gold_rougeLsum_recall": 57.9085,
|
| 139 |
+
"eval_loss": 2.1830742359161377,
|
| 140 |
+
"eval_runtime": 306.4961,
|
| 141 |
+
"eval_samples_per_second": 0.421,
|
| 142 |
+
"eval_steps_per_second": 0.421,
|
| 143 |
+
"step": 300
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.46,
|
| 147 |
+
"learning_rate": 4.267782426778243e-05,
|
| 148 |
+
"loss": 1.2287,
|
| 149 |
+
"step": 350
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.67,
|
| 153 |
+
"learning_rate": 4.1631799163179915e-05,
|
| 154 |
+
"loss": 1.2763,
|
| 155 |
+
"step": 400
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.67,
|
| 159 |
+
"eval_gen_len": 129.26356589147287,
|
| 160 |
+
"eval_gold_content__rouge1": 58.9265,
|
| 161 |
+
"eval_gold_content__rouge1_precision": 59.6196,
|
| 162 |
+
"eval_gold_content__rouge1_recall": 58.889,
|
| 163 |
+
"eval_gold_content__rouge2": 34.0912,
|
| 164 |
+
"eval_gold_content__rouge2_precision": 34.4828,
|
| 165 |
+
"eval_gold_content__rouge2_recall": 34.0341,
|
| 166 |
+
"eval_gold_content__rougeL": 43.4803,
|
| 167 |
+
"eval_gold_content__rougeL_precision": 43.8369,
|
| 168 |
+
"eval_gold_content__rougeL_recall": 43.5011,
|
| 169 |
+
"eval_gold_content__rougeLsum": 43.4751,
|
| 170 |
+
"eval_gold_content__rougeLsum_precision": 43.7794,
|
| 171 |
+
"eval_gold_content__rougeLsum_recall": 43.4949,
|
| 172 |
+
"eval_gold_rouge1": 62.3505,
|
| 173 |
+
"eval_gold_rouge1_precision": 62.9951,
|
| 174 |
+
"eval_gold_rouge1_recall": 62.2874,
|
| 175 |
+
"eval_gold_rouge2": 36.4292,
|
| 176 |
+
"eval_gold_rouge2_precision": 36.8521,
|
| 177 |
+
"eval_gold_rouge2_recall": 36.3282,
|
| 178 |
+
"eval_gold_rougeL": 43.8949,
|
| 179 |
+
"eval_gold_rougeL_precision": 44.2859,
|
| 180 |
+
"eval_gold_rougeL_recall": 43.8659,
|
| 181 |
+
"eval_gold_rougeLsum": 58.9232,
|
| 182 |
+
"eval_gold_rougeLsum_precision": 59.5425,
|
| 183 |
+
"eval_gold_rougeLsum_recall": 58.8475,
|
| 184 |
+
"eval_loss": 2.142529249191284,
|
| 185 |
+
"eval_runtime": 305.8865,
|
| 186 |
+
"eval_samples_per_second": 0.422,
|
| 187 |
+
"eval_steps_per_second": 0.422,
|
| 188 |
+
"step": 400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.88,
|
| 192 |
+
"learning_rate": 4.0585774058577406e-05,
|
| 193 |
+
"loss": 1.2922,
|
| 194 |
+
"step": 450
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.09,
|
| 198 |
+
"learning_rate": 3.95397489539749e-05,
|
| 199 |
+
"loss": 1.0938,
|
| 200 |
+
"step": 500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.09,
|
| 204 |
+
"eval_gen_len": 133.6046511627907,
|
| 205 |
+
"eval_gold_content__rouge1": 58.6518,
|
| 206 |
+
"eval_gold_content__rouge1_precision": 58.3803,
|
| 207 |
+
"eval_gold_content__rouge1_recall": 59.3574,
|
| 208 |
+
"eval_gold_content__rouge2": 33.2829,
|
| 209 |
+
