add
Browse files- all_results.json +17 -0
- config.json +57 -0
- eval_results.json +11 -0
- merges.txt +0 -0
- runs/Apr17_09-22-17_deeplearning28/1650187356.1828399/events.out.tfevents.1650187356.deeplearning28.62374.1 +3 -0
- runs/Apr17_09-22-17_deeplearning28/events.out.tfevents.1650187356.deeplearning28.62374.0 +3 -0
- runs/Apr17_09-22-17_deeplearning28/events.out.tfevents.1650187663.deeplearning28.62374.2 +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
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8317638952687184,
|
| 4 |
+
"eval_f1": 0.9058561897702001,
|
| 5 |
+
"eval_loss": 1.1073323488235474,
|
| 6 |
+
"eval_precision": 0.8954567659990229,
|
| 7 |
+
"eval_recall": 0.9165,
|
| 8 |
+
"eval_runtime": 6.9815,
|
| 9 |
+
"eval_samples": 54,
|
| 10 |
+
"eval_samples_per_second": 7.735,
|
| 11 |
+
"eval_steps_per_second": 0.143,
|
| 12 |
+
"train_loss": 0.12190062952041626,
|
| 13 |
+
"train_runtime": 303.1848,
|
| 14 |
+
"train_samples": 150,
|
| 15 |
+
"train_samples_per_second": 52.773,
|
| 16 |
+
"train_steps_per_second": 3.298
|
| 17 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
| 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 |
+
"eos_token_id": 2,
|
| 12 |
+
"finetuning_task": "ner",
|
| 13 |
+
"has_relative_attention_bias": true,
|
| 14 |
+
"has_spatial_attention_bias": true,
|
| 15 |
+
"hidden_act": "gelu",
|
| 16 |
+
"hidden_dropout_prob": 0.1,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"id2label": {
|
| 19 |
+
"0": "LABEL_0",
|
| 20 |
+
"1": "LABEL_1",
|
| 21 |
+
"2": "LABEL_2",
|
| 22 |
+
"3": "LABEL_3",
|
| 23 |
+
"4": "LABEL_4",
|
| 24 |
+
"5": "LABEL_5",
|
| 25 |
+
"6": "LABEL_6"
|
| 26 |
+
},
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"input_size": 224,
|
| 29 |
+
"intermediate_size": 3072,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_2": 2,
|
| 34 |
+
"LABEL_3": 3,
|
| 35 |
+
"LABEL_4": 4,
|
| 36 |
+
"LABEL_5": 5,
|
| 37 |
+
"LABEL_6": 6
|
| 38 |
+
},
|
| 39 |
+
"layer_norm_eps": 1e-05,
|
| 40 |
+
"max_2d_position_embeddings": 1024,
|
| 41 |
+
"max_position_embeddings": 514,
|
| 42 |
+
"max_rel_2d_pos": 256,
|
| 43 |
+
"max_rel_pos": 128,
|
| 44 |
+
"model_type": "layoutlmv3",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"rel_2d_pos_bins": 64,
|
| 49 |
+
"rel_pos_bins": 32,
|
| 50 |
+
"second_input_size": 112,
|
| 51 |
+
"shape_size": 128,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.12.5",
|
| 54 |
+
"type_vocab_size": 1,
|
| 55 |
+
"visual_embed": true,
|
| 56 |
+
"vocab_size": 50265,
|
| 57 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.8317638952687184,
|
| 3 |
+
"eval_f1": 0.9058561897702001,
|
| 4 |
+
"eval_loss": 1.1073323488235474,
|
| 5 |
+
"eval_precision": 0.8954567659990229,
|
| 6 |
+
"eval_recall": 0.9165,
|
| 7 |
+
"eval_runtime": 6.9815,
|
| 8 |
+
"eval_samples": 54,
|
| 9 |
+
"eval_samples_per_second": 7.735,
|
| 10 |
+
"eval_steps_per_second": 0.143
|
| 11 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/Apr17_09-22-17_deeplearning28/1650187356.1828399/events.out.tfevents.1650187356.deeplearning28.62374.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56b786e1c8f0a414418427c0bd4dac933d88d70b6c4e2bb105b6ba57d177344
|
| 3 |
+
size 4668
|
