hugodk-sch
commited on
Commit
•
1be5f09
1
Parent(s):
d78cfb3
Model save
Browse files- README.md +71 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1925 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: norallm/normistral-7b-warm
|
9 |
+
datasets:
|
10 |
+
- generator
|
11 |
+
model-index:
|
12 |
+
- name: ap-normistral-7b-sft-qlora
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# ap-normistral-7b-sft-qlora
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [norallm/normistral-7b-warm](https://huggingface.co/norallm/normistral-7b-warm) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6055
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0002
|
43 |
+
- train_batch_size: 4
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- gradient_accumulation_steps: 2
|
48 |
+
- total_train_batch_size: 8
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: cosine
|
51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
52 |
+
- num_epochs: 5
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 2.063 | 1.0 | 264 | 2.1618 |
|
59 |
+
| 1.2293 | 2.0 | 528 | 1.9121 |
|
60 |
+
| 0.6985 | 3.0 | 792 | 1.6916 |
|
61 |
+
| 0.4922 | 4.0 | 1056 | 1.6054 |
|
62 |
+
| 0.3396 | 5.0 | 1320 | 1.6055 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- PEFT 0.10.0
|
68 |
+
- Transformers 4.39.0.dev0
|
69 |
+
- Pytorch 2.1.2+cu121
|
70 |
+
- Datasets 2.14.6
|
71 |
+
- Tokenizers 0.15.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83946192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b5c07d98db55fecda1329927555dad628dfc0ae6094d254e93e0c9ce37ea1d8
|
3 |
size 83946192
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 1.0955926315350966,
|
4 |
+
"train_runtime": 10263.5013,
|
5 |
+
"train_samples": 4208,
|
6 |
+
"train_samples_per_second": 1.028,
|
7 |
+
"train_steps_per_second": 0.129
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 1.0955926315350966,
|
4 |
+
"train_runtime": 10263.5013,
|
5 |
+
"train_samples": 4208,
|
6 |
+
"train_samples_per_second": 1.028,
|
7 |
+
"train_steps_per_second": 0.129
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1925 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1320,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 0.2333984375,
|
14 |
+
"learning_rate": 1.5151515151515152e-06,
|
15 |
+
"loss": 2.504,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02,
|
20 |
+
"grad_norm": 0.26171875,
|
21 |
+
"learning_rate": 7.5757575757575764e-06,
|
22 |
+
"loss": 2.4856,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04,
|
27 |
+
"grad_norm": 0.197265625,
|
28 |
+
"learning_rate": 1.5151515151515153e-05,
|
29 |
+
"loss": 2.4231,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.06,
|
34 |
+
"grad_norm": 0.1708984375,
|
35 |
+
"learning_rate": 2.272727272727273e-05,
|
36 |
+
"loss": 2.4239,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.08,
|
41 |
+
"grad_norm": 0.20703125,
|
42 |
+
"learning_rate": 3.0303030303030306e-05,
|
43 |
+
"loss": 2.4352,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09,
|
48 |
+
"grad_norm": 0.23046875,
|
49 |
+
"learning_rate": 3.787878787878788e-05,
|
50 |
+
"loss": 2.4108,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11,
|
55 |
+
"grad_norm": 0.2314453125,
|
56 |
+
"learning_rate": 4.545454545454546e-05,
|
57 |
+
"loss": 2.3658,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.13,
|
62 |
+
"grad_norm": 0.1875,
|
63 |
+
"learning_rate": 5.303030303030303e-05,
|
64 |
+
"loss": 2.3141,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15,
|
69 |
+
"grad_norm": 0.181640625,
|
70 |
+
"learning_rate": 6.060606060606061e-05,
|
71 |
+
"loss": 2.3152,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.17,