"eval_gold_content__rouge2_precision": 33.2277,
|
| 210 |
+
"eval_gold_content__rouge2_recall": 33.588,
|
| 211 |
+
"eval_gold_content__rougeL": 42.8525,
|
| 212 |
+
"eval_gold_content__rougeL_precision": 42.7057,
|
| 213 |
+
"eval_gold_content__rougeL_recall": 43.3466,
|
| 214 |
+
"eval_gold_content__rougeLsum": 42.8745,
|
| 215 |
+
"eval_gold_content__rougeLsum_precision": 42.7141,
|
| 216 |
+
"eval_gold_content__rougeLsum_recall": 43.3652,
|
| 217 |
+
"eval_gold_rouge1": 62.1112,
|
| 218 |
+
"eval_gold_rouge1_precision": 61.6416,
|
| 219 |
+
"eval_gold_rouge1_recall": 63.0257,
|
| 220 |
+
"eval_gold_rouge2": 35.6622,
|
| 221 |
+
"eval_gold_rouge2_precision": 35.5027,
|
| 222 |
+
"eval_gold_rouge2_recall": 36.0691,
|
| 223 |
+
"eval_gold_rougeL": 42.9354,
|
| 224 |
+
"eval_gold_rougeL_precision": 42.6368,
|
| 225 |
+
"eval_gold_rougeL_recall": 43.5109,
|
| 226 |
+
"eval_gold_rougeLsum": 58.3501,
|
| 227 |
+
"eval_gold_rougeLsum_precision": 57.9716,
|
| 228 |
+
"eval_gold_rougeLsum_recall": 59.1286,
|
| 229 |
+
"eval_loss": 2.240668535232544,
|
| 230 |
+
"eval_runtime": 327.5299,
|
| 231 |
+
"eval_samples_per_second": 0.394,
|
| 232 |
+
"eval_steps_per_second": 0.394,
|
| 233 |
+
"step": 500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.3,
|
| 237 |
+
"learning_rate": 3.849372384937239e-05,
|
| 238 |
+
"loss": 1.0109,
|
| 239 |
+
"step": 550
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.51,
|
| 243 |
+
"learning_rate": 3.744769874476988e-05,
|
| 244 |
+
"loss": 0.9934,
|
| 245 |
+
"step": 600
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.51,
|
| 249 |
+
"eval_gen_len": 130.85271317829458,
|
| 250 |
+
"eval_gold_content__rouge1": 58.5347,
|
| 251 |
+
"eval_gold_content__rouge1_precision": 58.7796,
|
| 252 |
+
"eval_gold_content__rouge1_recall": 58.8349,
|
| 253 |
+
"eval_gold_content__rouge2": 33.8458,
|
| 254 |
+
"eval_gold_content__rouge2_precision": 33.9726,
|
| 255 |
+
"eval_gold_content__rouge2_recall": 34.0374,
|
| 256 |
+
"eval_gold_content__rougeL": 43.289,
|
| 257 |
+
"eval_gold_content__rougeL_precision": 43.4375,
|
| 258 |
+
"eval_gold_content__rougeL_recall": 43.4558,
|
| 259 |
+
"eval_gold_content__rougeLsum": 43.2637,
|
| 260 |
+
"eval_gold_content__rougeLsum_precision": 43.4389,
|
| 261 |
+
"eval_gold_content__rougeLsum_recall": 43.486,
|
| 262 |
+
"eval_gold_rouge1": 62.1317,
|
| 263 |
+
"eval_gold_rouge1_precision": 62.2568,
|
| 264 |
+
"eval_gold_rouge1_recall": 62.4558,
|
| 265 |
+
"eval_gold_rouge2": 36.5123,
|
| 266 |
+
"eval_gold_rouge2_precision": 36.6028,
|
| 267 |
+
"eval_gold_rouge2_recall": 36.7019,
|
| 268 |
+
"eval_gold_rougeL": 43.3287,
|
| 269 |
+
"eval_gold_rougeL_precision": 43.4139,
|
| 270 |
+
"eval_gold_rougeL_recall": 43.5481,
|
| 271 |
+
"eval_gold_rougeLsum": 58.7645,
