Commit
·
06ab5ca
1
Parent(s):
628db30
new update
Browse files- all_results.json +17 -0
- config.json +63 -0
- eval_results.json +12 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +637 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.87,
|
| 3 |
+
"eval_accuracy": 0.9627190437507253,
|
| 4 |
+
"eval_f1": 0.961489415965315,
|
| 5 |
+
"eval_loss": 0.25795629620552063,
|
| 6 |
+
"eval_precision": 0.9496221662468514,
|
| 7 |
+
"eval_recall": 0.9736570247933884,
|
| 8 |
+
"eval_runtime": 3.2529,
|
| 9 |
+
"eval_samples": 93,
|
| 10 |
+
"eval_samples_per_second": 28.59,
|
| 11 |
+
"eval_steps_per_second": 0.922,
|
| 12 |
+
"train_loss": 0.16514424514770507,
|
| 13 |
+
"train_runtime": 1048.0167,
|
| 14 |
+
"train_samples": 1010,
|
| 15 |
+
"train_samples_per_second": 7.633,
|
| 16 |
+
"train_steps_per_second": 0.954
|
| 17 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "layoutlmv3-base-chinese",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 128,
|
| 10 |
+
"device": "cuda",
|
| 11 |
+
"discrete_vae_type": "dall-e",
|
| 12 |
+
"discrete_vae_weight_path": "",
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"finetuning_task": "ner",
|
| 15 |
+
"has_relative_attention_bias": true,
|
| 16 |
+
"has_spatial_attention_bias": true,
|
| 17 |
+
"hidden_act": "gelu",
|
| 18 |
+
"hidden_dropout_prob": 0.1,
|
| 19 |
+
"hidden_size": 768,
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "LABEL_0",
|
| 22 |
+
"1": "LABEL_1",
|
| 23 |
+
"2": "LABEL_2",
|
| 24 |
+
"3": "LABEL_3",
|
| 25 |
+
"4": "LABEL_4",
|
| 26 |
+
"5": "LABEL_5",
|
| 27 |
+
"6": "LABEL_6"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"input_size": 224,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"LABEL_0": 0,
|
| 34 |
+
"LABEL_1": 1,
|
| 35 |
+
"LABEL_2": 2,
|
| 36 |
+
"LABEL_3": 3,
|
| 37 |
+
"LABEL_4": 4,
|
| 38 |
+
"LABEL_5": 5,
|
| 39 |
+
"LABEL_6": 6
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-05,
|
| 42 |
+
"max_2d_position_embeddings": 1024,
|
| 43 |
+
"max_position_embeddings": 514,
|
| 44 |
+
"max_rel_2d_pos": 256,
|
| 45 |
+
"max_rel_pos": 128,
|
| 46 |
+
"mim": false,
|
| 47 |
+
"model_type": "layoutlmv3",
|
| 48 |
+
"num_attention_heads": 12,
|
| 49 |
+
"num_hidden_layers": 12,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"position_embedding_type": "absolute",
|
| 52 |
+
"rel_2d_pos_bins": 64,
|
| 53 |
+
"rel_pos_bins": 32,
|
| 54 |
+
"second_input_size": 112,
|
| 55 |
+
"shape_size": 128,
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.12.5",
|
| 58 |
+
"type_vocab_size": 1,
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"visual_embed": true,
|
| 61 |
+
"vocab_size": 250002,
|
| 62 |
+
"wpa_task": false
|
| 63 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.87,
|
| 3 |
+
"eval_accuracy": 0.9627190437507253,
|
| 4 |
+
"eval_f1": 0.961489415965315,
|
| 5 |
+
"eval_loss": 0.25795629620552063,
|
| 6 |
+
"eval_precision": 0.9496221662468514,
|
| 7 |
+
"eval_recall": 0.9736570247933884,
|
| 8 |
+
"eval_runtime": 3.2529,
|
| 9 |
+
"eval_samples": 93,
|
| 10 |
+
"eval_samples_per_second": 28.59,
|
| 11 |
+
"eval_steps_per_second": 0.922
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c6b41c4cca53bef42d8b7fe1d6cba8b65d6132de44d5f42ce23f4d1da81e4f2
|
| 3 |
+
size 1115012947