|
76 |
+
"grad_norm": 0.1572265625,
|
77 |
+
"learning_rate": 6.818181818181818e-05,
|
78 |
+
"loss": 2.294,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.19,
|
83 |
+
"grad_norm": 0.1611328125,
|
84 |
+
"learning_rate": 7.575757575757576e-05,
|
85 |
+
"loss": 2.2869,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.21,
|
90 |
+
"grad_norm": 0.158203125,
|
91 |
+
"learning_rate": 8.333333333333334e-05,
|
92 |
+
"loss": 2.2961,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.23,
|
97 |
+
"grad_norm": 0.150390625,
|
98 |
+
"learning_rate": 9.090909090909092e-05,
|
99 |
+
"loss": 2.2337,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.25,
|
104 |
+
"grad_norm": 0.171875,
|
105 |
+
"learning_rate": 9.848484848484849e-05,
|
106 |
+
"loss": 2.2716,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.27,
|
111 |
+
"grad_norm": 0.166015625,
|
112 |
+
"learning_rate": 0.00010606060606060606,
|
113 |
+
"loss": 2.2456,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.28,
|
118 |
+
"grad_norm": 0.162109375,
|
119 |
+
"learning_rate": 0.00011363636363636365,
|
120 |
+
"loss": 2.2372,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3,
|
125 |
+
"grad_norm": 0.158203125,
|
126 |
+
"learning_rate": 0.00012121212121212122,
|
127 |
+
"loss": 2.231,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.32,
|
132 |
+
"grad_norm": 0.2412109375,
|
133 |
+
"learning_rate": 0.00012878787878787878,
|
134 |
+
"loss": 2.2575,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.34,
|
139 |
+
"grad_norm": 0.1640625,
|
140 |
+
"learning_rate": 0.00013636363636363637,
|
141 |
+
"loss": 2.2734,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.36,
|
146 |
+
"grad_norm": 0.17578125,
|
147 |
+
"learning_rate": 0.00014393939393939396,
|
148 |
+
"loss": 2.2141,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.38,
|
153 |
+
"grad_norm": 0.1767578125,
|
154 |
+
"learning_rate": 0.00015151515151515152,
|
155 |
+
"loss": 2.2526,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.4,
|
160 |
+
"grad_norm": 0.1748046875,
|
161 |
+
"learning_rate": 0.0001590909090909091,
|
162 |
+
"loss": 2.2879,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.42,
|
167 |
+
"grad_norm": 0.1884765625,
|
168 |
+
"learning_rate": 0.0001666666666666667,
|
169 |
+
"loss": 2.1986,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.44,
|
174 |
+
"grad_norm": 0.2021484375,
|
175 |
+
"learning_rate": 0.00017424242424242425,
|
176 |
+
"loss": 2.2265,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.45,
|
181 |
+
"grad_norm": 0.2001953125,
|
182 |
+
"learning_rate": 0.00018181818181818183,
|
183 |
+
"loss": 2.196,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.47,
|
188 |
+
"grad_norm": 0.234375,
|
189 |
+
"learning_rate": 0.00018939393939393942,
|
190 |
+
"loss": 2.1943,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.49,
|
195 |
+
"grad_norm": 0.2314453125,
|
196 |
+
"learning_rate": 0.00019696969696969698,
|
197 |
+
"loss": 2.2055,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.51,
|
202 |
+
"grad_norm": 0.2392578125,
|
203 |
+
"learning_rate": 0.0001999968531423333,
|
204 |
+
"loss": 2.173,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.53,
|
209 |
+
"grad_norm": 0.2431640625,
|
210 |
+
"learning_rate": 0.0001999776230627102,
|
211 |
+
"loss": 2.1762,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.55,
|
216 |
+
"grad_norm": 0.255859375,
|
217 |
+
"learning_rate": 0.0001999409145155235,
|
218 |
+
"loss": 2.1762,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.57,
|
223 |
+
"grad_norm": 0.265625,
|
224 |
+
"learning_rate": 0.0001998867339183008,
|
225 |
+
