Jinchen Ge
commited on
Commit
•
36baff5
1
Parent(s):
fd841b9
Add fine-tuned model
Browse files- README.md +60 -0
- all_results.json +14 -0
- config.json +41 -0
- eval_results.json +9 -0
- ipu_config.json +31 -0
- merges.txt +0 -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 +1357 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- wikitext
|
6 |
+
model-index:
|
7 |
+
- name: clm_output_medium
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# clm_output_medium
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the wikitext wikitext-103-raw-v1 dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.6973
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
+
- distributed_type: IPU
|
42 |
+
- gradient_accumulation_steps: 256
|
43 |
+
- total_train_batch_size: 1024
|
44 |
+
- total_eval_batch_size: 18
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 10.0
|
49 |
+
- training precision: Mixed Precision
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.18.0.dev0
|
58 |
+
- Pytorch 1.10.0+cpu
|
59 |
+
- Datasets 2.0.0
|
60 |
+
- Tokenizers 0.11.6
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 2.697265625,
|
4 |
+
"eval_runtime": 1045.8094,
|
5 |
+
"eval_samples": 240,
|
6 |
+
"eval_samples_per_second": 0.229,
|
7 |
+
"eval_steps_per_second": 0.013,
|
8 |
+
"perplexity": 14.83910053420958,
|
9 |
+
"train_loss": 2.8070910754504506,
|
10 |
+
"train_runtime": 11217.8167,
|
11 |
+
"train_samples": 114248,
|
12 |
+
"train_samples_per_second": 101.845,
|
13 |
+
"train_steps_per_second": 0.099
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-medium",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"PoptorchPipelinedGPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": true,
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"summary_activation": null,
|
27 |
+
"summary_first_dropout": 0.1,
|
28 |
+
"summary_proj_to_labels": true,
|
29 |
+
"summary_type": "cls_index",
|
30 |
+
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float16",
|
38 |
+
"transformers_version": "4.18.0.dev0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_loss": 2.697265625,
|
4 |
+
"eval_runtime": 1045.8094,
|
5 |
+
"eval_samples": 240,
|
6 |
+
"eval_samples_per_second": 0.229,
|
7 |
+
"eval_steps_per_second": 0.013,
|
8 |
+
"perplexity": 14.83910053420958
|
9 |
+
}
|
ipu_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"device_iterations": 2,
|
3 |
+
"embedding_serialization_factor": 5,
|
4 |
+
"enable_half_first_order_momentum": true,
|
5 |
+
"enable_half_partials": true,
|
6 |
+
"executable_cache_dir": "./exe_cache",
|
7 |
+
"gradient_accumulation_steps": 256,
|
8 |
+
"inference_device_iterations": 9,
|
9 |
+
"inference_replication_factor": 2,
|
10 |
+
"ipus_per_replica": 8,
|
11 |
+
"layers_per_ipu": [
|
12 |
+
0,
|
13 |
+
3,
|
14 |
+
3,
|
15 |
+
3,
|
16 |
+
3,
|
17 |
+
4,
|
18 |
+
4,
|
19 |
+
4
|
20 |
+
],
|
21 |
+
"matmul_proportion": 0.25,
|
22 |
+
"optimizer_state_offchip": true,
|
23 |
+
"optimum_version": "1.0.0",
|
24 |
+
"output_mode": "final",
|
25 |
+
"profile_dir": "",
|
26 |
+
"recompute_checkpoint_every_layer": true,
|
27 |
+
"replicated_tensor_sharding": true,
|
28 |
+
"replication_factor": 2,
|
29 |
+
"seed": 42,
|
30 |
+
"use_popdist": false
|
31 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d31e1d5b593aa0a1bae1062b163e60bc9e0c9d6a7d0f0c7b147d053027cf921
|
3 |
+
size 734915801
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2-medium", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 2.8070910754504506,
|
4 |
+
"train_runtime": 11217.8167,
|
5 |
+
"train_samples": 114248,
|
6 |
+
"train_samples_per_second": 101.845,
|
7 |
+
"train_steps_per_second": 0.099
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 1110,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 4.504504504504505e-07,
|
13 |
+
"loss": 3.2559,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 9.00900900900901e-07,
|
19 |
+
"loss": 3.2281,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.14,
|
24 |
+
"learning_rate": 1.3513513513513515e-06,
|
25 |
+
"loss": 3.1953,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.18,
|
30 |
+
"learning_rate": 1.801801801801802e-06,
|
31 |
+
"loss": 3.0844,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.23,
|
36 |
+
"learning_rate": 2.2522522522522524e-06,
|
37 |
+
"loss": 3.2563,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.27,
|
42 |
+
"learning_rate": 2.702702702702703e-06,
|
43 |
+
"loss": 3.098,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.32,
|
48 |
+
"learning_rate": 3.1531531531531532e-06,
|
49 |
+
"loss": 2.9754,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.36,
|
54 |
+
"learning_rate": 3.603603603603604e-06,
|
55 |
+
"loss": 3.1168,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.41,
|
60 |
+
"learning_rate": 4.0540540540540545e-06,
