LiYuan199701
commited on
Commit
•
f26777c
1
Parent(s):
abf4c09
Add model weights and configurations
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +58 -1
- checkpoint-13/config.json +37 -0
- checkpoint-13/optimizer.pt +3 -0
- checkpoint-13/pytorch_model.bin +3 -0
- checkpoint-13/rng_state.pth +3 -0
- checkpoint-13/scheduler.pt +3 -0
- checkpoint-13/special_tokens_map.json +1 -0
- checkpoint-13/tokenizer.json +0 -0
- checkpoint-13/tokenizer_config.json +1 -0
- checkpoint-13/trainer_state.json +25 -0
- checkpoint-13/training_args.bin +3 -0
- checkpoint-13/vocab.txt +0 -0
- checkpoint-26/config.json +37 -0
- checkpoint-26/optimizer.pt +3 -0
- checkpoint-26/pytorch_model.bin +3 -0
- checkpoint-26/rng_state.pth +3 -0
- checkpoint-26/scheduler.pt +3 -0
- checkpoint-26/special_tokens_map.json +1 -0
- checkpoint-26/tokenizer.json +0 -0
- checkpoint-26/tokenizer_config.json +1 -0
- checkpoint-26/trainer_state.json +34 -0
- checkpoint-26/training_args.bin +3 -0
- checkpoint-26/vocab.txt +0 -0
- checkpoint-35702/config.json +37 -0
- checkpoint-35702/optimizer.pt +3 -0
- checkpoint-35702/pytorch_model.bin +3 -0
- checkpoint-35702/rng_state.pth +3 -0
- checkpoint-35702/scheduler.pt +3 -0
- checkpoint-35702/special_tokens_map.json +1 -0
- checkpoint-35702/tokenizer.json +0 -0
- checkpoint-35702/tokenizer_config.json +1 -0
- checkpoint-35702/trainer_state.json +451 -0
- checkpoint-35702/training_args.bin +3 -0
- checkpoint-35702/vocab.txt +0 -0
- checkpoint-71404/config.json +37 -0
- checkpoint-71404/optimizer.pt +3 -0
- checkpoint-71404/pytorch_model.bin +3 -0
- checkpoint-71404/rng_state.pth +3 -0
- checkpoint-71404/scheduler.pt +3 -0
- checkpoint-71404/special_tokens_map.json +1 -0
- checkpoint-71404/tokenizer.json +0 -0
- checkpoint-71404/tokenizer_config.json +1 -0
- checkpoint-71404/trainer_state.json +886 -0
- checkpoint-71404/training_args.bin +3 -0
- checkpoint-71404/vocab.txt +0 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- runs/Apr27_04-29-22_a457e5c667c8/1651033831.5069559/events.out.tfevents.1651033831.a457e5c667c8.98.1 +3 -0
- runs/Apr27_04-29-22_a457e5c667c8/events.out.tfevents.1651033831.a457e5c667c8.98.0 +3 -0
- runs/Apr27_04-29-22_a457e5c667c8/events.out.tfevents.1651033873.a457e5c667c8.98.2 +3 -0
README.md
CHANGED
|
@@ -1,3 +1,60 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: distilbert-base-uncased-finetuned-mnli
|
| 9 |
+
results: []
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# distilbert-base-uncased-finetuned-mnli
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.8244
|
| 20 |
+
- Accuracy: 0.6617
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 2
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 51 |
+
| 0.8981 | 1.0 | 35702 | 0.8662 | 0.6371 |
|
| 52 |
+
| 0.7837 | 2.0 | 71404 | 0.8244 | 0.6617 |
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.18.0
|
| 58 |
+
- Pytorch 1.11.0+cu113
|
| 59 |
+
- Datasets 2.1.0
|
| 60 |
+
- Tokenizers 0.12.1
|
checkpoint-13/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3
|
| 23 |
+
},
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.18.0",
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
checkpoint-13/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14ae301c531056906f9e80347151258358682c2853a86f031f89366d11d482dd
|
| 3 |
+
size 535712225
|
checkpoint-13/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1295509e3e54526b462734fedcaa630d6131909b21fdefa42eb653f1a66b4e15
|
| 3 |
+
size 267860465
|
checkpoint-13/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3df29cec05354a25dd347170384b4cda8a08e5f4f1885f2b0a7ab07c8ee95598
|
| 3 |
+
size 14503
|
checkpoint-13/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6e9d89a5bd86901cfea599a980713ac341e0c480f14a074ff38b818780f1dd0
|
| 3 |
+
size 623
|
checkpoint-13/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-13/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-13/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
checkpoint-13/trainer_state.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.43,
|
| 3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-mnli/checkpoint-13",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 13,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.43,
|
| 13 |
+
"eval_loss": 1.2553551197052002,
|
| 14 |
+
"eval_runtime": 0.5695,
|
| 15 |
+
"eval_samples_per_second": 175.596,
|
| 16 |
+
"eval_steps_per_second": 12.292,
|
| 17 |
+
"step": 13
|
| 18 |
+
}
|
| 19 |
+
],
|
| 20 |
+
"max_steps": 26,
|
| 21 |
+
"num_train_epochs": 2,
|
| 22 |
+
"total_flos": 26494424678400.0,
|
| 23 |
+
"trial_name": null,
|
| 24 |
+
"trial_params": null
|
| 25 |
+
}
|
checkpoint-13/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ddcdf0fab9ae58016832dcbd510e3859fca80f08fc775daf1d3ddd7a9780a83
|
| 3 |
+
size 3119
|
checkpoint-13/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-26/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3
|
| 23 |
+
},
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.18.0",
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
checkpoint-26/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b015994f612e4137abe25f5c36ce812e91418bac0d8cbfecd0a7306c8e729dfd
|
| 3 |
+
size 535712225
|
checkpoint-26/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5140ed6f9897893c5e8df5d9d329c7034fea1ea17be33e200bb30eb3776cbc32
|
| 3 |
+
size 267860465
