Commit
•
439800e
1
Parent(s):
e0f08a5
initial commit
Browse files- added_tokens.json +3 -0
- config.json +32 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +8 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +376 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<SI>": 32100
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Models/SciFive-base-Pubmed_PMC",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.23.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32101
|
| 32 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d9ea065454b35572388a62d3d0a7cd5100bd8014101fe6bbf5f73a4c7df63f1
|
| 3 |
+
size 1783213757
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71413a1b0814e110b4ecade2b272b54cabbd3baa369267003ebca3ad292e96e6
|
| 3 |
+
size 891617855
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:498e5d1b403cdb26095903182848c3acd506ada604263ef45385f25d25a7aded
|
| 3 |
+
size 15523
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:114b7994e9c3948691fed889bfd4214a5e51eef63f78bae30eecd11f40a53b6f
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<SI>"
|
| 4 |
+
],
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"unk_token": "<unk>"
|
| 8 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"name_or_path": "Models/SciFive-base-Pubmed_PMC",
|
| 107 |
+
"pad_token": "<pad>",
|
| 108 |
+
"special_tokens_map_file": null,
|
| 109 |
+
"tokenizer_class": "T5Tokenizer",
|
| 110 |
+
"unk_token": "<unk>"
|
| 111 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 27.4584,
|
| 3 |
+
"best_model_checkpoint": "vilmedic/SciFiverouge-1/checkpoint-66726",
|
| 4 |
+
"epoch": 35.99029126213592,
|
| 5 |
+
"global_step": 66726,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.0,
|
| 12 |
+
"learning_rate": 2.9538455297488754e-05,
|
| 13 |
+
"loss": 1.8057,
|
| 14 |
+
"step": 3707
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.0,
|
| 18 |
+
"eval_bleu": 83.8658,
|
| 19 |
+
"eval_f1_radgraph": 0.2199,
|
| 20 |
+
"eval_loss": 1.5417813062667847,
|
| 21 |
+
"eval_rouge1": 28.1224,
|
| 22 |
+
"eval_rouge2": 14.9915,
|
| 23 |
+
"eval_rougeL": 25.1977,
|
| 24 |
+
"eval_rougeLsum": 27.135,
|
| 25 |
+
"eval_runtime": 525.382,
|
| 26 |
+
"eval_samples_per_second": 14.11,
|
| 27 |
+
"eval_steps_per_second": 0.442,
|
| 28 |
+
"step": 3707
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 4.0,
|
| 32 |
+
"learning_rate": 2.8935795570433828e-05,
|
| 33 |
+
"loss": 1.5951,
|
| 34 |
+
"step": 7414
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 4.0,
|
| 38 |
+
"eval_bleu": 91.197,
|
| 39 |
+
"eval_f1_radgraph": 0.227,
|
| 40 |
+
"eval_loss": 1.4663870334625244,
|
| 41 |
+
"eval_rouge1": 28.885,
|
| 42 |
+
"eval_rouge2": 15.7599,
|
| 43 |
+
"eval_rougeL": 25.9785,
|
| 44 |
+
"eval_rougeLsum": 27.819,
|
| 45 |
+
"eval_runtime": 515.8882,
|
| 46 |
+
"eval_samples_per_second": 14.369,
|
| 47 |
+
"eval_steps_per_second": 0.45,
|
| 48 |
+
"step": 7414
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 6.0,
|
| 52 |
+
"learning_rate": 2.8333135843378902e-05,
|
| 53 |
+
"loss": 1.5199,
|
| 54 |
+
"step": 11121
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_bleu": 87.253,
|
| 59 |
+
"eval_f1_radgraph": 0.2314,
|
| 60 |
+
"eval_loss": 1.4249236583709717,
|
| 61 |
+
"eval_rouge1": 29.0849,
|
| 62 |
+
"eval_rouge2": 16.0903,
|
| 63 |
+
"eval_rougeL": 26.1967,
|
| 64 |
+
"eval_rougeLsum": 28.0078,
