Commit
•
59f6d0a
1
Parent(s):
591ca4a
End of training
Browse files- README.md +15 -15
- model.safetensors +1 -1
- run-0/checkpoint-1250/config.json +41 -0
- run-0/checkpoint-1250/model.safetensors +3 -0
- run-0/checkpoint-1250/optimizer.pt +3 -0
- run-0/checkpoint-1250/rng_state.pth +3 -0
- run-0/checkpoint-1250/scheduler.pt +3 -0
- run-0/checkpoint-1250/special_tokens_map.json +7 -0
- run-0/checkpoint-1250/tokenizer.json +0 -0
- run-0/checkpoint-1250/tokenizer_config.json +55 -0
- run-0/checkpoint-1250/trainer_state.json +369 -0
- run-0/checkpoint-1250/training_args.bin +3 -0
- run-0/checkpoint-1250/vocab.txt +0 -0
- run-0/checkpoint-2750/config.json +41 -0
- run-0/checkpoint-2750/model.safetensors +3 -0
- run-0/checkpoint-2750/optimizer.pt +3 -0
- run-0/checkpoint-2750/rng_state.pth +3 -0
- run-0/checkpoint-2750/scheduler.pt +3 -0
- run-0/checkpoint-2750/special_tokens_map.json +7 -0
- run-0/checkpoint-2750/tokenizer.json +0 -0
- run-0/checkpoint-2750/tokenizer_config.json +55 -0
- run-0/checkpoint-2750/trainer_state.json +783 -0
- run-0/checkpoint-2750/training_args.bin +3 -0
- run-0/checkpoint-2750/vocab.txt +0 -0
- run-0/checkpoint-3000/config.json +41 -0
- run-0/checkpoint-3000/model.safetensors +3 -0
- run-0/checkpoint-3000/optimizer.pt +3 -0
- run-0/checkpoint-3000/rng_state.pth +3 -0
- run-0/checkpoint-3000/scheduler.pt +3 -0
- run-0/checkpoint-3000/special_tokens_map.json +7 -0
- run-0/checkpoint-3000/tokenizer.json +0 -0
- run-0/checkpoint-3000/tokenizer_config.json +55 -0
- run-0/checkpoint-3000/trainer_state.json +852 -0
- run-0/checkpoint-3000/training_args.bin +3 -0
- run-0/checkpoint-3000/vocab.txt +0 -0
- runs/Dec27_11-45-30_ArtanisPC/events.out.tfevents.1703673939.ArtanisPC.7175.0 +3 -0
- runs/Dec27_12-29-10_ArtanisPC/events.out.tfevents.1703676554.ArtanisPC.7175.1 +3 -0
- runs/Dec27_12-29-10_ArtanisPC/events.out.tfevents.1703680039.ArtanisPC.7175.2 +3 -0
- runs/Dec27_22-15-55_ArtanisPC/events.out.tfevents.1703711759.ArtanisPC.7175.13 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +2 -2
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
- Accuracy: 0.8831
|
| 22 |
|
| 23 |
## Model description
|
|
@@ -37,9 +37,9 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 41 |
- train_batch_size: 16
|
| 42 |
-
- eval_batch_size:
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: constant_with_warmup
|
|
@@ -50,18 +50,18 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6887
|
| 21 |
- Accuracy: 0.8831
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2.754984679344267e-05
|
| 41 |
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: constant_with_warmup
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 0.4485 | 0.32 | 250 | 0.4413 | 0.8328 |
|
| 54 |
+
| 0.3639 | 0.64 | 500 | 0.3684 | 0.8610 |
|
| 55 |
+
| 0.3761 | 0.96 | 750 | 0.3548 | 0.8645 |
|
| 56 |
+
| 0.2545 | 1.28 | 1000 | 0.4220 | 0.8719 |
|
| 57 |
+
| 0.2114 | 1.6 | 1250 | 0.4347 | 0.8716 |
|
| 58 |
+
| 0.2752 | 1.92 | 1500 | 0.4132 | 0.8760 |
|
| 59 |
+
| 0.0953 | 2.24 | 1750 | 0.6133 | 0.8741 |
|
| 60 |
+
| 0.1268 | 2.56 | 2000 | 0.6199 | 0.8796 |
|
| 61 |
+
| 0.1913 | 2.88 | 2250 | 0.5158 | 0.8744 |
|
| 62 |
+
| 0.0897 | 3.21 | 2500 | 0.6667 | 0.8818 |
|
| 63 |
+
| 0.0631 | 3.53 | 2750 | 0.6777 | 0.8770 |
|
| 64 |
+
| 0.0678 | 3.85 | 3000 | 0.6887 | 0.8831 |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 433279996
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0ad560c3e37936e6dad835de0ae94d89bfdd4c000a8e15c452e329a2b2cd32
|
| 3 |
size 433279996
|
run-0/checkpoint-1250/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "bert",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.36.0.dev0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 28996
|
| 41 |
+
}
|
run-0/checkpoint-1250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b335a464acf06e426d2dec585143b4c5c1ce38590987f339fcea895224927fa
|
| 3 |
+
size 433279996
|
run-0/checkpoint-1250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:232f982526fd5da519102936b69a302e8bcc1368a6560027c6eeb3f385e6b212
|
| 3 |
+
size 866681082
|
run-0/checkpoint-1250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cdc434ff6098e0554d4787843fcf7ca49a5c34abae95380fd18fedf04abdf7d
|
| 3 |
+
size 14244
|
run-0/checkpoint-1250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac07d56f59c162718ed3b41b4743390ede2991c6d3831b5f7334f9b82223418d
|
| 3 |
+
size 1064
|
run-0/checkpoint-1250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-0/checkpoint-1250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-1250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-0/checkpoint-1250/trainer_state.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8641896220371557,
|
| 3 |
+
"best_model_checkpoint": "bert_sentiment_trainer/run-0/checkpoint-1250",
|
| 4 |
+
"epoch": 1.6025641025641026,
|
| 5 |
+
"eval_steps": 250,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 3.9713257988848205e-05,
|
| 14 |
+
"loss": 1.2334,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 7.942651597769641e-05,
|
| 20 |
+
"loss": 0.8942,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 7.942651597769641e-05,
|
| 26 |
+
"loss": 0.7179,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 7.942651597769641e-05,
|
| 32 |
+
"loss": 0.5899,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 7.942651597769641e-05,
|
| 38 |
+
"loss": 0.495,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 7.942651597769641e-05,
|
| 44 |
+
"loss": 0.5849,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
+
"learning_rate": 7.942651597769641e-05,
|
| 50 |
+
"loss": 0.6265,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 7.942651597769641e-05,
|
| 56 |
+
"loss": 0.6048,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.29,
|
| 61 |
+
"learning_rate": 7.942651597769641e-05,
|
| 62 |
+
"loss": 0.5534,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.32,
|
| 67 |
+
"learning_rate": 7.942651597769641e-05,
|
| 68 |
+
"loss": 0.51,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.32,
|
| 73 |
+
"eval_accuracy": 0.7882767456758488,
|
| 74 |
+
"eval_loss": 0.5534642338752747,
|
| 75 |
+
"eval_runtime": 31.4685,
|
| 76 |
+
"eval_samples_per_second": 99.21,
|
| 77 |
+
"eval_steps_per_second": 24.818,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.35,
|
| 82 |
+
"learning_rate": 7.942651597769641e-05,
|
| 83 |
+
"loss": 0.518,
|
| 84 |
+
"step": 275
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.38,
|
| 88 |
+
"learning_rate": 7.942651597769641e-05,
|
| 89 |
+
"loss": 0.5262,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.42,
|
| 94 |
+
"learning_rate": 7.942651597769641e-05,
|
| 95 |
+
"loss": 0.532,
|
| 96 |
+
"step": 325
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.45,
|
| 100 |
+
"learning_rate": 7.942651597769641e-05,
|
| 101 |
+
"loss": 0.5475,
|
| 102 |
+
"step": 350
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.48,
|
| 106 |
+
"learning_rate": 7.942651597769641e-05,
|
| 107 |
+
"loss": 0.4561,
|
| 108 |
+
"step": 375
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.51,
|
| 112 |
+
"learning_rate": 7.942651597769641e-05,
|
| 113 |
+
"loss": 0.4714,
|
| 114 |
+
"step": 400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.54,
|
| 118 |
+
"learning_rate": 7.942651597769641e-05,
|
| 119 |
+
"loss": 0.489,
|
| 120 |
+
"step": 425
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.58,
|
| 124 |
+
"learning_rate": 7.942651597769641e-05,
|
| 125 |
+
"loss": 0.5076,
|
| 126 |
+
"step": 450
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.61,
|
| 130 |
+
"learning_rate": 7.942651597769641e-05,
|
| 131 |
+
"loss": 0.5218,
|
| 132 |
+
"step": 475
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.64,
|
| 136 |
+
"learning_rate": 7.942651597769641e-05,
|
| 137 |
+
"loss": 0.4021,
|
| 138 |
+
"step": 500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.64,