|
checkpoint-26/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab7107f8f12911d83fd4acf1036eecac8568f6c2547fab3e465074eacb351559
|
| 3 |
+
size 14503
|
checkpoint-26/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f2b3f8597016bfcda3f90e9c28b7f920e0052487224afc4ffcfbd2e909a612c
|
| 3 |
+
size 623
|
checkpoint-26/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-26/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-26/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
checkpoint-26/trainer_state.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.43,
|
| 3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-mnli/checkpoint-13",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 26,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.43,
|
| 13 |
+
"eval_loss": 1.2553551197052002,
|
| 14 |
+
"eval_runtime": 0.5695,
|
| 15 |
+
"eval_samples_per_second": 175.596,
|
| 16 |
+
"eval_steps_per_second": 12.292,
|
| 17 |
+
"step": 13
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.43,
|
| 22 |
+
"eval_loss": 1.217254877090454,
|
| 23 |
+
"eval_runtime": 0.58,
|
| 24 |
+
"eval_samples_per_second": 172.399,
|
| 25 |
+
"eval_steps_per_second": 12.068,
|
| 26 |
+
"step": 26
|
| 27 |
+
}
|
| 28 |
+
],
|
| 29 |
+
"max_steps": 26,
|
| 30 |
+
"num_train_epochs": 2,
|
| 31 |
+
"total_flos": 52988849356800.0,
|
| 32 |
+
"trial_name": null,
|
| 33 |
+
"trial_params": null
|
| 34 |
+
}
|
checkpoint-26/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ddcdf0fab9ae58016832dcbd510e3859fca80f08fc775daf1d3ddd7a9780a83
|
| 3 |
+
size 3119
|
checkpoint-26/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-35702/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3
|
| 23 |
+
},
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.18.0",
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
checkpoint-35702/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24ac78d9cfa13f6213586ba2d859e06585978324fb65bfdf9b7689d2a3418d18
|
| 3 |
+
size 535712353
|
checkpoint-35702/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dc13f58747c6ddb30f99543ebcaa4357988245f7340388bc036c5d10c0f247f
|
| 3 |
+
size 267860465
|
checkpoint-35702/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12f91a6243a26d24770ff141db34c77d3f6eae341dd3368689fe09baa941aa85
|
| 3 |
+
size 14503
|
checkpoint-35702/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cd5914861a4c4f6623e5081d63c24af822e623e6bfdf278636cf79281eabe56
|
| 3 |
+
size 623
|
checkpoint-35702/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-35702/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-35702/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
checkpoint-35702/trainer_state.json
ADDED
|
@@ -0,0 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.63705,
|
| 3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-mnli/checkpoint-35702",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 35702,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.9859951823427263e-05,
|
| 13 |
+
"loss": 1.1951,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 1.971990364685452e-05,
|
| 19 |
+
"loss": 1.1418,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 1.9579855470281778e-05,
|
| 25 |
+
"loss": 1.099,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 1.9439807293709036e-05,
|
| 31 |
+
"loss": 1.0961,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 1.9299759117136297e-05,
|
| 37 |
+
"loss": 1.0836,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"learning_rate": 1.9159710940563555e-05,
|
| 43 |
+
"loss": 1.0721,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"learning_rate": 1.9019662763990812e-05,
|
| 49 |
+
"loss": 1.0654,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.11,
|
| 54 |
+
"learning_rate": 1.8879614587418074e-05,
|
| 55 |
+
"loss": 1.0439,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.13,
|
| 60 |
+
"learning_rate": 1.873956641084533e-05,
|
| 61 |
+
"loss": 1.0453,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.14,
|
| 66 |
+
"learning_rate": 1.8599518234272592e-05,
|
| 67 |
+
"loss": 1.0399,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"learning_rate": 1.845947005769985e-05,
|
| 73 |
+
"loss": 1.0295,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.17,
|
| 78 |
+
"learning_rate": 1.8319421881127108e-05,
|
| 79 |
+
"loss": 1.0417,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18,
|
| 84 |
+
"learning_rate": 1.817937370455437e-05,
|
| 85 |
+
"loss": 1.0327,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"learning_rate": 1.8039325527981627e-05,
|
| 91 |
+
"loss": 1.0148,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.21,
|
| 96 |
+
"learning_rate": 1.7899277351408884e-05,
|
| 97 |
+
"loss": 1.0171,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.22,
|
| 102 |
+
"learning_rate": 1.7759229174836145e-05,
|
| 103 |
+
"loss": 1.0113,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.24,
|
| 108 |
+
"learning_rate": 1.7619180998263403e-05,
|
| 109 |
+
"loss": 1.0062,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.25,
|
| 114 |
+
"learning_rate": 1.7479132821690664e-05,
|
| 115 |
+
"loss": 1.0022,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.27,
|
| 120 |
+
"learning_rate": 1.7339084645117922e-05,
|
| 121 |
+
"loss": 0.9908,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.28,
|
| 126 |
+