|
61 |
+
"loss": 3.2441,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.45,
|
66 |
+
"learning_rate": 4.504504504504505e-06,
|
67 |
+
"loss": 3.084,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.5,
|
72 |
+
"learning_rate": 4.954954954954955e-06,
|
73 |
+
"loss": 3.1965,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.54,
|
78 |
+
"learning_rate": 5.405405405405406e-06,
|
79 |
+
"loss": 2.9336,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.59,
|
84 |
+
"learning_rate": 5.855855855855856e-06,
|
85 |
+
"loss": 2.977,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.63,
|
90 |
+
"learning_rate": 6.3063063063063065e-06,
|
91 |
+
"loss": 3.0297,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.68,
|
96 |
+
"learning_rate": 6.7567567567567575e-06,
|
97 |
+
"loss": 2.9363,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.72,
|
102 |
+
"learning_rate": 7.207207207207208e-06,
|
103 |
+
"loss": 2.9477,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.77,
|
108 |
+
"learning_rate": 7.657657657657658e-06,
|
109 |
+
"loss": 3.0219,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.81,
|
114 |
+
"learning_rate": 8.108108108108109e-06,
|
115 |
+
"loss": 2.9004,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.86,
|
120 |
+
"learning_rate": 8.55855855855856e-06,
|
121 |
+
"loss": 2.991,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.9,
|
126 |
+
"learning_rate": 9.00900900900901e-06,
|
127 |
+
"loss": 2.8973,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.95,
|
132 |
+
"learning_rate": 9.45945945945946e-06,
|
133 |
+
"loss": 2.9184,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.99,
|
138 |
+
"learning_rate": 9.90990990990991e-06,
|
139 |
+
"loss": 2.868,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.04,
|
144 |
+
"learning_rate": 9.95995995995996e-06,
|
145 |
+
"loss": 2.8301,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.08,
|
150 |
+
"learning_rate": 9.90990990990991e-06,
|
151 |
+
"loss": 2.716,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.13,
|
156 |
+
"learning_rate": 9.85985985985986e-06,
|
157 |
+
"loss": 2.8859,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.17,
|
162 |
+
"learning_rate": 9.80980980980981e-06,
|
163 |
+
"loss": 2.8418,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.22,
|
168 |
+
"learning_rate": 9.75975975975976e-06,
|
169 |
+
"loss": 2.8004,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.26,
|
174 |
+
"learning_rate": 9.70970970970971e-06,
|
175 |
+
"loss": 2.8203,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.31,
|
180 |
+
"learning_rate": 9.65965965965966e-06,
|
181 |
+
"loss": 2.8668,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.35,
|
186 |
+
"learning_rate": 9.60960960960961e-06,
|
187 |
+
"loss": 2.8055,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.4,
|
192 |
+
"learning_rate": 9.55955955955956e-06,
|
193 |
+
"loss": 2.7934,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.44,
|
198 |
+
"learning_rate": 9.50950950950951e-06,
|
199 |
+
"loss": 2.9164,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.49,
|
204 |
+
"learning_rate": 9.45945945945946e-06,
|
205 |
+
"loss": 2.9328,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.53,
|
210 |
+
"learning_rate": 9.40940940940941e-06,
|
211 |
+
"loss": 2.9363,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.58,
|
216 |
+
"learning_rate": 9.35935935935936e-06,
|
217 |
+
"loss": 2.841,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.62,
|
222 |
+
"learning_rate": 9.30930930930931e-06,
|
223 |
+
"loss": 2.7398,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.67,
|
228 |
+
"learning_rate": 9.25925925925926e-06,
|
229 |
+
"loss": 2.8695,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.71,
|
234 |
+
"learning_rate": 9.20920920920921e-06,
|
235 |
+
"loss": 2.8363,
|
236 |
+
"step": 190
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.76,
|
240 |
+
"learning_rate": 9.15915915915916e-06,
|
241 |
+
"loss": 2.8844,
|
242 |
+
"step": 195
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.8,
|
246 |
+
"learning_rate": 9.10910910910911e-06,
|
247 |
+
"loss": 2.7594,
|
248 |
+
"step": 200
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.85,
|
252 |
+
"learning_rate": 9.05905905905906e-06,
|
253 |
+
"loss": 2.8078,
|
254 |
+
"step": 205
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.89,
|
258 |
+
"learning_rate": 9.00900900900901e-06,
|
259 |
+
"loss": 2.9926,
|
260 |
+
"step": 210
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.94,
|
264 |
+
"learning_rate": 8.95895895895896e-06,
|
265 |
+
"loss": 2.8766,
|
266 |
+
"step": 215
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.98,
|
270 |
+
"learning_rate": 8.90890890890891e-06,
|
271 |
+
"loss": 2.8145,
|
272 |
+
"step": 220