runs/Apr17_09-22-17_deeplearning28/events.out.tfevents.1650187356.deeplearning28.62374.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a51a059f1e8d92b176e851ce3f7d93912de23d218b5408971a1e950f01569225
|
| 3 |
+
size 28437
|
runs/Apr17_09-22-17_deeplearning28/events.out.tfevents.1650187663.deeplearning28.62374.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73d6bf2f4828829ac579df22b615df28002226f081334f02e419947b166f48da
|
| 3 |
+
size 512
|
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}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "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"}, "add_prefix_space": true, "errors": "replace", "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"}, "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"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/mnt/localdata/users/yupanhuang/models/layoutlmv3/pts/layoutlmv3-base", "tokenizer_class": "LayoutLMv3Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 0.12190062952041626,
|
| 4 |
+
"train_runtime": 303.1848,
|
| 5 |
+
"train_samples": 150,
|
| 6 |
+
"train_samples_per_second": 52.773,
|
| 7 |
+
"train_steps_per_second": 3.298
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,637 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 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": 2.0,
|
| 12 |
+
"eval_accuracy": 0.6288470372071658,
|
| 13 |
+
"eval_f1": 0.43084004602991943,
|
| 14 |
+
"eval_loss": 1.2868107557296753,
|
| 15 |
+
"eval_precision": 0.3991471215351812,
|
| 16 |
+
"eval_recall": 0.468,
|
| 17 |
+
"eval_runtime": 1.4977,
|
| 18 |
+
"eval_samples_per_second": 36.054,
|
| 19 |
+
"eval_steps_per_second": 0.668,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.0,
|
| 24 |
+
"eval_accuracy": 0.7672255397335783,
|
| 25 |
+
"eval_f1": 0.7671957671957673,
|
| 26 |
+
"eval_loss": 0.8454405665397644,
|
| 27 |
+
"eval_precision": 0.7391102873030584,
|
| 28 |
+
"eval_recall": 0.7975,
|
| 29 |
+
"eval_runtime": 2.3492,
|
| 30 |
+
"eval_samples_per_second": 22.986,
|
| 31 |
+
"eval_steps_per_second": 0.426,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 6.0,
|
| 36 |
+
"eval_accuracy": 0.7731970601745521,
|
| 37 |
+
"eval_f1": 0.8189655172413792,
|
| 38 |
+
"eval_loss": 0.6648961305618286,
|
| 39 |
+
"eval_precision": 0.7858455882352942,
|
| 40 |
+
"eval_recall": 0.855,
|
| 41 |
+
"eval_runtime": 2.4309,
|
| 42 |
+
"eval_samples_per_second": 22.214,
|
| 43 |
+
"eval_steps_per_second": 0.411,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 8.0,
|
| 48 |
+
"eval_accuracy": 0.8240698208543867,
|
| 49 |
+
"eval_f1": 0.8516630250060694,
|
| 50 |
+
"eval_loss": 0.6003230810165405,
|
| 51 |
+
"eval_precision": 0.827748938178386,
|
| 52 |
+
"eval_recall": 0.877,
|
| 53 |
+
"eval_runtime": 1.946,
|
| 54 |
+
"eval_samples_per_second": 27.749,
|
| 55 |
+
"eval_steps_per_second": 0.514,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 10.0,
|
| 60 |
+
"eval_accuracy": 0.8000689021589343,
|
| 61 |
+
"eval_f1": 0.8560497369679579,
|
| 62 |
+
"eval_loss": 0.5940394401550293,
|
| 63 |
+
"eval_precision": 0.8203483043079743,
|
| 64 |
+
"eval_recall": 0.895,
|
| 65 |
+
"eval_runtime": 1.5738,
|
| 66 |
+
"eval_samples_per_second": 34.312,
|
| 67 |
+
"eval_steps_per_second": 0.635,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 12.0,
|
| 72 |
+
"eval_accuracy": 0.8124712907671107,