"learning_rate": 1.719903646854518e-05,
|
| 127 |
+
"loss": 0.9919,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29,
|
| 132 |
+
"learning_rate": 1.705898829197244e-05,
|
| 133 |
+
"loss": 0.9875,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.31,
|
| 138 |
+
"learning_rate": 1.69189401153997e-05,
|
| 139 |
+
"loss": 0.9908,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.32,
|
| 144 |
+
"learning_rate": 1.6778891938826956e-05,
|
| 145 |
+
"loss": 0.9807,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.34,
|
| 150 |
+
"learning_rate": 1.6638843762254217e-05,
|
| 151 |
+
"loss": 0.9622,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.35,
|
| 156 |
+
"learning_rate": 1.6498795585681475e-05,
|
| 157 |
+
"loss": 0.9698,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.36,
|
| 162 |
+
"learning_rate": 1.6358747409108736e-05,
|
| 163 |
+
"loss": 0.9611,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38,
|
| 168 |
+
"learning_rate": 1.6218699232535994e-05,
|
| 169 |
+
"loss": 0.9844,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.39,
|
| 174 |
+
"learning_rate": 1.6078651055963252e-05,
|
| 175 |
+
"loss": 0.9717,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.41,
|
| 180 |
+
"learning_rate": 1.5938602879390513e-05,
|
| 181 |
+
"loss": 0.978,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.42,
|
| 186 |
+
"learning_rate": 1.579855470281777e-05,
|
| 187 |
+
"loss": 0.9684,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.43,
|
| 192 |
+
"learning_rate": 1.5658506526245028e-05,
|
| 193 |
+
"loss": 0.9518,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.45,
|
| 198 |
+
"learning_rate": 1.551845834967229e-05,
|
| 199 |
+
"loss": 0.9592,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.46,
|
| 204 |
+
"learning_rate": 1.5378410173099547e-05,
|
| 205 |
+
"loss": 0.9482,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.48,
|
| 210 |
+
"learning_rate": 1.5238361996526806e-05,
|
| 211 |
+
"loss": 0.9565,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.49,
|
| 216 |
+
"learning_rate": 1.5098313819954064e-05,
|
| 217 |
+
"loss": 0.956,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.5,
|
| 222 |
+
"learning_rate": 1.4958265643381324e-05,
|
| 223 |
+
"loss": 0.9432,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.52,
|
| 228 |
+
"learning_rate": 1.4818217466808585e-05,
|
| 229 |
+
"loss": 0.943,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.53,
|
| 234 |
+
"learning_rate": 1.4678169290235842e-05,
|
| 235 |
+
"loss": 0.9354,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.55,
|
| 240 |
+
"learning_rate": 1.4538121113663102e-05,
|
| 241 |
+
"loss": 0.958,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.56,
|
| 246 |
+
"learning_rate": 1.439807293709036e-05,
|
| 247 |
+
"loss": 0.9358,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.57,
|
| 252 |
+
"learning_rate": 1.4258024760517619e-05,
|
| 253 |
+
"loss": 0.9395,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.59,
|
| 258 |
+
"learning_rate": 1.4117976583944878e-05,
|
| 259 |
+
"loss": 0.9448,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.6,
|
| 264 |
+
"learning_rate": 1.3977928407372136e-05,
|
| 265 |
+
"loss": 0.9349,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.62,
|
| 270 |
+
"learning_rate": 1.3837880230799397e-05,
|
| 271 |
+
"loss": 0.9444,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.63,
|
| 276 |
+
"learning_rate": 1.3697832054226653e-05,
|
| 277 |
+
"loss": 0.929,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.64,
|
| 282 |
+
"learning_rate": 1.3557783877653914e-05,
|
| 283 |
+
"loss": 0.933,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.66,
|
| 288 |
+
"learning_rate": 1.3417735701081174e-05,
|
| 289 |
+
"loss": 0.9357,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.67,
|
| 294 |
+
"learning_rate": 1.3277687524508432e-05,
|
| 295 |
+
"loss": 0.9182,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.69,
|
| 300 |
+
"learning_rate": 1.3137639347935691e-05,
|
| 301 |
+
"loss": 0.9279,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7,
|
| 306 |
+
"learning_rate": 1.299759117136295e-05,
|
| 307 |
+
"loss": 0.9245,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.71,
|
| 312 |
+
"learning_rate": 1.2857542994790208e-05,
|
| 313 |
+
"loss": 0.9205,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.73,
|
| 318 |
+
"learning_rate": 1.271749481821747e-05,
|
| 319 |
+
"loss": 0.9214,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.74,
|
| 324 |
+
"learning_rate": 1.2577446641644725e-05,
|
| 325 |
+
"loss": 0.9388,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.76,
|
| 330 |
+
"learning_rate": 1.2437398465071986e-05,
|
| 331 |
+
"loss": 0.9256,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.77,
|
| 336 |
+
"learning_rate": 1.2297350288499246e-05,
|
| 337 |
+
"loss": 0.9206,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.78,
|
| 342 |
+
"learning_rate": 1.2157302111926503e-05,
|
| 343 |
+
"loss": 0.9091,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.8,
|
| 348 |
+
"learning_rate": 1.2017253935353763e-05,
|
| 349 |
+
"loss": 0.9267,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.81,
|
| 354 |
+
"learning_rate": 1.187720575878102e-05,
|
| 355 |
+
"loss": 0.9103,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.83,
|
| 360 |
+
