add
Browse files- all_results.json +17 -0
- config.json +57 -0
- eval_results.json +12 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr17_09-33-08_deeplearning28/1650188009.8508577/events.out.tfevents.1650188009.deeplearning28.14524.1 +3 -0
- runs/Apr17_09-33-08_deeplearning28/events.out.tfevents.1650188009.deeplearning28.14524.0 +3 -0
- runs/Apr17_09-33-08_deeplearning28/events.out.tfevents.1650188436.deeplearning28.14524.2 +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": 0.8518603582912264,
|
| 4 |
+
"eval_f1": 0.9214607303651825,
|
| 5 |
+
"eval_loss": 1.5228424072265625,
|
| 6 |
+
"eval_precision": 0.9219219219219219,
|
| 7 |
+
"eval_recall": 0.921,
|
| 8 |
+
"eval_runtime": 1.9518,
|
| 9 |
+
"eval_samples": 54,
|
| 10 |
+
"eval_samples_per_second": 27.666,
|
| 11 |
+
"eval_steps_per_second": 0.512,
|
| 12 |
+
"train_loss": 0.06096216064691544,
|
| 13 |
+
"train_runtime": 422.6711,
|
| 14 |
+
"train_samples": 150,
|
| 15 |
+
"train_samples_per_second": 37.854,
|
| 16 |
+
"train_steps_per_second": 2.366
|
| 17 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 171,
|
| 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": 1024,
|
| 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": 4096,
|
| 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": 16,
|
| 46 |
+
"num_hidden_layers": 24,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"rel_2d_pos_bins": 64,
|
| 49 |
+
"rel_pos_bins": 32,
|
| 50 |
+
"second_input_size": 112,
|
| 51 |
+
"shape_size": 170,
|
| 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 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8518603582912264,
|
| 4 |
+
"eval_f1": 0.9214607303651825,
|
| 5 |
+
"eval_loss": 1.5228424072265625,
|
| 6 |
+
"eval_precision": 0.9219219219219219,
|
| 7 |
+
"eval_recall": 0.921,
|
| 8 |
+
"eval_runtime": 1.9518,
|
| 9 |
+
"eval_samples": 54,
|
| 10 |
+
"eval_samples_per_second": 27.666,
|
| 11 |
+
"eval_steps_per_second": 0.512
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a157a911bc98bbf1f44b60de19938fad42c96656385059a30c99e22dafab1aea
|
| 3 |
+
size 1424221523
|
runs/Apr17_09-33-08_deeplearning28/1650188009.8508577/events.out.tfevents.1650188009.deeplearning28.14524.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df226d1a1db5fe634c3d5dace215a3376da4231f1468fa218d0d50d4946f3fab
|
| 3 |
+
size 4671
|
runs/Apr17_09-33-08_deeplearning28/events.out.tfevents.1650188009.deeplearning28.14524.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb0db0bdfe9fb620e11bc72253e53fee2bb3be3b08cbab0e2ef9f3018de2617
|
| 3 |
+
size 28477
|
runs/Apr17_09-33-08_deeplearning28/events.out.tfevents.1650188436.deeplearning28.14524.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:026614ceee2b421724f3e788a44f3bf8558859d3b28d621c809f2c77ec31f55d
|
| 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-large", "tokenizer_class": "LayoutLMv3Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 0.06096216064691544,
|
| 4 |
+
"train_runtime": 422.6711,
|
| 5 |
+
"train_samples": 150,
|
| 6 |
+
"train_samples_per_second": 37.854,
|
| 7 |
+
"train_steps_per_second": 2.366
