commit from mujeen
Browse files- README.md +77 -0
- all_results.json +14 -0
- config.json +45 -0
- eval_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +640 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- glue
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: albert-base-v2_mnli_bc
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Text Classification
|
| 16 |
+
type: text-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: GLUE MNLI
|
| 19 |
+
type: glue
|
| 20 |
+
args: mnli
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.9398776667163956
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# albert-base-v2_mnli_bc
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE MNLI dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2952
|
| 35 |
+
- Accuracy: 0.9399
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 2e-05
|
| 55 |
+
- train_batch_size: 16
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 3.0
|
| 61 |
+
- mixed_precision_training: Native AMP
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 67 |
+
| 0.2159 | 1.0 | 16363 | 0.2268 | 0.9248 |
|
| 68 |
+
| 0.1817 | 2.0 | 32726 | 0.2335 | 0.9347 |
|
| 69 |
+
| 0.0863 | 3.0 | 49089 | 0.3014 | 0.9401 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.13.0
|
| 75 |
+
- Pytorch 1.10.1+cu111
|
| 76 |
+
- Datasets 1.17.0
|
| 77 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9398776667163956,
|
| 4 |
+
"eval_loss": 0.29518571496009827,
|
| 5 |
+
"eval_runtime": 20.3417,
|
| 6 |
+
"eval_samples": 6703,
|
| 7 |
+
"eval_samples_per_second": 329.52,
|
| 8 |
+
"eval_steps_per_second": 41.196,
|
| 9 |
+
"train_loss": 0.18007777646369438,
|
| 10 |
+
"train_runtime": 3964.6017,
|
| 11 |
+
"train_samples": 261802,
|
| 12 |
+
"train_samples_per_second": 198.105,
|
| 13 |
+
"train_steps_per_second": 12.382
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"finetuning_task": "mnli",
|
| 13 |
+
"gap_size": 0,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_dropout_prob": 0,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "entailment",
|
| 19 |
+
"1": "neutral",
|
| 20 |
+
"2": "contradiction"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"inner_group_num": 1,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"contradiction": 2,
|
| 27 |
+
"entailment": 0,
|
| 28 |
+
"neutral": 1
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"max_position_embeddings": 512,
|
| 32 |
+
"model_type": "albert",
|
| 33 |
+
"net_structure_type": 0,
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_groups": 1,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"num_memory_blocks": 0,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"position_embedding_type": "absolute",
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.13.0",
|
| 43 |
+
"type_vocab_size": 2,
|
| 44 |
+
"vocab_size": 30000
|
| 45 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9398776667163956,
|
| 4 |
+
"eval_loss": 0.29518571496009827,
|
| 5 |
+
"eval_runtime": 20.3417,
|
| 6 |
+
"eval_samples": 6703,
|
| 7 |
+
"eval_samples_per_second": 329.52,
|
| 8 |
+
"eval_steps_per_second": 41.196
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cdcba525b43ff3485608ba533547b4360360badc06e472edc4ef4ee17ea78de
|
| 3 |
+
size 46755537
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.18007777646369438,
|
| 4 |
+
"train_runtime": 3964.6017,
|
| 5 |
+
"train_samples": 261802,
|
| 6 |
+
"train_samples_per_second": 198.105,
|
| 7 |
+
"train_steps_per_second": 12.382
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,640 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9400777047220562,
|
| 3 |
+
"best_model_checkpoint": "/hdd1/mujeen/retrieval_prf/output/albert-base-v2_mnli_bc/checkpoint-49089",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 49089,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.979832549043574e-05,
|
| 13 |
+
"loss": 0.4104,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 1.9595021287864898e-05,
|
| 19 |
+
"loss": 0.3325,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 1.939171708529406e-05,