"learning_rate": 1.173715758220828e-05,
|
| 361 |
+
"loss": 0.9032,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.84,
|
| 366 |
+
"learning_rate": 1.1597109405635541e-05,
|
| 367 |
+
"loss": 0.9075,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.85,
|
| 372 |
+
"learning_rate": 1.1457061229062799e-05,
|
| 373 |
+
"loss": 0.9016,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.87,
|
| 378 |
+
"learning_rate": 1.1317013052490058e-05,
|
| 379 |
+
"loss": 0.9119,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.88,
|
| 384 |
+
"learning_rate": 1.1176964875917316e-05,
|
| 385 |
+
"loss": 0.9085,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.9,
|
| 390 |
+
"learning_rate": 1.1036916699344575e-05,
|
| 391 |
+
"loss": 0.894,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.91,
|
| 396 |
+
"learning_rate": 1.0896868522771835e-05,
|
| 397 |
+
"loss": 0.9156,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.92,
|
| 402 |
+
"learning_rate": 1.0756820346199093e-05,
|
| 403 |
+
"loss": 0.8944,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.94,
|
| 408 |
+
"learning_rate": 1.0616772169626352e-05,
|
| 409 |
+
"loss": 0.8824,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.95,
|
| 414 |
+
"learning_rate": 1.047672399305361e-05,
|
| 415 |
+
"loss": 0.9014,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.97,
|
| 420 |
+
"learning_rate": 1.033667581648087e-05,
|
| 421 |
+
"loss": 0.9022,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.98,
|
| 426 |
+
"learning_rate": 1.019662763990813e-05,
|
| 427 |
+
"loss": 0.8888,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.99,
|
| 432 |
+
"learning_rate": 1.0056579463335388e-05,
|
| 433 |
+
"loss": 0.8981,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0,
|
| 438 |
+
"eval_accuracy": 0.63705,
|
| 439 |
+
"eval_loss": 0.8662445545196533,
|
| 440 |
+
"eval_runtime": 112.0196,
|
| 441 |
+
"eval_samples_per_second": 178.54,
|
| 442 |
+
"eval_steps_per_second": 11.159,
|
| 443 |
+
"step": 35702
|
| 444 |
+
}
|
| 445 |
+
],
|
| 446 |
+
"max_steps": 71404,
|
| 447 |
+
"num_train_epochs": 2,
|
| 448 |
+
"total_flos": 7.567112374034842e+16,
|
| 449 |
+
"trial_name": null,
|
| 450 |
+
"trial_params": null
|
| 451 |
+
}
|
checkpoint-35702/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b69140ab6b24ac5d06b1ffa0cda477a62e57823010306ba7159c6f1c22522fe
|
| 3 |
+
size 3119
|
checkpoint-35702/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-71404/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3
|
| 23 |
+
},
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.18.0",
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
checkpoint-71404/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:033c8d340e0be89ec59b924621244f788959be445ee546b3f92fdc1248e98005
|
| 3 |
+
size 535712545
|
checkpoint-71404/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f997ca2e55d65912dbf0139e6c3853d4a06f592cb04c60a1766c6557f06a87
|
| 3 |
+
size 267860465
|
checkpoint-71404/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590fa2ab684a0256a1eed6423ca4a8b197a92cc903c6613514418f5125d9c88d
|
| 3 |
+
size 14503
|
checkpoint-71404/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc9cf6973eb6dca3eeef731eda115482e40b297cd7f06999e95553ef4a2b1a4a
|
| 3 |
+
size 623
|
checkpoint-71404/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-71404/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
checkpoint-71404/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
checkpoint-71404/trainer_state.json
ADDED
|
@@ -0,0 +1,886 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6617,
|
| 3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-mnli/checkpoint-71404",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 71404,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.9859951823427263e-05,
|
| 13 |
+
"loss": 1.1951,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 1.971990364685452e-05,
|
| 19 |
+
"loss": 1.1418,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 1.9579855470281778e-05,
|
| 25 |
+
"loss": 1.099,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 1.9439807293709036e-05,
|
| 31 |
+
"loss": 1.0961,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 1.9299759117136297e-05,
|
| 37 |
+
"loss": 1.0836,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"learning_rate": 1.9159710940563555e-05,
|
| 43 |
+
"loss": 1.0721,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"learning_rate": 1.9019662763990812e-05,
|
| 49 |
+
"loss": 1.0654,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.11,
|
| 54 |
+
"learning_rate": 1.8879614587418074e-05,
|
| 55 |
+
"loss": 1.0439,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.13,
|
| 60 |
+
"learning_rate": 1.873956641084533e-05,
|
| 61 |
+
"loss": 1.0453,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.14,
|
| 66 |
+
"learning_rate": 1.8599518234272592e-05,
|
| 67 |
+
"loss": 1.0399,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"learning_rate": 1.845947005769985e-05,
|
| 73 |
+
"loss": 1.0295,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.17,
|
| 78 |
+
"learning_rate": 1.8319421881127108e-05,
|
| 79 |
+
"loss": 1.0417,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18,
|
| 84 |
+
"learning_rate": 1.817937370455437e-05,
|
| 85 |
+
"loss": 1.0327,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"learning_rate": 1.8039325527981627e-05,