|
| 65 |
+
"eval_runtime": 513.5301,
|
| 66 |
+
"eval_samples_per_second": 14.435,
|
| 67 |
+
"eval_steps_per_second": 0.452,
|
| 68 |
+
"step": 11121
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 8.0,
|
| 72 |
+
"learning_rate": 2.7730476116323972e-05,
|
| 73 |
+
"loss": 1.4705,
|
| 74 |
+
"step": 14828
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 8.0,
|
| 78 |
+
"eval_bleu": 85.3504,
|
| 79 |
+
"eval_f1_radgraph": 0.2342,
|
| 80 |
+
"eval_loss": 1.3992971181869507,
|
| 81 |
+
"eval_rouge1": 29.3725,
|
| 82 |
+
"eval_rouge2": 16.356,
|
| 83 |
+
"eval_rougeL": 26.4644,
|
| 84 |
+
"eval_rougeLsum": 28.2535,
|
| 85 |
+
"eval_runtime": 522.0475,
|
| 86 |
+
"eval_samples_per_second": 14.2,
|
| 87 |
+
"eval_steps_per_second": 0.444,
|
| 88 |
+
"step": 14828
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 10.0,
|
| 92 |
+
"learning_rate": 2.7127816389269046e-05,
|
| 93 |
+
"loss": 1.4326,
|
| 94 |
+
"step": 18535
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 10.0,
|
| 98 |
+
"eval_bleu": 90.5282,
|
| 99 |
+
"eval_f1_radgraph": 0.2341,
|
| 100 |
+
"eval_loss": 1.38131844997406,
|
| 101 |
+
"eval_rouge1": 29.5246,
|
| 102 |
+
"eval_rouge2": 16.41,
|
| 103 |
+
"eval_rougeL": 26.5568,
|
| 104 |
+
"eval_rougeLsum": 28.3933,
|
| 105 |
+
"eval_runtime": 515.287,
|
| 106 |
+
"eval_samples_per_second": 14.386,
|
| 107 |
+
"eval_steps_per_second": 0.45,
|
| 108 |
+
"step": 18535
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 12.0,
|
| 112 |
+
"learning_rate": 2.652515666221412e-05,
|
| 113 |
+
"loss": 1.4015,
|
| 114 |
+
"step": 22242
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 12.0,
|
| 118 |
+
"eval_bleu": 91.7941,
|
| 119 |
+
"eval_f1_radgraph": 0.2346,
|
| 120 |
+
"eval_loss": 1.366599440574646,
|
| 121 |
+
"eval_rouge1": 29.7344,
|
| 122 |
+
"eval_rouge2": 16.6795,
|
| 123 |
+
"eval_rougeL": 26.7433,
|
| 124 |
+
"eval_rougeLsum": 28.603,
|
| 125 |
+
"eval_runtime": 515.9852,
|
| 126 |
+
"eval_samples_per_second": 14.367,
|
| 127 |
+
"eval_steps_per_second": 0.45,
|
| 128 |
+
"step": 22242
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 14.0,
|
| 132 |
+
"learning_rate": 2.5922496935159194e-05,
|
| 133 |
+
"loss": 1.3756,
|
| 134 |
+
"step": 25949
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 14.0,
|
| 138 |
+
"eval_bleu": 92.9315,
|
| 139 |
+
"eval_f1_radgraph": 0.2377,
|
| 140 |
+
"eval_loss": 1.356188178062439,
|
| 141 |
+
"eval_rouge1": 29.8231,
|
| 142 |
+
"eval_rouge2": 16.7219,
|
| 143 |
+
"eval_rougeL": 26.8298,
|
| 144 |
+
"eval_rougeLsum": 28.6547,
|
| 145 |
+
"eval_runtime": 526.1612,
|
| 146 |
+
"eval_samples_per_second": 14.089,
|
| 147 |
+
"eval_steps_per_second": 0.441,
|
| 148 |
+
"step": 25949
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 16.0,
|
| 152 |
+
"learning_rate": 2.5319837208104264e-05,
|
| 153 |
+
"loss": 1.3534,
|
| 154 |
+
"step": 29656
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 16.0,
|
| 158 |
+
"eval_bleu": 90.1592,
|
| 159 |
+
"eval_f1_radgraph": 0.2402,
|
| 160 |
+
"eval_loss": 1.348175048828125,
|
| 161 |
+
"eval_rouge1": 29.9244,
|
| 162 |
+
"eval_rouge2": 16.8767,
|
| 163 |
+
"eval_rougeL": 26.9699,
|
| 164 |
+
"eval_rougeLsum": 28.7771,
|
| 165 |
+
"eval_runtime": 517.9401,
|
| 166 |
+
"eval_samples_per_second": 14.312,
|
| 167 |
+
"eval_steps_per_second": 0.448,
|
| 168 |
+
"step": 29656