|
| 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": 0.7733118971061094,
|
| 13 |
+
"eval_f1": 0.7518500246669956,
|
| 14 |
+
"eval_loss": 0.8074839115142822,
|
| 15 |
+
"eval_precision": 0.7419668938656281,
|
| 16 |
+
"eval_recall": 0.762,
|
| 17 |
+
"eval_runtime": 2.1702,
|
| 18 |
+
"eval_samples_per_second": 24.883,
|
| 19 |
+
"eval_steps_per_second": 0.461,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.0,
|
| 24 |
+
"eval_accuracy": 0.8378502526412495,
|
| 25 |
+
"eval_f1": 0.8489243413101281,
|
| 26 |
+
"eval_loss": 0.6263514161109924,
|
| 27 |
+
"eval_precision": 0.8217126813289658,
|
| 28 |
+
"eval_recall": 0.878,
|
| 29 |
+
"eval_runtime": 1.8285,
|
| 30 |
+
"eval_samples_per_second": 29.533,
|
| 31 |
+
"eval_steps_per_second": 0.547,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 6.0,
|
| 36 |
+
"eval_accuracy": 0.8375057418465779,
|
| 37 |
+
"eval_f1": 0.8824383164005806,
|
| 38 |
+
"eval_loss": 0.5844890475273132,
|
| 39 |
+
"eval_precision": 0.8547328959700093,
|
| 40 |
+
"eval_recall": 0.912,
|
| 41 |
+
"eval_runtime": 1.6994,
|
| 42 |
+
"eval_samples_per_second": 31.775,
|
| 43 |
+
"eval_steps_per_second": 0.588,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 8.0,
|
| 48 |
+
"eval_accuracy": 0.8396876435461644,
|
| 49 |
+
"eval_f1": 0.8708251473477405,
|
| 50 |
+
"eval_loss": 0.7096832990646362,
|
| 51 |
+
"eval_precision": 0.8556949806949807,
|
| 52 |
+
"eval_recall": 0.8865,
|
| 53 |
+
"eval_runtime": 1.9498,
|
| 54 |
+
"eval_samples_per_second": 27.695,
|
| 55 |
+
"eval_steps_per_second": 0.513,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 10.0,
|
| 60 |
+
"eval_accuracy": 0.8438217730822233,
|
| 61 |
+
"eval_f1": 0.8839153959665518,
|
| 62 |
+
"eval_loss": 0.7337720394134521,
|
| 63 |
+
"eval_precision": 0.8697967086156825,
|
| 64 |
+
"eval_recall": 0.8985,
|
| 65 |
+
"eval_runtime": 1.6222,
|
| 66 |
+
"eval_samples_per_second": 33.289,
|
| 67 |
+
"eval_steps_per_second": 0.616,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 12.0,
|
| 72 |
+
"eval_accuracy": 0.8494487827285255,
|
| 73 |
+
"eval_f1": 0.8967391304347826,
|
| 74 |
+
"eval_loss": 0.8648139238357544,
|
| 75 |
+
"eval_precision": 0.88623046875,
|
| 76 |
+
"eval_recall": 0.9075,
|
| 77 |
+
"eval_runtime": 1.6638,
|
| 78 |
+
"eval_samples_per_second": 32.455,
|
| 79 |
+
"eval_steps_per_second": 0.601,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 14.0,
|
| 84 |
+
"eval_accuracy": 0.8330271015158475,
|
| 85 |
+
"eval_f1": 0.8940709501364426,
|
| 86 |
+
"eval_loss": 0.8960414528846741,
|
| 87 |
+
"eval_precision": 0.8872476612506155,
|
| 88 |
+
"eval_recall": 0.901,
|
| 89 |
+
"eval_runtime": 1.8377,
|
| 90 |
+
"eval_samples_per_second": 29.384,
|
| 91 |
+
"eval_steps_per_second": 0.544,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 16.0,
|
| 96 |
+
"eval_accuracy": 0.8408360128617364,
|
| 97 |
+
"eval_f1": 0.897062453715132,
|
| 98 |
+
"eval_loss": 0.9291977882385254,
|
| 99 |
+
"eval_precision": 0.8859093125304729,
|
| 100 |
+
"eval_recall": 0.9085,
|
| 101 |
+
"eval_runtime": 2.2856,
|
| 102 |
+