|
| 142 |
+
"eval_accuracy": 0.8456117873158232,
|
| 143 |
+
"eval_loss": 0.42485159635543823,
|
| 144 |
+
"eval_runtime": 31.441,
|
| 145 |
+
"eval_samples_per_second": 99.297,
|
| 146 |
+
"eval_steps_per_second": 24.84,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 7.942651597769641e-05,
|
| 152 |
+
"loss": 0.4485,
|
| 153 |
+
"step": 525
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.71,
|
| 157 |
+
"learning_rate": 7.942651597769641e-05,
|
| 158 |
+
"loss": 0.4676,
|
| 159 |
+
"step": 550
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.74,
|
| 163 |
+
"learning_rate": 7.942651597769641e-05,
|
| 164 |
+
"loss": 0.4046,
|
| 165 |
+
"step": 575
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.77,
|
| 169 |
+
"learning_rate": 7.942651597769641e-05,
|
| 170 |
+
"loss": 0.4399,
|
| 171 |
+
"step": 600
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8,
|
| 175 |
+
"learning_rate": 7.942651597769641e-05,
|
| 176 |
+
"loss": 0.483,
|
| 177 |
+
"step": 625
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.83,
|
| 181 |
+
"learning_rate": 7.942651597769641e-05,
|
| 182 |
+
"loss": 0.4302,
|
| 183 |
+
"step": 650
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.87,
|
| 187 |
+
"learning_rate": 7.942651597769641e-05,
|
| 188 |
+
"loss": 0.5286,
|
| 189 |
+
"step": 675
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9,
|
| 193 |
+
"learning_rate": 7.942651597769641e-05,
|
| 194 |
+
"loss": 0.4311,
|
| 195 |
+
"step": 700
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.93,
|
| 199 |
+
"learning_rate": 7.942651597769641e-05,
|
| 200 |
+
"loss": 0.4233,
|
| 201 |
+
"step": 725
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.96,
|
| 205 |
+
"learning_rate": 7.942651597769641e-05,
|
| 206 |
+
"loss": 0.4372,
|
| 207 |
+
"step": 750
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.96,
|
| 211 |
+
"eval_accuracy": 0.8500960922485586,
|
| 212 |
+
"eval_loss": 0.5209916830062866,
|
| 213 |
+
"eval_runtime": 31.4247,
|
| 214 |
+
"eval_samples_per_second": 99.349,
|
| 215 |
+
"eval_steps_per_second": 24.853,
|
| 216 |
+
"step": 750
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.99,
|
| 220 |
+
"learning_rate": 7.942651597769641e-05,
|
| 221 |
+
"loss": 0.424,
|
| 222 |
+
"step": 775
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.03,
|
| 226 |
+
"learning_rate": 7.942651597769641e-05,
|
| 227 |
+
"loss": 0.3704,
|
| 228 |
+
"step": 800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.06,
|
| 232 |
+
"learning_rate": 7.942651597769641e-05,
|
| 233 |
+
"loss": 0.3088,
|
| 234 |
+
"step": 825
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.09,
|
| 238 |
+
"learning_rate": 7.942651597769641e-05,
|
| 239 |
+
"loss": 0.2909,
|
| 240 |
+
"step": 850
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.12,
|
| 244 |
+
"learning_rate": 7.942651597769641e-05,
|
| 245 |
+
"loss": 0.2681,
|
| 246 |
+
"step": 875
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.15,
|
| 250 |
+
"learning_rate": 7.942651597769641e-05,
|
| 251 |
+
"loss": 0.3973,
|
| 252 |
+
"step": 900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.19,
|
| 256 |
+
"learning_rate": 7.942651597769641e-05,
|
| 257 |
+
"loss": 0.297,
|
| 258 |
+
"step": 925
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.22,
|
| 262 |
+
"learning_rate": 7.942651597769641e-05,
|
| 263 |
+
"loss": 0.2422,
|
| 264 |
+
"step": 950
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.25,
|
| 268 |
+
"learning_rate": 7.942651597769641e-05,
|
| 269 |
+
"loss": 0.2867,
|
| 270 |
+
"step": 975
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.28,
|
| 274 |
+
"learning_rate": 7.942651597769641e-05,
|
| 275 |
+
"loss": 0.3266,
|
| 276 |
+
"step": 1000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.28,
|
| 280 |
+
"eval_accuracy": 0.856181934657271,
|
| 281 |
+
"eval_loss": 0.3950304090976715,
|
| 282 |
+
"eval_runtime": 30.2887,
|
| 283 |
+
"eval_samples_per_second": 103.075,
|
| 284 |
+
"eval_steps_per_second": 25.785,
|
| 285 |
+
"step": 1000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.31,
|
| 289 |
+
"learning_rate": 7.942651597769641e-05,
|
| 290 |
+
"loss": 0.3269,
|
| 291 |
+
"step": 1025
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.35,
|
| 295 |
+
"learning_rate": 7.942651597769641e-05,
|
| 296 |
+
"loss": 0.3487,
|
| 297 |
+
"step": 1050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.38,
|
| 301 |
+
"learning_rate": 7.942651597769641e-05,
|
| 302 |
+
"loss": 0.3183,
|
| 303 |
+
"step": 1075
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.41,
|
| 307 |
+
"learning_rate": 7.942651597769641e-05,
|
| 308 |
+
"loss": 0.2852,
|
| 309 |
+
"step": 1100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.44,
|
| 313 |
+
"learning_rate": 7.942651597769641e-05,
|
| 314 |
+
"loss": 0.2746,
|
| 315 |
+
"step": 1125
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.47,
|
| 319 |
+
"learning_rate": 7.942651597769641e-05,
|
| 320 |
+
"loss": 0.3225,
|
| 321 |
+
"step": 1150
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.51,
|
| 325 |
+
"learning_rate": 7.942651597769641e-05,
|
| 326 |
+
"loss": 0.2891,
|
| 327 |
+
"step": 1175
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.54,
|
| 331 |
+
"learning_rate": 7.942651597769641e-05,
|
| 332 |
+
"loss": 0.3634,
|
| 333 |
+
"step": 1200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.57,
|
| 337 |
+
"learning_rate": 7.942651597769641e-05,
|
| 338 |
+
"loss": 0.3269,
|
| 339 |
+
"step": 1225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6,
|
| 343 |
+
"learning_rate": 7.942651597769641e-05,
|
| 344 |
+
"loss": 0.3018,
|
| 345 |
+
"step": 1250
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.6,
|
| 349 |
+
"eval_accuracy": 0.8641896220371557,
|
| 350 |
+
"eval_loss": 0.41122835874557495,
|
| 351 |
+
"eval_runtime": 30.2612,
|
| 352 |
+
"eval_samples_per_second": 103.168,
|
| 353 |
+
"eval_steps_per_second": 25.809,
|
| 354 |
+
"step": 1250
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 25,
|
| 358 |
+
"max_steps": 3000,
|
| 359 |
+
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 4,
|
| 361 |
+
"save_steps": 250,
|
| 362 |
+
"total_flos": 5262099731137536.0,
|
| 363 |
+
"trial_name": null,
|
| 364 |
+
"trial_params": {
|
| 365 |
+
"learning_rate": 7.942651597769641e-05,
|
| 366 |
+
"per_device_eval_batch_size": 4,
|
| 367 |
+
"per_device_train_batch_size": 16
|
| 368 |
+
}
|
| 369 |
+
}
|
run-0/checkpoint-1250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a80260bc43050598885ca65b27a19bd3017acc59969e8c39101e7e300d8c14
|
| 3 |
+
size 4664
|
run-0/checkpoint-1250/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-2750/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "bert",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.36.0.dev0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 28996
|
| 41 |
+
}
|
run-0/checkpoint-2750/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdbb95b9d5a83d0e84ea60bef02fcc618e34c4453a5dc3227998ccc7a54c92ea
|
| 3 |
+
size 433279996
|
run-0/checkpoint-2750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7280cf6d2f24cc397770788f0e4bbd63c719c6d2bb58387c7f1703e661afc253
|
| 3 |
+
size 866681082
|
run-0/checkpoint-2750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f02b9cb6a2d9978c791f178c09f195cefcef73d1f59d9e6cd65fec90f7bb95c
|
| 3 |
+
size 14244
|
run-0/checkpoint-2750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e106c0df641d501046ce5f9d50dece253317540755e5b42d51a7056bb9a5aa39
|
| 3 |
+
size 1064
|
run-0/checkpoint-2750/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-0/checkpoint-2750/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-2750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-0/checkpoint-2750/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8641896220371557,
