Upload 13 files
Browse files- README.md +53 -3
- added_tokens.json +3 -0
- all_results.json +8 -0
- config.json +28 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +991 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,53 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: DeB3RTa_3
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# DeB3RTa_3
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
+
|
| 16 |
+
## Model description
|
| 17 |
+
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Intended uses & limitations
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Training and evaluation data
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
### Training hyperparameters
|
| 31 |
+
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 0.0001
|
| 34 |
+
- train_batch_size: 192
|
| 35 |
+
- eval_batch_size: 8
|
| 36 |
+
- seed: 42
|
| 37 |
+
- gradient_accumulation_steps: 8
|
| 38 |
+
- total_train_batch_size: 1536
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 42 |
+
- num_epochs: 50.0
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
### Framework versions
|
| 49 |
+
|
| 50 |
+
- Transformers 4.30.2
|
| 51 |
+
- Pytorch 2.2.0+cu121
|
| 52 |
+
- Datasets 2.13.1
|
| 53 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.005664803918222426,
|
| 4 |
+
"train_runtime": 6206.924,
|
| 5 |
+
"train_samples": 2477405,
|
| 6 |
+
"train_samples_per_second": 19956.785,
|
| 7 |
+
"train_steps_per_second": 12.994
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 1536,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 3072,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"max_relative_positions": -1,
|
| 14 |
+
"model_type": "deberta-v2",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pooler_dropout": 0,
|
| 19 |
+
"pooler_hidden_act": "gelu",
|
| 20 |
+
"pooler_hidden_size": 1536,
|
| 21 |
+
"pos_att_type": null,
|
| 22 |
+
"position_biased_input": true,
|
| 23 |
+
"relative_attention": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.30.2",
|
| 26 |
+
"type_vocab_size": 0,
|
| 27 |
+
"vocab_size": 128100
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdea08c94f1b19046bb4f3a97813eeda9a7ca770e5c04724bf7579f59bd4dd7a
|
| 3 |
+
size 283856744
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a7dca4775e0a7d7bd45b7f3b63f967cf06b0d59a20c95a1d97831b083e0b71f
|
| 3 |
+
size 1707027634
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
|
| 3 |
+
size 2447305
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.005664803918222426,
|
| 4 |
+
"train_runtime": 6206.924,
|
| 5 |
+
"train_samples": 2477405,
|
| 6 |
+
"train_samples_per_second": 19956.785,
|
| 7 |
+
"train_steps_per_second": 12.994
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,991 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 80650,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.31,
|
| 12 |
+
"learning_rate": 6.195786864931847e-05,
|
| 13 |
+
"loss": 7.3347,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.62,
|
| 18 |
+
"learning_rate": 9.97582756158962e-05,
|
| 19 |
+
"loss": 4.6943,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.93,
|
| 24 |
+
"learning_rate": 9.913204664153402e-05,
|
| 25 |
+
"loss": 1.9617,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.24,
|
| 30 |
+
"learning_rate": 9.850581766717182e-05,
|
| 31 |
+
"loss": 1.4872,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.55,
|
| 36 |
+
"learning_rate": 9.787958869280964e-05,
|
| 37 |
+
"loss": 1.3048,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.86,
|
| 42 |
+
"learning_rate": 9.725335971844745e-05,
|
| 43 |
+
"loss": 1.1881,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.17,
|
| 48 |
+
"learning_rate": 9.662713074408527e-05,
|
| 49 |
+
"loss": 1.105,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.48,
|
| 54 |
+
"learning_rate": 9.600090176972308e-05,
|
| 55 |
+
"loss": 1.0428,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.79,
|
| 60 |
+
"learning_rate": 9.53746727953609e-05,
|
| 61 |
+
"loss": 0.9918,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.1,
|
| 66 |
+
"learning_rate": 9.47484438209987e-05,
|
| 67 |
+
"loss": 0.9489,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.41,
|
| 72 |
+
"learning_rate": 9.412221484663653e-05,
|
| 73 |
+
"loss": 0.9121,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.72,