|
| 91 |
+
"loss": 1.0148,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.21,
|
| 96 |
+
"learning_rate": 1.7899277351408884e-05,
|
| 97 |
+
"loss": 1.0171,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.22,
|
| 102 |
+
"learning_rate": 1.7759229174836145e-05,
|
| 103 |
+
"loss": 1.0113,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.24,
|
| 108 |
+
"learning_rate": 1.7619180998263403e-05,
|
| 109 |
+
"loss": 1.0062,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.25,
|
| 114 |
+
"learning_rate": 1.7479132821690664e-05,
|
| 115 |
+
"loss": 1.0022,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.27,
|
| 120 |
+
"learning_rate": 1.7339084645117922e-05,
|
| 121 |
+
"loss": 0.9908,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.28,
|
| 126 |
+
"learning_rate": 1.719903646854518e-05,
|
| 127 |
+
"loss": 0.9919,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29,
|
| 132 |
+
"learning_rate": 1.705898829197244e-05,
|
| 133 |
+
"loss": 0.9875,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.31,
|
| 138 |
+
"learning_rate": 1.69189401153997e-05,
|
| 139 |
+
"loss": 0.9908,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.32,
|
| 144 |
+
"learning_rate": 1.6778891938826956e-05,
|
| 145 |
+
"loss": 0.9807,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.34,
|
| 150 |
+
"learning_rate": 1.6638843762254217e-05,
|
| 151 |
+
"loss": 0.9622,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.35,
|
| 156 |
+
"learning_rate": 1.6498795585681475e-05,
|
| 157 |
+
"loss": 0.9698,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.36,
|
| 162 |
+
"learning_rate": 1.6358747409108736e-05,
|
| 163 |
+
"loss": 0.9611,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38,
|
| 168 |
+
"learning_rate": 1.6218699232535994e-05,
|
| 169 |
+
"loss": 0.9844,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.39,
|
| 174 |
+
"learning_rate": 1.6078651055963252e-05,
|
| 175 |
+
"loss": 0.9717,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.41,
|
| 180 |
+
"learning_rate": 1.5938602879390513e-05,
|
| 181 |
+
"loss": 0.978,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.42,
|
| 186 |
+
"learning_rate": 1.579855470281777e-05,
|
| 187 |
+
"loss": 0.9684,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.43,
|
| 192 |
+
"learning_rate": 1.5658506526245028e-05,
|
| 193 |
+
"loss": 0.9518,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.45,
|
| 198 |
+
"learning_rate": 1.551845834967229e-05,
|
| 199 |
+
"loss": 0.9592,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.46,
|
| 204 |
+
"learning_rate": 1.5378410173099547e-05,
|
| 205 |
+
"loss": 0.9482,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.48,
|
| 210 |
+
"learning_rate": 1.5238361996526806e-05,
|
| 211 |
+
"loss": 0.9565,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.49,
|
| 216 |
+
"learning_rate": 1.5098313819954064e-05,
|
| 217 |
+
"loss": 0.956,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.5,
|
| 222 |
+
"learning_rate": 1.4958265643381324e-05,
|
| 223 |
+
"loss": 0.9432,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.52,
|
| 228 |
+
"learning_rate": 1.4818217466808585e-05,
|
| 229 |
+
"loss": 0.943,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.53,
|
| 234 |
+
"learning_rate": 1.4678169290235842e-05,
|
| 235 |
+
"loss": 0.9354,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.55,
|
| 240 |
+
"learning_rate": 1.4538121113663102e-05,
|
| 241 |
+
"loss": 0.958,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.56,
|
| 246 |
+
"learning_rate": 1.439807293709036e-05,
|
| 247 |
+
"loss": 0.9358,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.57,
|
| 252 |
+
"learning_rate": 1.4258024760517619e-05,
|
| 253 |
+
"loss": 0.9395,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.59,
|
| 258 |
+
"learning_rate": 1.4117976583944878e-05,
|
| 259 |
+
"loss": 0.9448,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.6,
|
| 264 |
+
"learning_rate": 1.3977928407372136e-05,
|
| 265 |
+
"loss": 0.9349,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.62,
|
| 270 |
+
"learning_rate": 1.3837880230799397e-05,
|
| 271 |
+
"loss": 0.9444,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.63,
|
| 276 |
+
"learning_rate": 1.3697832054226653e-05,
|
| 277 |
+
"loss": 0.929,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.64,
|
| 282 |
+
"learning_rate": 1.3557783877653914e-05,
|
| 283 |
+
"loss": 0.933,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.66,
|
| 288 |
+
"learning_rate": 1.3417735701081174e-05,
|
| 289 |
+
"loss": 0.9357,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.67,
|
| 294 |
+
"learning_rate": 1.3277687524508432e-05,
|
| 295 |
+
"loss": 0.9182,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.69,
|
| 300 |
+
"learning_rate": 1.3137639347935691e-05,
|
| 301 |
+
"loss": 0.9279,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7,
|
| 306 |
+
"learning_rate": 1.299759117136295e-05,
|
| 307 |
+
"loss": 0.9245,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.71,
|
| 312 |
+
"learning_rate": 1.2857542994790208e-05,
|
| 313 |
+
"loss": 0.9205,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.73,
|
| 318 |
+
"learning_rate": 1.271749481821747e-05,
|
| 319 |
+
"loss": 0.9214,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.74,
|
| 324 |
+
"learning_rate": 1.2577446641644725e-05,