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.03,
|
276 |
+
"learning_rate": 8.85885885885886e-06,
|
277 |
+
"loss": 2.7383,
|
278 |
+
"step": 225
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.07,
|
282 |
+
"learning_rate": 8.80880880880881e-06,
|
283 |
+
"loss": 2.7613,
|
284 |
+
"step": 230
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.12,
|
288 |
+
"learning_rate": 8.75875875875876e-06,
|
289 |
+
"loss": 2.9582,
|
290 |
+
"step": 235
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.16,
|
294 |
+
"learning_rate": 8.70870870870871e-06,
|
295 |
+
"loss": 2.8043,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.21,
|
300 |
+
"learning_rate": 8.65865865865866e-06,
|
301 |
+
"loss": 2.7922,
|
302 |
+
"step": 245
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.25,
|
306 |
+
"learning_rate": 8.60860860860861e-06,
|
307 |
+
"loss": 2.9848,
|
308 |
+
"step": 250
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.3,
|
312 |
+
"learning_rate": 8.55855855855856e-06,
|
313 |
+
"loss": 2.8777,
|
314 |
+
"step": 255
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.34,
|
318 |
+
"learning_rate": 8.50850850850851e-06,
|
319 |
+
"loss": 2.9402,
|
320 |
+
"step": 260
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.39,
|
324 |
+
"learning_rate": 8.45845845845846e-06,
|
325 |
+
"loss": 2.7785,
|
326 |
+
"step": 265
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.43,
|
330 |
+
"learning_rate": 8.408408408408409e-06,
|
331 |
+
"loss": 2.8871,
|
332 |
+
"step": 270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.48,
|
336 |
+
"learning_rate": 8.358358358358359e-06,
|
337 |
+
"loss": 2.8348,
|
338 |
+
"step": 275
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.52,
|
342 |
+
"learning_rate": 8.308308308308309e-06,
|
343 |
+
"loss": 2.7664,
|
344 |
+
"step": 280
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.57,
|
348 |
+
"learning_rate": 8.258258258258259e-06,
|
349 |
+
"loss": 2.7973,
|
350 |
+
"step": 285
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.61,
|
354 |
+
"learning_rate": 8.208208208208209e-06,
|
355 |
+
"loss": 2.7527,
|
356 |
+
"step": 290
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.66,
|
360 |
+
"learning_rate": 8.158158158158159e-06,
|
361 |
+
"loss": 2.7844,
|
362 |
+
"step": 295
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.7,
|
366 |
+
"learning_rate": 8.108108108108109e-06,
|
367 |
+
"loss": 2.8102,
|
368 |
+
"step": 300
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.75,
|
372 |
+
"learning_rate": 8.058058058058059e-06,
|
373 |
+
"loss": 2.923,
|
374 |
+
"step": 305
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.79,
|
378 |
+
"learning_rate": 8.00800800800801e-06,
|
379 |
+
"loss": 2.7535,
|
380 |
+
"step": 310
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.84,
|
384 |
+
"learning_rate": 7.95795795795796e-06,
|
385 |
+
"loss": 2.8164,
|
386 |
+
"step": 315
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.88,
|
390 |
+
"learning_rate": 7.90790790790791e-06,
|
391 |
+
"loss": 2.8312,
|
392 |
+
"step": 320
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.93,
|
396 |
+
"learning_rate": 7.85785785785786e-06,
|
397 |
+
"loss": 2.8027,
|
398 |
+
"step": 325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.97,
|
402 |
+
"learning_rate": 7.807807807807808e-06,
|
403 |
+
"loss": 2.7281,
|
404 |
+
"step": 330
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 3.02,
|
408 |
+
"learning_rate": 7.757757757757758e-06,
|
409 |
+
"loss": 2.8328,
|
410 |
+
"step": 335
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 3.06,
|
414 |
+
"learning_rate": 7.707707707707708e-06,
|
415 |
+
"loss": 2.8695,
|
416 |
+
"step": 340
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 3.11,
|
420 |
+
"learning_rate": 7.657657657657658e-06,
|
421 |
+
"loss": 2.8,
|
422 |
+
"step": 345
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 3.15,
|
426 |
+
"learning_rate": 7.607607607607608e-06,
|
427 |
+
"loss": 2.8832,
|
428 |
+
"step": 350
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 3.2,
|
432 |
+
"learning_rate": 7.557557557557558e-06,
|
433 |
+
"loss": 2.7445,
|
434 |
+
"step": 355
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 3.24,
|
438 |
+
"learning_rate": 7.507507507507507e-06,
|
439 |
+
"loss": 2.7359,
|
440 |
+
"step": 360
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 3.29,
|
444 |
+
"learning_rate": 7.457457457457457e-06,
|
445 |
+
"loss": 2.6559,
|
446 |
+
"step": 365
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 3.33,
|
450 |
+
"learning_rate": 7.4074074074074075e-06,
|
451 |
+
"loss": 2.7598,
|
452 |
+
"step": 370
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 3.38,
|
456 |
+
"learning_rate": 7.3573573573573575e-06,
|
457 |
+
"loss": 2.8637,
|
458 |
+
"step": 375