|
| 3 |
+
"best_model_checkpoint": "bert_sentiment_trainer/run-0/checkpoint-1250",
|
| 4 |
+
"epoch": 3.5256410256410255,
|
| 5 |
+
"eval_steps": 250,
|
| 6 |
+
"global_step": 2750,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 3.9713257988848205e-05,
|
| 14 |
+
"loss": 1.2334,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 7.942651597769641e-05,
|
| 20 |
+
"loss": 0.8942,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 7.942651597769641e-05,
|
| 26 |
+
"loss": 0.7179,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 7.942651597769641e-05,
|
| 32 |
+
"loss": 0.5899,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 7.942651597769641e-05,
|
| 38 |
+
"loss": 0.495,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 7.942651597769641e-05,
|
| 44 |
+
"loss": 0.5849,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
+
"learning_rate": 7.942651597769641e-05,
|
| 50 |
+
"loss": 0.6265,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 7.942651597769641e-05,
|
| 56 |
+
"loss": 0.6048,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.29,
|
| 61 |
+
"learning_rate": 7.942651597769641e-05,
|
| 62 |
+
"loss": 0.5534,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.32,
|
| 67 |
+
"learning_rate": 7.942651597769641e-05,
|
| 68 |
+
"loss": 0.51,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.32,
|
| 73 |
+
"eval_accuracy": 0.7882767456758488,
|
| 74 |
+
"eval_loss": 0.5534642338752747,
|
| 75 |
+
"eval_runtime": 31.4685,
|
| 76 |
+
"eval_samples_per_second": 99.21,
|
| 77 |
+
"eval_steps_per_second": 24.818,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.35,
|
| 82 |
+
"learning_rate": 7.942651597769641e-05,
|
| 83 |
+
"loss": 0.518,
|
| 84 |
+
"step": 275
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.38,
|
| 88 |
+
"learning_rate": 7.942651597769641e-05,
|
| 89 |
+
"loss": 0.5262,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.42,
|
| 94 |
+
"learning_rate": 7.942651597769641e-05,
|
| 95 |
+
"loss": 0.532,
|
| 96 |
+
"step": 325
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.45,
|
| 100 |
+
"learning_rate": 7.942651597769641e-05,
|
| 101 |
+
"loss": 0.5475,
|
| 102 |
+
"step": 350
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.48,
|
| 106 |
+
"learning_rate": 7.942651597769641e-05,
|
| 107 |
+
"loss": 0.4561,
|
| 108 |
+
"step": 375
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.51,
|
| 112 |
+
"learning_rate": 7.942651597769641e-05,
|
| 113 |
+
"loss": 0.4714,
|
| 114 |
+
"step": 400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.54,
|
| 118 |
+
"learning_rate": 7.942651597769641e-05,
|
| 119 |
+
"loss": 0.489,
|
| 120 |
+
"step": 425
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.58,
|
| 124 |
+
"learning_rate": 7.942651597769641e-05,
|
| 125 |
+
"loss": 0.5076,
|
| 126 |
+
"step": 450
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.61,
|
| 130 |
+
"learning_rate": 7.942651597769641e-05,
|
| 131 |
+
"loss": 0.5218,
|
| 132 |
+
"step": 475
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.64,
|
| 136 |
+
"learning_rate": 7.942651597769641e-05,
|
| 137 |
+
"loss": 0.4021,
|
| 138 |
+
"step": 500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.64,
|
| 142 |
+
"eval_accuracy": 0.8456117873158232,
|
| 143 |
+
"eval_loss": 0.42485159635543823,
|
| 144 |
+
"eval_runtime": 31.441,
|
| 145 |
+
"eval_samples_per_second": 99.297,
|
| 146 |
+
"eval_steps_per_second": 24.84,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 7.942651597769641e-05,
|
| 152 |
+
"loss": 0.4485,
|
| 153 |
+
"step": 525
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.71,
|
| 157 |
+
"learning_rate": 7.942651597769641e-05,
|
| 158 |
+
"loss": 0.4676,
|
| 159 |
+
"step": 550
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.74,
|
| 163 |
+
"learning_rate": 7.942651597769641e-05,
|
| 164 |
+
"loss": 0.4046,
|
| 165 |
+
"step": 575
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.77,
|
| 169 |
+
"learning_rate": 7.942651597769641e-05,
|
| 170 |
+
"loss": 0.4399,
|
| 171 |
+
"step": 600
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8,
|
| 175 |
+
"learning_rate": 7.942651597769641e-05,
|
| 176 |
+
"loss": 0.483,
|
| 177 |
+
"step": 625
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.83,
|
| 181 |
+
"learning_rate": 7.942651597769641e-05,
|
| 182 |
+
"loss": 0.4302,
|
| 183 |
+
"step": 650
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.87,
|
| 187 |
+
"learning_rate": 7.942651597769641e-05,
|
| 188 |
+
"loss": 0.5286,
|
| 189 |
+
"step": 675
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9,
|
| 193 |
+
"learning_rate": 7.942651597769641e-05,
|
| 194 |
+
"loss": 0.4311,
|
| 195 |
+
"step": 700
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.93,
|
| 199 |
+
"learning_rate": 7.942651597769641e-05,
|
| 200 |
+
"loss": 0.4233,
|
| 201 |
+
"step": 725
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.96,
|
| 205 |
+
"learning_rate": 7.942651597769641e-05,
|
| 206 |
+
"loss": 0.4372,
|
| 207 |
+
"step": 750
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.96,
|
| 211 |
+
"eval_accuracy": 0.8500960922485586,
|
| 212 |
+
"eval_loss": 0.5209916830062866,
|
| 213 |
+
"eval_runtime": 31.4247,
|
| 214 |
+
"eval_samples_per_second": 99.349,
|
| 215 |
+
"eval_steps_per_second": 24.853,
|
| 216 |
+
"step": 750
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.99,
|
| 220 |
+
"learning_rate": 7.942651597769641e-05,
|
| 221 |
+
"loss": 0.424,
|
| 222 |
+
"step": 775
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.03,
|
| 226 |
+
"learning_rate": 7.942651597769641e-05,
|
| 227 |
+
"loss": 0.3704,
|
| 228 |
+
"step": 800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.06,
|
| 232 |
+
"learning_rate": 7.942651597769641e-05,
|
| 233 |
+
"loss": 0.3088,
|
| 234 |
+
"step": 825
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.09,
|
| 238 |
+
"learning_rate": 7.942651597769641e-05,
|
| 239 |
+
"loss": 0.2909,
|
| 240 |
+
"step": 850
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.12,
|
| 244 |
+
"learning_rate": 7.942651597769641e-05,
|
| 245 |
+
"loss": 0.2681,
|
| 246 |
+
"step": 875
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.15,
|
| 250 |
+
"learning_rate": 7.942651597769641e-05,
|
| 251 |
+
"loss": 0.3973,
|
| 252 |
+
"step": 900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.19,
|
| 256 |
+
"learning_rate": 7.942651597769641e-05,
|
| 257 |
+
"loss": 0.297,
|
| 258 |
+
"step": 925
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.22,
|
| 262 |
+
"learning_rate": 7.942651597769641e-05,
|
| 263 |
+
"loss": 0.2422,
|
| 264 |
+
"step": 950
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.25,
|
| 268 |
+
"learning_rate": 7.942651597769641e-05,
|
| 269 |
+
"loss": 0.2867,
|
| 270 |
+
"step": 975
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.28,
|
| 274 |
+
"learning_rate": 7.942651597769641e-05,
|
| 275 |
+
"loss": 0.3266,
|
| 276 |
+
"step": 1000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.28,
|
| 280 |
+
"eval_accuracy": 0.856181934657271,
|
| 281 |
+
"eval_loss": 0.3950304090976715,
|
| 282 |
+
"eval_runtime": 30.2887,
|
| 283 |
+
"eval_samples_per_second": 103.075,
|
| 284 |
+
"eval_steps_per_second": 25.785,
|
| 285 |
+
"step": 1000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.31,
|
| 289 |
+
"learning_rate": 7.942651597769641e-05,
|
| 290 |
+
"loss": 0.3269,
|
| 291 |
+
"step": 1025
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.35,
|
| 295 |
+
"learning_rate": 7.942651597769641e-05,
|
| 296 |
+
"loss": 0.3487,
|
| 297 |
+
"step": 1050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.38,
|
| 301 |
+
"learning_rate": 7.942651597769641e-05,
|
| 302 |
+
"loss": 0.3183,
|
| 303 |
+
"step": 1075
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.41,
|
| 307 |
+
"learning_rate": 7.942651597769641e-05,
|