|
| 325 |
+
"loss": 0.9388,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.76,
|
| 330 |
+
"learning_rate": 1.2437398465071986e-05,
|
| 331 |
+
"loss": 0.9256,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.77,
|
| 336 |
+
"learning_rate": 1.2297350288499246e-05,
|
| 337 |
+
"loss": 0.9206,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.78,
|
| 342 |
+
"learning_rate": 1.2157302111926503e-05,
|
| 343 |
+
"loss": 0.9091,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.8,
|
| 348 |
+
"learning_rate": 1.2017253935353763e-05,
|
| 349 |
+
"loss": 0.9267,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.81,
|
| 354 |
+
"learning_rate": 1.187720575878102e-05,
|
| 355 |
+
"loss": 0.9103,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.83,
|
| 360 |
+
"learning_rate": 1.173715758220828e-05,
|
| 361 |
+
"loss": 0.9032,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.84,
|
| 366 |
+
"learning_rate": 1.1597109405635541e-05,
|
| 367 |
+
"loss": 0.9075,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.85,
|
| 372 |
+
"learning_rate": 1.1457061229062799e-05,
|
| 373 |
+
"loss": 0.9016,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.87,
|
| 378 |
+
"learning_rate": 1.1317013052490058e-05,
|
| 379 |
+
"loss": 0.9119,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.88,
|
| 384 |
+
"learning_rate": 1.1176964875917316e-05,
|
| 385 |
+
"loss": 0.9085,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.9,
|
| 390 |
+
"learning_rate": 1.1036916699344575e-05,
|
| 391 |
+
"loss": 0.894,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.91,
|
| 396 |
+
"learning_rate": 1.0896868522771835e-05,
|
| 397 |
+
"loss": 0.9156,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.92,
|
| 402 |
+
"learning_rate": 1.0756820346199093e-05,
|
| 403 |
+
"loss": 0.8944,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.94,
|
| 408 |
+
"learning_rate": 1.0616772169626352e-05,
|
| 409 |
+
"loss": 0.8824,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.95,
|
| 414 |
+
"learning_rate": 1.047672399305361e-05,
|
| 415 |
+
"loss": 0.9014,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.97,
|
| 420 |
+
"learning_rate": 1.033667581648087e-05,
|
| 421 |
+
"loss": 0.9022,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.98,
|
| 426 |
+
"learning_rate": 1.019662763990813e-05,
|
| 427 |
+
"loss": 0.8888,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.99,
|
| 432 |
+
"learning_rate": 1.0056579463335388e-05,
|
| 433 |
+
"loss": 0.8981,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0,
|
| 438 |
+
"eval_accuracy": 0.63705,
|
| 439 |
+
"eval_loss": 0.8662445545196533,
|
| 440 |
+
"eval_runtime": 112.0196,
|
| 441 |
+
"eval_samples_per_second": 178.54,
|
| 442 |
+
"eval_steps_per_second": 11.159,
|
| 443 |
+
"step": 35702
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.01,
|
| 447 |
+
"learning_rate": 9.916531286762647e-06,
|
| 448 |
+
"loss": 0.8662,
|
| 449 |
+
"step": 36000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.02,
|
| 453 |
+
"learning_rate": 9.776483110189907e-06,
|
| 454 |
+
"loss": 0.8255,
|
| 455 |
+
"step": 36500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.04,
|
| 459 |
+
"learning_rate": 9.636434933617164e-06,
|
| 460 |
+
"loss": 0.8377,
|
| 461 |
+
"step": 37000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.05,
|
| 465 |
+
"learning_rate": 9.496386757044424e-06,
|
| 466 |
+
"loss": 0.8203,
|
| 467 |
+
"step": 37500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.06,
|
| 471 |
+
"learning_rate": 9.356338580471683e-06,
|
| 472 |
+
"loss": 0.8399,
|
| 473 |
+
"step": 38000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.08,
|
| 477 |
+
"learning_rate": 9.216290403898943e-06,
|
| 478 |
+
"loss": 0.8215,
|
| 479 |
+
"step": 38500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.09,
|
| 483 |
+
"learning_rate": 9.0762422273262e-06,
|
| 484 |
+
"loss": 0.8266,
|
| 485 |
+
"step": 39000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.11,
|
| 489 |
+
"learning_rate": 8.93619405075346e-06,
|
| 490 |
+
"loss": 0.8445,
|
| 491 |
+
"step": 39500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.12,
|
| 495 |
+
"learning_rate": 8.79614587418072e-06,
|
| 496 |
+
"loss": 0.8159,
|
| 497 |
+
"step": 40000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.13,
|
| 501 |
+
"learning_rate": 8.656097697607979e-06,
|
| 502 |
+
"loss": 0.8139,
|
| 503 |
+
"step": 40500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.15,
|
| 507 |
+
"learning_rate": 8.516049521035236e-06,
|
| 508 |
+
"loss": 0.8303,
|
| 509 |
+
"step": 41000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.16,
|
| 513 |
+
"learning_rate": 8.376001344462496e-06,
|
| 514 |
+
"loss": 0.8004,
|
| 515 |
+
"step": 41500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.18,
|
| 519 |
+
"learning_rate": 8.235953167889755e-06,
|
| 520 |
+
"loss": 0.8373,
|
| 521 |
+
"step": 42000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.19,
|
| 525 |
+
"learning_rate": 8.095904991317015e-06,
|
| 526 |
+
"loss": 0.8121,
|
| 527 |
+
"step": 42500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2,
|
| 531 |
+
"learning_rate": 7.955856814744272e-06,
|
| 532 |
+
"loss": 0.8083,
|
| 533 |
+
"step": 43000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.22,
|
| 537 |
+
"learning_rate": 7.815808638171532e-06,
