Model save
Browse files- README.md +67 -0
- all_results.json +15 -0
- config.json +29 -0
- eval_results.json +10 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- train_results.json +8 -0
- trainer_state.json +2815 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: EleutherAI/pythia-31m
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: BL-pythia-31m-simple_wikipedia_LM-2048-scratch
|
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 |
+
# BL-pythia-31m-simple_wikipedia_LM-2048-scratch
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 4.1763
|
20 |
+
- Accuracy: 0.3676
|
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: 0.0005
|
40 |
+
- train_batch_size: 2
|
41 |
+
- eval_batch_size: 2
|
42 |
+
- seed: 80085
|
43 |
+
- gradient_accumulation_steps: 64
|
44 |
+
- total_train_batch_size: 128
|
45 |
+
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07
|
46 |
+
- lr_scheduler_type: inverse_sqrt
|
47 |
+
- lr_scheduler_warmup_ratio: 0.05
|
48 |
+
- num_epochs: 3.0
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 5.8617 | 0.45 | 100 | 5.5276 | 0.2451 |
|
55 |
+
| 5.2782 | 0.9 | 200 | 4.9596 | 0.2965 |
|
56 |
+
| 4.9996 | 1.35 | 300 | 4.6412 | 0.3310 |
|
57 |
+
| 4.6292 | 1.8 | 400 | 4.4344 | 0.3485 |
|
58 |
+
| 4.5339 | 2.25 | 500 | 4.2875 | 0.3600 |
|
59 |
+
| 4.5214 | 2.7 | 600 | 4.1763 | 0.3676 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.33.1
|
65 |
+
- Pytorch 2.2.0.dev20230907+cu118
|
66 |
+
- Datasets 2.14.5
|
67 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.4115085490962384,
|
4 |
+
"eval_loss": 3.6757330894470215,
|
5 |
+
"eval_runtime": 15.1278,
|
6 |
+
"eval_samples": 500,
|
7 |
+
"eval_samples_per_second": 33.052,
|
8 |
+
"eval_steps_per_second": 16.526,
|
9 |
+
"perplexity": 39.47758685408379,
|
10 |
+
"train_loss": 4.728262927737576,
|
11 |
+
"train_runtime": 4788.6915,
|
12 |
+
"train_samples": 28488,
|
13 |
+
"train_samples_per_second": 17.847,
|
14 |
+
"train_steps_per_second": 0.279
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-31m",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": 0.1,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 256,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 1024,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "gpt_neox",
|
18 |
+
"num_attention_heads": 8,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rotary_emb_base": 10000,
|
22 |
+
"rotary_pct": 0.25,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.33.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_parallel_residual": true,
|
28 |
+
"vocab_size": 50304
|
29 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.4115085490962384,
|
4 |
+
"eval_loss": 3.6757330894470215,
|
5 |
+
"eval_runtime": 15.1278,
|
6 |
+
"eval_samples": 500,
|
7 |
+
"eval_samples_per_second": 33.052,
|
8 |
+
"eval_steps_per_second": 16.526,
|
9 |
+
"perplexity": 39.47758685408379
|
10 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.33.1"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd3df4e1df517657c3eff9bdbc5929ac336fa8d09a965f84864c64eb7bdd56af
|
3 |
+
size 121988328
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 4.728262927737576,
|
4 |
+
"train_runtime": 4788.6915,
|
5 |
+
"train_samples": 28488,
|
6 |
+
"train_samples_per_second": 17.847,
|
7 |
+
"train_steps_per_second": 0.279
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2815 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9991575400168493,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1335,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2.2388059701492536e-05,
|
14 |
+
"loss": 10.8621,
|
15 |
+
"step": 3
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.477611940298507e-05,
|
20 |
+
"loss": 10.767,
|
21 |
+
"step": 6
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 6.716417910447761e-05,
|
26 |
+
"loss": 10.5723,
|
27 |
+
"step": 9
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.03,
|
31 |
+
"learning_rate": 8.955223880597014e-05,
|
32 |
+
"loss": 10.4057,
|
33 |
+
"step": 12
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03,
|
37 |
+
"learning_rate": 0.00011194029850746269,
|
38 |
+
"loss": 10.2623,
|
39 |
+
"step": 15
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04,
|
43 |
+
"learning_rate": 0.00013432835820895522,
|
44 |
+
"loss": 10.0998,
|
45 |
+
"step": 18
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.05,
|
49 |
+
"learning_rate": 0.00015671641791044778,
|
50 |
+
"loss": 9.9577,
|
51 |
+
"step": 21
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.05,
|
55 |
+
"learning_rate": 0.00017910447761194028,
|
56 |
+
"loss": 9.8105,
|
57 |
+
"step": 24
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.06,
|
61 |
+
"learning_rate": 0.00020149253731343284,
|
62 |
+
"loss": 9.5994,
|
63 |
+
"step": 27
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.07,
|
67 |
+
"learning_rate": 0.00022388059701492538,
|
68 |
+
"loss": 9.4189,
|
69 |
+
"step": 30
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.07,
|
73 |
+
"learning_rate": 0.0002462686567164179,
|
74 |
+
"loss": 9.1967,
|
75 |
+
"step": 33
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.08,
|
79 |
+
"learning_rate": 0.00026865671641791044,
|
80 |
+
"loss": 8.9757,
|
81 |
+
"step": 36
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.09,
|
85 |
+
"learning_rate": 0.00029104477611940297,
|
86 |
+
"loss": 8.7393,
|
87 |
+
"step": 39
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.09,
|
91 |
+
"learning_rate": 0.00031343283582089556,
|
92 |
+
"loss": 8.4736,
|
93 |
+
"step": 42
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.1,
|
97 |
+
"learning_rate": 0.0003358208955223881,
|
98 |
+
"loss": 8.3719,
|
99 |
+
"step": 45
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.11,
|
103 |
+
"learning_rate": 0.00035820895522388057,
|
104 |
+
"loss": 8.1845,
|
105 |
+
"step": 48
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.11,
|
109 |
+
"learning_rate": 0.00038059701492537315,
|
110 |
+
"loss": 7.9457,
|
111 |
+
"step": 51
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.12,
|
115 |
+
"learning_rate": 0.0004029850746268657,
|
116 |
+
"loss": 7.7169,
|
117 |
+
"step": 54
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.13,
|
121 |
+
"learning_rate": 0.0004253731343283582,
|
122 |
+
"loss": 7.4515,
|
123 |
+
"step": 57
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.13,
|
127 |
+
"learning_rate": 0.00044776119402985075,
|
128 |
+
"loss": 7.3122,
|
129 |
+
"step": 60
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.14,
|
133 |
+
"learning_rate": 0.00047014925373134334,
|
134 |
+
"loss": 7.0979,
|
135 |
+
"step": 63
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.15,
|
139 |
+
"learning_rate": 0.0004925373134328358,
|
140 |
+
"loss": 7.0553,
|
141 |
+
"step": 66
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.16,
|
145 |
+
"learning_rate": 0.0004927003381249152,
|
146 |
+
"loss": 6.9408,
|
147 |
+
"step": 69
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.16,
|
151 |
+
"learning_rate": 0.00048232653761625933,
|
152 |
+
"loss": 6.7523,
|
153 |
+
"step": 72
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.17,
|
157 |
+
"learning_rate": 0.00047258156262526085,
|
158 |
+
"loss": 6.5754,
|
159 |
+
"step": 75
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.18,
|
163 |
+
"learning_rate": 0.0004634043479981492,
|
164 |
+
"loss": 6.2952,
|
165 |
+
"step": 78
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.18,
|
169 |
+
"learning_rate": 0.00045474182065958054,
|
170 |
+
"loss": 6.3841,
|
171 |
+
"step": 81
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.19,
|
175 |
+
"learning_rate": 0.00044654760317883456,
|
176 |
+
"loss": 6.3261,
|
177 |
+
"step": 84
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.2,
|
181 |
+
"learning_rate": 0.0004387809654396872,
|
182 |
+
"loss": 6.2896,
|
183 |
+
"step": 87
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.2,
|
187 |
+
"learning_rate": 0.0004314059701848262,
|
188 |
+
"loss": 6.3229,
|
189 |
+
"step": 90
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.21,
|
193 |
+
"learning_rate": 0.0004243907714379761,
|
194 |
+
"loss": 6.0904,
|
195 |
+
"step": 93
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.22,
|
199 |
+
"learning_rate": 0.00041770703449507126,
|
200 |
+
"loss": 6.0741,
|
201 |
+
"step": 96
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.22,
|
205 |
+
"learning_rate": 0.00041132945334843116,
|
206 |
+
"loss": 6.077,
|
207 |
+
"step": 99
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.22,
|
211 |
+
"eval_accuracy": 0.24181827063996092,
|
212 |
+
"eval_loss": 5.63174295425415,
|
213 |
+
"eval_runtime": 15.0735,
|
214 |
+
"eval_samples_per_second": 33.171,
|
215 |
+
"eval_steps_per_second": 16.585,
|
216 |
+
"step": 100
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.23,
|
220 |
+
"learning_rate": 0.00040523534677334083,
|
221 |
+
"loss": 6.0036,
|
222 |
+
"step": 102
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.24,
|
226 |
+
"learning_rate": 0.0003994043183589901,
|
227 |
+
"loss": 5.9912,
|
228 |
+
"step": 105
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.24,
|
232 |
+
"learning_rate": 0.000393817968854384,
|
233 |
+
"loss": 5.9011,
|
234 |
+
"step": 108
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.25,
|
238 |
+
"learning_rate": 0.00038845965157388086,
|
239 |
+
"loss": 5.944,
|
240 |
+
"step": 111
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.26,
|
244 |
+
"learning_rate": 0.00038331426344633137,
|
245 |
+
"loss": 5.6939,
|
246 |
+
"step": 114
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 0.26,
|
250 |
+
"learning_rate": 0.00037836806572753097,
|
251 |
+
"loss": 5.8592,
|
252 |
+
"step": 117
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 0.27,
|
256 |
+
"learning_rate": 0.0003736085295243316,
|
257 |
+