| 308 |
+
"loss": 0.2852,
|
| 309 |
+
"step": 1100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.44,
|
| 313 |
+
"learning_rate": 7.942651597769641e-05,
|
| 314 |
+
"loss": 0.2746,
|
| 315 |
+
"step": 1125
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.47,
|
| 319 |
+
"learning_rate": 7.942651597769641e-05,
|
| 320 |
+
"loss": 0.3225,
|
| 321 |
+
"step": 1150
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.51,
|
| 325 |
+
"learning_rate": 7.942651597769641e-05,
|
| 326 |
+
"loss": 0.2891,
|
| 327 |
+
"step": 1175
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.54,
|
| 331 |
+
"learning_rate": 7.942651597769641e-05,
|
| 332 |
+
"loss": 0.3634,
|
| 333 |
+
"step": 1200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.57,
|
| 337 |
+
"learning_rate": 7.942651597769641e-05,
|
| 338 |
+
"loss": 0.3269,
|
| 339 |
+
"step": 1225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6,
|
| 343 |
+
"learning_rate": 7.942651597769641e-05,
|
| 344 |
+
"loss": 0.3018,
|
| 345 |
+
"step": 1250
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.6,
|
| 349 |
+
"eval_accuracy": 0.8641896220371557,
|
| 350 |
+
"eval_loss": 0.41122835874557495,
|
| 351 |
+
"eval_runtime": 30.2612,
|
| 352 |
+
"eval_samples_per_second": 103.168,
|
| 353 |
+
"eval_steps_per_second": 25.809,
|
| 354 |
+
"step": 1250
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.63,
|
| 358 |
+
"learning_rate": 7.942651597769641e-05,
|
| 359 |
+
"loss": 0.3177,
|
| 360 |
+
"step": 1275
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.67,
|
| 364 |
+
"learning_rate": 7.942651597769641e-05,
|
| 365 |
+
"loss": 0.3021,
|
| 366 |
+
"step": 1300
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.7,
|
| 370 |
+
"learning_rate": 7.942651597769641e-05,
|
| 371 |
+
"loss": 0.3148,
|
| 372 |
+
"step": 1325
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.73,
|
| 376 |
+
"learning_rate": 7.942651597769641e-05,
|
| 377 |
+
"loss": 0.3312,
|
| 378 |
+
"step": 1350
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.76,
|
| 382 |
+
"learning_rate": 7.942651597769641e-05,
|
| 383 |
+
"loss": 0.2438,
|
| 384 |
+
"step": 1375
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.79,
|
| 388 |
+
"learning_rate": 7.942651597769641e-05,
|
| 389 |
+
"loss": 0.3289,
|
| 390 |
+
"step": 1400
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.83,
|
| 394 |
+
"learning_rate": 7.942651597769641e-05,
|
| 395 |
+
"loss": 0.3437,
|
| 396 |
+
"step": 1425
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.86,
|
| 400 |
+
"learning_rate": 7.942651597769641e-05,
|
| 401 |
+
"loss": 0.2688,
|
| 402 |
+
"step": 1450
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.89,
|
| 406 |
+
"learning_rate": 7.942651597769641e-05,
|
| 407 |
+
"loss": 0.2776,
|
| 408 |
+
"step": 1475
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.92,
|
| 412 |
+
"learning_rate": 7.942651597769641e-05,
|
| 413 |
+
"loss": 0.2878,
|
| 414 |
+
"step": 1500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.92,
|
| 418 |
+
"eval_accuracy": 0.860345932094811,
|
| 419 |
+
"eval_loss": 0.4497346878051758,
|
| 420 |
+
"eval_runtime": 30.3296,
|
| 421 |
+
"eval_samples_per_second": 102.936,
|
| 422 |
+
"eval_steps_per_second": 25.75,
|
| 423 |
+
"step": 1500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.96,
|
| 427 |
+
"learning_rate": 7.942651597769641e-05,
|
| 428 |
+
"loss": 0.3063,
|
| 429 |
+
"step": 1525
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.99,
|
| 433 |
+
"learning_rate": 7.942651597769641e-05,
|
| 434 |
+
"loss": 0.3134,
|
| 435 |
+
"step": 1550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.02,
|
| 439 |
+
"learning_rate": 7.942651597769641e-05,
|
| 440 |
+
"loss": 0.199,
|
| 441 |
+
"step": 1575
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.05,
|
| 445 |
+
"learning_rate": 7.942651597769641e-05,
|
| 446 |
+
"loss": 0.1655,
|
| 447 |
+
"step": 1600
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.08,
|
| 451 |
+
"learning_rate": 7.942651597769641e-05,
|
| 452 |
+
"loss": 0.1884,
|
| 453 |
+
"step": 1625
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.12,
|
| 457 |
+
"learning_rate": 7.942651597769641e-05,
|
| 458 |
+
"loss": 0.1679,
|
| 459 |
+
"step": 1650
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.15,
|
| 463 |
+
"learning_rate": 7.942651597769641e-05,
|
| 464 |
+
"loss": 0.2939,
|
| 465 |
+
"step": 1675
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.18,
|
| 469 |
+
"learning_rate": 7.942651597769641e-05,
|
| 470 |
+
"loss": 0.2126,
|
| 471 |
+
"step": 1700
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.21,
|
| 475 |
+
"learning_rate": 7.942651597769641e-05,
|
| 476 |
+
"loss": 0.1194,
|
| 477 |
+
"step": 1725
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.24,
|
| 481 |
+
"learning_rate": 7.942651597769641e-05,
|
| 482 |
+
"loss": 0.1432,
|
| 483 |
+
"step": 1750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.24,
|
| 487 |
+
"eval_accuracy": 0.8587443946188341,
|
| 488 |
+
"eval_loss": 0.5730303525924683,
|
| 489 |
+
"eval_runtime": 31.4543,
|
| 490 |
+
"eval_samples_per_second": 99.255,
|
| 491 |
+
"eval_steps_per_second": 24.83,
|
| 492 |
+
"step": 1750
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.28,
|
| 496 |
+
"learning_rate": 7.942651597769641e-05,
|
| 497 |
+
"loss": 0.1837,
|
| 498 |
+
"step": 1775
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.31,
|
| 502 |
+
"learning_rate": 7.942651597769641e-05,
|
| 503 |
+
"loss": 0.1633,
|
| 504 |
+
"step": 1800
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.34,
|
| 508 |
+
"learning_rate": 7.942651597769641e-05,
|
| 509 |
+
"loss": 0.1829,
|
| 510 |
+
"step": 1825
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.37,
|
| 514 |
+
"learning_rate": 7.942651597769641e-05,
|
| 515 |
+
"loss": 0.1597,
|
| 516 |
+
"step": 1850
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.4,
|
| 520 |
+
"learning_rate": 7.942651597769641e-05,
|
| 521 |
+
"loss": 0.1995,
|
| 522 |
+
"step": 1875
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.44,
|
| 526 |
+
"learning_rate": 7.942651597769641e-05,
|
| 527 |
+
"loss": 0.1709,
|
| 528 |
+
"step": 1900
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.47,
|
| 532 |
+
"learning_rate": 7.942651597769641e-05,
|
| 533 |
+
"loss": 0.2337,
|
| 534 |
+
"step": 1925
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.5,
|
| 538 |
+
"learning_rate": 7.942651597769641e-05,
|
| 539 |
+
"loss": 0.1308,
|
| 540 |
+
"step": 1950
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.53,
|
| 544 |
+
"learning_rate": 7.942651597769641e-05,
|
| 545 |
+
"loss": 0.2534,
|
| 546 |
+
"step": 1975
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.56,
|
| 550 |
+
"learning_rate": 7.942651597769641e-05,
|
| 551 |
+
"loss": 0.2154,
|
| 552 |
+
"step": 2000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.56,
|
| 556 |
+
"eval_accuracy": 0.8625880845611787,
|
| 557 |
+
"eval_loss": 0.5824428796768188,
|
| 558 |
+
"eval_runtime": 31.5134,
|
| 559 |
+
"eval_samples_per_second": 99.069,
|
| 560 |
+
"eval_steps_per_second": 24.783,
|
| 561 |
+
"step": 2000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.6,
|
| 565 |
+
"learning_rate": 7.942651597769641e-05,
|
| 566 |
+
"loss": 0.2489,
|
| 567 |
+
"step": 2025
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.63,
|
| 571 |
+
"learning_rate": 7.942651597769641e-05,
|
| 572 |
+
"loss": 0.2025,
|
| 573 |
+
"step": 2050
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.66,
|
| 577 |
+
"learning_rate": 7.942651597769641e-05,
|
| 578 |
+
"loss": 0.2566,
|
| 579 |
+
"step": 2075
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.69,
|
| 583 |
+
"learning_rate": 7.942651597769641e-05,
|
| 584 |
+
"loss": 0.1954,
|
| 585 |
+
"step": 2100
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.72,
|
| 589 |
+