|
| 272 |
+
"eval_gold_rougeLsum_precision": 58.911,
|
| 273 |
+
"eval_gold_rougeLsum_recall": 59.0483,
|
| 274 |
+
"eval_loss": 2.2259631156921387,
|
| 275 |
+
"eval_runtime": 327.0684,
|
| 276 |
+
"eval_samples_per_second": 0.394,
|
| 277 |
+
"eval_steps_per_second": 0.394,
|
| 278 |
+
"step": 600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.72,
|
| 282 |
+
"learning_rate": 3.640167364016737e-05,
|
| 283 |
+
"loss": 1.012,
|
| 284 |
+
"step": 650
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.93,
|
| 288 |
+
"learning_rate": 3.5355648535564854e-05,
|
| 289 |
+
"loss": 1.04,
|
| 290 |
+
"step": 700
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.93,
|
| 294 |
+
"eval_gen_len": 128.65891472868216,
|
| 295 |
+
"eval_gold_content__rouge1": 58.99,
|
| 296 |
+
"eval_gold_content__rouge1_precision": 59.5164,
|
| 297 |
+
"eval_gold_content__rouge1_recall": 58.9141,
|
| 298 |
+
"eval_gold_content__rouge2": 33.6019,
|
| 299 |
+
"eval_gold_content__rouge2_precision": 33.946,
|
| 300 |
+
"eval_gold_content__rouge2_recall": 33.5476,
|
| 301 |
+
"eval_gold_content__rougeL": 43.6877,
|
| 302 |
+
"eval_gold_content__rougeL_precision": 44.0417,
|
| 303 |
+
"eval_gold_content__rougeL_recall": 43.7057,
|
| 304 |
+
"eval_gold_content__rougeLsum": 43.621,
|
| 305 |
+
"eval_gold_content__rougeLsum_precision": 44.0079,
|
| 306 |
+
"eval_gold_content__rougeLsum_recall": 43.6015,
|
| 307 |
+
"eval_gold_rouge1": 62.5394,
|
| 308 |
+
"eval_gold_rouge1_precision": 63.0444,
|
| 309 |
+
"eval_gold_rouge1_recall": 62.4707,
|
| 310 |
+
"eval_gold_rouge2": 36.2644,
|
| 311 |
+
"eval_gold_rouge2_precision": 36.6473,
|
| 312 |
+
"eval_gold_rouge2_recall": 36.1616,
|
| 313 |
+
"eval_gold_rougeL": 43.9778,
|
| 314 |
+
"eval_gold_rougeL_precision": 44.2802,
|
| 315 |
+
"eval_gold_rougeL_recall": 43.943,
|
| 316 |
+
"eval_gold_rougeLsum": 58.8109,
|
| 317 |
+
"eval_gold_rougeLsum_precision": 59.3138,
|
| 318 |
+
"eval_gold_rougeLsum_recall": 58.7047,
|
| 319 |
+
"eval_loss": 2.248823404312134,
|
| 320 |
+
"eval_runtime": 305.3298,
|
| 321 |
+
"eval_samples_per_second": 0.422,
|
| 322 |
+
"eval_steps_per_second": 0.422,
|
| 323 |
+
"step": 700
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.14,
|
| 327 |
+
"learning_rate": 3.4309623430962344e-05,
|
| 328 |
+
"loss": 0.8781,
|
| 329 |
+
"step": 750
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.35,
|
| 333 |
+
"learning_rate": 3.3263598326359835e-05,
|
| 334 |
+
"loss": 0.8043,
|
| 335 |
+
"step": 800
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.35,
|
| 339 |
+
"eval_gen_len": 132.66666666666666,
|
| 340 |
+
"eval_gold_content__rouge1": 58.6355,
|
| 341 |
+
"eval_gold_content__rouge1_precision": 58.401,
|
| 342 |
+
"eval_gold_content__rouge1_recall": 59.3404,