"loss": 5.6326,
|
258 |
+
"step": 120
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.28,
|
262 |
+
"learning_rate": 0.0003690242021719143,
|
263 |
+
"loss": 5.6688,
|
264 |
+
"step": 123
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.28,
|
268 |
+
"learning_rate": 0.0003646045912169894,
|
269 |
+
"loss": 5.668,
|
270 |
+
"step": 126
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.29,
|
274 |
+
"learning_rate": 0.0003603400633295028,
|
275 |
+
"loss": 5.7459,
|
276 |
+
"step": 129
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.3,
|
280 |
+
"learning_rate": 0.00035622175592450755,
|
281 |
+
"loss": 5.7216,
|
282 |
+
"step": 132
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.3,
|
286 |
+
"learning_rate": 0.00035224149964771913,
|
287 |
+
"loss": 5.498,
|
288 |
+
"step": 135
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.31,
|
292 |
+
"learning_rate": 0.0003483917501810324,
|
293 |
+
"loss": 5.4487,
|
294 |
+
"step": 138
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.32,
|
298 |
+
"learning_rate": 0.000344665528071977,
|
299 |
+
"loss": 5.764,
|
300 |
+
"step": 141
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.32,
|
304 |
+
"learning_rate": 0.0003410563654946854,
|
305 |
+
"loss": 5.5443,
|
306 |
+
"step": 144
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.33,
|
310 |
+
"learning_rate": 0.0003375582590180435,
|
311 |
+
"loss": 5.4449,
|
312 |
+
"step": 147
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.34,
|
316 |
+
"learning_rate": 0.0003341656275960571,
|
317 |
+
"loss": 5.5276,
|
318 |
+
"step": 150
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.34,
|
322 |
+
"learning_rate": 0.0003308732751114942,
|
323 |
+
"loss": 5.6636,
|
324 |
+
"step": 153
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.35,
|
328 |
+
"learning_rate": 0.000327676356900822,
|
329 |
+
"loss": 5.4768,
|
330 |
+
"step": 156
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.36,
|
334 |
+
"learning_rate": 0.00032457034976979266,
|
335 |
+
"loss": 5.4652,
|
336 |
+
"step": 159
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 0.36,
|
340 |
+
"learning_rate": 0.00032155102507750626,
|
341 |
+
"loss": 5.3164,
|
342 |
+
"step": 162
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.37,
|
346 |
+
"learning_rate": 0.00031861442452461495,
|
347 |
+
"loss": 5.4037,
|
348 |
+
"step": 165
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.38,
|
352 |
+
"learning_rate": 0.0003157568383303535,
|
353 |
+
"loss": 5.4498,
|
354 |
+
"step": 168
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.38,
|
358 |
+
"learning_rate": 0.00031297478552475916,
|
359 |
+
"loss": 5.324,
|
360 |
+
"step": 171
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.39,
|
364 |
+
"learning_rate": 0.00031026499611798295,
|
365 |
+
"loss": 5.315,
|
366 |
+
"step": 174
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.4,
|
370 |
+
"learning_rate": 0.0003076243949389936,
|
371 |
+
"loss": 5.3265,
|
372 |
+
"step": 177
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 0.4,
|
376 |
+
"learning_rate": 0.0003050500869620521,
|
377 |
+
"loss": 5.3672,
|
378 |
+
"step": 180
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.41,
|
382 |
+
"learning_rate": 0.0003025393439617544,
|
383 |
+
"loss": 5.4474,
|
384 |
+
"step": 183
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.42,
|
388 |
+
"learning_rate": 0.000300089592356783,
|
389 |
+
"loss": 5.1284,
|
390 |
+
"step": 186
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.42,
|
394 |
+
"learning_rate": 0.00029769840211922306,
|
395 |
+
"loss": 5.3965,
|
396 |
+
"step": 189
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.43,
|
400 |
+
"learning_rate": 0.000295363476640788,
|
401 |
+
"loss": 5.3393,
|
402 |
+
"step": 192
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.44,
|
406 |
+
"learning_rate": 0.0002930826434598881,
|
407 |
+
"loss": 5.303,
|
408 |
+
"step": 195
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.44,
|
412 |
+
"learning_rate": 0.0002908538457644313,
|
413 |
+
"loss": 5.2531,
|
414 |
+
"step": 198
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.45,
|
418 |
+
"eval_accuracy": 0.3039560332193454,
|
419 |
+
"eval_loss": 4.939572811126709,
|
420 |
+
"eval_runtime": 15.0765,
|
421 |
+
"eval_samples_per_second": 33.164,
|
422 |
+
"eval_steps_per_second": 16.582,
|
423 |
+
"step": 200
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.45,
|
427 |
+
"learning_rate": 0.00028867513459481295,
|
428 |
+
"loss": 5.3185,
|
429 |
+
"step": 201
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.46,
|
433 |
+
"learning_rate": 0.00028654466167991145,
|
434 |
+
"loss": 5.3985,
|
435 |
+
"step": 204
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.47,
|
439 |
+
"learning_rate": 0.00028446067284623944,
|
440 |
+
"loss": 5.1464,
|
441 |
+
"step": 207
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.47,
|
445 |
+
"learning_rate": 0.0002824215019468326,
|
446 |
+
"loss": 5.4369,
|
447 |
+
"step": 210
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.48,
|
451 |
+
"learning_rate": 0.0002804255652621247,
|
452 |
+
"loss": 5.1641,
|
453 |
+
"step": 213
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.49,
|
457 |
+
"learning_rate": 0.0002784713563300476,
|
458 |
+
"loss": 5.2121,
|
459 |
+
"step": 216
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.49,
|
463 |
+
"learning_rate": 0.0002765574411670027,
|
464 |
+
"loss": 5.2232,
|
465 |
+
"step": 219
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.5,
|
469 |
+
"learning_rate": 0.00027468245384525467,
|
470 |
+
"loss": 5.4016,
|
471 |
+
"step": 222
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.51,
|
475 |
+
"learning_rate": 0.00027284509239574835,
|
476 |
+
"loss": 5.1446,
|
477 |
+
"step": 225
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.51,
|
481 |
+
"learning_rate": 0.0002710441150084276,
|
482 |
+
"loss": 5.1719,
|
483 |
+
"step": 228
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.52,
|
487 |
+
"learning_rate": 0.0002692783365048561,
|
488 |
+
"loss": 5.3019,
|
489 |
+
"step": 231
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.53,
|
493 |
+
"learning_rate": 0.00026754662506037446,
|
494 |
+
"loss": 5.2286,
|
495 |
+
"step": 234
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.53,
|
499 |
+
"learning_rate": 0.0002658478991551975,
|
500 |
+
"loss": 5.2272,
|
501 |
+
"step": 237
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.54,
|
505 |
+
"learning_rate": 0.0002641811247357893,
|
506 |
+
"loss": 5.282,
|
507 |
+
"step": 240
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.55,
|
511 |
+
"learning_rate": 0.00026254531256958934,
|
512 |
+
"loss": 4.952,
|
513 |
+
"step": 243
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.55,
|
517 |
+
"learning_rate": 0.0002609395157777161,
|
518 |
+
"loss": 5.1267,
|
519 |
+
"step": 246
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.56,
|
523 |
+
"learning_rate": 0.00025936282753166636,
|
524 |
+
"loss": 5.1316,
|
525 |
+
"step": 249
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.57,
|
529 |
+
"learning_rate": 0.0002578143789012823,
|
530 |
+
"loss": 4.9848,
|
531 |
+
"step": 252
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.57,
|
535 |
+
"learning_rate": 0.00025629333684238444,
|
536 |
+
"loss": 4.7754,
|
537 |
+
"step": 255
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.58,
|
541 |
+
"learning_rate": 0.0002547989023134814,
|
542 |
+
"loss": 5.2225,
|
543 |
+
"step": 258
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.59,
|
547 |
+
"learning_rate": 0.0002533303085118872,
|
548 |
+
"loss": 5.1217,
|
549 |
+
"step": 261
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.59,
|
553 |
+
"learning_rate": 0.0002518868192203985,
|
554 |
+
"loss": 4.8745,
|
555 |
+
"step": 264
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.6,
|
559 |
+
"learning_rate": 0.0002504677272564347,
|
560 |
+
"loss": 5.0165,
|
561 |
+
"step": 267
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.61,
|
565 |
+
"learning_rate": 0.00024907235301622105,
|
566 |
+
"loss": 5.0835,
|
567 |
+
"step": 270
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.61,
|
571 |
+
"learning_rate": 0.0002477000431072053,
|
572 |
+
"loss": 5.2976,
|
573 |
+
"step": 273
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.62,
|
577 |
+
"learning_rate": 0.0002463501690624576,
|
578 |
+
"loss": 4.7942,
|
579 |
+
"step": 276
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.63,
|
583 |
+
"learning_rate": 0.0002450221261313084,
|
584 |
+
"loss": 5.0896,
|
585 |
+
"step": 279
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.63,
|
589 |
+
"learning_rate": 0.00024371533214093726,
|
590 |
+
"loss": 5.0112,
|
591 |
+
"step": 282
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.64,
|
595 |
+
"learning_rate": 0.0002424292264240461,
|
596 |
+
"loss": 4.9796,
|
597 |
+
"step": 285
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.65,
|
601 |
+
"learning_rate": 0.00024116326880812967,
|
602 |
+
"loss": 5.1468,
|
603 |
+
"step": 288
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.65,
|
607 |
+
"learning_rate": 0.0002399169386622059,
|
608 |
+
"loss": 4.7967,
|
609 |
+
"step": 291
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.66,
|
613 |
+
"learning_rate": 0.00023868973399718358,
|
614 |
+
"loss": 4.973,
|
615 |
+
"step": 294
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.67,
|
619 |
+
"learning_rate": 0.00023748117061633836,
|
620 |
+
"loss": 5.1543,
|
621 |
+
"step": 297
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.67,
|
625 |
+
"learning_rate": 0.00023629078131263043,
|
626 |
+
"loss": 4.8465,
|
627 |
+
"step": 300
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.67,
|
631 |
+
"eval_accuracy": 0.333695163654128,
|
632 |
+
"eval_loss": 4.60669469833374,
|
633 |
+