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 18.0,
|
| 172 |
+
"learning_rate": 2.4717177481049338e-05,
|
| 173 |
+
"loss": 1.3335,
|
| 174 |
+
"step": 33363
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 18.0,
|
| 178 |
+
"eval_bleu": 93.8733,
|
| 179 |
+
"eval_f1_radgraph": 0.2412,
|
| 180 |
+
"eval_loss": 1.3401567935943604,
|
| 181 |
+
"eval_rouge1": 29.9866,
|
| 182 |
+
"eval_rouge2": 16.8753,
|
| 183 |
+
"eval_rougeL": 26.967,
|
| 184 |
+
"eval_rougeLsum": 28.8217,
|
| 185 |
+
"eval_runtime": 520.2162,
|
| 186 |
+
"eval_samples_per_second": 14.25,
|
| 187 |
+
"eval_steps_per_second": 0.446,
|
| 188 |
+
"step": 33363
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 19.99,
|
| 192 |
+
"learning_rate": 2.4114517753994412e-05,
|
| 193 |
+
"loss": 1.3157,
|
| 194 |
+
"step": 37070
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 19.99,
|
| 198 |
+
"eval_bleu": 90.6225,
|
| 199 |
+
"eval_f1_radgraph": 0.2409,
|
| 200 |
+
"eval_loss": 1.3334068059921265,
|
| 201 |
+
"eval_rouge1": 30.0245,
|
| 202 |
+
"eval_rouge2": 17.0323,
|
| 203 |
+
"eval_rougeL": 27.0771,
|
| 204 |
+
"eval_rougeLsum": 28.8866,
|
| 205 |
+
"eval_runtime": 523.6658,
|
| 206 |
+
"eval_samples_per_second": 14.156,
|
| 207 |
+
"eval_steps_per_second": 0.443,
|
| 208 |
+
"step": 37070
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 21.99,
|
| 212 |
+
"learning_rate": 2.3511858026939486e-05,
|
| 213 |
+
"loss": 1.2994,
|
| 214 |
+
"step": 40777
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 21.99,
|
| 218 |
+
"eval_bleu": 93.6108,
|
| 219 |
+
"eval_f1_radgraph": 0.2403,
|
| 220 |
+
"eval_loss": 1.3307315111160278,
|
| 221 |
+
"eval_rouge1": 29.9589,
|
| 222 |
+
"eval_rouge2": 16.9066,
|
| 223 |
+
"eval_rougeL": 26.9681,
|
| 224 |
+
"eval_rougeLsum": 28.7908,
|
| 225 |
+
"eval_runtime": 516.1874,
|
| 226 |
+
"eval_samples_per_second": 14.361,
|
| 227 |
+
"eval_steps_per_second": 0.449,
|
| 228 |
+
"step": 40777
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 23.99,
|
| 232 |
+
"learning_rate": 2.290919829988456e-05,
|
| 233 |
+
"loss": 1.2843,
|
| 234 |
+
"step": 44484
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 23.99,
|
| 238 |
+
"eval_bleu": 95.5973,
|
| 239 |
+
"eval_f1_radgraph": 0.241,
|
| 240 |
+
"eval_loss": 1.3280918598175049,
|
| 241 |
+
"eval_rouge1": 30.1835,
|
| 242 |
+
"eval_rouge2": 17.1623,
|
| 243 |
+
"eval_rougeL": 27.182,
|
| 244 |
+
"eval_rougeLsum": 29.0235,
|
| 245 |
+
"eval_runtime": 517.0183,
|
| 246 |
+
"eval_samples_per_second": 14.338,
|
| 247 |
+
"eval_steps_per_second": 0.449,
|
| 248 |
+
"step": 44484
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 25.99,
|
| 252 |
+
"learning_rate": 2.230653857282963e-05,
|
| 253 |
+
"loss": 1.2693,
|
| 254 |
+
"step": 48191
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 25.99,
|
| 258 |
+
"eval_bleu": 94.2149,
|
| 259 |
+
"eval_f1_radgraph": 0.2427,
|
| 260 |
+
"eval_loss": 1.3227483034133911,
|
| 261 |
+
"eval_rouge1": 30.2847,
|
| 262 |
+
"eval_rouge2": 17.2726,
|
| 263 |
+
"eval_rougeL": 27.2884,
|
| 264 |
+
"eval_rougeLsum": 29.1106,
|
| 265 |
+
"eval_runtime": 529.2786,
|
| 266 |
+
"eval_samples_per_second": 14.006,
|
| 267 |
+
"eval_steps_per_second": 0.438,
|
| 268 |
+
"step": 48191
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 27.99,
|
| 272 |
+
"learning_rate": 2.1703878845774707e-05,
|
| 273 |
+
"loss": 1.2564,
|
| 274 |
+