"loss": 2.157,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.59,
|
230 |
+
"grad_norm": 0.32421875,
|
231 |
+
"learning_rate": 0.0001998150907430998,
|
232 |
+
"loss": 2.1838,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.61,
|
237 |
+
"grad_norm": 0.2734375,
|
238 |
+
"learning_rate": 0.00019972599751485226,
|
239 |
+
"loss": 2.1985,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.62,
|
244 |
+
"grad_norm": 0.31640625,
|
245 |
+
"learning_rate": 0.00019961946980917456,
|
246 |
+
"loss": 2.1016,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.64,
|
251 |
+
"grad_norm": 0.27734375,
|
252 |
+
"learning_rate": 0.0001994955262496446,
|
253 |
+
"loss": 2.1371,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.66,
|
258 |
+
"grad_norm": 0.3125,
|
259 |
+
"learning_rate": 0.00019935418850454588,
|
260 |
+
"loss": 2.1527,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.68,
|
265 |
+
"grad_norm": 0.37109375,
|
266 |
+
"learning_rate": 0.00019919548128307954,
|
267 |
+
"loss": 2.118,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.7,
|
272 |
+
"grad_norm": 0.2890625,
|
273 |
+
"learning_rate": 0.00019901943233104443,
|
274 |
+
"loss": 2.098,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.72,
|
279 |
+
"grad_norm": 0.3515625,
|
280 |
+
"learning_rate": 0.00019882607242598663,
|
281 |
+
"loss": 2.0853,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.74,
|
286 |
+
"grad_norm": 0.30078125,
|
287 |
+
"learning_rate": 0.00019861543537181867,
|
288 |
+
"loss": 2.0832,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.76,
|
293 |
+
"grad_norm": 0.31640625,
|
294 |
+
"learning_rate": 0.00019838755799290994,
|
295 |
+
"loss": 2.1097,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.78,
|
300 |
+
"grad_norm": 0.306640625,
|
301 |
+
"learning_rate": 0.00019814248012764877,
|
302 |
+
"loss": 2.0618,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.8,
|
307 |
+
"grad_norm": 0.294921875,
|
308 |
+
"learning_rate": 0.00019788024462147788,
|
309 |
+
"loss": 2.0607,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.81,
|
314 |
+
"grad_norm": 0.3125,
|
315 |
+
"learning_rate": 0.00019760089731940384,
|
316 |
+
"loss": 2.0829,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.83,
|
321 |
+
"grad_norm": 0.361328125,
|
322 |
+
"learning_rate": 0.00019730448705798239,
|
323 |
+
"loss": 1.9736,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.85,
|
328 |
+
"grad_norm": 0.37109375,
|
329 |
+
"learning_rate": 0.0001969910656567805,
|
330 |
+
"loss": 2.033,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.87,
|
335 |
+
"grad_norm": 0.3671875,
|
336 |
+
"learning_rate": 0.00019666068790931732,
|
337 |
+
"loss": 1.9864,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.89,
|
342 |
+
"grad_norm": 0.37890625,
|
343 |
+
"learning_rate": 0.00019631341157348465,
|
344 |
+
"loss": 2.008,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.91,
|
349 |
+
"grad_norm": 0.361328125,
|
350 |
+
"learning_rate": 0.00019594929736144976,
|
351 |
+
"loss": 2.089,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.93,
|
356 |
+
"grad_norm": 0.34765625,
|
357 |
+
"learning_rate": 0.00019556840892904126,
|
358 |
+
"loss": 1.9851,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.95,
|
363 |
+
"grad_norm": 0.36328125,
|
364 |
+
"learning_rate": 0.0001951708128646208,
|
365 |
+
"loss": 1.9994,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.97,
|
370 |
+
"grad_norm": 0.3515625,
|
371 |
+
"learning_rate": 0.0001947565786774415,
|
372 |
+
"loss": 1.9324,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.98,
|
377 |
+
"grad_norm": 0.34765625,
|
378 |
+
"learning_rate": 0.00019432577878549637,