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "add_prefix_space": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "layoutlmv3-base-chinese", "tokenizer_class": "XLMRobertaTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.87,
|
| 3 |
+
"train_loss": 0.16514424514770507,
|
| 4 |
+
"train_runtime": 1048.0167,
|
| 5 |
+
"train_samples": 1010,
|
| 6 |
+
"train_samples_per_second": 7.633,
|
| 7 |
+
"train_steps_per_second": 0.954
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,637 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.874015748031496,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"eval_accuracy": 0.8157711500522223,
|
| 13 |
+
"eval_f1": 0.5942329873125721,
|
| 14 |
+
"eval_loss": 0.4848455488681793,
|
| 15 |
+
"eval_precision": 0.5368903709879116,
|
| 16 |
+
"eval_recall": 0.6652892561983471,
|
| 17 |
+
"eval_runtime": 2.2498,
|
| 18 |
+
"eval_samples_per_second": 41.337,
|
| 19 |
+
"eval_steps_per_second": 1.333,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.31,
|
| 24 |
+
"eval_accuracy": 0.8389520714865962,
|
| 25 |
+
"eval_f1": 0.7553421368547419,
|
| 26 |
+
"eval_loss": 0.39182421565055847,
|
| 27 |
+
"eval_precision": 0.705697622252131,
|
| 28 |
+
"eval_recall": 0.8125,
|
| 29 |
+
"eval_runtime": 2.9557,
|
| 30 |
+
"eval_samples_per_second": 31.465,
|
| 31 |
+
"eval_steps_per_second": 1.015,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.47,
|
| 36 |
+
"eval_accuracy": 0.8849947777648833,
|
| 37 |
+
"eval_f1": 0.8393364928909953,
|
| 38 |
+
"eval_loss": 0.34172168374061584,
|
| 39 |
+
"eval_precision": 0.7753940455341506,
|
| 40 |
+
"eval_recall": 0.9147727272727273,
|
| 41 |
+
"eval_runtime": 2.9806,
|
| 42 |
+
"eval_samples_per_second": 31.202,
|
| 43 |
+
"eval_steps_per_second": 1.007,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.63,
|
| 48 |
+
"eval_accuracy": 0.8782929093652083,
|
| 49 |
+
"eval_f1": 0.878610002347969,
|
| 50 |
+
"eval_loss": 0.3457355201244354,
|
| 51 |
+
"eval_precision": 0.8054240206629358,
|
| 52 |
+
"eval_recall": 0.9664256198347108,
|
| 53 |
+
"eval_runtime": 3.288,
|
| 54 |
+
"eval_samples_per_second": 28.285,
|
| 55 |
+
"eval_steps_per_second": 0.912,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.79,
|
| 60 |
+
"eval_accuracy": 0.9183880700940003,
|
| 61 |
+
"eval_f1": 0.8993830090175606,
|
| 62 |
+
"eval_loss": 0.26329365372657776,
|
| 63 |
+
"eval_precision": 0.8318700614574188,
|
| 64 |
+
"eval_recall": 0.9788223140495868,
|
| 65 |
+
"eval_runtime": 3.262,
|
| 66 |
+
"eval_samples_per_second": 28.51,
|
| 67 |
+
"eval_steps_per_second": 0.92,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.94,
|
| 72 |
+
"eval_accuracy": 0.9218695601717535,
|
| 73 |
+
"eval_f1": 0.908175497482618,
|
| 74 |
+
"eval_loss": 0.27159208059310913,
|
| 75 |
+
"eval_precision": 0.847427293064877,
|
| 76 |
+
"eval_recall": 0.9783057851239669,
|
| 77 |
+
"eval_runtime": 2.2237,
|
| 78 |
+
"eval_samples_per_second": 41.822,
|
| 79 |
+
"eval_steps_per_second": 1.349,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.1,
|
| 84 |
+
"eval_accuracy": 0.931965881397238,
|
| 85 |
+
"eval_f1": 0.8820210939416238,
|
| 86 |
+
"eval_loss": 0.20828573405742645,
|
| 87 |
+
"eval_precision": 0.8397944885567492,
|
| 88 |
+
"eval_recall": 0.9287190082644629,
|