|
| 343 |
+
"eval_gold_content__rouge2": 32.7864,
|
| 344 |
+
"eval_gold_content__rouge2_precision": 32.6957,
|
| 345 |
+
"eval_gold_content__rouge2_recall": 33.0917,
|
| 346 |
+
"eval_gold_content__rougeL": 42.5009,
|
| 347 |
+
"eval_gold_content__rougeL_precision": 42.3598,
|
| 348 |
+
"eval_gold_content__rougeL_recall": 42.9895,
|
| 349 |
+
"eval_gold_content__rougeLsum": 42.5917,
|
| 350 |
+
"eval_gold_content__rougeLsum_precision": 42.4082,
|
| 351 |
+
"eval_gold_content__rougeLsum_recall": 43.0791,
|
| 352 |
+
"eval_gold_rouge1": 62.2945,
|
| 353 |
+
"eval_gold_rouge1_precision": 62.0757,
|
| 354 |
+
"eval_gold_rouge1_recall": 62.9913,
|
| 355 |
+
"eval_gold_rouge2": 35.3636,
|
| 356 |
+
"eval_gold_rouge2_precision": 35.2951,
|
| 357 |
+
"eval_gold_rouge2_recall": 35.6452,
|
| 358 |
+
"eval_gold_rougeL": 42.9827,
|
| 359 |
+
"eval_gold_rougeL_precision": 42.8331,
|
| 360 |
+
"eval_gold_rougeL_recall": 43.4049,
|
| 361 |
+
"eval_gold_rougeLsum": 58.3145,
|
| 362 |
+
"eval_gold_rougeLsum_precision": 58.1325,
|
| 363 |
+
"eval_gold_rougeLsum_recall": 58.895,
|
| 364 |
+
"eval_loss": 2.3569345474243164,
|
| 365 |
+
"eval_runtime": 317.4014,
|
| 366 |
+
"eval_samples_per_second": 0.406,
|
| 367 |
+
"eval_steps_per_second": 0.406,
|
| 368 |
+
"step": 800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.56,
|
| 372 |
+
"learning_rate": 3.2217573221757326e-05,
|
| 373 |
+
"loss": 0.8277,
|
| 374 |
+
"step": 850
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.77,
|
| 378 |
+
"learning_rate": 3.117154811715482e-05,
|
| 379 |
+
"loss": 0.8269,
|
| 380 |
+
"step": 900
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.77,
|
| 384 |
+
"eval_gen_len": 131.32558139534885,
|
| 385 |
+
"eval_gold_content__rouge1": 58.3411,
|
| 386 |
+
"eval_gold_content__rouge1_precision": 58.2642,
|
| 387 |
+
"eval_gold_content__rouge1_recall": 58.9275,
|
| 388 |
+
"eval_gold_content__rouge2": 33.3716,
|
| 389 |
+
"eval_gold_content__rouge2_precision": 33.4297,
|
| 390 |
+
"eval_gold_content__rouge2_recall": 33.6498,
|
| 391 |
+
"eval_gold_content__rougeL": 42.2759,
|
| 392 |
+
"eval_gold_content__rougeL_precision": 42.2765,
|
| 393 |
+
"eval_gold_content__rougeL_recall": 42.687,
|
| 394 |
+
"eval_gold_content__rougeLsum": 42.2536,
|
| 395 |
+
"eval_gold_content__rougeLsum_precision": 42.2241,
|
| 396 |
+
"eval_gold_content__rougeLsum_recall": 42.7188,
|
| 397 |
+
"eval_gold_rouge1": 61.6417,
|
| 398 |
+
"eval_gold_rouge1_precision": 61.6121,
|
| 399 |
+
"eval_gold_rouge1_recall": 62.1201,
|
| 400 |
+
"eval_gold_rouge2": 35.6839,
|
| 401 |
+
"eval_gold_rouge2_precision": 35.7649,
|
| 402 |
+
"eval_gold_rouge2_recall": 35.8464,
|
| 403 |
+
"eval_gold_rougeL": 42.5074,
|
| 404 |
+
"eval_gold_rougeL_precision": 42.5107,
|