"step": 51898
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 27.99,
|
| 278 |
+
"eval_bleu": 94.0952,
|
| 279 |
+
"eval_f1_radgraph": 0.2446,
|
| 280 |
+
"eval_loss": 1.3205522298812866,
|
| 281 |
+
"eval_rouge1": 30.2975,
|
| 282 |
+
"eval_rouge2": 17.3352,
|
| 283 |
+
"eval_rougeL": 27.3306,
|
| 284 |
+
"eval_rougeLsum": 29.1631,
|
| 285 |
+
"eval_runtime": 522.5234,
|
| 286 |
+
"eval_samples_per_second": 14.187,
|
| 287 |
+
"eval_steps_per_second": 0.444,
|
| 288 |
+
"step": 51898
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 29.99,
|
| 292 |
+
"learning_rate": 2.1101219118719778e-05,
|
| 293 |
+
"loss": 1.2453,
|
| 294 |
+
"step": 55605
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 29.99,
|
| 298 |
+
"eval_bleu": 93.4725,
|
| 299 |
+
"eval_f1_radgraph": 0.2429,
|
| 300 |
+
"eval_loss": 1.3210633993148804,
|
| 301 |
+
"eval_rouge1": 30.2609,
|
| 302 |
+
"eval_rouge2": 17.3045,
|
| 303 |
+
"eval_rougeL": 27.2887,
|
| 304 |
+
"eval_rougeLsum": 29.0797,
|
| 305 |
+
"eval_runtime": 520.8063,
|
| 306 |
+
"eval_samples_per_second": 14.234,
|
| 307 |
+
"eval_steps_per_second": 0.445,
|
| 308 |
+
"step": 55605
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 31.99,
|
| 312 |
+
"learning_rate": 2.0498559391664852e-05,
|
| 313 |
+
"loss": 1.2332,
|
| 314 |
+
"step": 59312
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 31.99,
|
| 318 |
+
"eval_bleu": 90.7444,
|
| 319 |
+
"eval_f1_radgraph": 0.2423,
|
| 320 |
+
"eval_loss": 1.3173481225967407,
|
| 321 |
+
"eval_rouge1": 30.2939,
|
| 322 |
+
"eval_rouge2": 17.3007,
|
| 323 |
+
"eval_rougeL": 27.2658,
|
| 324 |
+
"eval_rougeLsum": 29.1106,
|
| 325 |
+
"eval_runtime": 520.4251,
|
| 326 |
+
"eval_samples_per_second": 14.244,
|
| 327 |
+
"eval_steps_per_second": 0.446,
|
| 328 |
+
"step": 59312
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 33.99,
|
| 332 |
+
"learning_rate": 1.9895899664609926e-05,
|
| 333 |
+
"loss": 1.2229,
|
| 334 |
+
"step": 63019
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 33.99,
|
| 338 |
+
"eval_bleu": 90.9915,
|
| 339 |
+
"eval_f1_radgraph": 0.2444,
|
| 340 |
+
"eval_loss": 1.317107081413269,
|
| 341 |
+
"eval_rouge1": 30.3679,
|
| 342 |
+
"eval_rouge2": 17.3809,
|
| 343 |
+
"eval_rougeL": 27.3829,
|
| 344 |
+
"eval_rougeLsum": 29.1488,
|
| 345 |
+
"eval_runtime": 520.2024,
|
| 346 |
+
"eval_samples_per_second": 14.25,
|
| 347 |
+
"eval_steps_per_second": 0.446,
|
| 348 |
+
"step": 63019
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 35.99,
|
| 352 |
+
"learning_rate": 1.9293239937555e-05,
|
| 353 |
+
"loss": 1.2123,
|
| 354 |
+
"step": 66726
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 35.99,
|
| 358 |
+
"eval_bleu": 96.0056,
|
| 359 |
+
"eval_f1_radgraph": 0.2452,
|
| 360 |
+
"eval_loss": 1.3161959648132324,
|
| 361 |
+
"eval_rouge1": 30.438,
|
| 362 |
+
"eval_rouge2": 17.4316,
|
| 363 |
+
"eval_rougeL": 27.4584,
|
| 364 |
+
"eval_rougeLsum": 29.2665,
|
| 365 |
+
"eval_runtime": 518.103,
|
| 366 |
+
"eval_samples_per_second": 14.308,
|
| 367 |
+
"eval_steps_per_second": 0.448,
|
| 368 |
+
"step": 66726
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 185400,
|
| 372 |
+
"num_train_epochs": 100,
|
| 373 |
+
"total_flos": 1.1641360206370867e+18,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61e1f7285feda686050d723b80545ecaa293ccd98ce0fa5cb5b1291844c7649c
|
| 3 |
+
size 3503
|