| 89 |
+
"eval_runtime": 2.2685,
|
| 90 |
+
"eval_samples_per_second": 40.996,
|
| 91 |
+
"eval_steps_per_second": 1.322,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.26,
|
| 96 |
+
"eval_accuracy": 0.893669490541952,
|
| 97 |
+
"eval_f1": 0.8734673859735164,
|
| 98 |
+
"eval_loss": 0.33937641978263855,
|
| 99 |
+
"eval_precision": 0.8314659197012139,
|
| 100 |
+
"eval_recall": 0.9199380165289256,
|
| 101 |
+
"eval_runtime": 3.2652,
|
| 102 |
+
"eval_samples_per_second": 28.482,
|
| 103 |
+
"eval_steps_per_second": 0.919,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.42,
|
| 108 |
+
"eval_accuracy": 0.883079958222119,
|
| 109 |
+
"eval_f1": 0.8970068347867075,
|
| 110 |
+
"eval_loss": 0.35709869861602783,
|
| 111 |
+
"eval_precision": 0.8248807975726051,
|
| 112 |
+
"eval_recall": 0.9829545454545454,
|
| 113 |
+
"eval_runtime": 3.2871,
|
| 114 |
+
"eval_samples_per_second": 28.292,
|
| 115 |
+
"eval_steps_per_second": 0.913,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.57,
|
| 120 |
+
"eval_accuracy": 0.9112800278519206,
|
| 121 |
+
"eval_f1": 0.8886283704572099,
|
| 122 |
+
"eval_loss": 0.2868669033050537,
|
| 123 |
+
"eval_precision": 0.8136539287247746,
|
| 124 |
+
"eval_recall": 0.9788223140495868,
|
| 125 |
+
"eval_runtime": 2.9919,
|
| 126 |
+
"eval_samples_per_second": 31.084,
|
| 127 |
+
"eval_steps_per_second": 1.003,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.73,
|
| 132 |
+
"eval_accuracy": 0.9393350353951492,
|
| 133 |
+
"eval_f1": 0.9247259439707675,
|
| 134 |
+
"eval_loss": 0.201907679438591,
|
| 135 |
+
"eval_precision": 0.8750576302443522,
|
| 136 |
+
"eval_recall": 0.9803719008264463,
|
| 137 |
+
"eval_runtime": 2.2839,
|
| 138 |
+
"eval_samples_per_second": 40.72,
|
| 139 |
+
"eval_steps_per_second": 1.314,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.89,
|
| 144 |
+
"eval_accuracy": 0.9525937101079262,
|
| 145 |
+
"eval_f1": 0.9215399610136452,
|
| 146 |
+
"eval_loss": 0.1594531089067459,
|
| 147 |
+
"eval_precision": 0.8722324723247232,
|
| 148 |
+
"eval_recall": 0.9767561983471075,
|
| 149 |
+
"eval_runtime": 2.9584,
|
| 150 |
+
"eval_samples_per_second": 31.436,
|
| 151 |
+
"eval_steps_per_second": 1.014,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.05,
|
| 156 |
+
"eval_accuracy": 0.9378263896947894,
|
| 157 |
+
"eval_f1": 0.9166058837831268,
|
| 158 |
+
"eval_loss": 0.22776451706886292,
|
| 159 |
+
"eval_precision": 0.8658704639412035,
|
| 160 |
+
"eval_recall": 0.9736570247933884,
|
| 161 |
+
"eval_runtime": 3.2621,
|
| 162 |
+
"eval_samples_per_second": 28.509,
|
| 163 |
+
"eval_steps_per_second": 0.92,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.2,
|
| 168 |
+
"eval_accuracy": 0.9292677265869792,
|
| 169 |
+
"eval_f1": 0.8771048002010556,
|
| 170 |
+
"eval_loss": 0.23985013365745544,
|
| 171 |
+
"eval_precision": 0.8541360744003916,
|
| 172 |
+
"eval_recall": 0.9013429752066116,
|
| 173 |
+
"eval_runtime": 2.2706,
|
| 174 |
+
"eval_samples_per_second": 40.959,
|
| 175 |
+
"eval_steps_per_second": 1.321,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.36,
|
| 180 |
+
"eval_accuracy": 0.9322850179876987,
|
| 181 |
+
"eval_f1": 0.9097725568607848,
|
| 182 |
+
"eval_loss": 0.2839757800102234,
|
| 183 |
+
"eval_precision": 0.8813559322033898,