| 405 |
+
"eval_gold_rougeL_recall": 42.81,
|
| 406 |
+
"eval_gold_rougeLsum": 58.0849,
|
| 407 |
+
"eval_gold_rougeLsum_precision": 58.0593,
|
| 408 |
+
"eval_gold_rougeLsum_recall": 58.511,
|
| 409 |
+
"eval_loss": 2.332422971725464,
|
| 410 |
+
"eval_runtime": 323.7426,
|
| 411 |
+
"eval_samples_per_second": 0.398,
|
| 412 |
+
"eval_steps_per_second": 0.398,
|
| 413 |
+
"step": 900
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.97,
|
| 417 |
+
"learning_rate": 3.0125523012552304e-05,
|
| 418 |
+
"loss": 0.8544,
|
| 419 |
+
"step": 950
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.18,
|
| 423 |
+
"learning_rate": 2.9079497907949792e-05,
|
| 424 |
+
"loss": 0.6838,
|
| 425 |
+
"step": 1000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.18,
|
| 429 |
+
"eval_gen_len": 131.14728682170542,
|
| 430 |
+
"eval_gold_content__rouge1": 57.4335,
|
| 431 |
+
"eval_gold_content__rouge1_precision": 57.3305,
|
| 432 |
+
"eval_gold_content__rouge1_recall": 57.8738,
|
| 433 |
+
"eval_gold_content__rouge2": 31.9398,
|
| 434 |
+
"eval_gold_content__rouge2_precision": 31.9439,
|
| 435 |
+
"eval_gold_content__rouge2_recall": 32.1494,
|
| 436 |
+
"eval_gold_content__rougeL": 41.5105,
|
| 437 |
+
"eval_gold_content__rougeL_precision": 41.3791,
|
| 438 |
+
"eval_gold_content__rougeL_recall": 41.8825,
|
| 439 |
+
"eval_gold_content__rougeLsum": 41.5048,
|
| 440 |
+
"eval_gold_content__rougeLsum_precision": 41.3923,
|
| 441 |
+
"eval_gold_content__rougeLsum_recall": 41.8949,
|
| 442 |
+
"eval_gold_rouge1": 61.3986,
|
| 443 |
+
"eval_gold_rouge1_precision": 61.2071,
|
| 444 |
+
"eval_gold_rouge1_recall": 61.9882,
|
| 445 |
+
"eval_gold_rouge2": 34.4586,
|
| 446 |
+
"eval_gold_rouge2_precision": 34.403,
|
| 447 |
+
"eval_gold_rouge2_recall": 34.7027,
|
| 448 |
+
"eval_gold_rougeL": 41.8032,
|
| 449 |
+
"eval_gold_rougeL_precision": 41.6313,
|
| 450 |
+
"eval_gold_rougeL_recall": 42.2476,
|
| 451 |
+
"eval_gold_rougeLsum": 57.302,
|
| 452 |
+
"eval_gold_rougeLsum_precision": 57.1356,
|
| 453 |
+
"eval_gold_rougeLsum_recall": 57.8116,
|
| 454 |
+
"eval_loss": 2.4267024993896484,
|
| 455 |
+
"eval_runtime": 321.0984,
|
| 456 |
+
"eval_samples_per_second": 0.402,
|
| 457 |
+
"eval_steps_per_second": 0.402,
|
| 458 |
+
"step": 1000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.39,
|
| 462 |
+
"learning_rate": 2.8033472803347283e-05,
|
| 463 |
+
"loss": 0.6376,
|
| 464 |
+
"step": 1050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.6,
|
| 468 |
+
"learning_rate": 2.6987447698744773e-05,
|
| 469 |
+
"loss": 0.6719,
|
| 470 |
+
"step": 1100
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.6,
|
| 474 |
+
"eval_gen_len": 132.86046511627907,
|
| 475 |
+
"eval_gold_content__rouge1": 58.6491,
|
| 476 |
+