"eval_runtime": 15.1591,
|
634 |
+
"eval_samples_per_second": 32.984,
|
635 |
+
"eval_steps_per_second": 16.492,
|
636 |
+
"step": 300
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.68,
|
640 |
+
"learning_rate": 0.0002351181151098428,
|
641 |
+
"loss": 4.8838,
|
642 |
+
"step": 303
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.69,
|
646 |
+
"learning_rate": 0.00023396273654473972,
|
647 |
+
"loss": 4.8887,
|
648 |
+
"step": 306
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.69,
|
652 |
+
"learning_rate": 0.00023282422498765095,
|
653 |
+
"loss": 4.9501,
|
654 |
+
"step": 309
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.7,
|
658 |
+
"learning_rate": 0.0002317021739990746,
|
659 |
+
"loss": 4.7838,
|
660 |
+
"step": 312
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.71,
|
664 |
+
"learning_rate": 0.00023059619072006193,
|
665 |
+
"loss": 4.9579,
|
666 |
+
"step": 315
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.71,
|
670 |
+
"learning_rate": 0.00022950589529430995,
|
671 |
+
"loss": 4.8143,
|
672 |
+
"step": 318
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.72,
|
676 |
+
"learning_rate": 0.00022843092032002904,
|
677 |
+
"loss": 4.8685,
|
678 |
+
"step": 321
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.73,
|
682 |
+
"learning_rate": 0.00022737091032979027,
|
683 |
+
"loss": 4.782,
|
684 |
+
"step": 324
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.73,
|
688 |
+
"learning_rate": 0.00022632552129668023,
|
689 |
+
"loss": 4.9198,
|
690 |
+
"step": 327
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.74,
|
694 |
+
"learning_rate": 0.00022529442016520462,
|
695 |
+
"loss": 5.005,
|
696 |
+
"step": 330
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.75,
|
700 |
+
"learning_rate": 0.00022427728440548833,
|
701 |
+
"loss": 4.9693,
|
702 |
+
"step": 333
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.75,
|
706 |
+
"learning_rate": 0.00022327380158941728,
|
707 |
+
"loss": 4.9218,
|
708 |
+
"step": 336
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 0.76,
|
712 |
+
"learning_rate": 0.00022228366898745637,
|
713 |
+
"loss": 4.9192,
|
714 |
+
"step": 339
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.77,
|
718 |
+
"learning_rate": 0.00022130659318496252,
|
719 |
+
"loss": 4.8076,
|
720 |
+
"step": 342
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.78,
|
724 |
+
"learning_rate": 0.00022034228971688836,
|
725 |
+
"loss": 4.7961,
|
726 |
+
"step": 345
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.78,
|
730 |
+
"learning_rate": 0.0002193904827198436,
|
731 |
+
"loss": 4.5936,
|
732 |
+
"step": 348
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.79,
|
736 |
+
"learning_rate": 0.00021845090460054803,
|
737 |
+
"loss": 4.8138,
|
738 |
+
"step": 351
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.8,
|
742 |
+
"learning_rate": 0.00021752329571977103,
|
743 |
+
"loss": 4.7873,
|
744 |
+
"step": 354
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.8,
|
748 |
+
"learning_rate": 0.00021660740409091007,
|
749 |
+
"loss": 4.8076,
|
750 |
+
"step": 357
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.81,
|
754 |
+
"learning_rate": 0.0002157029850924131,
|
755 |
+
"loss": 4.6999,
|
756 |
+
"step": 360
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.82,
|
760 |
+
"learning_rate": 0.00021480980119330037,
|
761 |
+
"loss": 4.8198,
|
762 |
+
"step": 363
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.82,
|
766 |
+
"learning_rate": 0.00021392762169108589,
|
767 |
+
"loss": 4.7778,
|
768 |
+
"step": 366
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.83,
|
772 |
+
"learning_rate": 0.0002130562224614416,
|
773 |
+
"loss": 4.8642,
|
774 |
+
"step": 369
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.84,
|
778 |
+
"learning_rate": 0.00021219538571898804,
|
779 |
+
"loss": 4.934,
|
780 |
+
"step": 372
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.84,
|
784 |
+
"learning_rate": 0.00021134489978863144,
|
785 |
+
"loss": 4.777,
|
786 |
+
"step": 375
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.85,
|
790 |
+
"learning_rate": 0.0002105045588869023,
|
791 |
+
"loss": 4.7246,
|
792 |
+
"step": 378
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.86,
|
796 |
+
"learning_rate": 0.00020967416291278203,
|
797 |
+
"loss": 4.6483,
|
798 |
+
"step": 381
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.86,
|
802 |
+
"learning_rate": 0.00020885351724753563,
|
803 |
+
"loss": 4.688,
|
804 |
+
"step": 384
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.87,
|
808 |
+
"learning_rate": 0.00020804243256309523,
|
809 |
+
"loss": 4.7668,
|
810 |
+
"step": 387
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.88,
|
814 |
+
"learning_rate": 0.00020724072463856603,
|
815 |
+
"loss": 4.7151,
|
816 |
+
"step": 390
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.88,
|
820 |
+
"learning_rate": 0.00020644821418445137,
|
821 |
+
"loss": 4.5894,
|
822 |
+
"step": 393
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.89,
|
826 |
+
"learning_rate": 0.00020566472667421558,
|
827 |
+
"loss": 4.8375,
|
828 |
+
"step": 396
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.9,
|
832 |
+
"learning_rate": 0.00020489009218282547,
|
833 |
+
"loss": 4.7991,
|
834 |
+
"step": 399
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.9,
|
838 |
+
"eval_accuracy": 0.35269369809477286,
|
839 |
+
"eval_loss": 4.39344596862793,
|
840 |
+
"eval_runtime": 15.1249,
|
841 |
+
"eval_samples_per_second": 33.058,
|
842 |
+
"eval_steps_per_second": 16.529,
|
843 |
+
"step": 400
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.9,
|
847 |
+
"learning_rate": 0.00020412414523193154,
|
848 |
+
"loss": 4.857,
|
849 |
+
"step": 402
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.91,
|
853 |
+
"learning_rate": 0.00020336672464136806,
|
854 |
+
"loss": 4.9338,
|
855 |
+
"step": 405
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.92,
|
859 |
+
"learning_rate": 0.00020261767338667041,
|
860 |
+
"loss": 4.6781,
|
861 |
+
"step": 408
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.92,
|
865 |
+
"learning_rate": 0.00020187683846232233,
|
866 |
+
"loss": 4.7474,
|
867 |
+
"step": 411
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.93,
|
871 |
+
"learning_rate": 0.00020114407075046392,
|
872 |
+
"loss": 4.7408,
|
873 |
+
"step": 414
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.94,
|
877 |
+
"learning_rate": 0.00020041922489480405,
|
878 |
+
"loss": 4.8301,
|
879 |
+
"step": 417
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.94,
|
883 |
+
"learning_rate": 0.00019970215917949506,
|
884 |
+
"loss": 4.5838,
|
885 |
+
"step": 420
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.95,
|
889 |
+
"learning_rate": 0.00019899273541274044,
|
890 |
+
"loss": 4.6515,
|
891 |
+
"step": 423
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.96,
|
895 |
+
"learning_rate": 0.0001982908188149191,
|
896 |
+
"loss": 4.7319,
|
897 |
+
"step": 426
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.96,
|
901 |
+
"learning_rate": 0.00019759627791102,
|
902 |
+
"loss": 4.6515,
|
903 |
+
"step": 429
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.97,
|
907 |
+
"learning_rate": 0.000196908984427192,
|
908 |
+
"loss": 4.7311,
|
909 |
+
"step": 432
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.98,
|
913 |
+
"learning_rate": 0.00019622881319122527,
|
914 |
+
"loss": 4.6038,
|
915 |
+
"step": 435
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.98,
|
919 |
+
"learning_rate": 0.00019555564203678732,
|
920 |
+
"loss": 4.7496,
|
921 |
+
"step": 438
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.99,
|
925 |
+
"learning_rate": 0.0001948893517112488,
|
926 |
+
"loss": 4.6959,
|
927 |
+
"step": 441
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.0,
|
931 |
+
"learning_rate": 0.00019422982578694043,
|
932 |
+
"loss": 4.5849,
|
933 |
+
"step": 444
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.0,
|
937 |
+
"learning_rate": 0.00019357695057569082,
|
938 |
+
"loss": 4.655,
|
939 |
+
"step": 447
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.01,
|
943 |
+
"learning_rate": 0.00019293061504650376,
|
944 |
+
"loss": 4.7408,
|
945 |
+
"step": 450
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 1.02,
|
949 |
+
"learning_rate": 0.00019229071074623857,
|
950 |
+
"loss": 4.7902,
|
951 |
+
"step": 453
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 1.02,
|
955 |
+
"learning_rate": 0.00019165713172316568,
|
956 |
+
"loss": 4.6149,
|
957 |
+
"step": 456
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.03,
|
961 |
+
"learning_rate": 0.0001910297744532743,
|
962 |
+
"loss": 4.6644,
|
963 |
+
"step": 459
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 1.04,
|
967 |
+
"learning_rate": 0.00019040853776921678,
|
968 |
+
"loss": 4.613,
|
969 |
+
"step": 462
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.04,
|
973 |
+
"learning_rate": 0.00018979332279177815,
|
974 |
+
"loss": 4.542,
|
975 |
+
"step": 465
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 1.05,
|
979 |
+
"learning_rate": 0.00018918403286376548,
|
980 |
+
"loss": 4.7666,
|
981 |
+
"step": 468
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 1.06,
|
985 |
+
"learning_rate": 0.00018858057348621743,
|
986 |
+
"loss": 4.6471,
|
987 |
+
"step": 471
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 1.06,
|
991 |
+
"learning_rate": 0.0001879828522568376,
|
992 |
+
"loss": 4.5803,
|
993 |
+
"step": 474
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 1.07,
|
997 |
+
"learning_rate": 0.00018739077881056078,
|
998 |
+
"loss": 4.5415,
|
999 |
+
"step": 477
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 1.08,
|
1003 |
+
"learning_rate": 0.0001868042647621658,
|
1004 |
+
"loss": 4.5641,
|
1005 |
+
"step": 480
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 1.09,