|
| 184 |
+
"eval_recall": 0.9400826446280992,
|
| 185 |
+
"eval_runtime": 3.2602,
|
| 186 |
+
"eval_samples_per_second": 28.525,
|
| 187 |
+
"eval_steps_per_second": 0.92,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.52,
|
| 192 |
+
"eval_accuracy": 0.9572356968782639,
|
| 193 |
+
"eval_f1": 0.9368919930157147,
|
| 194 |
+
"eval_loss": 0.15871362388134003,
|
| 195 |
+
"eval_precision": 0.9059334298118669,
|
| 196 |
+
"eval_recall": 0.9700413223140496,
|
| 197 |
+
"eval_runtime": 2.2505,
|
| 198 |
+
"eval_samples_per_second": 41.325,
|
| 199 |
+
"eval_steps_per_second": 1.333,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.68,
|
| 204 |
+
"eval_accuracy": 0.9558431008471626,
|
| 205 |
+
"eval_f1": 0.9427135678391959,
|
| 206 |
+
"eval_loss": 0.16202741861343384,
|
| 207 |
+
"eval_precision": 0.9178082191780822,
|
| 208 |
+
"eval_recall": 0.96900826446281,
|
| 209 |
+
"eval_runtime": 3.2378,
|
| 210 |
+
"eval_samples_per_second": 28.723,
|
| 211 |
+
"eval_steps_per_second": 0.927,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.83,
|
| 216 |
+
"eval_accuracy": 0.9299059997679007,
|
| 217 |
+
"eval_f1": 0.9343610144206862,
|
| 218 |
+
"eval_loss": 0.27064642310142517,
|
| 219 |
+
"eval_precision": 0.9007670182166826,
|
| 220 |
+
"eval_recall": 0.9705578512396694,
|
| 221 |
+
"eval_runtime": 3.2832,
|
| 222 |
+
"eval_samples_per_second": 28.326,
|
| 223 |
+
"eval_steps_per_second": 0.914,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.99,
|
| 228 |
+
"eval_accuracy": 0.9477486364163862,
|
| 229 |
+
"eval_f1": 0.9423980222496909,
|
| 230 |
+
"eval_loss": 0.18907134234905243,
|
| 231 |
+
"eval_precision": 0.9037458511142722,
|
| 232 |
+
"eval_recall": 0.984504132231405,
|
| 233 |
+
"eval_runtime": 3.2921,
|
| 234 |
+
"eval_samples_per_second": 28.25,
|
| 235 |
+
"eval_steps_per_second": 0.911,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.15,
|
| 240 |
+
"eval_accuracy": 0.9234072182894278,
|
| 241 |
+
"eval_f1": 0.9175810155651952,
|
| 242 |
+
"eval_loss": 0.26186808943748474,
|
| 243 |
+
"eval_precision": 0.9067070095814422,
|
| 244 |
+
"eval_recall": 0.9287190082644629,
|
| 245 |
+
"eval_runtime": 3.296,
|
| 246 |
+
"eval_samples_per_second": 28.216,
|
| 247 |
+
"eval_steps_per_second": 0.91,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.31,
|
| 252 |
+
"eval_accuracy": 0.9601949634443542,
|
| 253 |
+
"eval_f1": 0.9384654342871613,
|
| 254 |
+
"eval_loss": 0.1693572849035263,
|
| 255 |
+
"eval_precision": 0.9205166418281172,
|
| 256 |
+
"eval_recall": 0.9571280991735537,
|
| 257 |
+
"eval_runtime": 2.2486,
|
| 258 |
+
"eval_samples_per_second": 41.36,
|
| 259 |
+
"eval_steps_per_second": 1.334,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.46,
|
| 264 |
+
"eval_accuracy": 0.9532900081234769,
|
| 265 |
+
"eval_f1": 0.9351432880844646,
|
| 266 |
+
"eval_loss": 0.20067894458770752,
|
| 267 |
+
"eval_precision": 0.910871694417238,
|
| 268 |
+
"eval_recall": 0.9607438016528925,
|
| 269 |
+
"eval_runtime": 3.2966,
|
| 270 |
+
"eval_samples_per_second": 28.211,
|
| 271 |
+
"eval_steps_per_second": 0.91,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.62,
|
| 276 |
+
"eval_accuracy": 0.9529998839503308,
|
| 277 |
+
"eval_f1": 0.9408805031446541,
|
| 278 |
+
"eval_loss": 0.2007509469985962,