|
| 73 |
+
"eval_f1": 0.8579682233991335,
|
| 74 |
+
"eval_loss": 0.6028273701667786,
|
| 75 |
+
"eval_precision": 0.8272980501392758,
|
| 76 |
+
"eval_recall": 0.891,
|
| 77 |
+
"eval_runtime": 2.3361,
|
| 78 |
+
"eval_samples_per_second": 23.116,
|
| 79 |
+
"eval_steps_per_second": 0.428,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 14.0,
|
| 84 |
+
"eval_accuracy": 0.8300413412953606,
|
| 85 |
+
"eval_f1": 0.8839373163565133,
|
| 86 |
+
"eval_loss": 0.5925479531288147,
|
| 87 |
+
"eval_precision": 0.8661228406909789,
|
| 88 |
+
"eval_recall": 0.9025,
|
| 89 |
+
"eval_runtime": 1.549,
|
| 90 |
+
"eval_samples_per_second": 34.86,
|
| 91 |
+
"eval_steps_per_second": 0.646,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 16.0,
|
| 96 |
+
"eval_accuracy": 0.8147680293982544,
|
| 97 |
+
"eval_f1": 0.864694471387003,
|
| 98 |
+
"eval_loss": 0.6319019198417664,
|
| 99 |
+
"eval_precision": 0.8394538606403014,
|
| 100 |
+
"eval_recall": 0.8915,
|
| 101 |
+
"eval_runtime": 1.7343,
|
| 102 |
+
"eval_samples_per_second": 31.136,
|
| 103 |
+
"eval_steps_per_second": 0.577,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 18.0,
|
| 108 |
+
"eval_accuracy": 0.8295819935691319,
|
| 109 |
+
"eval_f1": 0.8697776691913022,
|
| 110 |
+
"eval_loss": 0.660470187664032,
|
| 111 |
+
"eval_precision": 0.8504538939321548,
|
| 112 |
+
"eval_recall": 0.89,
|
| 113 |
+
"eval_runtime": 1.7198,
|
| 114 |
+
"eval_samples_per_second": 31.398,
|
| 115 |
+
"eval_steps_per_second": 0.581,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 20.0,
|
| 120 |
+
"eval_accuracy": 0.8275149288011024,
|
| 121 |
+
"eval_f1": 0.8871046228710462,
|
| 122 |
+
"eval_loss": 0.6778170466423035,
|
| 123 |
+
"eval_precision": 0.8639810426540284,
|
| 124 |
+
"eval_recall": 0.9115,
|
| 125 |
+
"eval_runtime": 1.5366,
|
| 126 |
+
"eval_samples_per_second": 35.142,
|
| 127 |
+
"eval_steps_per_second": 0.651,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 22.0,
|
| 132 |
+
"eval_accuracy": 0.815686724850712,
|
| 133 |
+
"eval_f1": 0.8839615668883962,
|
| 134 |
+
"eval_loss": 0.7490019798278809,
|
| 135 |
+
"eval_precision": 0.8712967459932006,
|
| 136 |
+
"eval_recall": 0.897,
|
| 137 |
+
"eval_runtime": 2.3087,
|
| 138 |
+
"eval_samples_per_second": 23.39,
|
| 139 |
+
"eval_steps_per_second": 0.433,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 24.0,
|
| 144 |
+
"eval_accuracy": 0.8222324299494718,
|
| 145 |
+
"eval_f1": 0.8948667324777887,
|
| 146 |
+
"eval_loss": 0.7746959924697876,
|
| 147 |
+
"eval_precision": 0.8835282651072125,
|
| 148 |
+
"eval_recall": 0.9065,
|
| 149 |
+
"eval_runtime": 1.9661,
|
| 150 |
+
"eval_samples_per_second": 27.465,
|
| 151 |
+
"eval_steps_per_second": 0.509,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 26.0,
|
| 156 |
+
"eval_accuracy": 0.8058107487367937,
|
| 157 |
+
"eval_f1": 0.8912883435582821,
|
| 158 |
+
"eval_loss": 0.8429032564163208,
|
| 159 |
+
"eval_precision": 0.8751807228915662,
|
| 160 |
+
"eval_recall": 0.908,
|
| 161 |
+
"eval_runtime": 1.9643,
|
| 162 |
+
"eval_samples_per_second": 27.491,
|
| 163 |
+
"eval_steps_per_second": 0.509,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 28.0,
|
| 168 |
+
"eval_accuracy": 0.8129306384933395,
|
| 169 |
+
"eval_f1": 0.8899308983218163,
|
| 170 |
+