"eval_samples_per_second": 23.626,
|
| 103 |
+
"eval_steps_per_second": 0.438,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 18.0,
|
| 108 |
+
"eval_accuracy": 0.8530087276067984,
|
| 109 |
+
"eval_f1": 0.9070520807376028,
|
| 110 |
+
"eval_loss": 0.956124484539032,
|
| 111 |
+
"eval_precision": 0.9041231992051664,
|
| 112 |
+
"eval_recall": 0.91,
|
| 113 |
+
"eval_runtime": 2.1004,
|
| 114 |
+
"eval_samples_per_second": 25.71,
|
| 115 |
+
"eval_steps_per_second": 0.476,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 20.0,
|
| 120 |
+
"eval_accuracy": 0.8460036747818098,
|
| 121 |
+
"eval_f1": 0.9054455445544554,
|
| 122 |
+
"eval_loss": 1.1085299253463745,
|
| 123 |
+
"eval_precision": 0.8965686274509804,
|
| 124 |
+
"eval_recall": 0.9145,
|
| 125 |
+
"eval_runtime": 1.9718,
|
| 126 |
+
"eval_samples_per_second": 27.386,
|
| 127 |
+
"eval_steps_per_second": 0.507,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 22.0,
|
| 132 |
+
"eval_accuracy": 0.8494487827285255,
|
| 133 |
+
"eval_f1": 0.9123157631776169,
|
| 134 |
+
"eval_loss": 1.1246980428695679,
|
| 135 |
+
"eval_precision": 0.9116325511732402,
|
| 136 |
+
"eval_recall": 0.913,
|
| 137 |
+
"eval_runtime": 2.2938,
|
| 138 |
+
"eval_samples_per_second": 23.541,
|
| 139 |
+
"eval_steps_per_second": 0.436,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 24.0,
|
| 144 |
+
"eval_accuracy": 0.8488745980707395,
|
| 145 |
+
"eval_f1": 0.9118450459399057,
|
| 146 |
+
"eval_loss": 1.2039830684661865,
|
| 147 |
+
"eval_precision": 0.9057720769610261,
|
| 148 |
+
"eval_recall": 0.918,
|
| 149 |
+
"eval_runtime": 2.3959,
|
| 150 |
+
"eval_samples_per_second": 22.539,
|
| 151 |
+
"eval_steps_per_second": 0.417,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 26.0,
|
| 156 |
+
"eval_accuracy": 0.8449701423977951,
|
| 157 |
+
"eval_f1": 0.9141426783479348,
|
| 158 |
+
"eval_loss": 1.2313123941421509,
|
| 159 |
+
"eval_precision": 0.9152882205513785,
|
| 160 |
+
"eval_recall": 0.913,
|
| 161 |
+
"eval_runtime": 1.8248,
|
| 162 |
+
"eval_samples_per_second": 29.592,
|
| 163 |
+
"eval_steps_per_second": 0.548,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 28.0,
|
| 168 |
+
"eval_accuracy": 0.8450849793293523,
|
| 169 |
+
"eval_f1": 0.9095876800794833,
|
| 170 |
+
"eval_loss": 1.2972946166992188,
|
| 171 |
+
"eval_precision": 0.903751233958539,
|
| 172 |
+
"eval_recall": 0.9155,
|
| 173 |
+
"eval_runtime": 2.3256,
|
| 174 |
+
"eval_samples_per_second": 23.219,
|
| 175 |
+
"eval_steps_per_second": 0.43,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 30.0,
|
| 180 |
+
"eval_accuracy": 0.8516306844281121,
|
| 181 |
+
"eval_f1": 0.9177467597208374,
|
| 182 |
+
"eval_loss": 1.27461838722229,
|
| 183 |
+
"eval_precision": 0.9150099403578529,
|
| 184 |
+
"eval_recall": 0.9205,
|
| 185 |
+
"eval_runtime": 2.085,
|
| 186 |
+
"eval_samples_per_second": 25.899,
|
| 187 |
+
"eval_steps_per_second": 0.48,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 32.0,
|
| 192 |
+
"eval_accuracy": 0.8451998162609095,
|
| 193 |
+
"eval_f1": 0.9093167701863354,
|
| 194 |
+
"eval_loss": 1.3256772756576538,