|
| 279 |
+
"eval_precision": 0.9171162334477685,
|
| 280 |
+
"eval_recall": 0.9659090909090909,
|
| 281 |
+
"eval_runtime": 2.9788,
|
| 282 |
+
"eval_samples_per_second": 31.22,
|
| 283 |
+
"eval_steps_per_second": 1.007,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.78,
|
| 288 |
+
"eval_accuracy": 0.9438609724962284,
|
| 289 |
+
"eval_f1": 0.9448345035105317,
|
| 290 |
+
"eval_loss": 0.2780458927154541,
|
| 291 |
+
"eval_precision": 0.9181286549707602,
|
| 292 |
+
"eval_recall": 0.9731404958677686,
|
| 293 |
+
"eval_runtime": 2.2763,
|
| 294 |
+
"eval_samples_per_second": 40.855,
|
| 295 |
+
"eval_steps_per_second": 1.318,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.94,
|
| 300 |
+
"learning_rate": 3.5e-05,
|
| 301 |
+
"loss": 0.2747,
|
| 302 |
+
"step": 500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.94,
|
| 306 |
+
"eval_accuracy": 0.9434838110711384,
|
| 307 |
+
"eval_f1": 0.9407256004087889,
|
| 308 |
+
"eval_loss": 0.22288289666175842,
|
| 309 |
+
"eval_precision": 0.9307381193124368,
|
| 310 |
+
"eval_recall": 0.9509297520661157,
|
| 311 |
+
"eval_runtime": 2.2152,
|
| 312 |
+
"eval_samples_per_second": 41.983,
|
| 313 |
+
"eval_steps_per_second": 1.354,
|
| 314 |
+
"step": 500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.09,
|
| 318 |
+
"eval_accuracy": 0.9413659046071718,
|
| 319 |
+
"eval_f1": 0.9442211055276382,
|
| 320 |
+
"eval_loss": 0.2373497188091278,
|
| 321 |
+
"eval_precision": 0.9192759295499021,
|
| 322 |
+
"eval_recall": 0.9705578512396694,
|
| 323 |
+
"eval_runtime": 2.286,
|
| 324 |
+
"eval_samples_per_second": 40.682,
|
| 325 |
+
"eval_steps_per_second": 1.312,
|
| 326 |
+
"step": 520
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.25,
|
| 330 |
+
"eval_accuracy": 0.9290066148311478,
|
| 331 |
+
"eval_f1": 0.9232756393696718,
|
| 332 |
+
"eval_loss": 0.32156404852867126,
|
| 333 |
+
"eval_precision": 0.9235142118863049,
|
| 334 |
+
"eval_recall": 0.9230371900826446,
|
| 335 |
+
"eval_runtime": 3.2781,
|
| 336 |
+
"eval_samples_per_second": 28.371,
|
| 337 |
+
"eval_steps_per_second": 0.915,
|
| 338 |
+
"step": 540
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.41,
|
| 342 |
+
"eval_accuracy": 0.9621387954044331,
|
| 343 |
+
"eval_f1": 0.9501378100726634,
|
| 344 |
+
"eval_loss": 0.1727248579263687,
|
| 345 |
+
"eval_precision": 0.9226277372262773,
|
| 346 |
+
"eval_recall": 0.9793388429752066,
|
| 347 |
+
"eval_runtime": 3.2891,
|
| 348 |
+
"eval_samples_per_second": 28.275,
|
| 349 |
+
"eval_steps_per_second": 0.912,
|
| 350 |
+
"step": 560
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.57,
|
| 354 |
+
"eval_accuracy": 0.9612974353023094,
|
| 355 |
+
"eval_f1": 0.9563451776649746,
|
| 356 |
+
"eval_loss": 0.2031358927488327,
|
| 357 |
+
"eval_precision": 0.9401197604790419,
|
| 358 |
+
"eval_recall": 0.9731404958677686,
|
| 359 |
+
"eval_runtime": 2.9761,
|
| 360 |
+
"eval_samples_per_second": 31.249,
|
| 361 |
+
"eval_steps_per_second": 1.008,
|
| 362 |
+
"step": 580
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.72,
|
| 366 |
+
"eval_accuracy": 0.9507079029824765,
|
| 367 |
+
"eval_f1": 0.9494897959183674,
|
| 368 |
+
"eval_loss": 0.24843396246433258,
|
| 369 |
+
"eval_precision": 0.9380040322580645,
|
| 370 |
+