"learning_rate": 7.942651597769641e-05,
|
| 590 |
+
"loss": 0.1965,
|
| 591 |
+
"step": 2125
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.76,
|
| 595 |
+
"learning_rate": 7.942651597769641e-05,
|
| 596 |
+
"loss": 0.2578,
|
| 597 |
+
"step": 2150
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.79,
|
| 601 |
+
"learning_rate": 7.942651597769641e-05,
|
| 602 |
+
"loss": 0.2349,
|
| 603 |
+
"step": 2175
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.82,
|
| 607 |
+
"learning_rate": 7.942651597769641e-05,
|
| 608 |
+
"loss": 0.227,
|
| 609 |
+
"step": 2200
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.85,
|
| 613 |
+
"learning_rate": 7.942651597769641e-05,
|
| 614 |
+
"loss": 0.2325,
|
| 615 |
+
"step": 2225
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.88,
|
| 619 |
+
"learning_rate": 7.942651597769641e-05,
|
| 620 |
+
"loss": 0.2678,
|
| 621 |
+
"step": 2250
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.88,
|
| 625 |
+
"eval_accuracy": 0.8632286995515696,
|
| 626 |
+
"eval_loss": 0.5371272563934326,
|
| 627 |
+
"eval_runtime": 31.4396,
|
| 628 |
+
"eval_samples_per_second": 99.302,
|
| 629 |
+
"eval_steps_per_second": 24.841,
|
| 630 |
+
"step": 2250
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.92,
|
| 634 |
+
"learning_rate": 7.942651597769641e-05,
|
| 635 |
+
"loss": 0.2809,
|
| 636 |
+
"step": 2275
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.95,
|
| 640 |
+
"learning_rate": 7.942651597769641e-05,
|
| 641 |
+
"loss": 0.2497,
|
| 642 |
+
"step": 2300
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.98,
|
| 646 |
+
"learning_rate": 7.942651597769641e-05,
|
| 647 |
+
"loss": 0.2487,
|
| 648 |
+
"step": 2325
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.01,
|
| 652 |
+
"learning_rate": 7.942651597769641e-05,
|
| 653 |
+
"loss": 0.2001,
|
| 654 |
+
"step": 2350
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.04,
|
| 658 |
+
"learning_rate": 7.942651597769641e-05,
|
| 659 |
+
"loss": 0.1682,
|
| 660 |
+
"step": 2375
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.08,
|
| 664 |
+
"learning_rate": 7.942651597769641e-05,
|
| 665 |
+
"loss": 0.1243,
|
| 666 |
+
"step": 2400
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.11,
|
| 670 |
+
"learning_rate": 7.942651597769641e-05,
|
| 671 |
+
"loss": 0.1468,
|
| 672 |
+
"step": 2425
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.14,
|
| 676 |
+
"learning_rate": 7.942651597769641e-05,
|
| 677 |
+
"loss": 0.1909,
|
| 678 |
+
"step": 2450
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 3.17,
|
| 682 |
+
"learning_rate": 7.942651597769641e-05,
|
| 683 |
+
"loss": 0.1254,
|
| 684 |
+
"step": 2475
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.21,
|
| 688 |
+
"learning_rate": 7.942651597769641e-05,
|
| 689 |
+
"loss": 0.1647,
|
| 690 |
+
"step": 2500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.21,
|
| 694 |
+
"eval_accuracy": 0.8632286995515696,
|
| 695 |
+
"eval_loss": 0.6494662165641785,
|
| 696 |
+
"eval_runtime": 31.5059,
|
| 697 |
+
"eval_samples_per_second": 99.092,
|
| 698 |
+
"eval_steps_per_second": 24.789,
|
| 699 |
+
"step": 2500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.24,
|
| 703 |
+
"learning_rate": 7.942651597769641e-05,
|
| 704 |
+
"loss": 0.1255,
|
| 705 |
+
"step": 2525
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.27,
|
| 709 |
+
"learning_rate": 7.942651597769641e-05,
|
| 710 |
+
"loss": 0.2115,
|
| 711 |
+
"step": 2550
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.3,
|
| 715 |
+
"learning_rate": 7.942651597769641e-05,
|
| 716 |
+
"loss": 0.1292,
|
| 717 |
+
"step": 2575
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.33,
|
| 721 |
+
"learning_rate": 7.942651597769641e-05,
|
| 722 |
+
"loss": 0.084,
|
| 723 |
+
"step": 2600
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.37,
|
| 727 |
+
"learning_rate": 7.942651597769641e-05,
|
| 728 |
+
"loss": 0.1508,
|
| 729 |
+
"step": 2625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.4,
|
| 733 |
+
"learning_rate": 7.942651597769641e-05,
|
| 734 |
+
"loss": 0.2381,
|
| 735 |
+
"step": 2650
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.43,
|
| 739 |
+
"learning_rate": 7.942651597769641e-05,
|
| 740 |
+
"loss": 0.119,
|
| 741 |
+
"step": 2675
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.46,
|
| 745 |
+
"learning_rate": 7.942651597769641e-05,
|
| 746 |
+
"loss": 0.2611,
|
| 747 |
+
"step": 2700
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.49,
|
| 751 |
+
"learning_rate": 7.942651597769641e-05,
|
| 752 |
+
"loss": 0.1441,
|
| 753 |
+
"step": 2725
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.53,
|
| 757 |
+
"learning_rate": 7.942651597769641e-05,
|
| 758 |
+
"loss": 0.1503,
|
| 759 |
+
"step": 2750
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.53,
|
| 763 |
+
"eval_accuracy": 0.8392056374119155,
|
| 764 |
+
"eval_loss": 0.739354133605957,
|
| 765 |
+
"eval_runtime": 31.689,
|
| 766 |
+
"eval_samples_per_second": 98.52,
|
| 767 |
+
"eval_steps_per_second": 24.646,
|
| 768 |
+
"step": 2750
|
| 769 |
+
}
|
| 770 |
+
],
|
| 771 |
+
"logging_steps": 25,
|
| 772 |
+
"max_steps": 3000,
|
| 773 |
+
"num_input_tokens_seen": 0,
|
| 774 |
+
"num_train_epochs": 4,
|
| 775 |
+
"save_steps": 250,
|
| 776 |
+
"total_flos": 1.1576408913988608e+16,
|
| 777 |
+
"trial_name": null,
|
| 778 |
+
"trial_params": {
|
| 779 |
+
"learning_rate": 7.942651597769641e-05,
|
| 780 |
+
"per_device_eval_batch_size": 4,
|
| 781 |
+
"per_device_train_batch_size": 16
|
| 782 |
+
}
|
| 783 |
+
}
|
run-0/checkpoint-2750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a80260bc43050598885ca65b27a19bd3017acc59969e8c39101e7e300d8c14
|
| 3 |
+
size 4664
|
run-0/checkpoint-2750/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "bert",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.36.0.dev0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 28996
|
| 41 |
+
}
|
run-0/checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f16b4aa536ebc84eb9f93f23ff4b038275b1b083ea428b36d6f05a950c3ae4bd
|
| 3 |
+
size 433279996
|
run-0/checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90e119e4d430dc78cc1e7f3befd87ecc80299be9f2d54240db9942af24788cee
|
| 3 |
+
size 866681082
|
run-0/checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73eb499cce13cf3dc690fc066e48e80cdcbcb1c0469b4ffea8359eb45e382fda
|
| 3 |
+
size 14244
|
run-0/checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c304939c753a79940dfd3547faf6c8a73cff363a570ce4999929bf266735f8bb
|
| 3 |
+
size 1064
|
run-0/checkpoint-3000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-0/checkpoint-3000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-3000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-0/checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,852 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8641896220371557,
|
| 3 |
+
"best_model_checkpoint": "bert_sentiment_trainer/run-0/checkpoint-1250",
|
| 4 |
+
"epoch": 3.8461538461538463,
|
| 5 |
+
"eval_steps": 250,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 3.9713257988848205e-05,
|
| 14 |
+
"loss": 1.2334,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 7.942651597769641e-05,
|
| 20 |
+
"loss": 0.8942,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 7.942651597769641e-05,
|
| 26 |
+
"loss": 0.7179,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 7.942651597769641e-05,
|
| 32 |
+
"loss": 0.5899,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 7.942651597769641e-05,
|
| 38 |
+
"loss": 0.495,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 7.942651597769641e-05,
|
| 44 |
+
"loss": 0.5849,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
+
"learning_rate": 7.942651597769641e-05,
|
| 50 |
+
"loss": 0.6265,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26,
|
| 55 |