|
| 78 |
+
"learning_rate": 9.349598587227433e-05,
|
| 79 |
+
"loss": 0.8837,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.03,
|
| 84 |
+
"learning_rate": 9.286975689791215e-05,
|
| 85 |
+
"loss": 0.8581,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.34,
|
| 90 |
+
"learning_rate": 9.224352792354997e-05,
|
| 91 |
+
"loss": 0.8315,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.65,
|
| 96 |
+
"learning_rate": 9.161729894918779e-05,
|
| 97 |
+
"loss": 0.8117,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.96,
|
| 102 |
+
"learning_rate": 9.09910699748256e-05,
|
| 103 |
+
"loss": 0.795,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.27,
|
| 108 |
+
"learning_rate": 9.036484100046342e-05,
|
| 109 |
+
"loss": 0.776,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.58,
|
| 114 |
+
"learning_rate": 8.973861202610123e-05,
|
| 115 |
+
"loss": 0.76,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 5.89,
|
| 120 |
+
"learning_rate": 8.911238305173905e-05,
|
| 121 |
+
"loss": 0.7464,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.2,
|
| 126 |
+
"learning_rate": 8.848615407737685e-05,
|
| 127 |
+
"loss": 0.732,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.51,
|
| 132 |
+
"learning_rate": 8.785992510301467e-05,
|
| 133 |
+
"loss": 0.7206,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.82,
|
| 138 |
+
"learning_rate": 8.723369612865248e-05,
|
| 139 |
+
"loss": 0.709,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.13,
|
| 144 |
+
"learning_rate": 8.66074671542903e-05,
|
| 145 |
+
"loss": 0.7003,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 7.44,
|
| 150 |
+
"learning_rate": 8.598123817992811e-05,
|
| 151 |
+
"loss": 0.6869,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 7.75,
|
| 156 |
+
"learning_rate": 8.535500920556593e-05,
|
| 157 |
+
"loss": 0.6808,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.06,
|
| 162 |
+
"learning_rate": 8.472878023120375e-05,
|
| 163 |
+
"loss": 0.671,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.37,
|
| 168 |
+
"learning_rate": 8.410255125684155e-05,
|
| 169 |
+
"loss": 0.6615,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.68,
|
| 174 |
+
"learning_rate": 8.347632228247937e-05,
|
| 175 |
+
"loss": 0.6552,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.99,
|
| 180 |
+
"learning_rate": 8.285009330811718e-05,
|
| 181 |
+
"loss": 0.6484,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 9.3,
|
| 186 |
+
"learning_rate": 8.2223864333755e-05,
|
| 187 |
+
"loss": 0.6395,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 9.61,
|
| 192 |
+
"learning_rate": 8.159763535939281e-05,
|
| 193 |
+
"loss": 0.6351,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 9.92,
|
| 198 |
+
"learning_rate": 8.097140638503063e-05,
|
| 199 |
+
"loss": 0.6297,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 10.23,
|
| 204 |
+
"learning_rate": 8.034642986861716e-05,
|
| 205 |
+
"loss": 0.6214,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 10.54,
|
| 210 |
+
"learning_rate": 7.972020089425498e-05,
|
| 211 |
+
"loss": 0.617,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 10.85,
|
| 216 |
+
"learning_rate": 7.909397191989279e-05,
|
| 217 |
+
"loss": 0.6122,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 11.16,
|
| 222 |
+
"learning_rate": 7.846774294553061e-05,
|
| 223 |
+
"loss": 0.6055,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 11.47,
|
| 228 |
+
"learning_rate": 7.784276642911714e-05,
|
| 229 |
+
"loss": 0.5992,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 11.78,
|
| 234 |
+
"learning_rate": 7.721653745475495e-05,
|
| 235 |
+
"loss": 0.5957,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 12.09,
|
| 240 |
+
"learning_rate": 7.65915609383415e-05,
|
| 241 |
+
"loss": 0.5919,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 12.4,
|
| 246 |
+
"learning_rate": 7.596533196397932e-05,
|
| 247 |
+
"loss": 0.5857,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 12.71,
|
| 252 |
+
"learning_rate": 7.533910298961712e-05,
|
| 253 |
+
"loss": 0.5825,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 13.02,
|
| 258 |
+
"learning_rate": 7.471287401525494e-05,
|
| 259 |
+
"loss": 0.5787,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.33,
|
| 264 |
+
"learning_rate": 7.408664504089275e-05,