"eval_recall": 0.9612603305785123,
|
| 371 |
+
"eval_runtime": 2.242,
|
| 372 |
+
"eval_samples_per_second": 41.481,
|
| 373 |
+
"eval_steps_per_second": 1.338,
|
| 374 |
+
"step": 600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.88,
|
| 378 |
+
"eval_accuracy": 0.9590054543344552,
|
| 379 |
+
"eval_f1": 0.9607390300230947,
|
| 380 |
+
"eval_loss": 0.2189687043428421,
|
| 381 |
+
"eval_precision": 0.9546149923508415,
|
| 382 |
+
"eval_recall": 0.9669421487603306,
|
| 383 |
+
"eval_runtime": 3.2795,
|
| 384 |
+
"eval_samples_per_second": 28.358,
|
| 385 |
+
"eval_steps_per_second": 0.915,
|
| 386 |
+
"step": 620
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.04,
|
| 390 |
+
"eval_accuracy": 0.9571486596263201,
|
| 391 |
+
"eval_f1": 0.9600409836065573,
|
| 392 |
+
"eval_loss": 0.25752872228622437,
|
| 393 |
+
"eval_precision": 0.9522357723577236,
|
| 394 |
+
"eval_recall": 0.9679752066115702,
|
| 395 |
+
"eval_runtime": 2.2527,
|
| 396 |
+
"eval_samples_per_second": 41.284,
|
| 397 |
+
"eval_steps_per_second": 1.332,
|
| 398 |
+
"step": 640
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.2,
|
| 402 |
+
"eval_accuracy": 0.9608622490425902,
|
| 403 |
+
"eval_f1": 0.9593869731800767,
|
| 404 |
+
"eval_loss": 0.24718773365020752,
|
| 405 |
+
"eval_precision": 0.9489641232945932,
|
| 406 |
+
"eval_recall": 0.9700413223140496,
|
| 407 |
+
"eval_runtime": 2.2796,
|
| 408 |
+
"eval_samples_per_second": 40.796,
|
| 409 |
+
"eval_steps_per_second": 1.316,
|
| 410 |
+
"step": 660
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 5.35,
|
| 414 |
+
"eval_accuracy": 0.9522165486828362,
|
| 415 |
+
"eval_f1": 0.9561671763506625,
|
| 416 |
+
"eval_loss": 0.2798936367034912,
|
| 417 |
+
"eval_precision": 0.9436619718309859,
|
| 418 |
+
"eval_recall": 0.96900826446281,
|
| 419 |
+
"eval_runtime": 3.2922,
|
| 420 |
+
"eval_samples_per_second": 28.249,
|
| 421 |
+
"eval_steps_per_second": 0.911,
|
| 422 |
+
"step": 680
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.51,
|
| 426 |
+
"eval_accuracy": 0.9556400139259603,
|
| 427 |
+
"eval_f1": 0.9535588086824837,
|
| 428 |
+
"eval_loss": 0.26087334752082825,
|
| 429 |
+
"eval_precision": 0.9323790720631787,
|
| 430 |
+
"eval_recall": 0.9757231404958677,
|
| 431 |
+
"eval_runtime": 2.2499,
|
| 432 |
+
"eval_samples_per_second": 41.335,
|
| 433 |
+
"eval_steps_per_second": 1.333,
|
| 434 |
+
"step": 700
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.67,
|
| 438 |
+
"eval_accuracy": 0.9529418591157015,
|
| 439 |
+
"eval_f1": 0.9502170028082715,
|
| 440 |
+
"eval_loss": 0.23053081333637238,
|
| 441 |
+
"eval_precision": 0.939424533064109,
|
| 442 |
+
"eval_recall": 0.9612603305785123,
|
| 443 |
+
"eval_runtime": 3.2663,
|
| 444 |
+
"eval_samples_per_second": 28.473,
|
| 445 |
+
"eval_steps_per_second": 0.918,
|
| 446 |
+
"step": 720
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.83,
|
| 450 |
+
"eval_accuracy": 0.9524486480213531,
|
| 451 |
+
"eval_f1": 0.954763709881223,
|
| 452 |
+
"eval_loss": 0.2539260983467102,
|
| 453 |
+
"eval_precision": 0.9346857991093518,
|
| 454 |
+
"eval_recall": 0.9757231404958677,
|
| 455 |
+
"eval_runtime": 3.298,
|
| 456 |
+
"eval_samples_per_second": 28.199,
|
| 457 |
+
"eval_steps_per_second": 0.91,
|
| 458 |
+
"step": 740