"eval_gold_content__rouge1_precision": 58.2647,
|
| 477 |
+
"eval_gold_content__rouge1_recall": 59.4943,
|
| 478 |
+
"eval_gold_content__rouge2": 33.6426,
|
| 479 |
+
"eval_gold_content__rouge2_precision": 33.4593,
|
| 480 |
+
"eval_gold_content__rouge2_recall": 34.0799,
|
| 481 |
+
"eval_gold_content__rougeL": 43.163,
|
| 482 |
+
"eval_gold_content__rougeL_precision": 42.8565,
|
| 483 |
+
"eval_gold_content__rougeL_recall": 43.7869,
|
| 484 |
+
"eval_gold_content__rougeLsum": 43.1082,
|
| 485 |
+
"eval_gold_content__rougeLsum_precision": 42.7496,
|
| 486 |
+
"eval_gold_content__rougeLsum_recall": 43.7595,
|
| 487 |
+
"eval_gold_rouge1": 62.3384,
|
| 488 |
+
"eval_gold_rouge1_precision": 61.9139,
|
| 489 |
+
"eval_gold_rouge1_recall": 63.1585,
|
| 490 |
+
"eval_gold_rouge2": 35.8046,
|
| 491 |
+
"eval_gold_rouge2_precision": 35.5978,
|
| 492 |
+
"eval_gold_rouge2_recall": 36.2046,
|
| 493 |
+
"eval_gold_rougeL": 43.2641,
|
| 494 |
+
"eval_gold_rougeL_precision": 42.9357,
|
| 495 |
+
"eval_gold_rougeL_recall": 43.8159,
|
| 496 |
+
"eval_gold_rougeLsum": 58.3628,
|
| 497 |
+
"eval_gold_rougeLsum_precision": 57.9516,
|
| 498 |
+
"eval_gold_rougeLsum_recall": 59.1191,
|
| 499 |
+
"eval_loss": 2.427868366241455,
|
| 500 |
+
"eval_runtime": 317.5232,
|
| 501 |
+
"eval_samples_per_second": 0.406,
|
| 502 |
+
"eval_steps_per_second": 0.406,
|
| 503 |
+
"step": 1100
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.81,
|
| 507 |
+
"learning_rate": 2.594142259414226e-05,
|
| 508 |
+
"loss": 0.6775,
|
| 509 |
+
"step": 1150
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.02,
|
| 513 |
+
"learning_rate": 2.489539748953975e-05,
|
| 514 |
+
"loss": 0.6835,
|
| 515 |
+
"step": 1200
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.02,
|
| 519 |
+
"eval_gen_len": 129.37209302325581,
|
| 520 |
+
"eval_gold_content__rouge1": 57.8101,
|
| 521 |
+
"eval_gold_content__rouge1_precision": 58.1747,
|
| 522 |
+
"eval_gold_content__rouge1_recall": 57.7813,
|
| 523 |
+
"eval_gold_content__rouge2": 31.8646,
|
| 524 |
+
"eval_gold_content__rouge2_precision": 32.0479,
|
| 525 |
+
"eval_gold_content__rouge2_recall": 31.8628,
|
| 526 |
+
"eval_gold_content__rougeL": 41.4763,
|
| 527 |
+
"eval_gold_content__rougeL_precision": 41.7604,
|
| 528 |
+
"eval_gold_content__rougeL_recall": 41.4871,
|
| 529 |
+
"eval_gold_content__rougeLsum": 41.4962,
|
| 530 |
+
"eval_gold_content__rougeLsum_precision": 41.7238,
|
| 531 |
+
"eval_gold_content__rougeLsum_recall": 41.498,
|
| 532 |
+
"eval_gold_rouge1": 61.4546,
|
| 533 |
+
"eval_gold_rouge1_precision": 61.8021,
|
| 534 |
+
"eval_gold_rouge1_recall": 61.3898,
|
| 535 |
+
"eval_gold_rouge2": 34.5481,
|
| 536 |
+
"eval_gold_rouge2_precision": 34.8132,
|
| 537 |
+
"eval_gold_rouge2_recall": 34.5658,
|
| 538 |