"eval_loss": 0.8374262452125549,
|
| 171 |
+
"eval_precision": 0.8786549707602339,
|
| 172 |
+
"eval_recall": 0.9015,
|
| 173 |
+
"eval_runtime": 1.7097,
|
| 174 |
+
"eval_samples_per_second": 31.584,
|
| 175 |
+
"eval_steps_per_second": 0.585,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 30.0,
|
| 180 |
+
"eval_accuracy": 0.8112080845199816,
|
| 181 |
+
"eval_f1": 0.8747830399206545,
|
| 182 |
+
"eval_loss": 0.9091736078262329,
|
| 183 |
+
"eval_precision": 0.867683226758485,
|
| 184 |
+
"eval_recall": 0.882,
|
| 185 |
+
"eval_runtime": 2.3751,
|
| 186 |
+
"eval_samples_per_second": 22.736,
|
| 187 |
+
"eval_steps_per_second": 0.421,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 32.0,
|
| 192 |
+
"eval_accuracy": 0.8288929719797887,
|
| 193 |
+
"eval_f1": 0.8963474827245804,
|
| 194 |
+
"eval_loss": 0.8785933256149292,
|
| 195 |
+
"eval_precision": 0.884990253411306,
|
| 196 |
+
"eval_recall": 0.908,
|
| 197 |
+
"eval_runtime": 2.0542,
|
| 198 |
+
"eval_samples_per_second": 26.288,
|
| 199 |
+
"eval_steps_per_second": 0.487,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 34.0,
|
| 204 |
+
"eval_accuracy": 0.8307303628847037,
|
| 205 |
+
"eval_f1": 0.8931750741839762,
|
| 206 |
+
"eval_loss": 0.91584312915802,
|
| 207 |
+
"eval_precision": 0.8835616438356164,
|
| 208 |
+
"eval_recall": 0.903,
|
| 209 |
+
"eval_runtime": 2.4582,
|
| 210 |
+
"eval_samples_per_second": 21.967,
|
| 211 |
+
"eval_steps_per_second": 0.407,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 36.0,
|
| 216 |
+
"eval_accuracy": 0.8259072117593018,
|
| 217 |
+
"eval_f1": 0.8948534843634572,
|
| 218 |
+
"eval_loss": 0.9160082340240479,
|
| 219 |
+
"eval_precision": 0.8816108685104318,
|
| 220 |
+
"eval_recall": 0.9085,
|
| 221 |
+
"eval_runtime": 2.3705,
|
| 222 |
+
"eval_samples_per_second": 22.78,
|
| 223 |
+
"eval_steps_per_second": 0.422,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 38.0,
|
| 228 |
+
"eval_accuracy": 0.8171796049609554,
|
| 229 |
+
"eval_f1": 0.8942850134903116,
|
| 230 |
+
"eval_loss": 0.9378513693809509,
|
| 231 |
+
"eval_precision": 0.8777082330284064,
|
| 232 |
+
"eval_recall": 0.9115,
|
| 233 |
+
"eval_runtime": 2.2021,
|
| 234 |
+
"eval_samples_per_second": 24.522,
|
| 235 |
+
"eval_steps_per_second": 0.454,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 40.0,
|
| 240 |
+
"eval_accuracy": 0.8079926504363804,
|
| 241 |
+
"eval_f1": 0.8961134197017844,
|
| 242 |
+
"eval_loss": 0.9751215577125549,
|
| 243 |
+
"eval_precision": 0.8766140602582496,
|
| 244 |
+
"eval_recall": 0.9165,
|
| 245 |
+
"eval_runtime": 1.9472,
|
| 246 |
+
"eval_samples_per_second": 27.733,
|
| 247 |
+
"eval_steps_per_second": 0.514,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 42.0,
|
| 252 |
+
"eval_accuracy": 0.8140790078089113,
|
| 253 |
+
"eval_f1": 0.8976067110782137,
|
| 254 |
+
"eval_loss": 0.922682523727417,
|
| 255 |
+
"eval_precision": 0.8860204578665368,
|
| 256 |
+
"eval_recall": 0.9095,
|
| 257 |
+
"eval_runtime": 1.9496,
|
| 258 |
+
"eval_samples_per_second": 27.699,
|
| 259 |
+
"eval_steps_per_second": 0.513,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 44.0,
|
| 264 |
+
"eval_accuracy": 0.8154570509875976,
|
| 265 |
+
"eval_f1": 0.8868017795353437,
|
| 266 |
+
"eval_loss": 1.0090957880020142,
|
| 267 |