|
| 265 |
+
"loss": 0.5721,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 13.64,
|
| 270 |
+
"learning_rate": 7.346041606653057e-05,
|
| 271 |
+
"loss": 0.5694,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 13.95,
|
| 276 |
+
"learning_rate": 7.283418709216838e-05,
|
| 277 |
+
"loss": 0.5672,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 14.26,
|
| 282 |
+
"learning_rate": 7.22079581178062e-05,
|
| 283 |
+
"loss": 0.5619,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 14.57,
|
| 288 |
+
"learning_rate": 7.158298160139275e-05,
|
| 289 |
+
"loss": 0.5586,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 14.88,
|
| 294 |
+
"learning_rate": 7.095800508497928e-05,
|
| 295 |
+
"loss": 0.5559,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.19,
|
| 300 |
+
"learning_rate": 7.033177611061709e-05,
|
| 301 |
+
"loss": 0.5519,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 15.5,
|
| 306 |
+
"learning_rate": 6.97055471362549e-05,
|
| 307 |
+
"loss": 0.5485,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 15.81,
|
| 312 |
+
"learning_rate": 6.907931816189271e-05,
|
| 313 |
+
"loss": 0.5459,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 16.12,
|
| 318 |
+
"learning_rate": 6.845308918753053e-05,
|
| 319 |
+
"loss": 0.5423,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 16.43,
|
| 324 |
+
"learning_rate": 6.782686021316834e-05,
|
| 325 |
+
"loss": 0.538,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 16.74,
|
| 330 |
+
"learning_rate": 6.720063123880616e-05,
|
| 331 |
+
"loss": 0.5366,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 17.05,
|
| 336 |
+
"learning_rate": 6.657440226444397e-05,
|
| 337 |
+
"loss": 0.5351,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 17.36,
|
| 342 |
+
"learning_rate": 6.594817329008179e-05,
|
| 343 |
+
"loss": 0.5299,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 17.67,
|
| 348 |
+
"learning_rate": 6.532194431571961e-05,
|
| 349 |
+
"loss": 0.5283,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 17.98,
|
| 354 |
+
"learning_rate": 6.469571534135743e-05,
|
| 355 |
+
"loss": 0.5259,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 18.29,
|
| 360 |
+
"learning_rate": 6.406948636699523e-05,
|
| 361 |
+
"loss": 0.5221,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 18.6,
|
| 366 |
+
"learning_rate": 6.344325739263305e-05,
|
| 367 |
+
"loss": 0.5197,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 18.91,
|
| 372 |
+
"learning_rate": 6.281702841827086e-05,
|
| 373 |
+
"loss": 0.5185,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 19.22,
|
| 378 |
+
"learning_rate": 6.219079944390868e-05,
|
| 379 |
+
"loss": 0.5138,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 19.53,
|
| 384 |
+
"learning_rate": 6.156457046954649e-05,
|
| 385 |
+
"loss": 0.5121,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 19.84,
|
| 390 |
+
"learning_rate": 6.09383414951843e-05,
|
| 391 |
+
"loss": 0.5112,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 20.15,
|
| 396 |
+
"learning_rate": 6.0312112520822115e-05,
|
| 397 |
+
"loss": 0.5072,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 20.46,
|
| 402 |
+
"learning_rate": 5.968588354645993e-05,
|
| 403 |
+
"loss": 0.5049,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 20.77,
|
| 408 |
+
"learning_rate": 5.905965457209774e-05,
|
| 409 |
+
"loss": 0.5043,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 21.08,
|
| 414 |
+
"learning_rate": 5.8433425597735556e-05,
|
| 415 |
+
"loss": 0.5013,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 21.39,
|
| 420 |
+
"learning_rate": 5.780719662337337e-05,
|
| 421 |
+
"loss": 0.4981,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 21.7,
|
| 426 |
+
"learning_rate": 5.718096764901118e-05,
|
| 427 |
+
"loss": 0.4975,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 22.01,
|
| 432 |
+
"learning_rate": 5.6554738674648996e-05,
|
| 433 |
+
"loss": 0.4959,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 22.32,
|
| 438 |
+
"learning_rate": 5.5928509700286816e-05,
|
| 439 |
+
"loss": 0.4921,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 22.63,
|
| 444 |
+
"learning_rate": 5.530228072592463e-05,
|
| 445 |
+
"loss": 0.4921,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 22.94,
|
| 450 |
+
"learning_rate": 5.467605175156244e-05,