|
1009 |
+
"learning_rate": 0.00018622322365085167,
|
1010 |
+
"loss": 4.6407,
|
1011 |
+
"step": 483
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 1.09,
|
1015 |
+
"learning_rate": 0.00018564757088669834,
|
1016 |
+
"loss": 4.7945,
|
1017 |
+
"step": 486
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.1,
|
1021 |
+
"learning_rate": 0.00018507722369893691,
|
1022 |
+
"loss": 4.4922,
|
1023 |
+
"step": 489
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 1.11,
|
1027 |
+
"learning_rate": 0.00018451210108595716,
|
1028 |
+
"loss": 4.4105,
|
1029 |
+
"step": 492
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.11,
|
1033 |
+
"learning_rate": 0.0001839521237669841,
|
1034 |
+
"loss": 4.5781,
|
1035 |
+
"step": 495
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 1.12,
|
1039 |
+
"learning_rate": 0.00018339721413535823,
|
1040 |
+
"loss": 4.2787,
|
1041 |
+
"step": 498
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 1.12,
|
1045 |
+
"eval_accuracy": 0.36416707376648755,
|
1046 |
+
"eval_loss": 4.238906383514404,
|
1047 |
+
"eval_runtime": 15.1858,
|
1048 |
+
"eval_samples_per_second": 32.925,
|
1049 |
+
"eval_steps_per_second": 16.463,
|
1050 |
+
"step": 500
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 1.13,
|
1054 |
+
"learning_rate": 0.0001828472962133565,
|
1055 |
+
"loss": 4.4456,
|
1056 |
+
"step": 501
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 1.13,
|
1060 |
+
"learning_rate": 0.0001823022956084947,
|
1061 |
+
"loss": 4.5287,
|
1062 |
+
"step": 504
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 1.14,
|
1066 |
+
"learning_rate": 0.00018176213947125418,
|
1067 |
+
"loss": 4.5194,
|
1068 |
+
"step": 507
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 1.15,
|
1072 |
+
"learning_rate": 0.00018122675645417804,
|
1073 |
+
"loss": 4.4069,
|
1074 |
+
"step": 510
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 1.15,
|
1078 |
+
"learning_rate": 0.0001806960766722851,
|
1079 |
+
"loss": 4.6053,
|
1080 |
+
"step": 513
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.16,
|
1084 |
+
"learning_rate": 0.0001801700316647514,
|
1085 |
+
"loss": 4.4653,
|
1086 |
+
"step": 516
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 1.17,
|
1090 |
+
"learning_rate": 0.00017964855435781174,
|
1091 |
+
"loss": 4.3869,
|
1092 |
+
"step": 519
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 1.17,
|
1096 |
+
"learning_rate": 0.0001791315790288356,
|
1097 |
+
"loss": 4.5346,
|
1098 |
+
"step": 522
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 1.18,
|
1102 |
+
"learning_rate": 0.00017861904127153383,
|
1103 |
+
"loss": 4.3397,
|
1104 |
+
"step": 525
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 1.19,
|
1108 |
+
"learning_rate": 0.00017811087796225377,
|
1109 |
+
"loss": 4.4981,
|
1110 |
+
"step": 528
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 1.19,
|
1114 |
+
"learning_rate": 0.00017760702722732373,
|
1115 |
+
"loss": 4.4315,
|
1116 |
+
"step": 531
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 1.2,
|
1120 |
+
"learning_rate": 0.0001771074284114076,
|
1121 |
+
"loss": 4.4401,
|
1122 |
+
"step": 534
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.21,
|
1126 |
+
"learning_rate": 0.00017661202204683334,
|
1127 |
+
"loss": 4.2521,
|
1128 |
+
"step": 537
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 1.21,
|
1132 |
+
"learning_rate": 0.00017612074982385957,
|
1133 |
+
"loss": 4.663,
|
1134 |
+
"step": 540
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 1.22,
|
1138 |
+
"learning_rate": 0.00017563355456184752,
|
1139 |
+
"loss": 4.5429,
|
1140 |
+
"step": 543
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 1.23,
|
1144 |
+
"learning_rate": 0.00017515038018130498,
|
1145 |
+
"loss": 4.6201,
|
1146 |
+
"step": 546
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 1.23,
|
1150 |
+
"learning_rate": 0.00017467117167677167,
|
1151 |
+
"loss": 4.5178,
|
1152 |
+
"step": 549
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 1.24,
|
1156 |
+
"learning_rate": 0.0001741958750905162,
|
1157 |
+
"loss": 4.4457,
|
1158 |
+
"step": 552
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 1.25,
|
1162 |
+
"learning_rate": 0.00017372443748701614,
|
1163 |
+
"loss": 4.4784,
|
1164 |
+
"step": 555
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.25,
|
1168 |
+
"learning_rate": 0.00017325680692819372,
|
1169 |
+
"loss": 4.6209,
|
1170 |
+
"step": 558
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 1.26,
|
1174 |
+
"learning_rate": 0.00017279293244938095,
|
1175 |
+
"loss": 4.4459,
|
1176 |
+
"step": 561
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 1.27,
|
1180 |
+
"learning_rate": 0.0001723327640359885,
|
1181 |
+
"loss": 4.4116,
|
1182 |
+
"step": 564
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 1.27,
|
1186 |
+
"learning_rate": 0.0001718762526008549,
|
1187 |
+
"loss": 4.414,
|
1188 |
+
"step": 567
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 1.28,
|
1192 |
+
"learning_rate": 0.00017142334996225191,
|
1193 |
+
"loss": 4.6379,
|
1194 |
+
"step": 570
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 1.29,
|
1198 |
+
"learning_rate": 0.00017097400882252448,
|
1199 |
+
"loss": 4.4434,
|
1200 |
+
"step": 573
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 1.29,
|
1204 |
+
"learning_rate": 0.0001705281827473427,
|
1205 |
+
"loss": 4.3952,
|
1206 |
+
"step": 576
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 1.3,
|
1210 |
+
"learning_rate": 0.00017008582614554666,
|
1211 |
+
"loss": 4.2903,
|
1212 |
+
"step": 579
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 1.31,
|
1216 |
+
"learning_rate": 0.0001696468942495628,
|
1217 |
+
"loss": 4.5144,
|
1218 |
+
"step": 582
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 1.31,
|
1222 |
+
"learning_rate": 0.0001692113430963735,
|
1223 |
+
"loss": 4.3821,
|
1224 |
+
"step": 585
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.32,
|
1228 |
+
"learning_rate": 0.00016877912950902176,
|
1229 |
+
"loss": 4.5597,
|
1230 |
+
"step": 588
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 1.33,
|
1234 |
+
"learning_rate": 0.00016835021107863206,
|
1235 |
+
"loss": 4.4296,
|
1236 |
+
"step": 591
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 1.33,
|
1240 |
+
"learning_rate": 0.00016792454614693233,
|
1241 |
+
"loss": 4.2632,
|
1242 |
+
"step": 594
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 1.34,
|
1246 |
+
"learning_rate": 0.00016750209378925862,
|
1247 |
+
"loss": 4.2681,
|
1248 |
+
"step": 597
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.35,
|
1252 |
+
"learning_rate": 0.00016708281379802854,
|
1253 |
+
"loss": 4.4893,
|
1254 |
+
"step": 600
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 1.35,
|
1258 |
+
"eval_accuracy": 0.3719882755251588,
|
1259 |
+
"eval_loss": 4.1261677742004395,
|
1260 |
+
"eval_runtime": 15.1896,
|
1261 |
+
"eval_samples_per_second": 32.917,
|
1262 |
+
"eval_steps_per_second": 16.459,
|
1263 |
+
"step": 600
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.35,
|
1267 |
+
"learning_rate": 0.00016666666666666666,
|
1268 |
+
"loss": 4.4189,
|
1269 |
+
"step": 603
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.36,
|
1273 |
+
"learning_rate": 0.00016625361357396908,
|
1274 |
+
"loss": 4.3687,
|
1275 |
+
"step": 606
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 1.37,
|
1279 |
+
"learning_rate": 0.0001658436163688913,
|
1280 |
+
"loss": 4.5189,
|
1281 |
+
"step": 609
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.37,
|
1285 |
+
"learning_rate": 0.0001654366375557471,
|
1286 |
+
"loss": 4.3339,
|
1287 |
+
"step": 612
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.38,
|
1291 |
+
"learning_rate": 0.00016503264027980518,
|
1292 |
+
"loss": 4.3293,
|
1293 |
+
"step": 615
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 1.39,
|
1297 |
+
"learning_rate": 0.00016463158831327043,
|
1298 |
+
"loss": 4.4765,
|
1299 |
+
"step": 618
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.4,
|
1303 |
+
"learning_rate": 0.00016423344604163842,
|
1304 |
+
"loss": 4.4114,
|
1305 |
+
"step": 621
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.4,
|
1309 |
+
"learning_rate": 0.000163838178450411,
|
1310 |
+
"loss": 4.4124,
|
1311 |
+
"step": 624
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.41,
|
1315 |
+
"learning_rate": 0.00016344575111216204,
|
1316 |
+
"loss": 4.4381,
|
1317 |
+
"step": 627
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 1.42,
|
1321 |
+
"learning_rate": 0.00016305613017394223,
|
1322 |
+
"loss": 4.3048,
|
1323 |
+
"step": 630
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.42,
|
1327 |
+
"learning_rate": 0.0001626692823450125,
|
1328 |
+
"loss": 4.4025,
|
1329 |
+
"step": 633
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.43,
|
1333 |
+
"learning_rate": 0.00016228517488489633,
|
1334 |
+
"loss": 4.4779,
|
1335 |
+
"step": 636
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 1.44,
|
1339 |
+
"learning_rate": 0.00016190377559174065,
|
1340 |
+
"loss": 4.3395,
|
1341 |
+
"step": 639
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.44,
|
1345 |
+
"learning_rate": 0.00016152505279097643,
|
1346 |
+
"loss": 4.4437,
|
1347 |
+
"step": 642
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.45,
|
1351 |
+
"learning_rate": 0.00016114897532426946,
|
1352 |
+
"loss": 4.4231,
|
1353 |
+
"step": 645
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.46,
|
1357 |
+
"learning_rate": 0.00016077551253875313,
|
1358 |
+
"loss": 4.284,
|
1359 |
+
"step": 648
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.46,
|
1363 |
+
"learning_rate": 0.00016040463427653402,
|
1364 |
+
"loss": 4.2703,
|
1365 |
+
"step": 651
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.47,
|
1369 |
+
"learning_rate": 0.00016003631086446298,
|
1370 |
+