|
| 195 |
+
"eval_precision": 0.9037037037037037,
|
| 196 |
+
"eval_recall": 0.915,
|
| 197 |
+
"eval_runtime": 1.6622,
|
| 198 |
+
"eval_samples_per_second": 32.487,
|
| 199 |
+
"eval_steps_per_second": 0.602,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 34.0,
|
| 204 |
+
"eval_accuracy": 0.8609324758842444,
|
| 205 |
+
"eval_f1": 0.9068725099601593,
|
| 206 |
+
"eval_loss": 1.1881499290466309,
|
| 207 |
+
"eval_precision": 0.9032738095238095,
|
| 208 |
+
"eval_recall": 0.9105,
|
| 209 |
+
"eval_runtime": 1.8765,
|
| 210 |
+
"eval_samples_per_second": 28.777,
|
| 211 |
+
"eval_steps_per_second": 0.533,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 36.0,
|
| 216 |
+
"eval_accuracy": 0.8310748736793753,
|
| 217 |
+
"eval_f1": 0.9006986027944112,
|
| 218 |
+
"eval_loss": 1.4595391750335693,
|
| 219 |
+
"eval_precision": 0.8989043824701195,
|
| 220 |
+
"eval_recall": 0.9025,
|
| 221 |
+
"eval_runtime": 1.593,
|
| 222 |
+
"eval_samples_per_second": 33.898,
|
| 223 |
+
"eval_steps_per_second": 0.628,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 38.0,
|
| 228 |
+
"eval_accuracy": 0.8542719338539274,
|
| 229 |
+
"eval_f1": 0.9134879082523062,
|
| 230 |
+
"eval_loss": 1.3311606645584106,
|
| 231 |
+
"eval_precision": 0.9109895574341124,
|
| 232 |
+
"eval_recall": 0.916,
|
| 233 |
+
"eval_runtime": 2.269,
|
| 234 |
+
"eval_samples_per_second": 23.799,
|
| 235 |
+
"eval_steps_per_second": 0.441,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 40.0,
|
| 240 |
+
"eval_accuracy": 0.8555351401010565,
|
| 241 |
+
"eval_f1": 0.9195,
|
| 242 |
+
"eval_loss": 1.2927559614181519,
|
| 243 |
+
"eval_precision": 0.9195,
|
| 244 |
+
"eval_recall": 0.9195,
|
| 245 |
+
"eval_runtime": 1.8831,
|
| 246 |
+
"eval_samples_per_second": 28.676,
|
| 247 |
+
"eval_steps_per_second": 0.531,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 42.0,
|
| 252 |
+
"eval_accuracy": 0.8598989435002297,
|
| 253 |
+
"eval_f1": 0.9248439450686643,
|
| 254 |
+
"eval_loss": 1.3193974494934082,
|
| 255 |
+
"eval_precision": 0.9236907730673317,
|
| 256 |
+
"eval_recall": 0.926,
|
| 257 |
+
"eval_runtime": 1.733,
|
| 258 |
+
"eval_samples_per_second": 31.16,
|
| 259 |
+
"eval_steps_per_second": 0.577,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 44.0,
|
| 264 |
+
"eval_accuracy": 0.8456591639871383,
|
| 265 |
+
"eval_f1": 0.9162290572643161,
|
| 266 |
+
"eval_loss": 1.455527424812317,
|
| 267 |
+
"eval_precision": 0.9164582291145573,
|
| 268 |
+
"eval_recall": 0.916,
|
| 269 |
+
"eval_runtime": 2.5054,
|
| 270 |
+
"eval_samples_per_second": 21.554,
|
| 271 |
+
"eval_steps_per_second": 0.399,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 46.0,
|
| 276 |
+
"eval_accuracy": 0.8541570969223702,
|
| 277 |
+
"eval_f1": 0.916729182295574,
|
| 278 |
+
"eval_loss": 1.4188611507415771,
|
| 279 |
+
"eval_precision": 0.9169584792396198,
|
| 280 |
+
"eval_recall": 0.9165,
|
| 281 |
+
"eval_runtime": 2.3672,
|
| 282 |
+
"eval_samples_per_second": 22.811,
|
| 283 |
+
"eval_steps_per_second": 0.422,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 48.0,
|