|
| 451 |
+
"loss": 0.4886,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 23.25,
|
| 456 |
+
"learning_rate": 5.404982277720026e-05,
|
| 457 |
+
"loss": 0.4856,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 23.56,
|
| 462 |
+
"learning_rate": 5.342359380283807e-05,
|
| 463 |
+
"loss": 0.4847,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 23.87,
|
| 468 |
+
"learning_rate": 5.2797364828475884e-05,
|
| 469 |
+
"loss": 0.4839,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 24.18,
|
| 474 |
+
"learning_rate": 5.21711358541137e-05,
|
| 475 |
+
"loss": 0.4814,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 24.49,
|
| 480 |
+
"learning_rate": 5.154490687975152e-05,
|
| 481 |
+
"loss": 0.4796,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 24.8,
|
| 486 |
+
"learning_rate": 5.091867790538933e-05,
|
| 487 |
+
"loss": 0.4784,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 25.11,
|
| 492 |
+
"learning_rate": 5.0292448931027144e-05,
|
| 493 |
+
"loss": 0.4757,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 25.42,
|
| 498 |
+
"learning_rate": 4.966621995666496e-05,
|
| 499 |
+
"loss": 0.4744,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 25.73,
|
| 504 |
+
"learning_rate": 4.903999098230277e-05,
|
| 505 |
+
"loss": 0.4734,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 26.04,
|
| 510 |
+
"learning_rate": 4.841376200794059e-05,
|
| 511 |
+
"loss": 0.4715,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 26.35,
|
| 516 |
+
"learning_rate": 4.7787533033578405e-05,
|
| 517 |
+
"loss": 0.4682,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 26.66,
|
| 522 |
+
"learning_rate": 4.716130405921622e-05,
|
| 523 |
+
"loss": 0.4683,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 26.97,
|
| 528 |
+
"learning_rate": 4.653507508485403e-05,
|
| 529 |
+
"loss": 0.4671,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 27.28,
|
| 534 |
+
"learning_rate": 4.5908846110491845e-05,
|
| 535 |
+
"loss": 0.4637,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 27.59,
|
| 540 |
+
"learning_rate": 4.528261713612966e-05,
|
| 541 |
+
"loss": 0.4633,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 27.9,
|
| 546 |
+
"learning_rate": 4.465638816176747e-05,
|
| 547 |
+
"loss": 0.4623,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 28.21,
|
| 552 |
+
"learning_rate": 4.4030159187405286e-05,
|
| 553 |
+
"loss": 0.4595,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 28.52,
|
| 558 |
+
"learning_rate": 4.34039302130431e-05,
|
| 559 |
+
"loss": 0.4593,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 28.83,
|
| 564 |
+
"learning_rate": 4.277770123868091e-05,
|
| 565 |
+
"loss": 0.4581,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 29.14,
|
| 570 |
+
"learning_rate": 4.2151472264318726e-05,
|
| 571 |
+
"loss": 0.4558,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 29.45,
|
| 576 |
+
"learning_rate": 4.152524328995654e-05,
|
| 577 |
+
"loss": 0.4534,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 29.76,
|
| 582 |
+
"learning_rate": 4.089901431559436e-05,
|
| 583 |
+
"loss": 0.4538,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 30.07,
|
| 588 |
+
"learning_rate": 4.0274037799180894e-05,
|
| 589 |
+
"loss": 0.4518,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 30.38,
|
| 594 |
+
"learning_rate": 3.9647808824818714e-05,
|
| 595 |
+
"loss": 0.4499,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 30.69,
|
| 600 |
+
"learning_rate": 3.902157985045653e-05,
|
| 601 |
+
"loss": 0.4503,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 31.0,
|
| 606 |
+
"learning_rate": 3.839535087609434e-05,
|
| 607 |
+
"loss": 0.4482,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 31.31,
|
| 612 |
+
"learning_rate": 3.7770374359680875e-05,
|
| 613 |
+
"loss": 0.4454,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 31.62,
|
| 618 |
+
"learning_rate": 3.714414538531869e-05,
|
| 619 |
+
"loss": 0.445,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 31.93,
|
| 624 |
+
"learning_rate": 3.65179164109565e-05,
|
| 625 |
+
"loss": 0.4443,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 32.24,
|
| 630 |
+
"learning_rate": 3.5891687436594315e-05,
|
| 631 |
+
"loss": 0.443,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 32.55,
|
| 636 |
+
"learning_rate": 3.5266710920180856e-05,