+
"eval_precision": 0.8768328445747801,
|
| 268 |
+
"eval_recall": 0.897,
|
| 269 |
+
"eval_runtime": 1.9314,
|
| 270 |
+
"eval_samples_per_second": 27.96,
|
| 271 |
+
"eval_steps_per_second": 0.518,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 46.0,
|
| 276 |
+
"eval_accuracy": 0.8182131373449701,
|
| 277 |
+
"eval_f1": 0.8956933034602937,
|
| 278 |
+
"eval_loss": 0.9963611960411072,
|
| 279 |
+
"eval_precision": 0.8919186911254338,
|
| 280 |
+
"eval_recall": 0.8995,
|
| 281 |
+
"eval_runtime": 2.4248,
|
| 282 |
+
"eval_samples_per_second": 22.27,
|
| 283 |
+
"eval_steps_per_second": 0.412,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 48.0,
|
| 288 |
+
"eval_accuracy": 0.8203950390445567,
|
| 289 |
+
"eval_f1": 0.896329365079365,
|
| 290 |
+
"eval_loss": 1.0006074905395508,
|
| 291 |
+
"eval_precision": 0.8892716535433071,
|
| 292 |
+
"eval_recall": 0.9035,
|
| 293 |
+
"eval_runtime": 2.4269,
|
| 294 |
+
"eval_samples_per_second": 22.25,
|
| 295 |
+
"eval_steps_per_second": 0.412,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 50.0,
|
| 300 |
+
"learning_rate": 5e-06,
|
| 301 |
+
"loss": 0.235,
|
| 302 |
+
"step": 500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 50.0,
|
| 306 |
+
"eval_accuracy": 0.8178686265502986,
|
| 307 |
+
"eval_f1": 0.8960199004975123,
|
| 308 |
+
"eval_loss": 1.0283308029174805,
|
| 309 |
+
"eval_precision": 0.8915841584158416,
|
| 310 |
+
"eval_recall": 0.9005,
|
| 311 |
+
"eval_runtime": 2.2977,
|
| 312 |
+
"eval_samples_per_second": 23.502,
|
| 313 |
+
"eval_steps_per_second": 0.435,
|
| 314 |
+
"step": 500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 52.0,
|
| 318 |
+
"eval_accuracy": 0.827859439595774,
|
| 319 |
+
"eval_f1": 0.8951014349332014,
|
| 320 |
+
"eval_loss": 0.9926251769065857,
|
| 321 |
+
"eval_precision": 0.885896180215475,
|
| 322 |
+
"eval_recall": 0.9045,
|
| 323 |
+
"eval_runtime": 1.6933,
|
| 324 |
+
"eval_samples_per_second": 31.891,
|
| 325 |
+
"eval_steps_per_second": 0.591,
|
| 326 |
+
"step": 520
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 54.0,
|
| 330 |
+
"eval_accuracy": 0.8228066146072577,
|
| 331 |
+
"eval_f1": 0.8948148148148148,
|
| 332 |
+
"eval_loss": 1.0112966299057007,
|
| 333 |
+
"eval_precision": 0.8839024390243903,
|
| 334 |
+
"eval_recall": 0.906,
|
| 335 |
+
"eval_runtime": 2.4054,
|
| 336 |
+
"eval_samples_per_second": 22.449,
|
| 337 |
+
"eval_steps_per_second": 0.416,
|
| 338 |
+
"step": 540
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 56.0,
|
| 342 |
+
"eval_accuracy": 0.8290078089113458,
|
| 343 |
+
"eval_f1": 0.8993819530284302,
|
| 344 |
+
"eval_loss": 1.004191279411316,
|
| 345 |
+
"eval_precision": 0.8894865525672372,
|
| 346 |
+
"eval_recall": 0.9095,
|
| 347 |
+
"eval_runtime": 1.6522,
|
| 348 |
+
"eval_samples_per_second": 32.684,
|
| 349 |
+
"eval_steps_per_second": 0.605,
|
| 350 |
+
"step": 560
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 58.0,
|
| 354 |
+
"eval_accuracy": 0.8225769407441433,
|
| 355 |
+
"eval_f1": 0.8922392486406326,
|
| 356 |
+
"eval_loss": 1.0357481241226196,
|
| 357 |
+
"eval_precision": 0.8822091886608016,
|
| 358 |
+
"eval_recall": 0.9025,
|
| 359 |
+
"eval_runtime": 2.1102,
|
| 360 |
+
"eval_samples_per_second": 25.59,
|
| 361 |
+
"eval_steps_per_second": 0.474,