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.98,
|
| 462 |
+
"eval_accuracy": 0.9543634675641175,
|
| 463 |
+
"eval_f1": 0.9617654606107262,
|
| 464 |
+
"eval_loss": 0.28202250599861145,
|
| 465 |
+
"eval_precision": 0.9556348801631821,
|
| 466 |
+
"eval_recall": 0.9679752066115702,
|
| 467 |
+
"eval_runtime": 3.2935,
|
| 468 |
+
"eval_samples_per_second": 28.237,
|
| 469 |
+
"eval_steps_per_second": 0.911,
|
| 470 |
+
"step": 760
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.14,
|
| 474 |
+
"eval_accuracy": 0.9599048392712081,
|
| 475 |
+
"eval_f1": 0.9617065021845285,
|
| 476 |
+
"eval_loss": 0.23321200907230377,
|
| 477 |
+
"eval_precision": 0.9570332480818414,
|
| 478 |
+
"eval_recall": 0.9664256198347108,
|
| 479 |
+
"eval_runtime": 3.2967,
|
| 480 |
+
"eval_samples_per_second": 28.21,
|
| 481 |
+
"eval_steps_per_second": 0.91,
|
| 482 |
+
"step": 780
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.3,
|
| 486 |
+
"eval_accuracy": 0.9590054543344552,
|
| 487 |
+
"eval_f1": 0.961734693877551,
|
| 488 |
+
"eval_loss": 0.25181254744529724,
|
| 489 |
+
"eval_precision": 0.9501008064516129,
|
| 490 |
+
"eval_recall": 0.9736570247933884,
|
| 491 |
+
"eval_runtime": 2.9863,
|
| 492 |
+
"eval_samples_per_second": 31.142,
|
| 493 |
+
"eval_steps_per_second": 1.005,
|
| 494 |
+
"step": 800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.46,
|
| 498 |
+
"eval_accuracy": 0.95752582105141,
|
| 499 |
+
"eval_f1": 0.9602258147292788,
|
| 500 |
+
"eval_loss": 0.2890544533729553,
|
| 501 |
+
"eval_precision": 0.954105048444671,
|
| 502 |
+
"eval_recall": 0.9664256198347108,
|
| 503 |
+
"eval_runtime": 2.2411,
|
| 504 |
+
"eval_samples_per_second": 41.497,
|
| 505 |
+
"eval_steps_per_second": 1.339,
|
| 506 |
+
"step": 820
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.61,
|
| 510 |
+
"eval_accuracy": 0.9568875478704886,
|
| 511 |
+
"eval_f1": 0.9569451563300871,
|
| 512 |
+
"eval_loss": 0.29066193103790283,
|
| 513 |
+
"eval_precision": 0.9496439471007121,
|
| 514 |
+
"eval_recall": 0.9643595041322314,
|
| 515 |
+
"eval_runtime": 2.2281,
|
| 516 |
+
"eval_samples_per_second": 41.74,
|
| 517 |
+
"eval_steps_per_second": 1.346,
|
| 518 |
+
"step": 840
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.77,
|
| 522 |
+
"eval_accuracy": 0.9598178020192643,
|
| 523 |
+
"eval_f1": 0.9613118114271074,
|
| 524 |
+
"eval_loss": 0.26129651069641113,
|
| 525 |
+
"eval_precision": 0.9537366548042705,
|
| 526 |
+
"eval_recall": 0.96900826446281,
|
| 527 |
+
"eval_runtime": 2.2516,
|
| 528 |
+
"eval_samples_per_second": 41.305,
|
| 529 |
+
"eval_steps_per_second": 1.332,
|
| 530 |
+
"step": 860
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.93,
|
| 534 |
+
"eval_accuracy": 0.9592085412556575,
|
| 535 |
+
"eval_f1": 0.96229802513465,
|
| 536 |
+
"eval_loss": 0.25751829147338867,
|
| 537 |
+
"eval_precision": 0.9556800815078961,
|
| 538 |
+
"eval_recall": 0.96900826446281,
|
| 539 |
+
"eval_runtime": 2.2645,
|
| 540 |
+
"eval_samples_per_second": 41.068,
|
| 541 |
+
"eval_steps_per_second": 1.325,
|
| 542 |
+
"step": 880
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.09,
|
| 546 |
+
"eval_accuracy": 0.9583381687362191,
|
| 547 |
+
"eval_f1": 0.9625832906201948,
|
| 548 |
+
"eval_loss": 0.26336678862571716,