"loss": 4.5442,
|
1371 |
+
"step": 654
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.48,
|
1375 |
+
"learning_rate": 0.00015967051310416313,
|
1376 |
+
"loss": 4.4264,
|
1377 |
+
"step": 657
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.48,
|
1381 |
+
"learning_rate": 0.00015930721226230747,
|
1382 |
+
"loss": 4.4124,
|
1383 |
+
"step": 660
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.49,
|
1387 |
+
"learning_rate": 0.00015894638006113876,
|
1388 |
+
"loss": 4.2462,
|
1389 |
+
"step": 663
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.5,
|
1393 |
+
"learning_rate": 0.0001585879886692247,
|
1394 |
+
"loss": 4.4239,
|
1395 |
+
"step": 666
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.5,
|
1399 |
+
"learning_rate": 0.00015823201069244109,
|
1400 |
+
"loss": 4.3737,
|
1401 |
+
"step": 669
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.51,
|
1405 |
+
"learning_rate": 0.00015787841916517674,
|
1406 |
+
"loss": 4.3488,
|
1407 |
+
"step": 672
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 1.52,
|
1411 |
+
"learning_rate": 0.00015752718754175364,
|
1412 |
+
"loss": 4.3232,
|
1413 |
+
"step": 675
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.52,
|
1417 |
+
"learning_rate": 0.0001571782896880563,
|
1418 |
+
"loss": 4.3468,
|
1419 |
+
"step": 678
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.53,
|
1423 |
+
"learning_rate": 0.00015683169987336384,
|
1424 |
+
"loss": 4.2461,
|
1425 |
+
"step": 681
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.54,
|
1429 |
+
"learning_rate": 0.00015648739276237958,
|
1430 |
+
"loss": 4.3453,
|
1431 |
+
"step": 684
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.54,
|
1435 |
+
"learning_rate": 0.00015614534340745214,
|
1436 |
+
"loss": 4.3133,
|
1437 |
+
"step": 687
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.55,
|
1441 |
+
"learning_rate": 0.00015580552724098266,
|
1442 |
+
"loss": 4.4003,
|
1443 |
+
"step": 690
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 1.56,
|
1447 |
+
"learning_rate": 0.0001554679200680133,
|
1448 |
+
"loss": 4.4224,
|
1449 |
+
"step": 693
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.56,
|
1453 |
+
"learning_rate": 0.00015513249805899147,
|
1454 |
+
"loss": 4.3176,
|
1455 |
+
"step": 696
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 1.57,
|
1459 |
+
"learning_rate": 0.00015479923774270487,
|
1460 |
+
"loss": 4.346,
|
1461 |
+
"step": 699
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 1.57,
|
1465 |
+
"eval_accuracy": 0.3792750366389839,
|
1466 |
+
"eval_loss": 4.030762672424316,
|
1467 |
+
"eval_runtime": 15.1012,
|
1468 |
+
"eval_samples_per_second": 33.11,
|
1469 |
+
"eval_steps_per_second": 16.555,
|
1470 |
+
"step": 700
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 1.58,
|
1474 |
+
"learning_rate": 0.00015446811599938306,
|
1475 |
+
"loss": 4.4625,
|
1476 |
+
"step": 702
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 1.58,
|
1480 |
+
"learning_rate": 0.00015413911005396052,
|
1481 |
+
"loss": 4.3274,
|
1482 |
+
"step": 705
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 1.59,
|
1486 |
+
"learning_rate": 0.0001538121974694968,
|
1487 |
+
"loss": 4.4441,
|
1488 |
+
"step": 708
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 1.6,
|
1492 |
+
"learning_rate": 0.00015348735614074976,
|
1493 |
+
"loss": 4.1558,
|
1494 |
+
"step": 711
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.6,
|
1498 |
+
"learning_rate": 0.0001531645642878972,
|
1499 |
+
"loss": 4.3941,
|
1500 |
+
"step": 714
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 1.61,
|
1504 |
+
"learning_rate": 0.0001528438004504034,
|
1505 |
+
"loss": 4.1691,
|
1506 |
+
"step": 717
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 1.62,
|
1510 |
+
"learning_rate": 0.00015252504348102605,
|
1511 |
+
"loss": 4.4237,
|
1512 |
+
"step": 720
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 1.62,
|
1516 |
+
"learning_rate": 0.0001522082725399605,
|
1517 |
+
"loss": 4.314,
|
1518 |
+
"step": 723
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 1.63,
|
1522 |
+
"learning_rate": 0.00015189346708911682,
|
1523 |
+
"loss": 4.2329,
|
1524 |
+
"step": 726
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 1.64,
|
1528 |
+
"learning_rate": 0.00015158060688652685,
|
1529 |
+
"loss": 4.2591,
|
1530 |
+
"step": 729
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 1.64,
|
1534 |
+
"learning_rate": 0.0001512696719808772,
|
1535 |
+
"loss": 4.3707,
|
1536 |
+
"step": 732
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 1.65,
|
1540 |
+
"learning_rate": 0.00015096064270616534,
|
1541 |
+
"loss": 4.3054,
|
1542 |
+
"step": 735
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 1.66,
|
1546 |
+
"learning_rate": 0.000150653499676475,
|
1547 |
+
"loss": 4.466,
|
1548 |
+
"step": 738
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 1.66,
|
1552 |
+
"learning_rate": 0.00015034822378086837,
|
1553 |
+
"loss": 4.2339,
|
1554 |
+
"step": 741
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.67,
|
1558 |
+
"learning_rate": 0.0001500447961783915,
|
1559 |
+
"loss": 4.2401,
|
1560 |
+
"step": 744
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 1.68,
|
1564 |
+
"learning_rate": 0.00014974319829319003,
|
1565 |
+
"loss": 4.1819,
|
1566 |
+
"step": 747
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 1.68,
|
1570 |
+
"learning_rate": 0.00014944341180973263,
|
1571 |
+
"loss": 4.2786,
|
1572 |
+
"step": 750
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 1.69,
|
1576 |
+
"learning_rate": 0.0001491454186681393,
|
1577 |
+
"loss": 4.3168,
|
1578 |
+
"step": 753
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.7,
|
1582 |
+
"learning_rate": 0.00014884920105961153,
|
1583 |
+
"loss": 4.266,
|
1584 |
+
"step": 756
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 1.71,
|
1588 |
+
"learning_rate": 0.00014855474142196195,
|
1589 |
+
"loss": 4.1603,
|
1590 |
+
"step": 759
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 1.71,
|
1594 |
+
"learning_rate": 0.00014826202243524108,
|
1595 |
+
"loss": 4.2068,
|
1596 |
+
"step": 762
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 1.72,
|
1600 |
+
"learning_rate": 0.00014797102701745806,
|
1601 |
+
"loss": 4.1314,
|
1602 |
+
"step": 765
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.73,
|
1606 |
+
"learning_rate": 0.000147681738320394,
|
1607 |
+
"loss": 4.201,
|
1608 |
+
"step": 768
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 1.73,
|
1612 |
+
"learning_rate": 0.00014739413972550443,
|
1613 |
+
"loss": 4.1408,
|
1614 |
+
"step": 771
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.74,
|
1618 |
+
"learning_rate": 0.00014710821483990966,
|
1619 |
+
"loss": 4.1985,
|
1620 |
+
"step": 774
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.75,
|
1624 |
+
"learning_rate": 0.0001468239474924699,
|
1625 |
+
"loss": 4.3132,
|
1626 |
+
"step": 777
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.75,
|
1630 |
+
"learning_rate": 0.00014654132172994404,
|
1631 |
+
"loss": 4.1763,
|
1632 |
+
"step": 780
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.76,
|
1636 |
+
"learning_rate": 0.00014626032181322903,
|
1637 |
+
"loss": 4.2122,
|
1638 |
+
"step": 783
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 1.77,
|
1642 |
+
"learning_rate": 0.00014598093221367836,
|
1643 |
+
"loss": 4.0161,
|
1644 |
+
"step": 786
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 1.77,
|
1648 |
+
"learning_rate": 0.0001457031376094977,
|
1649 |
+
"loss": 4.3279,
|
1650 |
+
"step": 789
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 1.78,
|
1654 |
+
"learning_rate": 0.00014542692288221565,
|
1655 |
+
"loss": 4.26,
|
1656 |
+
"step": 792
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 1.79,
|
1660 |
+
"learning_rate": 0.0001451522731132279,
|
1661 |
+
"loss": 4.2826,
|
1662 |
+
"step": 795
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 1.79,
|
1666 |
+
"learning_rate": 0.00014487917358041273,
|
1667 |
+
"loss": 4.1878,
|
1668 |
+
"step": 798
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 1.8,
|
1672 |
+
"eval_accuracy": 0.3845920859794822,
|
1673 |
+
"eval_loss": 3.957355499267578,
|
1674 |
+
"eval_runtime": 15.1878,
|
1675 |
+
"eval_samples_per_second": 32.921,
|
1676 |
+
"eval_steps_per_second": 16.461,
|
1677 |
+
"step": 800
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 1.8,
|
1681 |
+
"learning_rate": 0.00014460760975481632,
|
1682 |
+
"loss": 4.3063,
|
1683 |
+
"step": 801
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.81,
|
1687 |
+
"learning_rate": 0.00014433756729740648,
|
1688 |
+
"loss": 4.1148,
|
1689 |
+
"step": 804
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.81,
|
1693 |
+
"learning_rate": 0.00014406903205589218,
|
1694 |
+
"loss": 4.1089,
|
1695 |
+
"step": 807
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 1.82,
|
1699 |
+
"learning_rate": 0.00014380199006160872,
|
1700 |
+
"loss": 4.1745,
|
1701 |
+
"step": 810
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.83,
|
1705 |
+
"learning_rate": 0.00014353642752646544,
|
1706 |
+
"loss": 4.2486,
|
1707 |
+
"step": 813
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.83,
|
1711 |
+
"learning_rate": 0.00014327233083995573,
|
1712 |
+
"loss": 4.2344,
|
1713 |
+
"step": 816
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 1.84,
|
1717 |
+
"learning_rate": 0.00014300968656622687,
|
1718 |
+
"loss": 4.0578,
|
1719 |
+
"step": 819
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.85,
|
1723 |
+
"learning_rate": 0.00014274848144120935,
|
1724 |
+
"loss": 4.2833,
|
1725 |
+
"step": 822
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.85,
|
1729 |
+
"learning_rate": 0.000142488702369803,
|
1730 |
+
"loss": 4.1856,
|
1731 |
+
"step": 825
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.86,
|
1735 |
+