|
| 538 |
+
"loss": 0.8287,
|
| 539 |
+
"step": 43500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.23,
|
| 543 |
+
"learning_rate": 7.67576046159879e-06,
|
| 544 |
+
"loss": 0.8251,
|
| 545 |
+
"step": 44000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.25,
|
| 549 |
+
"learning_rate": 7.53571228502605e-06,
|
| 550 |
+
"loss": 0.8286,
|
| 551 |
+
"step": 44500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.26,
|
| 555 |
+
"learning_rate": 7.395664108453308e-06,
|
| 556 |
+
"loss": 0.8139,
|
| 557 |
+
"step": 45000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.27,
|
| 561 |
+
"learning_rate": 7.255615931880568e-06,
|
| 562 |
+
"loss": 0.8093,
|
| 563 |
+
"step": 45500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.29,
|
| 567 |
+
"learning_rate": 7.115567755307826e-06,
|
| 568 |
+
"loss": 0.8185,
|
| 569 |
+
"step": 46000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.3,
|
| 573 |
+
"learning_rate": 6.975519578735085e-06,
|
| 574 |
+
"loss": 0.8182,
|
| 575 |
+
"step": 46500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.32,
|
| 579 |
+
"learning_rate": 6.835471402162345e-06,
|
| 580 |
+
"loss": 0.8235,
|
| 581 |
+
"step": 47000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.33,
|
| 585 |
+
"learning_rate": 6.695423225589604e-06,
|
| 586 |
+
"loss": 0.8165,
|
| 587 |
+
"step": 47500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.34,
|
| 591 |
+
"learning_rate": 6.555375049016862e-06,
|
| 592 |
+
"loss": 0.8013,
|
| 593 |
+
"step": 48000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.36,
|
| 597 |
+
"learning_rate": 6.415326872444121e-06,
|
| 598 |
+
"loss": 0.8126,
|
| 599 |
+
"step": 48500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.37,
|
| 603 |
+
"learning_rate": 6.275278695871381e-06,
|
| 604 |
+
"loss": 0.8178,
|
| 605 |
+
"step": 49000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.39,
|
| 609 |
+
"learning_rate": 6.13523051929864e-06,
|
| 610 |
+
"loss": 0.8052,
|
| 611 |
+
"step": 49500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.4,
|
| 615 |
+
"learning_rate": 5.995182342725898e-06,
|
| 616 |
+
"loss": 0.8167,
|
| 617 |
+
"step": 50000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.41,
|
| 621 |
+
"learning_rate": 5.855134166153157e-06,
|
| 622 |
+
"loss": 0.8193,
|
| 623 |
+
"step": 50500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.43,
|
| 627 |
+
"learning_rate": 5.715085989580415e-06,
|
| 628 |
+
"loss": 0.8114,
|
| 629 |
+
"step": 51000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.44,
|
| 633 |
+
"learning_rate": 5.575037813007676e-06,
|
| 634 |
+
"loss": 0.7964,
|
| 635 |
+
"step": 51500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.46,
|
| 639 |
+
"learning_rate": 5.434989636434934e-06,
|
| 640 |
+
"loss": 0.8061,
|
| 641 |
+
"step": 52000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.47,
|
| 645 |
+
"learning_rate": 5.294941459862193e-06,
|
| 646 |
+
"loss": 0.8148,
|
| 647 |
+
"step": 52500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.48,
|
| 651 |
+
"learning_rate": 5.154893283289451e-06,
|
| 652 |
+
"loss": 0.7987,
|
| 653 |
+
"step": 53000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.5,
|
| 657 |
+
"learning_rate": 5.014845106716712e-06,
|
| 658 |
+
"loss": 0.7882,
|
| 659 |
+
"step": 53500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.51,
|
| 663 |
+
"learning_rate": 4.87479693014397e-06,
|
| 664 |
+
"loss": 0.8347,
|
| 665 |
+
"step": 54000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.53,
|
| 669 |
+
"learning_rate": 4.734748753571229e-06,
|
| 670 |
+
"loss": 0.8005,
|
| 671 |
+
"step": 54500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.54,
|
| 675 |
+
"learning_rate": 4.594700576998487e-06,
|
| 676 |
+
"loss": 0.7995,
|
| 677 |
+
"step": 55000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.55,
|
| 681 |
+
"learning_rate": 4.454652400425747e-06,
|
| 682 |
+
"loss": 0.8096,
|
| 683 |
+
"step": 55500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.57,
|
| 687 |
+
"learning_rate": 4.314604223853005e-06,
|
| 688 |
+
"loss": 0.788,
|
| 689 |
+
"step": 56000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.58,
|
| 693 |
+
"learning_rate": 4.174556047280265e-06,
|
| 694 |
+
"loss": 0.7972,
|
| 695 |
+
"step": 56500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.6,
|
| 699 |
+
"learning_rate": 4.034507870707523e-06,
|
| 700 |
+
"loss": 0.7841,
|
| 701 |
+
"step": 57000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.61,
|
| 705 |
+
"learning_rate": 3.894459694134783e-06,
|
| 706 |
+
"loss": 0.8075,
|
| 707 |
+
"step": 57500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.62,
|
| 711 |
+
"learning_rate": 3.7544115175620417e-06,
|
| 712 |
+
"loss": 0.8039,
|
| 713 |
+
"step": 58000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.64,
|
| 717 |
+
"learning_rate": 3.6143633409893007e-06,
|
| 718 |
+
"loss": 0.7813,
|
| 719 |
+
"step": 58500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.65,
|
| 723 |
+
"learning_rate": 3.4743151644165597e-06,
|
| 724 |
+
"loss": 0.7884,
|
| 725 |
+
"step": 59000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.67,
|
| 729 |
+
"learning_rate": 3.3342669878438182e-06,
|
| 730 |
+
"loss": 0.7981,
|
| 731 |
+
"step": 59500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.68,
|
| 735 |
+
"learning_rate": 3.1942188112710776e-06,