|
| 362 |
+
"step": 580
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 60.0,
|
| 366 |
+
"eval_accuracy": 0.8178686265502986,
|
| 367 |
+
"eval_f1": 0.901213171577123,
|
| 368 |
+
"eval_loss": 1.0394996404647827,
|
| 369 |
+
"eval_precision": 0.8925944090240314,
|
| 370 |
+
"eval_recall": 0.91,
|
| 371 |
+
"eval_runtime": 2.4208,
|
| 372 |
+
"eval_samples_per_second": 22.307,
|
| 373 |
+
"eval_steps_per_second": 0.413,
|
| 374 |
+
"step": 600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 62.0,
|
| 378 |
+
"eval_accuracy": 0.8201653651814423,
|
| 379 |
+
"eval_f1": 0.8971962616822431,
|
| 380 |
+
"eval_loss": 1.004025936126709,
|
| 381 |
+
"eval_precision": 0.882865440464666,
|
| 382 |
+
"eval_recall": 0.912,
|
| 383 |
+
"eval_runtime": 2.4098,
|
| 384 |
+
"eval_samples_per_second": 22.408,
|
| 385 |
+
"eval_steps_per_second": 0.415,
|
| 386 |
+
"step": 620
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 64.0,
|
| 390 |
+
"eval_accuracy": 0.8195911805236564,
|
| 391 |
+
"eval_f1": 0.8941929133858268,
|
| 392 |
+
"eval_loss": 1.029054880142212,
|
| 393 |
+
"eval_precision": 0.8803294573643411,
|
| 394 |
+
"eval_recall": 0.9085,
|
| 395 |
+
"eval_runtime": 2.4017,
|
| 396 |
+
"eval_samples_per_second": 22.484,
|
| 397 |
+
"eval_steps_per_second": 0.416,
|
| 398 |
+
"step": 640
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 66.0,
|
| 402 |
+
"eval_accuracy": 0.8279742765273312,
|
| 403 |
+
"eval_f1": 0.8993055555555556,
|
| 404 |
+
"eval_loss": 1.075648546218872,
|
| 405 |
+
"eval_precision": 0.8922244094488189,
|
| 406 |
+
"eval_recall": 0.9065,
|
| 407 |
+
"eval_runtime": 2.4111,
|
| 408 |
+
"eval_samples_per_second": 22.396,
|
| 409 |
+
"eval_steps_per_second": 0.415,
|
| 410 |
+
"step": 660
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 68.0,
|
| 414 |
+
"eval_accuracy": 0.8234956361966008,
|
| 415 |
+
"eval_f1": 0.8966716343765524,
|
| 416 |
+
"eval_loss": 1.1056932210922241,
|
| 417 |
+
"eval_precision": 0.8909180651530109,
|
| 418 |
+
"eval_recall": 0.9025,
|
| 419 |
+
"eval_runtime": 2.4045,
|
| 420 |
+
"eval_samples_per_second": 22.458,
|
| 421 |
+
"eval_steps_per_second": 0.416,
|
| 422 |
+
"step": 680
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 70.0,
|
| 426 |
+
"eval_accuracy": 0.8268259072117593,
|
| 427 |
+
"eval_f1": 0.9007407407407408,
|
| 428 |
+
"eval_loss": 1.1429905891418457,
|
| 429 |
+
"eval_precision": 0.8897560975609756,
|
| 430 |
+
"eval_recall": 0.912,
|
| 431 |
+
"eval_runtime": 2.3943,
|
| 432 |
+
"eval_samples_per_second": 22.553,
|
| 433 |
+
"eval_steps_per_second": 0.418,
|
| 434 |
+
"step": 700
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 72.0,
|
| 438 |
+
"eval_accuracy": 0.8221175930179145,
|
| 439 |
+
"eval_f1": 0.9012012748222604,
|
| 440 |
+
"eval_loss": 1.0474272966384888,
|
| 441 |
+
"eval_precision": 0.8840788840788841,
|
| 442 |
+
"eval_recall": 0.919,
|
| 443 |
+
"eval_runtime": 2.6325,
|
| 444 |
+
"eval_samples_per_second": 20.512,
|
| 445 |
+
"eval_steps_per_second": 0.38,
|
| 446 |
+
"step": 720
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 74.0,
|
| 450 |
+
"eval_accuracy": 0.8191318327974276,
|
| 451 |
+
"eval_f1": 0.9079694053787319,
|
| 452 |
+
"eval_loss": 1.1182180643081665,
|
| 453 |
+
"eval_precision": 0.8962493911349245,
|