"learning_rate": 0.00014223033642311972,
|
1736 |
+
"loss": 4.2869,
|
1737 |
+
"step": 828
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.87,
|
1741 |
+
"learning_rate": 0.0001419733708357808,
|
1742 |
+
"loss": 4.1484,
|
1743 |
+
"step": 831
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 1.87,
|
1747 |
+
"learning_rate": 0.00014171779300326768,
|
1748 |
+
"loss": 4.3338,
|
1749 |
+
"step": 834
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.88,
|
1753 |
+
"learning_rate": 0.00014146359047932533,
|
1754 |
+
"loss": 4.0804,
|
1755 |
+
"step": 837
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 1.89,
|
1759 |
+
"learning_rate": 0.0001412107509734163,
|
1760 |
+
"loss": 4.2786,
|
1761 |
+
"step": 840
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 1.89,
|
1765 |
+
"learning_rate": 0.0001409592623482247,
|
1766 |
+
"loss": 4.2871,
|
1767 |
+
"step": 843
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.9,
|
1771 |
+
"learning_rate": 0.0001407091126172092,
|
1772 |
+
"loss": 4.4272,
|
1773 |
+
"step": 846
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.91,
|
1777 |
+
"learning_rate": 0.0001404602899422033,
|
1778 |
+
"loss": 4.1707,
|
1779 |
+
"step": 849
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.91,
|
1783 |
+
"learning_rate": 0.00014021278263106235,
|
1784 |
+
"loss": 4.1172,
|
1785 |
+
"step": 852
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 1.92,
|
1789 |
+
"learning_rate": 0.00013996657913535574,
|
1790 |
+
"loss": 4.3611,
|
1791 |
+
"step": 855
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.93,
|
1795 |
+
"learning_rate": 0.00013972166804810385,
|
1796 |
+
"loss": 4.2268,
|
1797 |
+
"step": 858
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 1.93,
|
1801 |
+
"learning_rate": 0.00013947803810155813,
|
1802 |
+
"loss": 4.1159,
|
1803 |
+
"step": 861
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 1.94,
|
1807 |
+
"learning_rate": 0.0001392356781650238,
|
1808 |
+
"loss": 4.3072,
|
1809 |
+
"step": 864
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.95,
|
1813 |
+
"learning_rate": 0.00013899457724272379,
|
1814 |
+
"loss": 4.1207,
|
1815 |
+
"step": 867
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.95,
|
1819 |
+
"learning_rate": 0.00013875472447170365,
|
1820 |
+
"loss": 4.2149,
|
1821 |
+
"step": 870
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 1.96,
|
1825 |
+
"learning_rate": 0.0001385161091197755,
|
1826 |
+
"loss": 4.2332,
|
1827 |
+
"step": 873
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.97,
|
1831 |
+
"learning_rate": 0.00013827872058350135,
|
1832 |
+
"loss": 4.3785,
|
1833 |
+
"step": 876
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 1.97,
|
1837 |
+
"learning_rate": 0.00013804254838621383,
|
1838 |
+
"loss": 4.2428,
|
1839 |
+
"step": 879
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 1.98,
|
1843 |
+
"learning_rate": 0.0001378075821760741,
|
1844 |
+
"loss": 4.0385,
|
1845 |
+
"step": 882
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.99,
|
1849 |
+
"learning_rate": 0.0001375738117241664,
|
1850 |
+
"loss": 4.3084,
|
1851 |
+
"step": 885
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.99,
|
1855 |
+
"learning_rate": 0.00013734122692262733,
|
1856 |
+
"loss": 4.1674,
|
1857 |
+
"step": 888
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 2.0,
|
1861 |
+
"learning_rate": 0.0001371098177828104,
|
1862 |
+
"loss": 4.2508,
|
1863 |
+
"step": 891
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 2.01,
|
1867 |
+
"learning_rate": 0.00013687957443348414,
|
1868 |
+
"loss": 4.246,
|
1869 |
+
"step": 894
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 2.02,
|
1873 |
+
"learning_rate": 0.0001366504871190636,
|
1874 |
+
"loss": 4.125,
|
1875 |
+
"step": 897
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 2.02,
|
1879 |
+
"learning_rate": 0.00013642254619787418,
|
1880 |
+
"loss": 4.2311,
|
1881 |
+
"step": 900
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 2.02,
|
1885 |
+
"eval_accuracy": 0.38997361993160723,
|
1886 |
+
"eval_loss": 3.894345283508301,
|
1887 |
+
"eval_runtime": 15.1182,
|
1888 |
+
"eval_samples_per_second": 33.073,
|
1889 |
+
"eval_steps_per_second": 16.536,
|
1890 |
+
"step": 900
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 2.03,
|
1894 |
+
"learning_rate": 0.00013619574214044708,
|
1895 |
+
"loss": 3.9819,
|
1896 |
+
"step": 903
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 2.04,
|
1900 |
+
"learning_rate": 0.00013597006552784624,
|
1901 |
+
"loss": 4.1381,
|
1902 |
+
"step": 906
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"epoch": 2.04,
|
1906 |
+
"learning_rate": 0.00013574550705002514,
|
1907 |
+
"loss": 4.1994,
|
1908 |
+
"step": 909
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 2.05,
|
1912 |
+
"learning_rate": 0.0001355220575042138,
|
1913 |
+
"loss": 4.3326,
|
1914 |
+
"step": 912
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 2.06,
|
1918 |
+
"learning_rate": 0.00013529970779333468,
|
1919 |
+
"loss": 4.09,
|
1920 |
+
"step": 915
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 2.06,
|
1924 |
+
"learning_rate": 0.00013507844892444694,
|
1925 |
+
"loss": 4.1256,
|
1926 |
+
"step": 918
|
1927 |
+
},
|
1928 |
+
{
|
1929 |
+
"epoch": 2.07,
|
1930 |
+
"learning_rate": 0.000134858272007219,
|
1931 |
+
"loss": 4.043,
|
1932 |
+
"step": 921
|
1933 |
+
},
|
1934 |
+
{
|
1935 |
+
"epoch": 2.08,
|
1936 |
+
"learning_rate": 0.00013463916825242806,
|
1937 |
+
"loss": 4.1771,
|
1938 |
+
"step": 924
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 2.08,
|
1942 |
+
"learning_rate": 0.00013442112897048627,
|
1943 |
+
"loss": 4.175,
|
1944 |
+
"step": 927
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 2.09,
|
1948 |
+
"learning_rate": 0.00013420414556999363,
|
1949 |
+
"loss": 4.1617,
|
1950 |
+
"step": 930
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 2.1,
|
1954 |
+
"learning_rate": 0.00013398820955631575,
|
1955 |
+
"loss": 4.1036,
|
1956 |
+
"step": 933
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 2.1,
|
1960 |
+
"learning_rate": 0.00013377331253018723,
|
1961 |
+
"loss": 4.1814,
|
1962 |
+
"step": 936
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 2.11,
|
1966 |
+
"learning_rate": 0.00013355944618633945,
|
1967 |
+
"loss": 4.1713,
|
1968 |
+
"step": 939
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 2.12,
|
1972 |
+
"learning_rate": 0.0001333466023121524,
|
1973 |
+
"loss": 3.9674,
|
1974 |
+
"step": 942
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 2.12,
|
1978 |
+
"learning_rate": 0.00013313477278633005,
|
1979 |
+
"loss": 4.1862,
|
1980 |
+
"step": 945
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 2.13,
|
1984 |
+
"learning_rate": 0.00013292394957759875,
|
1985 |
+
"loss": 3.9531,
|
1986 |
+
"step": 948
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 2.14,
|
1990 |
+
"learning_rate": 0.0001327141247434285,
|
1991 |
+
"loss": 4.2624,
|
1992 |
+
"step": 951
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 2.14,
|
1996 |
+
"learning_rate": 0.0001325052904287759,
|
1997 |
+
"loss": 4.2659,
|
1998 |
+
"step": 954
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 2.15,
|
2002 |
+
"learning_rate": 0.0001322974388648493,
|
2003 |
+
"loss": 4.1861,
|
2004 |
+
"step": 957
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 2.16,
|
2008 |
+
"learning_rate": 0.00013209056236789465,
|
2009 |
+
"loss": 4.1348,
|
2010 |
+
"step": 960
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 2.16,
|
2014 |
+
"learning_rate": 0.0001318846533380027,
|
2015 |
+
"loss": 4.0551,
|
2016 |
+
"step": 963
|
2017 |
+
},
|
2018 |
+
{
|
2019 |
+
"epoch": 2.17,
|
2020 |
+
"learning_rate": 0.00013167970425793625,
|
2021 |
+
"loss": 4.1224,
|
2022 |
+
"step": 966
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 2.18,
|
2026 |
+
"learning_rate": 0.00013147570769197746,
|
2027 |
+
"loss": 4.223,
|
2028 |
+
"step": 969
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 2.18,
|
2032 |
+
"learning_rate": 0.00013127265628479467,
|
2033 |
+
"loss": 4.2638,
|
2034 |
+
"step": 972
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 2.19,
|
2038 |
+
"learning_rate": 0.00013107054276032882,
|
2039 |
+
"loss": 4.187,
|
2040 |
+
"step": 975
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 2.2,
|
2044 |
+
"learning_rate": 0.0001308693599206979,
|
2045 |
+
"loss": 4.2086,
|
2046 |
+
"step": 978
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 2.2,
|
2050 |
+
"learning_rate": 0.00013066910064512072,
|
2051 |
+
"loss": 4.0953,
|
2052 |
+
"step": 981
|
2053 |
+
},
|
2054 |
+
{
|
2055 |
+
"epoch": 2.21,
|
2056 |
+
"learning_rate": 0.00013046975788885806,
|
2057 |
+
"loss": 4.0066,
|
2058 |
+
"step": 984
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 2.22,
|
2062 |
+
"learning_rate": 0.0001302713246821718,
|
2063 |
+
"loss": 4.0972,
|
2064 |
+
"step": 987
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 2.22,
|
2068 |
+
"learning_rate": 0.00013007379412930154,
|
2069 |
+
"loss": 4.0935,
|
2070 |
+
"step": 990
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 2.23,
|
2074 |
+
"learning_rate": 0.00012987715940745797,
|
2075 |
+
"loss": 4.2207,
|
2076 |
+
"step": 993
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 2.24,
|
2080 |
+
"learning_rate": 0.00012968141376583318,
|
2081 |
+
"loss": 4.2459,
|
2082 |
+
"step": 996
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 2.24,
|
2086 |
+
"learning_rate": 0.00012948655052462697,
|
2087 |
+
"loss": 3.9241,
|
2088 |
+
"step": 999
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 2.25,
|
2092 |
+
"eval_accuracy": 0.3940625305324866,
|
2093 |
+
"eval_loss": 3.8381006717681885,
|
2094 |
+
"eval_runtime": 15.2257,
|
2095 |
+
"eval_samples_per_second": 32.839,
|
2096 |
+
"eval_steps_per_second": 16.42,
|
2097 |
+
"step": 1000