|
| 25 |
+
"loss": 0.3067,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 1.9188005459471572e-05,
|
| 31 |
+
"loss": 0.3078,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 1.898429383364909e-05,
|
| 37 |
+
"loss": 0.2841,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 1.8780582207826603e-05,
|
| 43 |
+
"loss": 0.2747,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 1.8576870582004117e-05,
|
| 49 |
+
"loss": 0.2749,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 1.837315895618163e-05,
|
| 55 |
+
"loss": 0.2612,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 1.8169447330359144e-05,
|
| 61 |
+
"loss": 0.2629,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.31,
|
| 66 |
+
"learning_rate": 1.796573570453666e-05,
|
| 67 |
+
"loss": 0.2586,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"learning_rate": 1.776202407871417e-05,
|
| 73 |
+
"loss": 0.2599,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.37,
|
| 78 |
+
"learning_rate": 1.755831245289169e-05,
|
| 79 |
+
"loss": 0.2579,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"learning_rate": 1.7354600827069202e-05,
|
| 85 |
+
"loss": 0.2479,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.43,
|
| 90 |
+
"learning_rate": 1.7150889201246716e-05,
|
| 91 |
+
"loss": 0.2444,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.46,
|
| 96 |
+
"learning_rate": 1.6947177575424233e-05,
|
| 97 |
+
"loss": 0.2419,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"learning_rate": 1.6743465949601747e-05,
|
| 103 |
+
"loss": 0.2452,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.52,
|
| 108 |
+
"learning_rate": 1.653975432377926e-05,
|
| 109 |
+
"loss": 0.2493,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.55,
|
| 114 |
+
"learning_rate": 1.6336042697956774e-05,
|
| 115 |
+
"loss": 0.2343,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.58,
|
| 120 |
+
"learning_rate": 1.6132738495385935e-05,
|
| 121 |
+
"loss": 0.2464,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.61,
|
| 126 |
+
"learning_rate": 1.5929026869563445e-05,
|
| 127 |
+
"loss": 0.2305,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.64,
|
| 132 |
+
"learning_rate": 1.5725315243740962e-05,
|
| 133 |
+
"loss": 0.231,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.67,
|
| 138 |
+
"learning_rate": 1.5521603617918476e-05,
|
| 139 |
+
"loss": 0.2339,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.7,
|
| 144 |
+
"learning_rate": 1.5318299415347636e-05,
|
| 145 |
+
"loss": 0.2267,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.73,
|
| 150 |
+
"learning_rate": 1.511458778952515e-05,
|
| 151 |
+
"loss": 0.2249,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.76,
|
| 156 |
+
"learning_rate": 1.4910876163702664e-05,
|
| 157 |
+
"loss": 0.233,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.79,
|
| 162 |
+
"learning_rate": 1.4707164537880179e-05,
|
| 163 |
+
"loss": 0.2257,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.83,
|
| 168 |
+
"learning_rate": 1.4503452912057691e-05,
|
| 169 |
+
"loss": 0.2277,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.86,
|
| 174 |
+
"learning_rate": 1.4299741286235206e-05,
|
| 175 |
+
"loss": 0.2225,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.89,
|
| 180 |
+
"learning_rate": 1.409602966041272e-05,
|
| 181 |
+
"loss": 0.226,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.92,
|
| 186 |
+
"learning_rate": 1.3892318034590235e-05,
|
| 187 |
+
"loss": 0.2173,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.95,
|
| 192 |
+
"learning_rate": 1.3689013832019396e-05,
|
| 193 |
+
"loss": 0.2191,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.98,
|
| 198 |
+
"learning_rate": 1.3485302206196908e-05,
|
| 199 |
+
"loss": 0.2159,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0,
|
| 204 |
+
"eval_accuracy": 0.9248356246264196,
|
| 205 |
+
"eval_loss": 0.22675447165966034,
|
| 206 |
+
"eval_runtime": 19.8714,
|
| 207 |
+
"eval_samples_per_second": 336.766,
|
| 208 |
+