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 3.42,
|
462 |
+
"learning_rate": 7.307307307307308e-06,
|
463 |
+
"loss": 2.7266,
|
464 |
+
"step": 380
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 3.47,
|
468 |
+
"learning_rate": 7.257257257257258e-06,
|
469 |
+
"loss": 2.7289,
|
470 |
+
"step": 385
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 3.51,
|
474 |
+
"learning_rate": 7.207207207207208e-06,
|
475 |
+
"loss": 2.7895,
|
476 |
+
"step": 390
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 3.56,
|
480 |
+
"learning_rate": 7.157157157157158e-06,
|
481 |
+
"loss": 2.7336,
|
482 |
+
"step": 395
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 3.6,
|
486 |
+
"learning_rate": 7.107107107107107e-06,
|
487 |
+
"loss": 2.6094,
|
488 |
+
"step": 400
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 3.65,
|
492 |
+
"learning_rate": 7.057057057057057e-06,
|
493 |
+
"loss": 2.9809,
|
494 |
+
"step": 405
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 3.69,
|
498 |
+
"learning_rate": 7.007007007007007e-06,
|
499 |
+
"loss": 2.8156,
|
500 |
+
"step": 410
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 3.74,
|
504 |
+
"learning_rate": 6.956956956956957e-06,
|
505 |
+
"loss": 2.798,
|
506 |
+
"step": 415
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 3.78,
|
510 |
+
"learning_rate": 6.906906906906907e-06,
|
511 |
+
"loss": 2.6703,
|
512 |
+
"step": 420
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 3.83,
|
516 |
+
"learning_rate": 6.856856856856857e-06,
|
517 |
+
"loss": 2.8105,
|
518 |
+
"step": 425
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 3.87,
|
522 |
+
"learning_rate": 6.8068068068068075e-06,
|
523 |
+
"loss": 2.6707,
|
524 |
+
"step": 430
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 3.92,
|
528 |
+
"learning_rate": 6.7567567567567575e-06,
|
529 |
+
"loss": 2.7289,
|
530 |
+
"step": 435
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 3.96,
|
534 |
+
"learning_rate": 6.706706706706707e-06,
|
535 |
+
"loss": 2.7004,
|
536 |
+
"step": 440
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 4.01,
|
540 |
+
"learning_rate": 6.656656656656657e-06,
|
541 |
+
"loss": 2.8719,
|
542 |
+
"step": 445
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 4.05,
|
546 |
+
"learning_rate": 6.606606606606607e-06,
|
547 |
+
"loss": 2.6273,
|
548 |
+
"step": 450
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.1,
|
552 |
+
"learning_rate": 6.556556556556557e-06,
|
553 |
+
"loss": 2.8629,
|
554 |
+
"step": 455
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 4.14,
|
558 |
+
"learning_rate": 6.506506506506507e-06,
|
559 |
+
"loss": 2.8672,
|
560 |
+
"step": 460
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 4.19,
|
564 |
+
"learning_rate": 6.456456456456457e-06,
|
565 |
+
"loss": 2.725,
|
566 |
+
"step": 465
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 4.23,
|
570 |
+
"learning_rate": 6.406406406406407e-06,
|
571 |
+
"loss": 2.8004,
|
572 |
+
"step": 470
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 4.28,
|
576 |
+
"learning_rate": 6.356356356356357e-06,
|
577 |
+
"loss": 2.882,
|
578 |
+
"step": 475
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 4.32,
|
582 |
+
"learning_rate": 6.3063063063063065e-06,
|
583 |
+
"loss": 2.8027,
|
584 |
+
"step": 480
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 4.37,
|
588 |
+
"learning_rate": 6.2562562562562565e-06,
|
589 |
+
"loss": 2.8988,
|
590 |
+
"step": 485
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 4.41,
|
594 |
+
"learning_rate": 6.206206206206207e-06,
|
595 |
+
"loss": 2.6898,
|
596 |
+
"step": 490
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 4.46,
|
600 |
+
"learning_rate": 6.156156156156157e-06,
|
601 |
+
"loss": 2.9855,
|
602 |
+
"step": 495
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 4.5,
|
606 |
+
"learning_rate": 6.106106106106107e-06,
|
607 |
+
"loss": 2.8246,
|
608 |
+
"step": 500
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 4.55,
|
612 |
+
"learning_rate": 6.056056056056057e-06,
|
613 |
+
"loss": 2.8918,
|
614 |
+
"step": 505
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 4.59,
|
618 |
+
"learning_rate": 6.006006006006007e-06,
|
619 |
+
"loss": 2.8988,
|
620 |
+
"step": 510
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 4.64,
|
624 |
+
"learning_rate": 5.955955955955957e-06,
|
625 |
+
"loss": 2.7313,
|
626 |
+
"step": 515
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 4.68,
|
630 |
+
"learning_rate": 5.905905905905906e-06,
|
631 |
+
"loss": 2.8082,
|
632 |
+
"step": 520
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 4.73,
|
636 |
+
"learning_rate": 5.855855855855856e-06,
|
637 |
+
"loss": 2.8164,
|
638 |
+
"step": 525
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 4.77,
|
642 |
+
"learning_rate": 5.805805805805806e-06,