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 2.25,
|
2101 |
+
"learning_rate": 0.0001292925630740897,
|
2102 |
+
"loss": 3.9667,
|
2103 |
+
"step": 1002
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 2.26,
|
2107 |
+
"learning_rate": 0.00012909944487358055,
|
2108 |
+
"loss": 3.9541,
|
2109 |
+
"step": 1005
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 2.26,
|
2113 |
+
"learning_rate": 0.00012890718945064115,
|
2114 |
+
"loss": 4.17,
|
2115 |
+
"step": 1008
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 2.27,
|
2119 |
+
"learning_rate": 0.00012871579040008455,
|
2120 |
+
"loss": 4.2002,
|
2121 |
+
"step": 1011
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 2.28,
|
2125 |
+
"learning_rate": 0.00012852524138309883,
|
2126 |
+
"loss": 3.8889,
|
2127 |
+
"step": 1014
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 2.28,
|
2131 |
+
"learning_rate": 0.00012833553612636562,
|
2132 |
+
"loss": 4.1517,
|
2133 |
+
"step": 1017
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 2.29,
|
2137 |
+
"learning_rate": 0.00012814666842119222,
|
2138 |
+
"loss": 4.0006,
|
2139 |
+
"step": 1020
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 2.3,
|
2143 |
+
"learning_rate": 0.0001279586321226585,
|
2144 |
+
"loss": 4.1701,
|
2145 |
+
"step": 1023
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 2.3,
|
2149 |
+
"learning_rate": 0.0001277714211487771,
|
2150 |
+
"loss": 4.0948,
|
2151 |
+
"step": 1026
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 2.31,
|
2155 |
+
"learning_rate": 0.00012758502947966702,
|
2156 |
+
"loss": 3.8545,
|
2157 |
+
"step": 1029
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 2.32,
|
2161 |
+
"learning_rate": 0.0001273994511567407,
|
2162 |
+
"loss": 4.0275,
|
2163 |
+
"step": 1032
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 2.33,
|
2167 |
+
"learning_rate": 0.000127214680281904,
|
2168 |
+
"loss": 4.0691,
|
2169 |
+
"step": 1035
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 2.33,
|
2173 |
+
"learning_rate": 0.00012703071101676877,
|
2174 |
+
"loss": 4.2064,
|
2175 |
+
"step": 1038
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 2.34,
|
2179 |
+
"learning_rate": 0.00012684753758187807,
|
2180 |
+
"loss": 4.0849,
|
2181 |
+
"step": 1041
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 2.35,
|
2185 |
+
"learning_rate": 0.0001266651542559436,
|
2186 |
+
"loss": 4.07,
|
2187 |
+
"step": 1044
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 2.35,
|
2191 |
+
"learning_rate": 0.00012648355537509508,
|
2192 |
+
"loss": 4.0875,
|
2193 |
+
"step": 1047
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 2.36,
|
2197 |
+
"learning_rate": 0.00012630273533214138,
|
2198 |
+
"loss": 4.1563,
|
2199 |
+
"step": 1050
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 2.37,
|
2203 |
+
"learning_rate": 0.00012612268857584364,
|
2204 |
+
"loss": 3.9259,
|
2205 |
+
"step": 1053
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 2.37,
|
2209 |
+
"learning_rate": 0.00012594340961019924,
|
2210 |
+
"loss": 4.0386,
|
2211 |
+
"step": 1056
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 2.38,
|
2215 |
+
"learning_rate": 0.00012576489299373717,
|
2216 |
+
"loss": 4.1156,
|
2217 |
+
"step": 1059
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 2.39,
|
2221 |
+
"learning_rate": 0.00012558713333882439,
|
2222 |
+
"loss": 4.1451,
|
2223 |
+
"step": 1062
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 2.39,
|
2227 |
+
"learning_rate": 0.0001254101253109829,
|
2228 |
+
"loss": 4.1658,
|
2229 |
+
"step": 1065
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 2.4,
|
2233 |
+
"learning_rate": 0.00012523386362821735,
|
2234 |
+
"loss": 3.9714,
|
2235 |
+
"step": 1068
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 2.41,
|
2239 |
+
"learning_rate": 0.00012505834306035296,
|
2240 |
+
"loss": 4.054,
|
2241 |
+
"step": 1071
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 2.41,
|
2245 |
+
"learning_rate": 0.00012488355842838386,
|
2246 |
+
"loss": 4.3048,
|
2247 |
+
"step": 1074
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 2.42,
|
2251 |
+
"learning_rate": 0.00012470950460383105,
|
2252 |
+
"loss": 4.1463,
|
2253 |
+
"step": 1077
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 2.43,
|
2257 |
+
"learning_rate": 0.00012453617650811052,
|
2258 |
+
"loss": 4.1869,
|
2259 |
+
"step": 1080
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 2.43,
|
2263 |
+
"learning_rate": 0.00012436356911191076,
|
2264 |
+
"loss": 4.1841,
|
2265 |
+
"step": 1083
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 2.44,
|
2269 |
+
"learning_rate": 0.00012419167743457984,
|
2270 |
+
"loss": 4.1018,
|
2271 |
+
"step": 1086
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 2.45,
|
2275 |
+
"learning_rate": 0.00012402049654352198,
|
2276 |
+
"loss": 4.0625,
|
2277 |
+
"step": 1089
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 2.45,
|
2281 |
+
"learning_rate": 0.00012385002155360265,
|
2282 |
+
"loss": 3.9801,
|
2283 |
+
"step": 1092
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 2.46,
|
2287 |
+
"learning_rate": 0.0001236802476265634,
|
2288 |
+
"loss": 3.8948,
|
2289 |
+
"step": 1095
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 2.47,
|
2293 |
+
"learning_rate": 0.0001235111699704449,
|
2294 |
+
"loss": 4.0892,
|
2295 |
+
"step": 1098
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 2.47,
|
2299 |
+
"eval_accuracy": 0.40057449926722033,
|
2300 |
+
"eval_loss": 3.7851128578186035,
|
2301 |
+
"eval_runtime": 15.1297,
|
2302 |
+
"eval_samples_per_second": 33.047,
|
2303 |
+
"eval_steps_per_second": 16.524,
|
2304 |
+
"step": 1100
|
2305 |
+
},
|
2306 |
+
{
|
2307 |
+
"epoch": 2.47,
|
2308 |
+
"learning_rate": 0.00012334278383901892,
|
2309 |
+
"loss": 4.1253,
|
2310 |
+
"step": 1101
|
2311 |
+
},
|
2312 |
+
{
|
2313 |
+
"epoch": 2.48,
|
2314 |
+
"learning_rate": 0.0001231750845312288,
|
2315 |
+
"loss": 4.1474,
|
2316 |
+
"step": 1104
|
2317 |
+
},
|
2318 |
+
{
|
2319 |
+
"epoch": 2.49,
|
2320 |
+
"learning_rate": 0.0001230080673906381,
|
2321 |
+
"loss": 3.9774,
|
2322 |
+
"step": 1107
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"epoch": 2.49,
|
2326 |
+
"learning_rate": 0.00012284172780488756,
|
2327 |
+
"loss": 3.9692,
|
2328 |
+
"step": 1110
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 2.5,
|
2332 |
+
"learning_rate": 0.00012267606120516025,
|
2333 |
+
"loss": 4.1343,
|
2334 |
+
"step": 1113
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 2.51,
|
2338 |
+
"learning_rate": 0.0001225110630656542,
|
2339 |
+
"loss": 3.9415,
|
2340 |
+
"step": 1116
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 2.51,
|
2344 |
+
"learning_rate": 0.00012234672890306351,
|
2345 |
+
"loss": 4.1099,
|
2346 |
+
"step": 1119
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 2.52,
|
2350 |
+
"learning_rate": 0.0001221830542760663,
|
2351 |
+
"loss": 4.1696,
|
2352 |
+
"step": 1122
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 2.53,
|
2356 |
+
"learning_rate": 0.00012202003478482084,
|
2357 |
+
"loss": 4.078,
|
2358 |
+
"step": 1125
|
2359 |
+
},
|
2360 |
+
{
|
2361 |
+
"epoch": 2.53,
|
2362 |
+
"learning_rate": 0.00012185766607046863,
|
2363 |
+
"loss": 4.0812,
|
2364 |
+
"step": 1128
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 2.54,
|
2368 |
+
"learning_rate": 0.00012169594381464496,
|
2369 |
+
"loss": 3.9068,
|
2370 |
+
"step": 1131
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 2.55,
|
2374 |
+
"learning_rate": 0.00012153486373899648,
|
2375 |
+
"loss": 4.1278,
|
2376 |
+
"step": 1134
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 2.55,
|
2380 |
+
"learning_rate": 0.00012137442160470578,
|
2381 |
+
"loss": 3.9715,
|
2382 |
+
"step": 1137
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 2.56,
|
2386 |
+
"learning_rate": 0.00012121461321202305,
|
2387 |
+
"loss": 4.1367,
|
2388 |
+
"step": 1140
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 2.57,
|
2392 |
+
"learning_rate": 0.00012105543439980414,
|
2393 |
+
"loss": 4.0155,
|
2394 |
+
"step": 1143
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 2.57,
|
2398 |
+
"learning_rate": 0.00012089688104505568,
|
2399 |
+
"loss": 3.9383,
|
2400 |
+
"step": 1146
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 2.58,
|
2404 |
+
"learning_rate": 0.00012073894906248632,
|
2405 |
+
"loss": 4.0753,
|
2406 |
+
"step": 1149
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 2.59,
|
2410 |
+
"learning_rate": 0.00012058163440406483,
|
2411 |
+
"loss": 3.9593,
|
2412 |
+
"step": 1152
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 2.59,
|
2416 |
+
"learning_rate": 0.00012042493305858426,
|
2417 |
+
"loss": 4.022,
|
2418 |
+
"step": 1155
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 2.6,
|
2422 |
+
"learning_rate": 0.00012026884105123223,
|
2423 |
+
"loss": 3.9807,
|
2424 |
+
"step": 1158
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 2.61,
|
2428 |
+
"learning_rate": 0.00012011335444316761,
|
2429 |
+
"loss": 3.956,
|
2430 |
+
"step": 1161
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 2.61,
|
2434 |
+
"learning_rate": 0.00011995846933110294,
|
2435 |
+
"loss": 3.9439,
|
2436 |
+
"step": 1164
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 2.62,
|
2440 |
+
"learning_rate": 0.0001198041818468931,
|
2441 |
+
"loss": 3.8425,
|
2442 |
+
"step": 1167
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 2.63,
|
2446 |
+
"learning_rate": 0.00011965048815712919,
|
2447 |
+
"loss": 3.7483,
|
2448 |
+
"step": 1170
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 2.64,
|
2452 |
+
"learning_rate": 0.00011949738446273892,
|
2453 |
+
"loss": 3.8322,
|
2454 |
+
"step": 1173
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 2.64,
|
2458 |
+
"learning_rate": 0.00011934486699859179,
|
2459 |
+
"loss": 4.0349,
|
2460 |
+
"step": 1176