"eval_steps_per_second": 42.121,
|
| 209 |
+
"step": 16363
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.01,
|
| 213 |
+
"learning_rate": 1.3281590580374423e-05,
|
| 214 |
+
"loss": 0.2072,
|
| 215 |
+
"step": 16500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.04,
|
| 219 |
+
"learning_rate": 1.3077878954551937e-05,
|
| 220 |
+
"loss": 0.1826,
|
| 221 |
+
"step": 17000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.07,
|
| 225 |
+
"learning_rate": 1.2874574751981098e-05,
|
| 226 |
+
"loss": 0.1817,
|
| 227 |
+
"step": 17500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.1,
|
| 231 |
+
"learning_rate": 1.267086312615861e-05,
|
| 232 |
+
"loss": 0.1745,
|
| 233 |
+
"step": 18000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.13,
|
| 237 |
+
"learning_rate": 1.2467151500336125e-05,
|
| 238 |
+
"loss": 0.1841,
|
| 239 |
+
"step": 18500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.16,
|
| 243 |
+
"learning_rate": 1.2263439874513639e-05,
|
| 244 |
+
"loss": 0.1856,
|
| 245 |
+
"step": 19000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.19,
|
| 249 |
+
"learning_rate": 1.2059728248691154e-05,
|
| 250 |
+
"loss": 0.19,
|
| 251 |
+
"step": 19500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.22,
|
| 255 |
+
"learning_rate": 1.185601662286867e-05,
|
| 256 |
+
"loss": 0.2017,
|
| 257 |
+
"step": 20000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.25,
|
| 261 |
+
"learning_rate": 1.1652304997046182e-05,
|
| 262 |
+
"loss": 0.1885,
|
| 263 |
+
"step": 20500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.28,
|
| 267 |
+
"learning_rate": 1.1449000794475342e-05,
|
| 268 |
+
"loss": 0.1732,
|
| 269 |
+
"step": 21000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.31,
|
| 273 |
+
"learning_rate": 1.12456965919045e-05,
|
| 274 |
+
"loss": 0.1852,
|
| 275 |
+
"step": 21500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.34,
|
| 279 |
+
"learning_rate": 1.104239238933366e-05,
|
| 280 |
+
"loss": 0.1899,
|
| 281 |
+
"step": 22000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.38,
|
| 285 |
+
"learning_rate": 1.0838680763511174e-05,
|
| 286 |
+
"loss": 0.172,
|
| 287 |
+
"step": 22500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.41,
|
| 291 |
+
"learning_rate": 1.063496913768869e-05,
|
| 292 |
+
"loss": 0.1869,
|
| 293 |
+
"step": 23000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.44,
|
| 297 |
+
"learning_rate": 1.0431257511866205e-05,
|
| 298 |
+
"loss": 0.1956,
|
| 299 |
+
"step": 23500
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.47,
|
| 303 |
+
"learning_rate": 1.0227545886043717e-05,
|
| 304 |
+
"loss": 0.1925,
|
| 305 |
+
"step": 24000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.5,
|
| 309 |
+
"learning_rate": 1.0023834260221232e-05,
|
| 310 |
+
"loss": 0.1867,
|
| 311 |
+
"step": 24500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.53,
|
| 315 |
+
"learning_rate": 9.820122634398746e-06,
|
| 316 |
+
"loss": 0.1829,
|
| 317 |
+
"step": 25000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.56,
|
| 321 |
+
"learning_rate": 9.616411008576261e-06,
|
| 322 |
+
"loss": 0.1764,
|
| 323 |
+
"step": 25500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.59,
|
| 327 |
+
"learning_rate": 9.412699382753775e-06,
|
| 328 |
+
"loss": 0.1717,
|
| 329 |
+
"step": 26000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.62,
|
| 333 |
+
"learning_rate": 9.208987756931288e-06,
|
| 334 |
+
"loss": 0.1767,
|
| 335 |
+
"step": 26500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.65,
|
| 339 |
+
"learning_rate": 9.005276131108804e-06,
|
| 340 |
+
"loss": 0.1723,
|
| 341 |
+
"step": 27000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.68,
|
| 345 |
+
"learning_rate": 8.801971928537963e-06,
|
| 346 |
+
"loss": 0.1753,
|
| 347 |
+
"step": 27500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.71,
|
| 351 |
+
"learning_rate": 8.598667725967122e-06,
|
| 352 |
+
"loss": 0.1865,
|
| 353 |
+
"step": 28000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.74,