|
| 637 |
+
"loss": 0.4416,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 32.86,
|
| 642 |
+
"learning_rate": 3.464048194581867e-05,
|
| 643 |
+
"loss": 0.4414,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 33.17,
|
| 648 |
+
"learning_rate": 3.401425297145648e-05,
|
| 649 |
+
"loss": 0.4391,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 33.48,
|
| 654 |
+
"learning_rate": 3.3388023997094296e-05,
|
| 655 |
+
"loss": 0.4369,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 33.79,
|
| 660 |
+
"learning_rate": 3.2763047480680836e-05,
|
| 661 |
+
"loss": 0.4368,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 34.1,
|
| 666 |
+
"learning_rate": 3.213681850631865e-05,
|
| 667 |
+
"loss": 0.4363,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 34.41,
|
| 672 |
+
"learning_rate": 3.1510589531956463e-05,
|
| 673 |
+
"loss": 0.434,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 34.72,
|
| 678 |
+
"learning_rate": 3.0884360557594284e-05,
|
| 679 |
+
"loss": 0.4337,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 35.03,
|
| 684 |
+
"learning_rate": 3.0259384041180817e-05,
|
| 685 |
+
"loss": 0.4324,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 35.34,
|
| 690 |
+
"learning_rate": 2.9633155066818634e-05,
|
| 691 |
+
"loss": 0.4311,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 35.65,
|
| 696 |
+
"learning_rate": 2.9006926092456448e-05,
|
| 697 |
+
"loss": 0.4298,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 35.96,
|
| 702 |
+
"learning_rate": 2.838069711809426e-05,
|
| 703 |
+
"loss": 0.4305,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 36.27,
|
| 708 |
+
"learning_rate": 2.77557206016808e-05,
|
| 709 |
+
"loss": 0.4273,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 36.58,
|
| 714 |
+
"learning_rate": 2.7129491627318615e-05,
|
| 715 |
+
"loss": 0.4274,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 36.89,
|
| 720 |
+
"learning_rate": 2.650326265295643e-05,
|
| 721 |
+
"loss": 0.4267,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 37.2,
|
| 726 |
+
"learning_rate": 2.5877033678594242e-05,
|
| 727 |
+
"loss": 0.4245,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 37.51,
|
| 732 |
+
"learning_rate": 2.5250804704232056e-05,
|
| 733 |
+
"loss": 0.4234,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 37.82,
|
| 738 |
+
"learning_rate": 2.462457572986987e-05,
|
| 739 |
+
"loss": 0.4237,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 38.13,
|
| 744 |
+
"learning_rate": 2.3998346755507686e-05,
|
| 745 |
+
"loss": 0.4217,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 38.44,
|
| 750 |
+
"learning_rate": 2.33721177811455e-05,
|
| 751 |
+
"loss": 0.42,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 38.75,
|
| 756 |
+
"learning_rate": 2.274714126473204e-05,
|
| 757 |
+
"loss": 0.4207,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 39.06,
|
| 762 |
+
"learning_rate": 2.2120912290369853e-05,
|
| 763 |
+
"loss": 0.4206,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 39.37,
|
| 768 |
+
"learning_rate": 2.1494683316007667e-05,
|
| 769 |
+
"loss": 0.4177,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 39.68,
|
| 774 |
+
"learning_rate": 2.086845434164548e-05,
|
| 775 |
+
"loss": 0.4183,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 39.99,
|
| 780 |
+
"learning_rate": 2.0243477825232017e-05,
|
| 781 |
+
"loss": 0.4163,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 40.3,
|
| 786 |
+
"learning_rate": 1.961724885086983e-05,
|
| 787 |
+
"loss": 0.4151,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 40.61,
|
| 792 |
+
"learning_rate": 1.8991019876507644e-05,
|
| 793 |
+
"loss": 0.4159,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 40.92,
|
| 798 |
+
"learning_rate": 1.836479090214546e-05,
|
| 799 |
+
"loss": 0.4146,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 41.23,
|
| 804 |
+
"learning_rate": 1.7738561927783275e-05,
|
| 805 |
+
"loss": 0.4134,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 41.54,
|
| 810 |
+
"learning_rate": 1.7112332953421088e-05,
|
| 811 |
+
"loss": 0.4124,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 41.85,
|
| 816 |
+
"learning_rate": 1.6486103979058905e-05,
|
| 817 |
+
"loss": 0.4119,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 42.16,
|
| 822 |
+