| 288 |
+
"eval_accuracy": 0.8516306844281121,
|
| 289 |
+
"eval_f1": 0.9209932279909707,
|
| 290 |
+
"eval_loss": 1.462133765220642,
|
| 291 |
+
"eval_precision": 0.9240060392551586,
|
| 292 |
+
"eval_recall": 0.918,
|
| 293 |
+
"eval_runtime": 2.0221,
|
| 294 |
+
"eval_samples_per_second": 26.705,
|
| 295 |
+
"eval_steps_per_second": 0.495,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 50.0,
|
| 300 |
+
"learning_rate": 5e-06,
|
| 301 |
+
"loss": 0.1212,
|
| 302 |
+
"step": 500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 50.0,
|
| 306 |
+
"eval_accuracy": 0.8492191088654111,
|
| 307 |
+
"eval_f1": 0.9188919391065635,
|
| 308 |
+
"eval_loss": 1.5107489824295044,
|
| 309 |
+
"eval_precision": 0.9172894867962132,
|
| 310 |
+
"eval_recall": 0.9205,
|
| 311 |
+
"eval_runtime": 2.2455,
|
| 312 |
+
"eval_samples_per_second": 24.048,
|
| 313 |
+
"eval_steps_per_second": 0.445,
|
| 314 |
+
"step": 500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 52.0,
|
| 318 |
+
"eval_accuracy": 0.8520900321543409,
|
| 319 |
+
"eval_f1": 0.9225037257824144,
|
| 320 |
+
"eval_loss": 1.3997772932052612,
|
| 321 |
+
"eval_precision": 0.9165844027640672,
|
| 322 |
+
"eval_recall": 0.9285,
|
| 323 |
+
"eval_runtime": 1.6019,
|
| 324 |
+
"eval_samples_per_second": 33.711,
|
| 325 |
+
"eval_steps_per_second": 0.624,
|
| 326 |
+
"step": 520
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 54.0,
|
| 330 |
+
"eval_accuracy": 0.8531235645383556,
|
| 331 |
+
"eval_f1": 0.9185,
|
| 332 |
+
"eval_loss": 1.3953099250793457,
|
| 333 |
+
"eval_precision": 0.9185,
|
| 334 |
+
"eval_recall": 0.9185,
|
| 335 |
+
"eval_runtime": 2.4867,
|
| 336 |
+
"eval_samples_per_second": 21.715,
|
| 337 |
+
"eval_steps_per_second": 0.402,
|
| 338 |
+
"step": 540
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 56.0,
|
| 342 |
+
"eval_accuracy": 0.8493339457969683,
|
| 343 |
+
"eval_f1": 0.9165622650964669,
|
| 344 |
+
"eval_loss": 1.424229621887207,
|
| 345 |
+
"eval_precision": 0.9186338523355098,
|
| 346 |
+
"eval_recall": 0.9145,
|
| 347 |
+
"eval_runtime": 2.2429,
|
| 348 |
+
"eval_samples_per_second": 24.076,
|
| 349 |
+
"eval_steps_per_second": 0.446,
|
| 350 |
+
"step": 560
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 58.0,
|
| 354 |
+
"eval_accuracy": 0.8508268259072118,
|
| 355 |
+
"eval_f1": 0.9144851657940662,
|
| 356 |
+
"eval_loss": 1.4575742483139038,
|
| 357 |
+
"eval_precision": 0.9119840875186475,
|
| 358 |
+
"eval_recall": 0.917,
|
| 359 |
+
"eval_runtime": 1.7215,
|
| 360 |
+
"eval_samples_per_second": 31.368,
|
| 361 |
+
"eval_steps_per_second": 0.581,
|
| 362 |
+
"step": 580
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 60.0,
|
| 366 |
+
"eval_accuracy": 0.8524345429490124,
|
| 367 |
+
"eval_f1": 0.9176001991535974,
|
| 368 |
+
"eval_loss": 1.469473123550415,
|
| 369 |
+
"eval_precision": 0.9137332672285573,
|
| 370 |
+
"eval_recall": 0.9215,
|
| 371 |
+
"eval_runtime": 2.1512,
|
| 372 |
+
"eval_samples_per_second": 25.102,
|
| 373 |
+
"eval_steps_per_second": 0.465,
|
| 374 |
+
"step": 600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 62.0,