+
"eval_gold_rougeL": 41.9335,
|
| 539 |
+
"eval_gold_rougeL_precision": 42.1417,
|
| 540 |
+
"eval_gold_rougeL_recall": 41.9428,
|
| 541 |
+
"eval_gold_rougeLsum": 57.518,
|
| 542 |
+
"eval_gold_rougeLsum_precision": 57.9298,
|
| 543 |
+
"eval_gold_rougeLsum_recall": 57.4184,
|
| 544 |
+
"eval_loss": 2.4904870986938477,
|
| 545 |
+
"eval_runtime": 306.5024,
|
| 546 |
+
"eval_samples_per_second": 0.421,
|
| 547 |
+
"eval_steps_per_second": 0.421,
|
| 548 |
+
"step": 1200
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.23,
|
| 552 |
+
"learning_rate": 2.3849372384937242e-05,
|
| 553 |
+
"loss": 0.5561,
|
| 554 |
+
"step": 1250
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.44,
|
| 558 |
+
"learning_rate": 2.280334728033473e-05,
|
| 559 |
+
"loss": 0.5495,
|
| 560 |
+
"step": 1300
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 5.44,
|
| 564 |
+
"eval_gen_len": 132.88372093023256,
|
| 565 |
+
"eval_gold_content__rouge1": 59.2827,
|
| 566 |
+
"eval_gold_content__rouge1_precision": 58.931,
|
| 567 |
+
"eval_gold_content__rouge1_recall": 60.0205,
|
| 568 |
+
"eval_gold_content__rouge2": 34.1327,
|
| 569 |
+
"eval_gold_content__rouge2_precision": 34.0164,
|
| 570 |
+
"eval_gold_content__rouge2_recall": 34.4858,
|
| 571 |
+
"eval_gold_content__rougeL": 43.5606,
|
| 572 |
+
"eval_gold_content__rougeL_precision": 43.3704,
|
| 573 |
+
"eval_gold_content__rougeL_recall": 44.1162,
|
| 574 |
+
"eval_gold_content__rougeLsum": 43.5148,
|
| 575 |
+
"eval_gold_content__rougeLsum_precision": 43.2937,
|
| 576 |
+
"eval_gold_content__rougeLsum_recall": 44.1221,
|
| 577 |
+
"eval_gold_rouge1": 62.7436,
|
| 578 |
+
"eval_gold_rouge1_precision": 62.4107,
|
| 579 |
+
"eval_gold_rouge1_recall": 63.4468,
|
| 580 |
+
"eval_gold_rouge2": 36.4478,
|
| 581 |
+
"eval_gold_rouge2_precision": 36.3739,
|
| 582 |
+
"eval_gold_rouge2_recall": 36.8162,
|
| 583 |
+
"eval_gold_rougeL": 43.7493,
|
| 584 |
+
"eval_gold_rougeL_precision": 43.5387,
|
| 585 |
+
"eval_gold_rougeL_recall": 44.2374,
|
| 586 |
+
"eval_gold_rougeLsum": 58.9706,
|
| 587 |
+
"eval_gold_rougeLsum_precision": 58.6953,
|
| 588 |
+
"eval_gold_rougeLsum_recall": 59.5665,
|
| 589 |
+
"eval_loss": 2.555025339126587,
|
| 590 |
+
"eval_runtime": 323.5705,
|
| 591 |
+
"eval_samples_per_second": 0.399,
|
| 592 |
+
"eval_steps_per_second": 0.399,
|
| 593 |
+
"step": 1300
|
| 594 |
+
}
|
| 595 |
+
],
|
| 596 |
+
"max_steps": 2390,
|
| 597 |
+
"num_train_epochs": 10,
|
| 598 |
+
"total_flos": 1.0265751601127424e+16,
|
| 599 |
+
"trial_name": null,
|
| 600 |
+
"trial_params": null
|
| 601 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cddb85f5f44ff43c0c6eb5a22fe562d947d358afe195033a9229ca9dd27355b
|
| 3 |
+
size 3503
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|