|
643 |
+
"loss": 2.7496,
|
644 |
+
"step": 530
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 4.82,
|
648 |
+
"learning_rate": 5.755755755755756e-06,
|
649 |
+
"loss": 2.5914,
|
650 |
+
"step": 535
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 4.86,
|
654 |
+
"learning_rate": 5.7057057057057065e-06,
|
655 |
+
"loss": 2.7824,
|
656 |
+
"step": 540
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 4.91,
|
660 |
+
"learning_rate": 5.6556556556556565e-06,
|
661 |
+
"loss": 2.6574,
|
662 |
+
"step": 545
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 4.95,
|
666 |
+
"learning_rate": 5.605605605605607e-06,
|
667 |
+
"loss": 2.8434,
|
668 |
+
"step": 550
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 5.0,
|
672 |
+
"learning_rate": 5.555555555555557e-06,
|
673 |
+
"loss": 2.8793,
|
674 |
+
"step": 555
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 5.05,
|
678 |
+
"learning_rate": 5.505505505505506e-06,
|
679 |
+
"loss": 2.7293,
|
680 |
+
"step": 560
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 5.09,
|
684 |
+
"learning_rate": 5.455455455455456e-06,
|
685 |
+
"loss": 2.7664,
|
686 |
+
"step": 565
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 5.14,
|
690 |
+
"learning_rate": 5.405405405405406e-06,
|
691 |
+
"loss": 2.7891,
|
692 |
+
"step": 570
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 5.18,
|
696 |
+
"learning_rate": 5.355355355355356e-06,
|
697 |
+
"loss": 2.868,
|
698 |
+
"step": 575
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 5.23,
|
702 |
+
"learning_rate": 5.305305305305306e-06,
|
703 |
+
"loss": 2.8664,
|
704 |
+
"step": 580
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 5.27,
|
708 |
+
"learning_rate": 5.255255255255256e-06,
|
709 |
+
"loss": 2.8324,
|
710 |
+
"step": 585
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 5.32,
|
714 |
+
"learning_rate": 5.205205205205206e-06,
|
715 |
+
"loss": 2.7469,
|
716 |
+
"step": 590
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 5.36,
|
720 |
+
"learning_rate": 5.155155155155156e-06,
|
721 |
+
"loss": 2.7973,
|
722 |
+
"step": 595
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 5.41,
|
726 |
+
"learning_rate": 5.105105105105106e-06,
|
727 |
+
"loss": 2.8254,
|
728 |
+
"step": 600
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 5.45,
|
732 |
+
"learning_rate": 5.055055055055056e-06,
|
733 |
+
"loss": 2.7656,
|
734 |
+
"step": 605
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 5.5,
|
738 |
+
"learning_rate": 5.005005005005006e-06,
|
739 |
+
"loss": 2.766,
|
740 |
+
"step": 610
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 5.54,
|
744 |
+
"learning_rate": 4.954954954954955e-06,
|
745 |
+
"loss": 2.8266,
|
746 |
+
"step": 615
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 5.59,
|
750 |
+
"learning_rate": 4.904904904904905e-06,
|
751 |
+
"loss": 2.868,
|
752 |
+
"step": 620
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 5.63,
|
756 |
+
"learning_rate": 4.854854854854855e-06,
|
757 |
+
"loss": 2.7523,
|
758 |
+
"step": 625
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 5.68,
|
762 |
+
"learning_rate": 4.804804804804805e-06,
|
763 |
+
"loss": 2.8625,
|
764 |
+
"step": 630
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 5.72,
|
768 |
+
"learning_rate": 4.754754754754755e-06,
|
769 |
+
"loss": 2.7098,
|
770 |
+
"step": 635
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 5.77,
|
774 |
+
"learning_rate": 4.704704704704705e-06,
|
775 |
+
"loss": 2.584,
|
776 |
+
"step": 640
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 5.81,
|
780 |
+
"learning_rate": 4.654654654654655e-06,
|
781 |
+
"loss": 2.7652,
|
782 |
+
"step": 645
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 5.86,
|
786 |
+
"learning_rate": 4.604604604604605e-06,
|
787 |
+
"loss": 2.7668,
|
788 |
+
"step": 650
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 5.9,
|
792 |
+
"learning_rate": 4.554554554554555e-06,
|
793 |
+
"loss": 2.9934,
|
794 |
+
"step": 655
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 5.95,
|
798 |
+
"learning_rate": 4.504504504504505e-06,
|
799 |
+
"loss": 2.807,
|
800 |
+
"step": 660
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 5.99,
|
804 |
+
"learning_rate": 4.454454454454455e-06,
|
805 |
+
"loss": 2.7543,
|
806 |
+
"step": 665
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 6.04,
|
810 |
+
"learning_rate": 4.404404404404405e-06,
|
811 |
+
"loss": 2.7055,
|
812 |
+
"step": 670
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 6.08,
|
816 |
+
"learning_rate": 4.354354354354355e-06,
|
817 |
+
"loss": 2.6199,
|
818 |
+
"step": 675
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 6.13,
|
822 |
+
"learning_rate": 4.304304304304305e-06,
|
823 |
+
"loss": 2.757,
|
824 |
+
"step": 680
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 6.17,