|
| 378 |
+
"eval_accuracy": 0.8517455213596693,
|
| 379 |
+
"eval_f1": 0.918474195961107,
|
| 380 |
+
"eval_loss": 1.4966249465942383,
|
| 381 |
+
"eval_precision": 0.9159622078567876,
|
| 382 |
+
"eval_recall": 0.921,
|
| 383 |
+
"eval_runtime": 2.0241,
|
| 384 |
+
"eval_samples_per_second": 26.678,
|
| 385 |
+
"eval_steps_per_second": 0.494,
|
| 386 |
+
"step": 620
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 64.0,
|
| 390 |
+
"eval_accuracy": 0.8484152503445108,
|
| 391 |
+
"eval_f1": 0.92,
|
| 392 |
+
"eval_loss": 1.5030325651168823,
|
| 393 |
+
"eval_precision": 0.92,
|
| 394 |
+
"eval_recall": 0.92,
|
| 395 |
+
"eval_runtime": 2.1745,
|
| 396 |
+
"eval_samples_per_second": 24.834,
|
| 397 |
+
"eval_steps_per_second": 0.46,
|
| 398 |
+
"step": 640
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 66.0,
|
| 402 |
+
"eval_accuracy": 0.8462333486449242,
|
| 403 |
+
"eval_f1": 0.9175591531755916,
|
| 404 |
+
"eval_loss": 1.4818426370620728,
|
| 405 |
+
"eval_precision": 0.9141439205955335,
|
| 406 |
+
"eval_recall": 0.921,
|
| 407 |
+
"eval_runtime": 2.068,
|
| 408 |
+
"eval_samples_per_second": 26.112,
|
| 409 |
+
"eval_steps_per_second": 0.484,
|
| 410 |
+
"step": 660
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 68.0,
|
| 414 |
+
"eval_accuracy": 0.8497932935231971,
|
| 415 |
+
"eval_f1": 0.9201501877346684,
|
| 416 |
+
"eval_loss": 1.4994901418685913,
|
| 417 |
+
"eval_precision": 0.9213032581453634,
|
| 418 |
+
"eval_recall": 0.919,
|
| 419 |
+
"eval_runtime": 1.5887,
|
| 420 |
+
"eval_samples_per_second": 33.99,
|
| 421 |
+
"eval_steps_per_second": 0.629,
|
| 422 |
+
"step": 680
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 70.0,
|
| 426 |
+
"eval_accuracy": 0.8501378043178687,
|
| 427 |
+
"eval_f1": 0.9175180662845751,
|
| 428 |
+
"eval_loss": 1.52091383934021,
|
| 429 |
+
"eval_precision": 0.914555389965226,
|
| 430 |
+
"eval_recall": 0.9205,
|
| 431 |
+
"eval_runtime": 2.0412,
|
| 432 |
+
"eval_samples_per_second": 26.455,
|
| 433 |
+
"eval_steps_per_second": 0.49,
|
| 434 |
+
"step": 700
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 72.0,
|
| 438 |
+
"eval_accuracy": 0.8465778594395957,
|
| 439 |
+
"eval_f1": 0.9170633926334252,
|
| 440 |
+
"eval_loss": 1.54710054397583,
|
| 441 |
+
"eval_precision": 0.9191361125062782,
|
| 442 |
+
"eval_recall": 0.915,
|
| 443 |
+
"eval_runtime": 1.9021,
|
| 444 |
+
"eval_samples_per_second": 28.39,
|
| 445 |
+
"eval_steps_per_second": 0.526,
|
| 446 |
+
"step": 720
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 74.0,
|
| 450 |
+
"eval_accuracy": 0.8531235645383556,
|
| 451 |
+
"eval_f1": 0.919080919080919,
|
| 452 |
+
"eval_loss": 1.5027331113815308,
|
| 453 |
+
"eval_precision": 0.9181636726546906,
|
| 454 |
+
"eval_recall": 0.92,
|
| 455 |
+
"eval_runtime": 2.6669,
|
| 456 |
+
"eval_samples_per_second": 20.248,
|
| 457 |
+
"eval_steps_per_second": 0.375,
|
| 458 |
+
"step": 740
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 76.0,
|
| 462 |
+
"eval_accuracy": 0.8531235645383556,
|
| 463 |
+
"eval_f1": 0.9171464330413016,
|
| 464 |