|
| 736 |
+
"loss": 0.7857,
|
| 737 |
+
"step": 60000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.69,
|
| 741 |
+
"learning_rate": 3.0541706346983362e-06,
|
| 742 |
+
"loss": 0.8166,
|
| 743 |
+
"step": 60500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.71,
|
| 747 |
+
"learning_rate": 2.9141224581255956e-06,
|
| 748 |
+
"loss": 0.8139,
|
| 749 |
+
"step": 61000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.72,
|
| 753 |
+
"learning_rate": 2.774074281552854e-06,
|
| 754 |
+
"loss": 0.7986,
|
| 755 |
+
"step": 61500
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.74,
|
| 759 |
+
"learning_rate": 2.6340261049801136e-06,
|
| 760 |
+
"loss": 0.8084,
|
| 761 |
+
"step": 62000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.75,
|
| 765 |
+
"learning_rate": 2.493977928407372e-06,
|
| 766 |
+
"loss": 0.7958,
|
| 767 |
+
"step": 62500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.76,
|
| 771 |
+
"learning_rate": 2.353929751834631e-06,
|
| 772 |
+
"loss": 0.8037,
|
| 773 |
+
"step": 63000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.78,
|
| 777 |
+
"learning_rate": 2.21388157526189e-06,
|
| 778 |
+
"loss": 0.8021,
|
| 779 |
+
"step": 63500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.79,
|
| 783 |
+
"learning_rate": 2.073833398689149e-06,
|
| 784 |
+
"loss": 0.8079,
|
| 785 |
+
"step": 64000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.81,
|
| 789 |
+
"learning_rate": 1.933785222116408e-06,
|
| 790 |
+
"loss": 0.7904,
|
| 791 |
+
"step": 64500
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.82,
|
| 795 |
+
"learning_rate": 1.7937370455436674e-06,
|
| 796 |
+
"loss": 0.8015,
|
| 797 |
+
"step": 65000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.83,
|
| 801 |
+
"learning_rate": 1.653688868970926e-06,
|
| 802 |
+
"loss": 0.8057,
|
| 803 |
+
"step": 65500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.85,
|
| 807 |
+
"learning_rate": 1.513640692398185e-06,
|
| 808 |
+
"loss": 0.7901,
|
| 809 |
+
"step": 66000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.86,
|
| 813 |
+
"learning_rate": 1.373592515825444e-06,
|
| 814 |
+
"loss": 0.7925,
|
| 815 |
+
"step": 66500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.88,
|
| 819 |
+
"learning_rate": 1.233544339252703e-06,
|
| 820 |
+
"loss": 0.8031,
|
| 821 |
+
"step": 67000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.89,
|
| 825 |
+
"learning_rate": 1.093496162679962e-06,
|
| 826 |
+
"loss": 0.7847,
|
| 827 |
+
"step": 67500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.9,
|
| 831 |
+
"learning_rate": 9.53447986107221e-07,
|
| 832 |
+
"loss": 0.792,
|
| 833 |
+
"step": 68000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.92,
|
| 837 |
+
"learning_rate": 8.133998095344799e-07,
|
| 838 |
+
"loss": 0.7927,
|
| 839 |
+
"step": 68500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.93,
|
| 843 |
+
"learning_rate": 6.733516329617389e-07,
|
| 844 |
+
"loss": 0.7759,
|
| 845 |
+
"step": 69000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.95,
|
| 849 |
+
"learning_rate": 5.333034563889979e-07,
|
| 850 |
+
"loss": 0.7915,
|
| 851 |
+
"step": 69500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.96,
|
| 855 |
+
"learning_rate": 3.9325527981625684e-07,
|
| 856 |
+
"loss": 0.7801,
|
| 857 |
+
"step": 70000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.97,
|
| 861 |
+
"learning_rate": 2.532071032435158e-07,
|
| 862 |
+
"loss": 0.787,
|
| 863 |
+
"step": 70500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.99,
|
| 867 |
+
"learning_rate": 1.1315892667077475e-07,
|
| 868 |
+
"loss": 0.7837,
|
| 869 |
+
"step": 71000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.0,
|
| 873 |
+
"eval_accuracy": 0.6617,
|
| 874 |
+
"eval_loss": 0.8244466781616211,
|
| 875 |
+
"eval_runtime": 111.9282,
|
| 876 |
+
"eval_samples_per_second": 178.686,
|
| 877 |
+
"eval_steps_per_second": 11.168,
|
| 878 |
+
"step": 71404
|
| 879 |
+
}
|
| 880 |
+
],
|
| 881 |
+
"max_steps": 71404,
|
| 882 |
+
"num_train_epochs": 2,
|
| 883 |
+
"total_flos": 1.5134224748069683e+17,
|
| 884 |
+
"trial_name": null,
|
| 885 |
+
"trial_params": null
|
| 886 |
+
}
|
checkpoint-71404/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b69140ab6b24ac5d06b1ffa0cda477a62e57823010306ba7159c6f1c22522fe
|
| 3 |
+
size 3119
|
checkpoint-71404/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2,
|
| 22 |
+
"LABEL_3": 3
|
| 23 |
+
},
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.18.0",
|
| 36 |
+
"vocab_size": 30522
|
| 37 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f997ca2e55d65912dbf0139e6c3853d4a06f592cb04c60a1766c6557f06a87
|
| 3 |
+
size 267860465
|
runs/Apr27_04-29-22_a457e5c667c8/1651033831.5069559/events.out.tfevents.1651033831.a457e5c667c8.98.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc40e4f680fd7ba8f81e195cab0e7417729c8153da9599922ea9f6011a725ce9
|
| 3 |
+
size 4907
|
runs/Apr27_04-29-22_a457e5c667c8/events.out.tfevents.1651033831.a457e5c667c8.98.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47234fdd630f3f90ea2c15bb8a21712ddcb7cbd538d4bf5ce6778dad08385166
|
| 3 |
+
size 4464
|
runs/Apr27_04-29-22_a457e5c667c8/events.out.tfevents.1651033873.a457e5c667c8.98.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13327737222f93a040bda917333a4a68dbf06f59c00b8732ae678c554d64cb68
|
| 3 |
+
size 357
|