+
"learning_rate": 7.942651597769641e-05,
|
| 56 |
+
"loss": 0.6048,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.29,
|
| 61 |
+
"learning_rate": 7.942651597769641e-05,
|
| 62 |
+
"loss": 0.5534,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.32,
|
| 67 |
+
"learning_rate": 7.942651597769641e-05,
|
| 68 |
+
"loss": 0.51,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.32,
|
| 73 |
+
"eval_accuracy": 0.7882767456758488,
|
| 74 |
+
"eval_loss": 0.5534642338752747,
|
| 75 |
+
"eval_runtime": 31.4685,
|
| 76 |
+
"eval_samples_per_second": 99.21,
|
| 77 |
+
"eval_steps_per_second": 24.818,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.35,
|
| 82 |
+
"learning_rate": 7.942651597769641e-05,
|
| 83 |
+
"loss": 0.518,
|
| 84 |
+
"step": 275
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.38,
|
| 88 |
+
"learning_rate": 7.942651597769641e-05,
|
| 89 |
+
"loss": 0.5262,
|
| 90 |
+
"step": 300
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.42,
|
| 94 |
+
"learning_rate": 7.942651597769641e-05,
|
| 95 |
+
"loss": 0.532,
|
| 96 |
+
"step": 325
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.45,
|
| 100 |
+
"learning_rate": 7.942651597769641e-05,
|
| 101 |
+
"loss": 0.5475,
|
| 102 |
+
"step": 350
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.48,
|
| 106 |
+
"learning_rate": 7.942651597769641e-05,
|
| 107 |
+
"loss": 0.4561,
|
| 108 |
+
"step": 375
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.51,
|
| 112 |
+
"learning_rate": 7.942651597769641e-05,
|
| 113 |
+
"loss": 0.4714,
|
| 114 |
+
"step": 400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.54,
|
| 118 |
+
"learning_rate": 7.942651597769641e-05,
|
| 119 |
+
"loss": 0.489,
|
| 120 |
+
"step": 425
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.58,
|
| 124 |
+
"learning_rate": 7.942651597769641e-05,
|
| 125 |
+
"loss": 0.5076,
|
| 126 |
+
"step": 450
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.61,
|
| 130 |
+
"learning_rate": 7.942651597769641e-05,
|
| 131 |
+
"loss": 0.5218,
|
| 132 |
+
"step": 475
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.64,
|
| 136 |
+
"learning_rate": 7.942651597769641e-05,
|
| 137 |
+
"loss": 0.4021,
|
| 138 |
+
"step": 500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.64,
|
| 142 |
+
"eval_accuracy": 0.8456117873158232,
|
| 143 |
+
"eval_loss": 0.42485159635543823,
|
| 144 |
+
"eval_runtime": 31.441,
|
| 145 |
+
"eval_samples_per_second": 99.297,
|
| 146 |
+
"eval_steps_per_second": 24.84,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 7.942651597769641e-05,
|
| 152 |
+
"loss": 0.4485,
|
| 153 |
+
"step": 525
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.71,
|
| 157 |
+
"learning_rate": 7.942651597769641e-05,
|
| 158 |
+
"loss": 0.4676,
|
| 159 |
+
"step": 550
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.74,
|
| 163 |
+
"learning_rate": 7.942651597769641e-05,
|
| 164 |
+
"loss": 0.4046,
|
| 165 |
+
"step": 575
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.77,
|
| 169 |
+
"learning_rate": 7.942651597769641e-05,
|
| 170 |
+
"loss": 0.4399,
|
| 171 |
+
"step": 600
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8,
|
| 175 |
+
"learning_rate": 7.942651597769641e-05,
|
| 176 |
+
"loss": 0.483,
|
| 177 |
+
"step": 625
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.83,
|
| 181 |
+
"learning_rate": 7.942651597769641e-05,
|
| 182 |
+
"loss": 0.4302,
|
| 183 |
+
"step": 650
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.87,
|
| 187 |
+
"learning_rate": 7.942651597769641e-05,
|
| 188 |
+
"loss": 0.5286,
|
| 189 |
+
"step": 675
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9,
|
| 193 |
+
"learning_rate": 7.942651597769641e-05,
|
| 194 |
+
"loss": 0.4311,
|
| 195 |
+
"step": 700
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.93,
|
| 199 |
+
"learning_rate": 7.942651597769641e-05,
|
| 200 |
+
"loss": 0.4233,
|
| 201 |
+
"step": 725
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.96,
|
| 205 |
+
"learning_rate": 7.942651597769641e-05,
|
| 206 |
+
"loss": 0.4372,
|
| 207 |
+
"step": 750
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.96,
|
| 211 |
+
"eval_accuracy": 0.8500960922485586,
|
| 212 |
+
"eval_loss": 0.5209916830062866,
|
| 213 |
+
"eval_runtime": 31.4247,
|
| 214 |
+
"eval_samples_per_second": 99.349,
|
| 215 |
+
"eval_steps_per_second": 24.853,
|
| 216 |
+
"step": 750
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.99,
|
| 220 |
+
"learning_rate": 7.942651597769641e-05,
|
| 221 |
+
"loss": 0.424,
|
| 222 |
+
"step": 775
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.03,
|
| 226 |
+
"learning_rate": 7.942651597769641e-05,
|
| 227 |
+
"loss": 0.3704,
|
| 228 |
+
"step": 800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.06,
|
| 232 |
+
"learning_rate": 7.942651597769641e-05,
|
| 233 |
+
"loss": 0.3088,
|
| 234 |
+
"step": 825
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.09,
|
| 238 |
+
"learning_rate": 7.942651597769641e-05,
|
| 239 |
+
"loss": 0.2909,
|
| 240 |
+
"step": 850
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.12,
|
| 244 |
+
"learning_rate": 7.942651597769641e-05,
|
| 245 |
+
"loss": 0.2681,
|
| 246 |
+
"step": 875
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.15,
|
| 250 |
+
"learning_rate": 7.942651597769641e-05,
|
| 251 |
+
"loss": 0.3973,
|
| 252 |
+
"step": 900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.19,
|
| 256 |
+
"learning_rate": 7.942651597769641e-05,
|
| 257 |
+
"loss": 0.297,
|
| 258 |
+
"step": 925
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.22,
|
| 262 |
+
"learning_rate": 7.942651597769641e-05,
|
| 263 |
+
"loss": 0.2422,
|
| 264 |
+
"step": 950
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.25,
|
| 268 |
+
"learning_rate": 7.942651597769641e-05,
|
| 269 |
+
"loss": 0.2867,
|
| 270 |
+
"step": 975
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.28,
|
| 274 |
+
"learning_rate": 7.942651597769641e-05,
|
| 275 |
+
"loss": 0.3266,
|
| 276 |
+
"step": 1000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.28,
|
| 280 |
+
"eval_accuracy": 0.856181934657271,
|
| 281 |
+
"eval_loss": 0.3950304090976715,
|
| 282 |
+
"eval_runtime": 30.2887,
|
| 283 |
+
"eval_samples_per_second": 103.075,
|
| 284 |
+
"eval_steps_per_second": 25.785,
|
| 285 |
+
"step": 1000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.31,
|
| 289 |
+
"learning_rate": 7.942651597769641e-05,
|
| 290 |
+
"loss": 0.3269,
|
| 291 |
+
"step": 1025
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.35,
|
| 295 |
+
"learning_rate": 7.942651597769641e-05,
|
| 296 |
+
"loss": 0.3487,
|
| 297 |
+
"step": 1050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.38,
|
| 301 |
+
"learning_rate": 7.942651597769641e-05,
|
| 302 |
+
"loss": 0.3183,
|
| 303 |
+
"step": 1075
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.41,
|
| 307 |
+
"learning_rate": 7.942651597769641e-05,
|
| 308 |
+
"loss": 0.2852,
|
| 309 |
+
"step": 1100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.44,
|
| 313 |
+
"learning_rate": 7.942651597769641e-05,
|
| 314 |
+
"loss": 0.2746,
|
| 315 |
+
"step": 1125
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.47,
|
| 319 |
+
"learning_rate": 7.942651597769641e-05,
|
| 320 |
+
"loss": 0.3225,
|
| 321 |
+
"step": 1150
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.51,
|
| 325 |
+
"learning_rate": 7.942651597769641e-05,
|
| 326 |
+
"loss": 0.2891,
|
| 327 |
+
"step": 1175
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.54,
|
| 331 |
+
"learning_rate": 7.942651597769641e-05,
|
| 332 |
+
"loss": 0.3634,
|
| 333 |
+
"step": 1200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.57,
|
| 337 |
+
"learning_rate": 7.942651597769641e-05,
|
| 338 |
+
"loss": 0.3269,
|
| 339 |
+
"step": 1225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6,
|
| 343 |
+