+
"eval_loss": 1.5013470649719238,
|
| 465 |
+
"eval_precision": 0.9182957393483709,
|
| 466 |
+
"eval_recall": 0.916,
|
| 467 |
+
"eval_runtime": 2.1913,
|
| 468 |
+
"eval_samples_per_second": 24.643,
|
| 469 |
+
"eval_steps_per_second": 0.456,
|
| 470 |
+
"step": 760
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 78.0,
|
| 474 |
+
"eval_accuracy": 0.8509416628387689,
|
| 475 |
+
"eval_f1": 0.9218045112781955,
|
| 476 |
+
"eval_loss": 1.5246856212615967,
|
| 477 |
+
"eval_precision": 0.9241206030150754,
|
| 478 |
+
"eval_recall": 0.9195,
|
| 479 |
+
"eval_runtime": 1.7299,
|
| 480 |
+
"eval_samples_per_second": 31.215,
|
| 481 |
+
"eval_steps_per_second": 0.578,
|
| 482 |
+
"step": 780
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 80.0,
|
| 486 |
+
"eval_accuracy": 0.8507119889756546,
|
| 487 |
+
"eval_f1": 0.9178286852589641,
|
| 488 |
+
"eval_loss": 1.5289556980133057,
|
| 489 |
+
"eval_precision": 0.9141865079365079,
|
| 490 |
+
"eval_recall": 0.9215,
|
| 491 |
+
"eval_runtime": 1.9199,
|
| 492 |
+
"eval_samples_per_second": 28.126,
|
| 493 |
+
"eval_steps_per_second": 0.521,
|
| 494 |
+
"step": 800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 82.0,
|
| 498 |
+
"eval_accuracy": 0.852779053743684,
|
| 499 |
+
"eval_f1": 0.9211576846307385,
|
| 500 |
+
"eval_loss": 1.523385763168335,
|
| 501 |
+
"eval_precision": 0.9193227091633466,
|
| 502 |
+
"eval_recall": 0.923,
|
| 503 |
+
"eval_runtime": 1.6928,
|
| 504 |
+
"eval_samples_per_second": 31.899,
|
| 505 |
+
"eval_steps_per_second": 0.591,
|
| 506 |
+
"step": 820
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 84.0,
|
| 510 |
+
"eval_accuracy": 0.8535829122645843,
|
| 511 |
+
"eval_f1": 0.9211183225162256,
|
| 512 |
+
"eval_loss": 1.5238100290298462,
|
| 513 |
+
"eval_precision": 0.919740777666999,
|
| 514 |
+
"eval_recall": 0.9225,
|
| 515 |
+
"eval_runtime": 1.7587,
|
| 516 |
+
"eval_samples_per_second": 30.704,
|
| 517 |
+
"eval_steps_per_second": 0.569,
|
| 518 |
+
"step": 840
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 86.0,
|
| 522 |
+
"eval_accuracy": 0.8497932935231971,
|
| 523 |
+
"eval_f1": 0.9178116412690482,
|
| 524 |
+
"eval_loss": 1.52961266040802,
|
| 525 |
+
"eval_precision": 0.9171243135297055,
|
| 526 |
+
"eval_recall": 0.9185,
|
| 527 |
+
"eval_runtime": 2.2872,
|
| 528 |
+
"eval_samples_per_second": 23.609,
|
| 529 |
+
"eval_steps_per_second": 0.437,
|
| 530 |
+
"step": 860
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 88.0,
|
| 534 |
+
"eval_accuracy": 0.8484152503445108,
|
| 535 |
+
"eval_f1": 0.9172293073268317,
|
| 536 |
+
"eval_loss": 1.5319523811340332,
|
| 537 |
+
"eval_precision": 0.9174587293646823,
|
| 538 |
+
"eval_recall": 0.917,
|
| 539 |
+
"eval_runtime": 1.8758,
|
| 540 |
+
"eval_samples_per_second": 28.788,
|
| 541 |
+
"eval_steps_per_second": 0.533,
|
| 542 |
+
"step": 880
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 90.0,
|
| 546 |
+
"eval_accuracy": 0.8516306844281121,
|
| 547 |
+
"eval_f1": 0.9216520650813517,
|
| 548 |
+
"eval_loss": 1.5241385698318481,
|
| 549 |
+
"eval_precision": 0.9228070175438596,