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 2.65,
|
2464 |
+
"learning_rate": 0.00011919293203311051,
|
2465 |
+
"loss": 4.0348,
|
2466 |
+
"step": 1179
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 2.66,
|
2470 |
+
"learning_rate": 0.00011904157586788735,
|
2471 |
+
"loss": 3.9782,
|
2472 |
+
"step": 1182
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 2.66,
|
2476 |
+
"learning_rate": 0.0001188907948373061,
|
2477 |
+
"loss": 4.0214,
|
2478 |
+
"step": 1185
|
2479 |
+
},
|
2480 |
+
{
|
2481 |
+
"epoch": 2.67,
|
2482 |
+
"learning_rate": 0.00011874058530816918,
|
2483 |
+
"loss": 4.03,
|
2484 |
+
"step": 1188
|
2485 |
+
},
|
2486 |
+
{
|
2487 |
+
"epoch": 2.68,
|
2488 |
+
"learning_rate": 0.00011859094367932986,
|
2489 |
+
"loss": 3.8793,
|
2490 |
+
"step": 1191
|
2491 |
+
},
|
2492 |
+
{
|
2493 |
+
"epoch": 2.68,
|
2494 |
+
"learning_rate": 0.00011844186638132986,
|
2495 |
+
"loss": 4.0513,
|
2496 |
+
"step": 1194
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 2.69,
|
2500 |
+
"learning_rate": 0.00011829334987604151,
|
2501 |
+
"loss": 3.9717,
|
2502 |
+
"step": 1197
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 2.7,
|
2506 |
+
"learning_rate": 0.00011814539065631521,
|
2507 |
+
"loss": 3.8988,
|
2508 |
+
"step": 1200
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 2.7,
|
2512 |
+
"eval_accuracy": 0.40605862237420615,
|
2513 |
+
"eval_loss": 3.735245704650879,
|
2514 |
+
"eval_runtime": 15.2272,
|
2515 |
+
"eval_samples_per_second": 32.836,
|
2516 |
+
"eval_steps_per_second": 16.418,
|
2517 |
+
"step": 1200
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 2.7,
|
2521 |
+
"learning_rate": 0.00011799798524563149,
|
2522 |
+
"loss": 4.0729,
|
2523 |
+
"step": 1203
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 2.71,
|
2527 |
+
"learning_rate": 0.00011785113019775794,
|
2528 |
+
"loss": 3.9832,
|
2529 |
+
"step": 1206
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 2.72,
|
2533 |
+
"learning_rate": 0.00011770482209641084,
|
2534 |
+
"loss": 4.0265,
|
2535 |
+
"step": 1209
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 2.72,
|
2539 |
+
"learning_rate": 0.0001175590575549214,
|
2540 |
+
"loss": 3.8835,
|
2541 |
+
"step": 1212
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 2.73,
|
2545 |
+
"learning_rate": 0.00011741383321590637,
|
2546 |
+
"loss": 4.047,
|
2547 |
+
"step": 1215
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 2.74,
|
2551 |
+
"learning_rate": 0.00011726914575094334,
|
2552 |
+
"loss": 3.9129,
|
2553 |
+
"step": 1218
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 2.74,
|
2557 |
+
"learning_rate": 0.00011712499186025038,
|
2558 |
+
"loss": 4.1231,
|
2559 |
+
"step": 1221
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 2.75,
|
2563 |
+
"learning_rate": 0.00011698136827236986,
|
2564 |
+
"loss": 3.909,
|
2565 |
+
"step": 1224
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 2.76,
|
2569 |
+
"learning_rate": 0.00011683827174385659,
|
2570 |
+
"loss": 3.9995,
|
2571 |
+
"step": 1227
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 2.76,
|
2575 |
+
"learning_rate": 0.00011669569905897041,
|
2576 |
+
"loss": 3.8527,
|
2577 |
+
"step": 1230
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 2.77,
|
2581 |
+
"learning_rate": 0.00011655364702937239,
|
2582 |
+
"loss": 3.943,
|
2583 |
+
"step": 1233
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 2.78,
|
2587 |
+
"learning_rate": 0.00011641211249382548,
|
2588 |
+
"loss": 3.9862,
|
2589 |
+
"step": 1236
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 2.78,
|
2593 |
+
"learning_rate": 0.0001162710923178991,
|
2594 |
+
"loss": 4.0563,
|
2595 |
+
"step": 1239
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 2.79,
|
2599 |
+
"learning_rate": 0.00011613058339367746,
|
2600 |
+
"loss": 3.8894,
|
2601 |
+
"step": 1242
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 2.8,
|
2605 |
+
"learning_rate": 0.00011599058263947197,
|
2606 |
+
"loss": 4.0139,
|
2607 |
+
"step": 1245
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 2.8,
|
2611 |
+
"learning_rate": 0.0001158510869995373,
|
2612 |
+
"loss": 4.077,
|
2613 |
+
"step": 1248
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 2.81,
|
2617 |
+
"learning_rate": 0.00011571209344379127,
|
2618 |
+
"loss": 3.997,
|
2619 |
+
"step": 1251
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 2.82,
|
2623 |
+
"learning_rate": 0.00011557359896753848,
|
2624 |
+
"loss": 4.1008,
|
2625 |
+
"step": 1254
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 2.82,
|
2629 |
+
"learning_rate": 0.00011543560059119733,
|
2630 |
+
"loss": 3.9626,
|
2631 |
+
"step": 1257
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 2.83,
|
2635 |
+
"learning_rate": 0.00011529809536003097,
|
2636 |
+
"loss": 4.166,
|
2637 |
+
"step": 1260
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 2.84,
|
2641 |
+
"learning_rate": 0.00011516108034388144,
|
2642 |
+
"loss": 3.9516,
|
2643 |
+
"step": 1263
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 2.84,
|
2647 |
+
"learning_rate": 0.00011502455263690746,
|
2648 |
+
"loss": 3.8293,
|
2649 |
+
"step": 1266
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 2.85,
|
2653 |
+
"learning_rate": 0.00011488850935732566,
|
2654 |
+
"loss": 3.9151,
|
2655 |
+
"step": 1269
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 2.86,
|
2659 |
+
"learning_rate": 0.00011475294764715498,
|
2660 |
+
"loss": 3.8377,
|
2661 |
+
"step": 1272
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 2.86,
|
2665 |
+
"learning_rate": 0.00011461786467196458,
|
2666 |
+
"loss": 3.9941,
|
2667 |
+
"step": 1275
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 2.87,
|
2671 |
+
"learning_rate": 0.00011448325762062485,
|
2672 |
+
"loss": 3.9573,
|
2673 |
+
"step": 1278
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 2.88,
|
2677 |
+
"learning_rate": 0.00011434912370506185,
|
2678 |
+
"loss": 4.0494,
|
2679 |
+
"step": 1281
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 2.88,
|
2683 |
+
"learning_rate": 0.00011421546016001452,
|
2684 |
+
"loss": 4.0166,
|
2685 |
+
"step": 1284
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 2.89,
|
2689 |
+
"learning_rate": 0.00011408226424279549,
|
2690 |
+
"loss": 4.0949,
|
2691 |
+
"step": 1287
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 2.9,
|
2695 |
+
"learning_rate": 0.00011394953323305457,
|
2696 |
+
"loss": 4.0741,
|
2697 |
+
"step": 1290
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 2.9,
|
2701 |
+
"learning_rate": 0.00011381726443254541,
|
2702 |
+
"loss": 3.9583,
|
2703 |
+
"step": 1293
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 2.91,
|
2707 |
+
"learning_rate": 0.00011368545516489513,
|
2708 |
+
"loss": 3.9649,
|
2709 |
+
"step": 1296
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 2.92,
|
2713 |
+
"learning_rate": 0.00011355410277537692,
|
2714 |
+
"loss": 3.9169,
|
2715 |
+
"step": 1299
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 2.92,
|
2719 |
+
"eval_accuracy": 0.4101592574499267,
|
2720 |
+
"eval_loss": 3.6907660961151123,
|
2721 |
+
"eval_runtime": 15.2368,
|
2722 |
+
"eval_samples_per_second": 32.815,
|
2723 |
+
"eval_steps_per_second": 16.408,
|
2724 |
+
"step": 1300
|
2725 |
+
},
|
2726 |
+
{
|
2727 |
+
"epoch": 2.93,
|
2728 |
+
"learning_rate": 0.00011342320463068534,
|
2729 |
+
"loss": 4.0254,
|
2730 |
+
"step": 1302
|
2731 |
+
},
|
2732 |
+
{
|
2733 |
+
"epoch": 2.93,
|
2734 |
+
"learning_rate": 0.00011329275811871468,
|
2735 |
+
"loss": 3.9481,
|
2736 |
+
"step": 1305
|
2737 |
+
},
|
2738 |
+
{
|
2739 |
+
"epoch": 2.94,
|
2740 |
+
"learning_rate": 0.00011316276064834012,
|
2741 |
+
"loss": 3.8534,
|
2742 |
+
"step": 1308
|
2743 |
+
},
|
2744 |
+
{
|
2745 |
+
"epoch": 2.95,
|
2746 |
+
"learning_rate": 0.00011303320964920135,
|
2747 |
+
"loss": 3.8253,
|
2748 |
+
"step": 1311
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 2.95,
|
2752 |
+
"learning_rate": 0.00011290410257148924,
|
2753 |
+
"loss": 3.8843,
|
2754 |
+
"step": 1314
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 2.96,
|
2758 |
+
"learning_rate": 0.00011277543688573506,
|
2759 |
+
"loss": 3.987,
|
2760 |
+
"step": 1317
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 2.97,
|
2764 |
+
"learning_rate": 0.00011264721008260231,
|
2765 |
+
"loss": 3.9692,
|
2766 |
+
"step": 1320
|
2767 |
+
},
|
2768 |
+
{
|
2769 |
+
"epoch": 2.97,
|
2770 |
+
"learning_rate": 0.00011251941967268115,
|
2771 |
+
"loss": 3.8917,
|
2772 |
+
"step": 1323
|
2773 |
+
},
|
2774 |
+
{
|
2775 |
+
"epoch": 2.98,
|
2776 |
+
"learning_rate": 0.00011239206318628546,
|
2777 |
+
"loss": 4.0324,
|
2778 |
+
"step": 1326
|
2779 |
+
},
|
2780 |
+
{
|
2781 |
+
"epoch": 2.99,
|
2782 |
+
"learning_rate": 0.00011226513817325236,
|
2783 |
+
"loss": 3.8372,
|
2784 |
+
"step": 1329
|
2785 |
+
},
|
2786 |
+
{
|
2787 |
+
"epoch": 2.99,
|
2788 |
+
"learning_rate": 0.00011213864220274417,
|
2789 |
+
"loss": 3.9239,
|
2790 |
+
"step": 1332
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 3.0,
|
2794 |
+
"learning_rate": 0.00011201257286305297,
|
2795 |
+
"loss": 3.8253,
|
2796 |
+
"step": 1335
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 3.0,
|
2800 |
+
"step": 1335,
|
2801 |
+
"total_flos": 1.849574515802112e+16,
|
2802 |
+
"train_loss": 4.728262927737576,
|
2803 |
+
"train_runtime": 4788.6915,
|
2804 |
+
"train_samples_per_second": 17.847,
|
2805 |
+
"train_steps_per_second": 0.279
|
2806 |
+
}
|
2807 |
+
],
|
2808 |
+
"logging_steps": 3,
|
2809 |
+
"max_steps": 1335,
|
2810 |
+
"num_train_epochs": 3,
|
2811 |
+
"save_steps": 100,
|
2812 |
+
"total_flos": 1.849574515802112e+16,
|
2813 |
+
"trial_name": null,
|
2814 |
+
"trial_params": null
|
2815 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f9d2cdeb00ce3eaecc2b86ad66abe416e6e1fc68d7ec65dad0628704c7adc7b
|
3 |
+
size 4664
|