| 454 |
+
"eval_recall": 0.92,
|
| 455 |
+
"eval_runtime": 2.4698,
|
| 456 |
+
"eval_samples_per_second": 21.864,
|
| 457 |
+
"eval_steps_per_second": 0.405,
|
| 458 |
+
"step": 740
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 76.0,
|
| 462 |
+
"eval_accuracy": 0.8267110702802021,
|
| 463 |
+
"eval_f1": 0.9056324110671936,
|
| 464 |
+
"eval_loss": 1.1421239376068115,
|
| 465 |
+
"eval_precision": 0.89501953125,
|
| 466 |
+
"eval_recall": 0.9165,
|
| 467 |
+
"eval_runtime": 2.0412,
|
| 468 |
+
"eval_samples_per_second": 26.455,
|
| 469 |
+
"eval_steps_per_second": 0.49,
|
| 470 |
+
"step": 760
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 78.0,
|
| 474 |
+
"eval_accuracy": 0.825447864033073,
|
| 475 |
+
"eval_f1": 0.9112103174603173,
|
| 476 |
+
"eval_loss": 1.1723241806030273,
|
| 477 |
+
"eval_precision": 0.9040354330708661,
|
| 478 |
+
"eval_recall": 0.9185,
|
| 479 |
+
"eval_runtime": 2.0338,
|
| 480 |
+
"eval_samples_per_second": 26.551,
|
| 481 |
+
"eval_steps_per_second": 0.492,
|
| 482 |
+
"step": 780
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 80.0,
|
| 486 |
+
"eval_accuracy": 0.8314193844740468,
|
| 487 |
+
"eval_f1": 0.9091358024691357,
|
| 488 |
+
"eval_loss": 1.0977429151535034,
|
| 489 |
+
"eval_precision": 0.8980487804878049,
|
| 490 |
+
"eval_recall": 0.9205,
|
| 491 |
+
"eval_runtime": 2.708,
|
| 492 |
+
"eval_samples_per_second": 19.941,
|
| 493 |
+
"eval_steps_per_second": 0.369,
|
| 494 |
+
"step": 800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 82.0,
|
| 498 |
+
"eval_accuracy": 0.826596233348645,
|
| 499 |
+
"eval_f1": 0.9020771513353116,
|
| 500 |
+
"eval_loss": 1.1165635585784912,
|
| 501 |
+
"eval_precision": 0.8923679060665362,
|
| 502 |
+
"eval_recall": 0.912,
|
| 503 |
+
"eval_runtime": 2.3964,
|
| 504 |
+
"eval_samples_per_second": 22.533,
|
| 505 |
+
"eval_steps_per_second": 0.417,
|
| 506 |
+
"step": 820
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 84.0,
|
| 510 |
+
"eval_accuracy": 0.83210840606339,
|
| 511 |
+
"eval_f1": 0.9058561897702001,
|
| 512 |
+
"eval_loss": 1.1296281814575195,
|
| 513 |
+
"eval_precision": 0.8954567659990229,
|
| 514 |
+
"eval_recall": 0.9165,
|
| 515 |
+
"eval_runtime": 1.5143,
|
| 516 |
+
"eval_samples_per_second": 35.659,
|
| 517 |
+
"eval_steps_per_second": 0.66,
|
| 518 |
+
"step": 840
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 86.0,
|
| 522 |
+
"eval_accuracy": 0.8313045475424896,
|
| 523 |
+
"eval_f1": 0.9070687098368759,
|
| 524 |
+
"eval_loss": 1.122943639755249,
|
| 525 |
+
"eval_precision": 0.896871945259042,
|
| 526 |
+
"eval_recall": 0.9175,
|
| 527 |
+
"eval_runtime": 2.2961,
|
| 528 |
+
"eval_samples_per_second": 23.518,
|
| 529 |
+
"eval_steps_per_second": 0.436,
|
| 530 |
+
"step": 860
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 88.0,
|
| 534 |
+
"eval_accuracy": 0.8325677537896188,
|
| 535 |
+
"eval_f1": 0.9080573405832921,
|
| 536 |
+
"eval_loss": 1.1123418807983398,
|
| 537 |
+
"eval_precision": 0.8978494623655914,
|
| 538 |
+
"eval_recall": 0.9185,
|
| 539 |
+
"eval_runtime": 2.1658,
|
| 540 |
+
"eval_samples_per_second": 24.933,
|
| 541 |
+
"eval_steps_per_second": 0.462,
|
| 542 |
+
"step": 880
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 90.0,
|
| 546 |
+
"eval_accuracy": 0.8325677537896188,