|
| 550 |
+
"eval_recall": 0.9205,
|
| 551 |
+
"eval_runtime": 2.319,
|
| 552 |
+
"eval_samples_per_second": 23.286,
|
| 553 |
+
"eval_steps_per_second": 0.431,
|
| 554 |
+
"step": 900
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 92.0,
|
| 558 |
+
"eval_accuracy": 0.8524345429490124,
|
| 559 |
+
"eval_f1": 0.922,
|
| 560 |
+
"eval_loss": 1.5183860063552856,
|
| 561 |
+
"eval_precision": 0.922,
|
| 562 |
+
"eval_recall": 0.922,
|
| 563 |
+
"eval_runtime": 1.8138,
|
| 564 |
+
"eval_samples_per_second": 29.771,
|
| 565 |
+
"eval_steps_per_second": 0.551,
|
| 566 |
+
"step": 920
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 94.0,
|
| 570 |
+
"eval_accuracy": 0.8526642168121268,
|
| 571 |
+
"eval_f1": 0.9215,
|
| 572 |
+
"eval_loss": 1.5182560682296753,
|
| 573 |
+
"eval_precision": 0.9215,
|
| 574 |
+
"eval_recall": 0.9215,
|
| 575 |
+
"eval_runtime": 2.1167,
|
| 576 |
+
"eval_samples_per_second": 25.511,
|
| 577 |
+
"eval_steps_per_second": 0.472,
|
| 578 |
+
"step": 940
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 96.0,
|
| 582 |
+
"eval_accuracy": 0.8523197060174552,
|
| 583 |
+
"eval_f1": 0.9209999999999999,
|
| 584 |
+
"eval_loss": 1.519921898841858,
|
| 585 |
+
"eval_precision": 0.921,
|
| 586 |
+
"eval_recall": 0.921,
|
| 587 |
+
"eval_runtime": 2.4525,
|
| 588 |
+
"eval_samples_per_second": 22.018,
|
| 589 |
+
"eval_steps_per_second": 0.408,
|
| 590 |
+
"step": 960
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 98.0,
|
| 594 |
+
"eval_accuracy": 0.8520900321543409,
|
| 595 |
+
"eval_f1": 0.9214607303651825,
|
| 596 |
+
"eval_loss": 1.5220308303833008,
|
| 597 |
+
"eval_precision": 0.9219219219219219,
|
| 598 |
+
"eval_recall": 0.921,
|
| 599 |
+
"eval_runtime": 2.2195,
|
| 600 |
+
"eval_samples_per_second": 24.33,
|
| 601 |
+
"eval_steps_per_second": 0.451,
|
| 602 |
+
"step": 980
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 100.0,
|
| 606 |
+
"learning_rate": 0.0,
|
| 607 |
+
"loss": 0.0007,
|
| 608 |
+
"step": 1000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 100.0,
|
| 612 |
+
"eval_accuracy": 0.8518603582912264,
|
| 613 |
+
"eval_f1": 0.9214607303651825,
|
| 614 |
+
"eval_loss": 1.5228424072265625,
|
| 615 |
+
"eval_precision": 0.9219219219219219,
|
| 616 |
+
"eval_recall": 0.921,
|
| 617 |
+
"eval_runtime": 2.3676,
|
| 618 |
+
"eval_samples_per_second": 22.808,
|
| 619 |
+
"eval_steps_per_second": 0.422,
|
| 620 |
+
"step": 1000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 100.0,
|
| 624 |
+
"step": 1000,
|
| 625 |
+
"total_flos": 1.4163133547413504e+16,
|
| 626 |
+
"train_loss": 0.06096216064691544,
|
| 627 |
+
"train_runtime": 422.6711,
|
| 628 |
+
"train_samples_per_second": 37.854,
|
| 629 |
+
"train_steps_per_second": 2.366
|
| 630 |
+
}
|
| 631 |
+
],
|
| 632 |
+
"max_steps": 1000,
|
| 633 |
+
"num_train_epochs": 100,
|
| 634 |
+
"total_flos": 1.4163133547413504e+16,
|
| 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 sha256:5b394575a08bc902fa892ef56a399e6133ca56af0b8655e32b95fe534d1cb43f
|
| 3 |
+
size 2927
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|