|
| 357 |
+
"learning_rate": 8.394956100144636e-06,
|
| 358 |
+
"loss": 0.1708,
|
| 359 |
+
"step": 28500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.77,
|
| 363 |
+
"learning_rate": 8.19124447432215e-06,
|
| 364 |
+
"loss": 0.1731,
|
| 365 |
+
"step": 29000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.8,
|
| 369 |
+
"learning_rate": 7.987532848499665e-06,
|
| 370 |
+
"loss": 0.1667,
|
| 371 |
+
"step": 29500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.83,
|
| 375 |
+
"learning_rate": 7.78382122267718e-06,
|
| 376 |
+
"loss": 0.1852,
|
| 377 |
+
"step": 30000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.86,
|
| 381 |
+
"learning_rate": 7.580109596854694e-06,
|
| 382 |
+
"loss": 0.1737,
|
| 383 |
+
"step": 30500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.89,
|
| 387 |
+
"learning_rate": 7.376397971032207e-06,
|
| 388 |
+
"loss": 0.1806,
|
| 389 |
+
"step": 31000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.93,
|
| 393 |
+
"learning_rate": 7.172686345209722e-06,
|
| 394 |
+
"loss": 0.1698,
|
| 395 |
+
"step": 31500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.96,
|
| 399 |
+
"learning_rate": 6.9689747193872355e-06,
|
| 400 |
+
"loss": 0.175,
|
| 401 |
+
"step": 32000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.99,
|
| 405 |
+
"learning_rate": 6.76526309356475e-06,
|
| 406 |
+
"loss": 0.1817,
|
| 407 |
+
"step": 32500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.0,
|
| 411 |
+
"eval_accuracy": 0.9346981470412433,
|
| 412 |
+
"eval_loss": 0.2335003763437271,
|
| 413 |
+
"eval_runtime": 19.6848,
|
| 414 |
+
"eval_samples_per_second": 339.958,
|
| 415 |
+
"eval_steps_per_second": 42.52,
|
| 416 |
+
"step": 32726
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.02,
|
| 420 |
+
"learning_rate": 6.5615514677422645e-06,
|
| 421 |
+
"loss": 0.1377,
|
| 422 |
+
"step": 33000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.05,
|
| 426 |
+
"learning_rate": 6.358247265171424e-06,
|
| 427 |
+
"loss": 0.0941,
|
| 428 |
+
"step": 33500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.08,
|
| 432 |
+
"learning_rate": 6.154535639348939e-06,
|
| 433 |
+
"loss": 0.1108,
|
| 434 |
+
"step": 34000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.11,
|
| 438 |
+
"learning_rate": 5.950824013526453e-06,
|
| 439 |
+
"loss": 0.1082,
|
| 440 |
+
"step": 34500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.14,
|
| 444 |
+
"learning_rate": 5.747112387703967e-06,
|
| 445 |
+
"loss": 0.1117,
|
| 446 |
+
"step": 35000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.17,
|
| 450 |
+
"learning_rate": 5.543400761881481e-06,
|
| 451 |
+
"loss": 0.1155,
|
| 452 |
+
"step": 35500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.2,
|
| 456 |
+
"learning_rate": 5.339689136058995e-06,
|
| 457 |
+
"loss": 0.1013,
|
| 458 |
+
"step": 36000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.23,
|
| 462 |
+
"learning_rate": 5.13597751023651e-06,
|
| 463 |
+
"loss": 0.1156,
|
| 464 |
+
"step": 36500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.26,
|
| 468 |
+
"learning_rate": 4.9322658844140235e-06,
|
| 469 |
+
"loss": 0.1014,
|
| 470 |
+
"step": 37000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.29,
|
| 474 |
+
"learning_rate": 4.729369105094828e-06,
|
| 475 |
+
"loss": 0.1124,
|
| 476 |
+
"step": 37500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.32,
|
| 480 |
+
"learning_rate": 4.5256574792723424e-06,
|
| 481 |
+
"loss": 0.1178,
|
| 482 |
+
"step": 38000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.35,
|
| 486 |
+
"learning_rate": 4.321945853449856e-06,
|
| 487 |
+
"loss": 0.1088,
|
| 488 |
+
"step": 38500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.38,
|
| 492 |
+
"learning_rate": 4.118641650879016e-06,
|
| 493 |
+
"loss": 0.1216,
|
| 494 |
+
"step": 39000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.41,
|
| 498 |
+
"learning_rate": 3.9149300250565305e-06,
|
| 499 |
+
"loss": 0.1087,
|
| 500 |
+
"step": 39500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.44,