"learning_rate": 7.942651597769641e-05,
|
| 344 |
+
"loss": 0.3018,
|
| 345 |
+
"step": 1250
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.6,
|
| 349 |
+
"eval_accuracy": 0.8641896220371557,
|
| 350 |
+
"eval_loss": 0.41122835874557495,
|
| 351 |
+
"eval_runtime": 30.2612,
|
| 352 |
+
"eval_samples_per_second": 103.168,
|
| 353 |
+
"eval_steps_per_second": 25.809,
|
| 354 |
+
"step": 1250
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.63,
|
| 358 |
+
"learning_rate": 7.942651597769641e-05,
|
| 359 |
+
"loss": 0.3177,
|
| 360 |
+
"step": 1275
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.67,
|
| 364 |
+
"learning_rate": 7.942651597769641e-05,
|
| 365 |
+
"loss": 0.3021,
|
| 366 |
+
"step": 1300
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.7,
|
| 370 |
+
"learning_rate": 7.942651597769641e-05,
|
| 371 |
+
"loss": 0.3148,
|
| 372 |
+
"step": 1325
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.73,
|
| 376 |
+
"learning_rate": 7.942651597769641e-05,
|
| 377 |
+
"loss": 0.3312,
|
| 378 |
+
"step": 1350
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.76,
|
| 382 |
+
"learning_rate": 7.942651597769641e-05,
|
| 383 |
+
"loss": 0.2438,
|
| 384 |
+
"step": 1375
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.79,
|
| 388 |
+
"learning_rate": 7.942651597769641e-05,
|
| 389 |
+
"loss": 0.3289,
|
| 390 |
+
"step": 1400
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.83,
|
| 394 |
+
"learning_rate": 7.942651597769641e-05,
|
| 395 |
+
"loss": 0.3437,
|
| 396 |
+
"step": 1425
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.86,
|
| 400 |
+
"learning_rate": 7.942651597769641e-05,
|
| 401 |
+
"loss": 0.2688,
|
| 402 |
+
"step": 1450
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.89,
|
| 406 |
+
"learning_rate": 7.942651597769641e-05,
|
| 407 |
+
"loss": 0.2776,
|
| 408 |
+
"step": 1475
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.92,
|
| 412 |
+
"learning_rate": 7.942651597769641e-05,
|
| 413 |
+
"loss": 0.2878,
|
| 414 |
+
"step": 1500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.92,
|
| 418 |
+
"eval_accuracy": 0.860345932094811,
|
| 419 |
+
"eval_loss": 0.4497346878051758,
|
| 420 |
+
"eval_runtime": 30.3296,
|
| 421 |
+
"eval_samples_per_second": 102.936,
|
| 422 |
+
"eval_steps_per_second": 25.75,
|
| 423 |
+
"step": 1500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.96,
|
| 427 |
+
"learning_rate": 7.942651597769641e-05,
|
| 428 |
+
"loss": 0.3063,
|
| 429 |
+
"step": 1525
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.99,
|
| 433 |
+
"learning_rate": 7.942651597769641e-05,
|
| 434 |
+
"loss": 0.3134,
|
| 435 |
+
"step": 1550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.02,
|
| 439 |
+
"learning_rate": 7.942651597769641e-05,
|
| 440 |
+
"loss": 0.199,
|
| 441 |
+
"step": 1575
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.05,
|
| 445 |
+
"learning_rate": 7.942651597769641e-05,
|
| 446 |
+
"loss": 0.1655,
|
| 447 |
+
"step": 1600
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.08,
|
| 451 |
+
"learning_rate": 7.942651597769641e-05,
|
| 452 |
+
"loss": 0.1884,
|
| 453 |
+
"step": 1625
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.12,
|
| 457 |
+
"learning_rate": 7.942651597769641e-05,
|
| 458 |
+
"loss": 0.1679,
|
| 459 |
+
"step": 1650
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.15,
|
| 463 |
+
"learning_rate": 7.942651597769641e-05,
|
| 464 |
+
"loss": 0.2939,
|
| 465 |
+
"step": 1675
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.18,
|
| 469 |
+
"learning_rate": 7.942651597769641e-05,
|
| 470 |
+
"loss": 0.2126,
|
| 471 |
+
"step": 1700
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.21,
|
| 475 |
+
"learning_rate": 7.942651597769641e-05,
|
| 476 |
+
"loss": 0.1194,
|
| 477 |
+
"step": 1725
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.24,
|
| 481 |
+
"learning_rate": 7.942651597769641e-05,
|
| 482 |
+
"loss": 0.1432,
|
| 483 |
+
"step": 1750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.24,
|
| 487 |
+
"eval_accuracy": 0.8587443946188341,
|
| 488 |
+
"eval_loss": 0.5730303525924683,
|
| 489 |
+
"eval_runtime": 31.4543,
|
| 490 |
+
"eval_samples_per_second": 99.255,
|
| 491 |
+
"eval_steps_per_second": 24.83,
|
| 492 |
+
"step": 1750
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.28,
|
| 496 |
+
"learning_rate": 7.942651597769641e-05,
|
| 497 |
+
"loss": 0.1837,
|
| 498 |
+
"step": 1775
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.31,
|
| 502 |
+
"learning_rate": 7.942651597769641e-05,
|
| 503 |
+
"loss": 0.1633,
|
| 504 |
+
"step": 1800
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.34,
|
| 508 |
+
"learning_rate": 7.942651597769641e-05,
|
| 509 |
+
"loss": 0.1829,
|
| 510 |
+
"step": 1825
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.37,
|
| 514 |
+
"learning_rate": 7.942651597769641e-05,
|
| 515 |
+
"loss": 0.1597,
|
| 516 |
+
"step": 1850
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.4,
|
| 520 |
+
"learning_rate": 7.942651597769641e-05,
|
| 521 |
+
"loss": 0.1995,
|
| 522 |
+
"step": 1875
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.44,
|
| 526 |
+
"learning_rate": 7.942651597769641e-05,
|
| 527 |
+
"loss": 0.1709,
|
| 528 |
+
"step": 1900
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.47,
|
| 532 |
+
"learning_rate": 7.942651597769641e-05,
|
| 533 |
+
"loss": 0.2337,
|
| 534 |
+
"step": 1925
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.5,
|
| 538 |
+
"learning_rate": 7.942651597769641e-05,
|
| 539 |
+
"loss": 0.1308,
|
| 540 |
+
"step": 1950
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.53,
|
| 544 |
+
"learning_rate": 7.942651597769641e-05,
|
| 545 |
+
"loss": 0.2534,
|
| 546 |
+
"step": 1975
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.56,
|
| 550 |
+
"learning_rate": 7.942651597769641e-05,
|
| 551 |
+
"loss": 0.2154,
|
| 552 |
+
"step": 2000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.56,
|
| 556 |
+
"eval_accuracy": 0.8625880845611787,
|
| 557 |
+
"eval_loss": 0.5824428796768188,
|
| 558 |
+
"eval_runtime": 31.5134,
|
| 559 |
+
"eval_samples_per_second": 99.069,
|
| 560 |
+
"eval_steps_per_second": 24.783,
|
| 561 |
+
"step": 2000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.6,
|
| 565 |
+
"learning_rate": 7.942651597769641e-05,
|
| 566 |
+
"loss": 0.2489,
|
| 567 |
+
"step": 2025
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.63,
|
| 571 |
+
"learning_rate": 7.942651597769641e-05,
|
| 572 |
+
"loss": 0.2025,
|
| 573 |
+
"step": 2050
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.66,
|
| 577 |
+
"learning_rate": 7.942651597769641e-05,
|
| 578 |
+
"loss": 0.2566,
|
| 579 |
+
"step": 2075
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.69,
|
| 583 |
+
"learning_rate": 7.942651597769641e-05,
|
| 584 |
+
"loss": 0.1954,
|
| 585 |
+
"step": 2100
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.72,
|
| 589 |
+
"learning_rate": 7.942651597769641e-05,
|
| 590 |
+
"loss": 0.1965,
|
| 591 |
+
"step": 2125
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.76,
|
| 595 |
+
"learning_rate": 7.942651597769641e-05,
|
| 596 |
+
"loss": 0.2578,
|
| 597 |
+
"step": 2150
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.79,
|
| 601 |
+
"learning_rate": 7.942651597769641e-05,
|
| 602 |
+
"loss": 0.2349,
|
| 603 |
+
"step": 2175
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.82,
|
| 607 |
+
"learning_rate": 7.942651597769641e-05,
|
| 608 |
+
"loss": 0.227,
|
| 609 |
+
"step": 2200
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.85,
|
| 613 |
+
"learning_rate": 7.942651597769641e-05,
|
| 614 |
+
"loss": 0.2325,
|
| 615 |
+
"step": 2225
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.88,
|
| 619 |
+
"learning_rate": 7.942651597769641e-05,
|
| 620 |
+
"loss": 0.2678,
|
| 621 |
+
"step": 2250