|
828 |
+
"learning_rate": 4.254254254254255e-06,
|
829 |
+
"loss": 2.7941,
|
830 |
+
"step": 685
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 6.22,
|
834 |
+
"learning_rate": 4.204204204204204e-06,
|
835 |
+
"loss": 2.7836,
|
836 |
+
"step": 690
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 6.26,
|
840 |
+
"learning_rate": 4.154154154154154e-06,
|
841 |
+
"loss": 2.7062,
|
842 |
+
"step": 695
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 6.31,
|
846 |
+
"learning_rate": 4.1041041041041045e-06,
|
847 |
+
"loss": 2.807,
|
848 |
+
"step": 700
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 6.35,
|
852 |
+
"learning_rate": 4.0540540540540545e-06,
|
853 |
+
"loss": 2.8246,
|
854 |
+
"step": 705
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 6.4,
|
858 |
+
"learning_rate": 4.004004004004005e-06,
|
859 |
+
"loss": 2.8395,
|
860 |
+
"step": 710
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 6.44,
|
864 |
+
"learning_rate": 3.953953953953955e-06,
|
865 |
+
"loss": 2.7781,
|
866 |
+
"step": 715
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 6.49,
|
870 |
+
"learning_rate": 3.903903903903904e-06,
|
871 |
+
"loss": 2.732,
|
872 |
+
"step": 720
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 6.53,
|
876 |
+
"learning_rate": 3.853853853853854e-06,
|
877 |
+
"loss": 2.7281,
|
878 |
+
"step": 725
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 6.58,
|
882 |
+
"learning_rate": 3.803803803803804e-06,
|
883 |
+
"loss": 2.6957,
|
884 |
+
"step": 730
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 6.62,
|
888 |
+
"learning_rate": 3.7537537537537537e-06,
|
889 |
+
"loss": 2.7516,
|
890 |
+
"step": 735
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 6.67,
|
894 |
+
"learning_rate": 3.7037037037037037e-06,
|
895 |
+
"loss": 2.741,
|
896 |
+
"step": 740
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 6.71,
|
900 |
+
"learning_rate": 3.653653653653654e-06,
|
901 |
+
"loss": 2.798,
|
902 |
+
"step": 745
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 6.76,
|
906 |
+
"learning_rate": 3.603603603603604e-06,
|
907 |
+
"loss": 2.741,
|
908 |
+
"step": 750
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 6.8,
|
912 |
+
"learning_rate": 3.5535535535535535e-06,
|
913 |
+
"loss": 2.7691,
|
914 |
+
"step": 755
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 6.85,
|
918 |
+
"learning_rate": 3.5035035035035036e-06,
|
919 |
+
"loss": 2.7039,
|
920 |
+
"step": 760
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 6.89,
|
924 |
+
"learning_rate": 3.4534534534534537e-06,
|
925 |
+
"loss": 2.7797,
|
926 |
+
"step": 765
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 6.94,
|
930 |
+
"learning_rate": 3.4034034034034037e-06,
|
931 |
+
"loss": 2.918,
|
932 |
+
"step": 770
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 6.98,
|
936 |
+
"learning_rate": 3.3533533533533534e-06,
|
937 |
+
"loss": 2.6195,
|
938 |
+
"step": 775
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 7.03,
|
942 |
+
"learning_rate": 3.3033033033033035e-06,
|
943 |
+
"loss": 2.5387,
|
944 |
+
"step": 780
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 7.07,
|
948 |
+
"learning_rate": 3.2532532532532535e-06,
|
949 |
+
"loss": 2.7352,
|
950 |
+
"step": 785
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 7.12,
|
954 |
+
"learning_rate": 3.2032032032032036e-06,
|
955 |
+
"loss": 2.5961,
|
956 |
+
"step": 790
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 7.16,
|
960 |
+
"learning_rate": 3.1531531531531532e-06,
|
961 |
+
"loss": 2.8273,
|
962 |
+
"step": 795
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 7.21,
|
966 |
+
"learning_rate": 3.1031031031031033e-06,
|
967 |
+
"loss": 2.6625,
|
968 |
+
"step": 800
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 7.25,
|
972 |
+
"learning_rate": 3.0530530530530534e-06,
|
973 |
+
"loss": 2.7,
|
974 |
+
"step": 805
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 7.3,
|
978 |
+
"learning_rate": 3.0030030030030034e-06,
|
979 |
+
"loss": 2.7527,
|
980 |
+
"step": 810
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 7.34,
|
984 |
+
"learning_rate": 2.952952952952953e-06,
|
985 |
+
"loss": 2.7172,
|
986 |
+
"step": 815
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 7.39,
|
990 |
+
"learning_rate": 2.902902902902903e-06,
|
991 |
+
"loss": 2.7395,
|
992 |
+
"step": 820
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 7.43,
|
996 |
+
"learning_rate": 2.8528528528528532e-06,
|
997 |
+
"loss": 2.6105,
|
998 |
+
"step": 825
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 7.48,
|
1002 |
+
"learning_rate": 2.8028028028028033e-06,
|
1003 |
+
"loss": 2.7566,
|
1004 |
+
"step": 830
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 7.52,
|
1008 |
+
"learning_rate": 2.752752752752753e-06,