|
| 504 |
+
"learning_rate": 3.7112183992340446e-06,
|
| 505 |
+
"loss": 0.1094,
|
| 506 |
+
"step": 40000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.48,
|
| 510 |
+
"learning_rate": 3.5075067734115587e-06,
|
| 511 |
+
"loss": 0.1137,
|
| 512 |
+
"step": 40500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.51,
|
| 516 |
+
"learning_rate": 3.303795147589073e-06,
|
| 517 |
+
"loss": 0.1161,
|
| 518 |
+
"step": 41000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.54,
|
| 522 |
+
"learning_rate": 3.1000835217665877e-06,
|
| 523 |
+
"loss": 0.1055,
|
| 524 |
+
"step": 41500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.57,
|
| 528 |
+
"learning_rate": 2.896371895944102e-06,
|
| 529 |
+
"loss": 0.1058,
|
| 530 |
+
"step": 42000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.6,
|
| 534 |
+
"learning_rate": 2.692660270121616e-06,
|
| 535 |
+
"loss": 0.1037,
|
| 536 |
+
"step": 42500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.63,
|
| 540 |
+
"learning_rate": 2.4889486442991304e-06,
|
| 541 |
+
"loss": 0.1023,
|
| 542 |
+
"step": 43000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.66,
|
| 546 |
+
"learning_rate": 2.2852370184766445e-06,
|
| 547 |
+
"loss": 0.0998,
|
| 548 |
+
"step": 43500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.69,
|
| 552 |
+
"learning_rate": 2.081932815905804e-06,
|
| 553 |
+
"loss": 0.1097,
|
| 554 |
+
"step": 44000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.72,
|
| 558 |
+
"learning_rate": 1.8782211900833183e-06,
|
| 559 |
+
"loss": 0.0914,
|
| 560 |
+
"step": 44500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.75,
|
| 564 |
+
"learning_rate": 1.6745095642608326e-06,
|
| 565 |
+
"loss": 0.1139,
|
| 566 |
+
"step": 45000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.78,
|
| 570 |
+
"learning_rate": 1.4707979384383466e-06,
|
| 571 |
+
"loss": 0.0998,
|
| 572 |
+
"step": 45500
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.81,
|
| 576 |
+
"learning_rate": 1.2670863126158612e-06,
|
| 577 |
+
"loss": 0.0959,
|
| 578 |
+
"step": 46000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.84,
|
| 582 |
+
"learning_rate": 1.0633746867933755e-06,
|
| 583 |
+
"loss": 0.0994,
|
| 584 |
+
"step": 46500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.87,
|
| 588 |
+
"learning_rate": 8.596630609708896e-07,
|
| 589 |
+
"loss": 0.1093,
|
| 590 |
+
"step": 47000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.9,
|
| 594 |
+
"learning_rate": 6.559514351484039e-07,
|
| 595 |
+
"loss": 0.0967,
|
| 596 |
+
"step": 47500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.93,
|
| 600 |
+
"learning_rate": 4.5264723257756327e-07,
|
| 601 |
+
"loss": 0.102,
|
| 602 |
+
"step": 48000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.96,
|
| 606 |
+
"learning_rate": 2.4893560675507757e-07,
|
| 607 |
+
"loss": 0.0966,
|
| 608 |
+
"step": 48500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.99,
|
| 612 |
+
"learning_rate": 4.522398093259183e-08,
|
| 613 |
+
"loss": 0.0863,
|
| 614 |
+
"step": 49000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.0,
|
| 618 |
+
"eval_accuracy": 0.9400777047220562,
|
| 619 |
+
"eval_loss": 0.3014400601387024,
|
| 620 |
+
"eval_runtime": 20.103,
|
| 621 |
+
"eval_samples_per_second": 332.885,
|
| 622 |
+
"eval_steps_per_second": 41.636,
|
| 623 |
+
"step": 49089
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.0,
|
| 627 |
+
"step": 49089,
|
| 628 |
+
"total_flos": 3063521562716160.0,
|
| 629 |
+
"train_loss": 0.18007777646369438,
|
| 630 |
+
"train_runtime": 3964.6017,
|
| 631 |
+
"train_samples_per_second": 198.105,
|
| 632 |
+
"train_steps_per_second": 12.382
|
| 633 |
+
}
|
| 634 |
+
],
|
| 635 |
+
"max_steps": 49089,
|
| 636 |
+
"num_train_epochs": 3,
|
| 637 |
+
"total_flos": 3063521562716160.0,
|
| 638 |
+
"trial_name": null,
|
| 639 |
+
"trial_params": null
|
| 640 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9fcca68eb9ecb6767ca0dede6fba187a388bc3a59d9acaad1c6a63c91f3fcda
|
| 3 |
+
size 2991
|