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.88,
|
| 625 |
+
"eval_accuracy": 0.8632286995515696,
|
| 626 |
+
"eval_loss": 0.5371272563934326,
|
| 627 |
+
"eval_runtime": 31.4396,
|
| 628 |
+
"eval_samples_per_second": 99.302,
|
| 629 |
+
"eval_steps_per_second": 24.841,
|
| 630 |
+
"step": 2250
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.92,
|
| 634 |
+
"learning_rate": 7.942651597769641e-05,
|
| 635 |
+
"loss": 0.2809,
|
| 636 |
+
"step": 2275
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.95,
|
| 640 |
+
"learning_rate": 7.942651597769641e-05,
|
| 641 |
+
"loss": 0.2497,
|
| 642 |
+
"step": 2300
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.98,
|
| 646 |
+
"learning_rate": 7.942651597769641e-05,
|
| 647 |
+
"loss": 0.2487,
|
| 648 |
+
"step": 2325
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.01,
|
| 652 |
+
"learning_rate": 7.942651597769641e-05,
|
| 653 |
+
"loss": 0.2001,
|
| 654 |
+
"step": 2350
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.04,
|
| 658 |
+
"learning_rate": 7.942651597769641e-05,
|
| 659 |
+
"loss": 0.1682,
|
| 660 |
+
"step": 2375
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.08,
|
| 664 |
+
"learning_rate": 7.942651597769641e-05,
|
| 665 |
+
"loss": 0.1243,
|
| 666 |
+
"step": 2400
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.11,
|
| 670 |
+
"learning_rate": 7.942651597769641e-05,
|
| 671 |
+
"loss": 0.1468,
|
| 672 |
+
"step": 2425
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.14,
|
| 676 |
+
"learning_rate": 7.942651597769641e-05,
|
| 677 |
+
"loss": 0.1909,
|
| 678 |
+
"step": 2450
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 3.17,
|
| 682 |
+
"learning_rate": 7.942651597769641e-05,
|
| 683 |
+
"loss": 0.1254,
|
| 684 |
+
"step": 2475
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.21,
|
| 688 |
+
"learning_rate": 7.942651597769641e-05,
|
| 689 |
+
"loss": 0.1647,
|
| 690 |
+
"step": 2500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.21,
|
| 694 |
+
"eval_accuracy": 0.8632286995515696,
|
| 695 |
+
"eval_loss": 0.6494662165641785,
|
| 696 |
+
"eval_runtime": 31.5059,
|
| 697 |
+
"eval_samples_per_second": 99.092,
|
| 698 |
+
"eval_steps_per_second": 24.789,
|
| 699 |
+
"step": 2500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.24,
|
| 703 |
+
"learning_rate": 7.942651597769641e-05,
|
| 704 |
+
"loss": 0.1255,
|
| 705 |
+
"step": 2525
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.27,
|
| 709 |
+
"learning_rate": 7.942651597769641e-05,
|
| 710 |
+
"loss": 0.2115,
|
| 711 |
+
"step": 2550
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.3,
|
| 715 |
+
"learning_rate": 7.942651597769641e-05,
|
| 716 |
+
"loss": 0.1292,
|
| 717 |
+
"step": 2575
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.33,
|
| 721 |
+
"learning_rate": 7.942651597769641e-05,
|
| 722 |
+
"loss": 0.084,
|
| 723 |
+
"step": 2600
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.37,
|
| 727 |
+
"learning_rate": 7.942651597769641e-05,
|
| 728 |
+
"loss": 0.1508,
|
| 729 |
+
"step": 2625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.4,
|
| 733 |
+
"learning_rate": 7.942651597769641e-05,
|
| 734 |
+
"loss": 0.2381,
|
| 735 |
+
"step": 2650
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.43,
|
| 739 |
+
"learning_rate": 7.942651597769641e-05,
|
| 740 |
+
"loss": 0.119,
|
| 741 |
+
"step": 2675
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.46,
|
| 745 |
+
"learning_rate": 7.942651597769641e-05,
|
| 746 |
+
"loss": 0.2611,
|
| 747 |
+
"step": 2700
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.49,
|
| 751 |
+
"learning_rate": 7.942651597769641e-05,
|
| 752 |
+
"loss": 0.1441,
|
| 753 |
+
"step": 2725
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.53,
|
| 757 |
+
"learning_rate": 7.942651597769641e-05,
|
| 758 |
+
"loss": 0.1503,
|
| 759 |
+
"step": 2750
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.53,
|
| 763 |
+
"eval_accuracy": 0.8392056374119155,
|
| 764 |
+
"eval_loss": 0.739354133605957,
|
| 765 |
+
"eval_runtime": 31.689,
|
| 766 |
+
"eval_samples_per_second": 98.52,
|
| 767 |
+
"eval_steps_per_second": 24.646,
|
| 768 |
+
"step": 2750
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.56,
|
| 772 |
+
"learning_rate": 7.942651597769641e-05,
|
| 773 |
+
"loss": 0.2223,
|
| 774 |
+
"step": 2775
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.59,
|
| 778 |
+
"learning_rate": 7.942651597769641e-05,
|
| 779 |
+
"loss": 0.1502,
|
| 780 |
+
"step": 2800
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.62,
|
| 784 |
+
"learning_rate": 7.942651597769641e-05,
|
| 785 |
+
"loss": 0.1995,
|
| 786 |
+
"step": 2825
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.65,
|
| 790 |
+
"learning_rate": 7.942651597769641e-05,
|
| 791 |
+
"loss": 0.2427,
|
| 792 |
+
"step": 2850
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.69,
|
| 796 |
+
"learning_rate": 7.942651597769641e-05,
|
| 797 |
+
"loss": 0.1054,
|
| 798 |
+
"step": 2875
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 3.72,
|
| 802 |
+
"learning_rate": 7.942651597769641e-05,
|
| 803 |
+
"loss": 0.1749,
|
| 804 |
+
"step": 2900
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.75,
|
| 808 |
+
"learning_rate": 7.942651597769641e-05,
|
| 809 |
+
"loss": 0.1824,
|
| 810 |
+
"step": 2925
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.78,
|
| 814 |
+
"learning_rate": 7.942651597769641e-05,
|
| 815 |
+
"loss": 0.2283,
|
| 816 |
+
"step": 2950
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.81,
|
| 820 |
+
"learning_rate": 7.942651597769641e-05,
|
| 821 |
+
"loss": 0.1316,
|
| 822 |
+
"step": 2975
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 3.85,
|
| 826 |
+
"learning_rate": 7.942651597769641e-05,
|
| 827 |
+
"loss": 0.2344,
|
| 828 |
+
"step": 3000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.85,
|
| 832 |
+
"eval_accuracy": 0.8494554772581678,
|
| 833 |
+
"eval_loss": 0.6297785043716431,
|
| 834 |
+
"eval_runtime": 30.5311,
|
| 835 |
+
"eval_samples_per_second": 102.256,
|
| 836 |
+
"eval_steps_per_second": 25.58,
|
| 837 |
+
"step": 3000
|
| 838 |
+
}
|
| 839 |
+
],
|
| 840 |
+
"logging_steps": 25,
|
| 841 |
+
"max_steps": 3000,
|
| 842 |
+
"num_input_tokens_seen": 0,
|
| 843 |
+
"num_train_epochs": 4,
|
| 844 |
+
"save_steps": 250,
|
| 845 |
+
"total_flos": 1.2628881483844608e+16,
|
| 846 |
+
"trial_name": null,
|
| 847 |
+
"trial_params": {
|
| 848 |
+
"learning_rate": 7.942651597769641e-05,
|
| 849 |
+
"per_device_eval_batch_size": 4,
|
| 850 |
+
"per_device_train_batch_size": 16
|
| 851 |
+
}
|
| 852 |
+
}
|
run-0/checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a80260bc43050598885ca65b27a19bd3017acc59969e8c39101e7e300d8c14
|
| 3 |
+
size 4664
|
run-0/checkpoint-3000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
runs/Dec27_11-45-30_ArtanisPC/events.out.tfevents.1703673939.ArtanisPC.7175.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5e9eb1ee6b1409be54be180752570853c1f7dd4da311b9565a135ecb5102152
|
| 3 |
+
size 27590
|
runs/Dec27_12-29-10_ArtanisPC/events.out.tfevents.1703676554.ArtanisPC.7175.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1005d2a735cef729d5f43daa1b14c0cb935732c2fa915f47962e69642028ae3
|
| 3 |
+
size 27589
|
runs/Dec27_12-29-10_ArtanisPC/events.out.tfevents.1703680039.ArtanisPC.7175.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:359e0fa3732cc22ee45340a6b8969c28f835be5bf0c0ac6090cbb4e3d53bf058
|
| 3 |
+
size 27588
|
runs/Dec27_22-15-55_ArtanisPC/events.out.tfevents.1703711759.ArtanisPC.7175.13
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8476f5c55b037dd01ac9cf74af8e125d57e4fba2fedebf0a6a01c71daa3924
|
| 3 |
+
size 32237
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ea2b70f4e127f6163cc48ab2516f0095bfa7fd472ed09a94b79232d1a14f08c
|
| 3 |
+
size 4664
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|