"learning_rate": 1.585987500469672e-05,
|
| 823 |
+
"loss": 0.4106,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 42.47,
|
| 828 |
+
"learning_rate": 1.5233646030334534e-05,
|
| 829 |
+
"loss": 0.4104,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 42.78,
|
| 834 |
+
"learning_rate": 1.4607417055972347e-05,
|
| 835 |
+
"loss": 0.4094,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 43.09,
|
| 840 |
+
"learning_rate": 1.398118808161016e-05,
|
| 841 |
+
"loss": 0.4091,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 43.4,
|
| 846 |
+
"learning_rate": 1.3354959107247974e-05,
|
| 847 |
+
"loss": 0.4082,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 43.71,
|
| 852 |
+
"learning_rate": 1.2728730132885787e-05,
|
| 853 |
+
"loss": 0.4074,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 44.02,
|
| 858 |
+
"learning_rate": 1.2102501158523603e-05,
|
| 859 |
+
"loss": 0.4067,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 44.33,
|
| 864 |
+
"learning_rate": 1.1476272184161418e-05,
|
| 865 |
+
"loss": 0.4062,
|
| 866 |
+
"step": 71500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 44.64,
|
| 870 |
+
"learning_rate": 1.0850043209799233e-05,
|
| 871 |
+
"loss": 0.4051,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 44.95,
|
| 876 |
+
"learning_rate": 1.0223814235437046e-05,
|
| 877 |
+
"loss": 0.4048,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 45.26,
|
| 882 |
+
"learning_rate": 9.59758526107486e-06,
|
| 883 |
+
"loss": 0.4034,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 45.57,
|
| 888 |
+
"learning_rate": 8.971356286712675e-06,
|
| 889 |
+
"loss": 0.4036,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 45.88,
|
| 894 |
+
"learning_rate": 8.345127312350489e-06,
|
| 895 |
+
"loss": 0.4038,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 46.19,
|
| 900 |
+
"learning_rate": 7.718898337988302e-06,
|
| 901 |
+
"loss": 0.4021,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 46.5,
|
| 906 |
+
"learning_rate": 7.092669363626117e-06,
|
| 907 |
+
"loss": 0.4023,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 46.81,
|
| 912 |
+
"learning_rate": 6.466440389263931e-06,
|
| 913 |
+
"loss": 0.4011,
|
| 914 |
+
"step": 75500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 47.12,
|
| 918 |
+
"learning_rate": 5.840211414901745e-06,
|
| 919 |
+
"loss": 0.4004,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 47.43,
|
| 924 |
+
"learning_rate": 5.2139824405395585e-06,
|
| 925 |
+
"loss": 0.3997,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 47.74,
|
| 930 |
+
"learning_rate": 4.587753466177374e-06,
|
| 931 |
+
"loss": 0.3999,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 48.05,
|
| 936 |
+
"learning_rate": 3.961524491815188e-06,
|
| 937 |
+
"loss": 0.3988,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 48.36,
|
| 942 |
+
"learning_rate": 3.3352955174530015e-06,
|
| 943 |
+
"loss": 0.3988,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 48.67,
|
| 948 |
+
"learning_rate": 2.709066543090816e-06,
|
| 949 |
+
"loss": 0.3978,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 48.98,
|
| 954 |
+
"learning_rate": 2.08283756872863e-06,
|
| 955 |
+
"loss": 0.3983,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 49.29,
|
| 960 |
+
"learning_rate": 1.4566085943664442e-06,
|
| 961 |
+
"loss": 0.398,
|
| 962 |
+
"step": 79500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 49.6,
|
| 966 |
+
"learning_rate": 8.303796200042584e-07,
|
| 967 |
+
"loss": 0.3974,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 49.91,
|
| 972 |
+
"learning_rate": 2.0415064564207257e-07,
|
| 973 |
+
"loss": 0.3975,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 50.0,
|
| 978 |
+
"step": 80650,
|
| 979 |
+
"total_flos": 2.180340696717392e+19,
|
| 980 |
+
"train_loss": 0.005664803918222426,
|
| 981 |
+
"train_runtime": 6206.924,
|
| 982 |
+
"train_samples_per_second": 19956.785,
|
| 983 |
+
"train_steps_per_second": 12.994
|
| 984 |
+
}
|
| 985 |
+
],
|
| 986 |
+
"max_steps": 80650,
|
| 987 |
+
"num_train_epochs": 50,
|
| 988 |
+
"total_flos": 2.180340696717392e+19,
|
| 989 |
+
"trial_name": null,
|
| 990 |
+
"trial_params": null
|
| 991 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:522564bf2d4d448e2bf363445b46c741db75b064eb272f118aceac2361d2c6ae
|
| 3 |
+
size 4408
|