|
1009 |
+
"loss": 2.6984,
|
1010 |
+
"step": 835
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 7.57,
|
1014 |
+
"learning_rate": 2.702702702702703e-06,
|
1015 |
+
"loss": 2.8969,
|
1016 |
+
"step": 840
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 7.61,
|
1020 |
+
"learning_rate": 2.652652652652653e-06,
|
1021 |
+
"loss": 2.6301,
|
1022 |
+
"step": 845
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 7.66,
|
1026 |
+
"learning_rate": 2.602602602602603e-06,
|
1027 |
+
"loss": 2.7102,
|
1028 |
+
"step": 850
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 7.7,
|
1032 |
+
"learning_rate": 2.552552552552553e-06,
|
1033 |
+
"loss": 2.9152,
|
1034 |
+
"step": 855
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 7.75,
|
1038 |
+
"learning_rate": 2.502502502502503e-06,
|
1039 |
+
"loss": 2.6543,
|
1040 |
+
"step": 860
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 7.79,
|
1044 |
+
"learning_rate": 2.4524524524524525e-06,
|
1045 |
+
"loss": 2.6109,
|
1046 |
+
"step": 865
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 7.84,
|
1050 |
+
"learning_rate": 2.4024024024024026e-06,
|
1051 |
+
"loss": 2.5871,
|
1052 |
+
"step": 870
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 7.88,
|
1056 |
+
"learning_rate": 2.3523523523523527e-06,
|
1057 |
+
"loss": 2.752,
|
1058 |
+
"step": 875
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 7.93,
|
1062 |
+
"learning_rate": 2.3023023023023023e-06,
|
1063 |
+
"loss": 2.716,
|
1064 |
+
"step": 880
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 7.97,
|
1068 |
+
"learning_rate": 2.2522522522522524e-06,
|
1069 |
+
"loss": 2.807,
|
1070 |
+
"step": 885
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 8.02,
|
1074 |
+
"learning_rate": 2.2022022022022024e-06,
|
1075 |
+
"loss": 2.877,
|
1076 |
+
"step": 890
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 8.06,
|
1080 |
+
"learning_rate": 2.1521521521521525e-06,
|
1081 |
+
"loss": 2.716,
|
1082 |
+
"step": 895
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 8.11,
|
1086 |
+
"learning_rate": 2.102102102102102e-06,
|
1087 |
+
"loss": 2.6879,
|
1088 |
+
"step": 900
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 8.15,
|
1092 |
+
"learning_rate": 2.0520520520520522e-06,
|
1093 |
+
"loss": 2.7137,
|
1094 |
+
"step": 905
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 8.2,
|
1098 |
+
"learning_rate": 2.0020020020020023e-06,
|
1099 |
+
"loss": 2.7133,
|
1100 |
+
"step": 910
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 8.24,
|
1104 |
+
"learning_rate": 1.951951951951952e-06,
|
1105 |
+
"loss": 2.7453,
|
1106 |
+
"step": 915
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 8.29,
|
1110 |
+
"learning_rate": 1.901901901901902e-06,
|
1111 |
+
"loss": 2.8281,
|
1112 |
+
"step": 920
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 8.33,
|
1116 |
+
"learning_rate": 1.8518518518518519e-06,
|
1117 |
+
"loss": 2.857,
|
1118 |
+
"step": 925
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 8.38,
|
1122 |
+
"learning_rate": 1.801801801801802e-06,
|
1123 |
+
"loss": 2.7105,
|
1124 |
+
"step": 930
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 8.42,
|
1128 |
+
"learning_rate": 1.7517517517517518e-06,
|
1129 |
+
"loss": 2.7879,
|
1130 |
+
"step": 935
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 8.47,
|
1134 |
+
"learning_rate": 1.7017017017017019e-06,
|
1135 |
+
"loss": 2.8539,
|
1136 |
+
"step": 940
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 8.51,
|
1140 |
+
"learning_rate": 1.6516516516516517e-06,
|
1141 |
+
"loss": 2.7656,
|
1142 |
+
"step": 945
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 8.56,
|
1146 |
+
"learning_rate": 1.6016016016016018e-06,
|
1147 |
+
"loss": 2.677,
|
1148 |
+
"step": 950
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 8.6,
|
1152 |
+
"learning_rate": 1.5515515515515517e-06,
|
1153 |
+
"loss": 2.809,
|
1154 |
+
"step": 955
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 8.65,
|
1158 |
+
"learning_rate": 1.5015015015015017e-06,
|
1159 |
+
"loss": 2.5945,
|
1160 |
+
"step": 960
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 8.69,
|
1164 |
+
"learning_rate": 1.4514514514514516e-06,
|
1165 |
+
"loss": 2.8148,
|
1166 |
+
"step": 965
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 8.74,
|
1170 |
+
"learning_rate": 1.4014014014014016e-06,
|
1171 |
+
"loss": 2.7242,
|
1172 |
+
"step": 970
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 8.78,
|
1176 |
+
"learning_rate": 1.3513513513513515e-06,
|
1177 |
+
"loss": 2.9172,
|
1178 |
+
"step": 975
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 8.83,
|
1182 |
+
"learning_rate": 1.3013013013013016e-06,
|
1183 |
+
"loss": 2.7965,
|
1184 |
+
"step": 980
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 8.87,
|
1188 |
+