|
| 547 |
+
"eval_f1": 0.9037843185753152,
|
| 548 |
+
"eval_loss": 1.1032230854034424,
|
| 549 |
+
"eval_precision": 0.8942731277533039,
|
| 550 |
+
"eval_recall": 0.9135,
|
| 551 |
+
"eval_runtime": 1.6625,
|
| 552 |
+
"eval_samples_per_second": 32.481,
|
| 553 |
+
"eval_steps_per_second": 0.601,
|
| 554 |
+
"step": 900
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 92.0,
|
| 558 |
+
"eval_accuracy": 0.83578318787322,
|
| 559 |
+
"eval_f1": 0.9086407526615499,
|
| 560 |
+
"eval_loss": 1.0933949947357178,
|
| 561 |
+
"eval_precision": 0.8999509563511525,
|
| 562 |
+
"eval_recall": 0.9175,
|
| 563 |
+
"eval_runtime": 2.2261,
|
| 564 |
+
"eval_samples_per_second": 24.258,
|
| 565 |
+
"eval_steps_per_second": 0.449,
|
| 566 |
+
"step": 920
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 94.0,
|
| 570 |
+
"eval_accuracy": 0.8360128617363344,
|
| 571 |
+
"eval_f1": 0.9090909090909091,
|
| 572 |
+
"eval_loss": 1.0976922512054443,
|
| 573 |
+
"eval_precision": 0.9008345606283751,
|
| 574 |
+
"eval_recall": 0.9175,
|
| 575 |
+
"eval_runtime": 2.4337,
|
| 576 |
+
"eval_samples_per_second": 22.189,
|
| 577 |
+
"eval_steps_per_second": 0.411,
|
| 578 |
+
"step": 940
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 96.0,
|
| 582 |
+
"eval_accuracy": 0.833945796968305,
|
| 583 |
+
"eval_f1": 0.9066205533596838,
|
| 584 |
+
"eval_loss": 1.1002885103225708,
|
| 585 |
+
"eval_precision": 0.89599609375,
|
| 586 |
+
"eval_recall": 0.9175,
|
| 587 |
+
"eval_runtime": 2.3183,
|
| 588 |
+
"eval_samples_per_second": 23.293,
|
| 589 |
+
"eval_steps_per_second": 0.431,
|
| 590 |
+
"step": 960
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 98.0,
|
| 594 |
+
"eval_accuracy": 0.8329122645842904,
|
| 595 |
+
"eval_f1": 0.9057164068299927,
|
| 596 |
+
"eval_loss": 1.1073625087738037,
|
| 597 |
+
"eval_precision": 0.8966193042626164,
|
| 598 |
+
"eval_recall": 0.915,
|
| 599 |
+
"eval_runtime": 2.4241,
|
| 600 |
+
"eval_samples_per_second": 22.276,
|
| 601 |
+
"eval_steps_per_second": 0.413,
|
| 602 |
+
"step": 980
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 100.0,
|
| 606 |
+
"learning_rate": 0.0,
|
| 607 |
+
"loss": 0.0088,
|
| 608 |
+
"step": 1000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 100.0,
|
| 612 |
+
"eval_accuracy": 0.8317638952687184,
|
| 613 |
+
"eval_f1": 0.9058561897702001,
|
| 614 |
+
"eval_loss": 1.1073323488235474,
|
| 615 |
+
"eval_precision": 0.8954567659990229,
|
| 616 |
+
"eval_recall": 0.9165,
|
| 617 |
+
"eval_runtime": 1.5045,
|
| 618 |
+
"eval_samples_per_second": 35.892,
|
| 619 |
+
"eval_steps_per_second": 0.665,
|
| 620 |
+
"step": 1000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 100.0,
|
| 624 |
+
"step": 1000,
|
| 625 |
+
"total_flos": 4006801297113088.0,
|
| 626 |
+
"train_loss": 0.12190062952041626,
|
| 627 |
+
"train_runtime": 303.1848,
|
| 628 |
+
"train_samples_per_second": 52.773,
|
| 629 |
+
"train_steps_per_second": 3.298
|
| 630 |
+
}
|
| 631 |
+
],
|
| 632 |
+
"max_steps": 1000,
|
| 633 |
+
"num_train_epochs": 100,
|
| 634 |
+
"total_flos": 4006801297113088.0,
|
| 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 sha256:2d2fd64da493d1cc0e186398f838f436ad4f7e1fcff300da892a6ec00409833a
|
| 3 |
+
size 2927
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|