|
| 549 |
+
"eval_precision": 0.9552390640895219,
|
| 550 |
+
"eval_recall": 0.9700413223140496,
|
| 551 |
+
"eval_runtime": 2.2487,
|
| 552 |
+
"eval_samples_per_second": 41.357,
|
| 553 |
+
"eval_steps_per_second": 1.334,
|
| 554 |
+
"step": 900
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 7.24,
|
| 558 |
+
"eval_accuracy": 0.9581640942323314,
|
| 559 |
+
"eval_f1": 0.9588550983899822,
|
| 560 |
+
"eval_loss": 0.2639918923377991,
|
| 561 |
+
"eval_precision": 0.9489124936772888,
|
| 562 |
+
"eval_recall": 0.96900826446281,
|
| 563 |
+
"eval_runtime": 2.996,
|
| 564 |
+
"eval_samples_per_second": 31.041,
|
| 565 |
+
"eval_steps_per_second": 1.001,
|
| 566 |
+
"step": 920
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 7.4,
|
| 570 |
+
"eval_accuracy": 0.9608622490425902,
|
| 571 |
+
"eval_f1": 0.9594284256187804,
|
| 572 |
+
"eval_loss": 0.2650795876979828,
|
| 573 |
+
"eval_precision": 0.9480584972264247,
|
| 574 |
+
"eval_recall": 0.9710743801652892,
|
| 575 |
+
"eval_runtime": 3.2719,
|
| 576 |
+
"eval_samples_per_second": 28.424,
|
| 577 |
+
"eval_steps_per_second": 0.917,
|
| 578 |
+
"step": 940
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 7.56,
|
| 582 |
+
"eval_accuracy": 0.9626900313334107,
|
| 583 |
+
"eval_f1": 0.9609992352791231,
|
| 584 |
+
"eval_loss": 0.26358404755592346,
|
| 585 |
+
"eval_precision": 0.9486663311524912,
|
| 586 |
+
"eval_recall": 0.9736570247933884,
|
| 587 |
+
"eval_runtime": 3.271,
|
| 588 |
+
"eval_samples_per_second": 28.432,
|
| 589 |
+
"eval_steps_per_second": 0.917,
|
| 590 |
+
"step": 960
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.72,
|
| 594 |
+
"eval_accuracy": 0.9627190437507253,
|
| 595 |
+
"eval_f1": 0.9622256253190403,
|
| 596 |
+
"eval_loss": 0.2597278356552124,
|
| 597 |
+
"eval_precision": 0.9510595358224017,
|
| 598 |
+
"eval_recall": 0.9736570247933884,
|
| 599 |
+
"eval_runtime": 2.9416,
|
| 600 |
+
"eval_samples_per_second": 31.616,
|
| 601 |
+
"eval_steps_per_second": 1.02,
|
| 602 |
+
"step": 980
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 7.87,
|
| 606 |
+
"learning_rate": 0.0,
|
| 607 |
+
"loss": 0.0555,
|
| 608 |
+
"step": 1000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 7.87,
|
| 612 |
+
"eval_accuracy": 0.9627190437507253,
|
| 613 |
+
"eval_f1": 0.961489415965315,
|
| 614 |
+
"eval_loss": 0.25795629620552063,
|
| 615 |
+
"eval_precision": 0.9496221662468514,
|
| 616 |
+
"eval_recall": 0.9736570247933884,
|
| 617 |
+
"eval_runtime": 3.3,
|
| 618 |
+
"eval_samples_per_second": 28.182,
|
| 619 |
+
"eval_steps_per_second": 0.909,
|
| 620 |
+
"step": 1000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7.87,
|
| 624 |
+
"step": 1000,
|
| 625 |
+
"total_flos": 2101461798354944.0,
|
| 626 |
+
"train_loss": 0.16514424514770507,
|
| 627 |
+
"train_runtime": 1048.0167,
|
| 628 |
+
"train_samples_per_second": 7.633,
|
| 629 |
+
"train_steps_per_second": 0.954
|
| 630 |
+
}
|
| 631 |
+
],
|
| 632 |
+
"max_steps": 1000,
|
| 633 |
+
"num_train_epochs": 8,
|
| 634 |
+
"total_flos": 2101461798354944.0,
|
| 635 |
+
"trial_name": null,
|
| 636 |
+
"trial_params": null
|
| 637 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02cd8c617615f92219a1e890e27e84cad009b93707a3ef529ab2887eee039560
|
| 3 |
+
size 2799
|