"learning_rate": 1.2512512512512514e-06,
|
1189 |
+
"loss": 2.8918,
|
1190 |
+
"step": 985
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 8.92,
|
1194 |
+
"learning_rate": 1.2012012012012013e-06,
|
1195 |
+
"loss": 2.6551,
|
1196 |
+
"step": 990
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 8.96,
|
1200 |
+
"learning_rate": 1.1511511511511512e-06,
|
1201 |
+
"loss": 2.8613,
|
1202 |
+
"step": 995
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 9.01,
|
1206 |
+
"learning_rate": 1.1011011011011012e-06,
|
1207 |
+
"loss": 2.7629,
|
1208 |
+
"step": 1000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 9.05,
|
1212 |
+
"learning_rate": 1.051051051051051e-06,
|
1213 |
+
"loss": 2.5543,
|
1214 |
+
"step": 1005
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 9.1,
|
1218 |
+
"learning_rate": 1.0010010010010011e-06,
|
1219 |
+
"loss": 2.9523,
|
1220 |
+
"step": 1010
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 9.14,
|
1224 |
+
"learning_rate": 9.50950950950951e-07,
|
1225 |
+
"loss": 2.7785,
|
1226 |
+
"step": 1015
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 9.19,
|
1230 |
+
"learning_rate": 9.00900900900901e-07,
|
1231 |
+
"loss": 2.6758,
|
1232 |
+
"step": 1020
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 9.23,
|
1236 |
+
"learning_rate": 8.508508508508509e-07,
|
1237 |
+
"loss": 2.5539,
|
1238 |
+
"step": 1025
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 9.28,
|
1242 |
+
"learning_rate": 8.008008008008009e-07,
|
1243 |
+
"loss": 2.6223,
|
1244 |
+
"step": 1030
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 9.32,
|
1248 |
+
"learning_rate": 7.507507507507509e-07,
|
1249 |
+
"loss": 2.882,
|
1250 |
+
"step": 1035
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 9.37,
|
1254 |
+
"learning_rate": 7.007007007007008e-07,
|
1255 |
+
"loss": 2.9254,
|
1256 |
+
"step": 1040
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 9.41,
|
1260 |
+
"learning_rate": 6.506506506506508e-07,
|
1261 |
+
"loss": 2.825,
|
1262 |
+
"step": 1045
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 9.46,
|
1266 |
+
"learning_rate": 6.006006006006006e-07,
|
1267 |
+
"loss": 2.7879,
|
1268 |
+
"step": 1050
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 9.5,
|
1272 |
+
"learning_rate": 5.505505505505506e-07,
|
1273 |
+
"loss": 2.7621,
|
1274 |
+
"step": 1055
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 9.55,
|
1278 |
+
"learning_rate": 5.005005005005006e-07,
|
1279 |
+
"loss": 2.7711,
|
1280 |
+
"step": 1060
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 9.59,
|
1284 |
+
"learning_rate": 4.504504504504505e-07,
|
1285 |
+
"loss": 2.7539,
|
1286 |
+
"step": 1065
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 9.64,
|
1290 |
+
"learning_rate": 4.0040040040040045e-07,
|
1291 |
+
"loss": 2.7781,
|
1292 |
+
"step": 1070
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 9.68,
|
1296 |
+
"learning_rate": 3.503503503503504e-07,
|
1297 |
+
"loss": 2.7246,
|
1298 |
+
"step": 1075
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 9.73,
|
1302 |
+
"learning_rate": 3.003003003003003e-07,
|
1303 |
+
"loss": 2.9125,
|
1304 |
+
"step": 1080
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 9.77,
|
1308 |
+
"learning_rate": 2.502502502502503e-07,
|
1309 |
+
"loss": 2.757,
|
1310 |
+
"step": 1085
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 9.82,
|
1314 |
+
"learning_rate": 2.0020020020020022e-07,
|
1315 |
+
"loss": 2.7824,
|
1316 |
+
"step": 1090
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 9.86,
|
1320 |
+
"learning_rate": 1.5015015015015016e-07,
|
1321 |
+
"loss": 2.6824,
|
1322 |
+
"step": 1095
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 9.91,
|
1326 |
+
"learning_rate": 1.0010010010010011e-07,
|
1327 |
+
"loss": 2.6035,
|
1328 |
+
"step": 1100
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 9.95,
|
1332 |
+
"learning_rate": 5.0050050050050056e-08,
|
1333 |
+
"loss": 2.7152,
|
1334 |
+
"step": 1105
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 10.0,
|
1338 |
+
"learning_rate": 0.0,
|
1339 |
+
"loss": 2.7191,
|
1340 |
+
"step": 1110
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 10.0,
|
1344 |
+
"step": 1110,
|
1345 |
+
"total_flos": 2.1618654360131705e+21,
|
1346 |
+
"train_loss": 2.8070910754504506,
|
1347 |
+
"train_runtime": 11217.8167,
|
1348 |
+
"train_samples_per_second": 101.845,
|
1349 |
+
"train_steps_per_second": 0.099
|
1350 |
+
}
|
1351 |
+
],
|
1352 |
+
"max_steps": 1110,
|
1353 |
+
"num_train_epochs": 10,
|
1354 |
+
"total_flos": 2.1618654360131705e+21,
|
1355 |
+
"trial_name": null,
|
1356 |
+
"trial_params": null
|
1357 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:979ff9182aeb728abc8d230808f9beacd1fa8f4313b31cd7cbe459946f5c8a87
|
3 |
+
size 2927
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|