|
379 |
+
"loss": 2.063,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.0,
|
384 |
+
"eval_loss": 2.1617629528045654,
|
385 |
+
"eval_runtime": 67.9579,
|
386 |
+
"eval_samples_per_second": 3.899,
|
387 |
+
"eval_steps_per_second": 0.5,
|
388 |
+
"step": 264
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.0,
|
392 |
+
"grad_norm": 0.4453125,
|
393 |
+
"learning_rate": 0.00019387848850285772,
|
394 |
+
"loss": 1.8981,
|
395 |
+
"step": 265
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.02,
|
399 |
+
"grad_norm": 0.439453125,
|
400 |
+
"learning_rate": 0.00019341478602651069,
|
401 |
+
"loss": 1.7606,
|
402 |
+
"step": 270
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.04,
|
406 |
+
"grad_norm": 0.47265625,
|
407 |
+
"learning_rate": 0.00019293475242268223,
|
408 |
+
"loss": 1.814,
|
409 |
+
"step": 275
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.06,
|
413 |
+
"grad_norm": 0.4140625,
|
414 |
+
"learning_rate": 0.0001924384716126692,
|
415 |
+
"loss": 1.7713,
|
416 |
+
"step": 280
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.08,
|
420 |
+
"grad_norm": 0.4765625,
|
421 |
+
"learning_rate": 0.00019192603035816656,
|
422 |
+
"loss": 1.8325,
|
423 |
+
"step": 285
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.1,
|
427 |
+
"grad_norm": 0.443359375,
|
428 |
+
"learning_rate": 0.0001913975182460996,
|
429 |
+
"loss": 1.7617,
|
430 |
+
"step": 290
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.12,
|
434 |
+
"grad_norm": 0.4140625,
|
435 |
+
"learning_rate": 0.00019085302767296182,
|
436 |
+
"loss": 1.8414,
|
437 |
+
"step": 295
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.14,
|
441 |
+
"grad_norm": 0.46484375,
|
442 |
+
"learning_rate": 0.00019029265382866214,
|
443 |
+
"loss": 1.7312,
|
444 |
+
"step": 300
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.16,
|
448 |
+
"grad_norm": 0.435546875,
|
449 |
+
"learning_rate": 0.000189716494679883,
|
450 |
+
"loss": 1.8303,
|
451 |
+
"step": 305
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.17,
|
455 |
+
"grad_norm": 0.4765625,
|
456 |
+
"learning_rate": 0.00018912465095295388,
|
457 |
+
"loss": 1.7397,
|
458 |
+
"step": 310
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.19,
|
462 |
+
"grad_norm": 0.54296875,
|
463 |
+
"learning_rate": 0.00018851722611624164,
|
464 |
+
"loss": 1.7772,
|
465 |
+
"step": 315
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.21,
|
469 |
+
"grad_norm": 0.45703125,
|
470 |
+
"learning_rate": 0.00018789432636206197,
|
471 |
+
"loss": 1.7317,
|
472 |
+
"step": 320
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.23,
|
476 |
+
"grad_norm": 0.5078125,
|
477 |
+
"learning_rate": 0.00018725606058811424,
|
478 |
+
"loss": 1.7184,
|
479 |
+
"step": 325
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.25,
|
483 |
+
"grad_norm": 0.451171875,
|
484 |
+
"learning_rate": 0.00018660254037844388,
|
485 |
+
"loss": 1.798,
|
486 |
+
"step": 330
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.27,
|
490 |
+
"grad_norm": 0.61328125,
|
491 |
+
"learning_rate": 0.00018593387998393457,
|
492 |
+
"loss": 1.6324,
|
493 |
+
"step": 335
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.29,
|
497 |
+
"grad_norm": 0.48046875,
|
498 |
+
"learning_rate": 0.00018525019630233463,
|
499 |
+
"loss": 1.6136,
|
500 |
+
"step": 340
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.31,
|
504 |
+
"grad_norm": 0.51171875,
|
505 |
+
"learning_rate": 0.00018455160885782045,
|
506 |
+
"loss": 1.7733,
|
507 |
+
"step": 345
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.33,
|
511 |
+
"grad_norm": 0.6328125,
|
512 |
+
"learning_rate": 0.00018383823978010075,
|
513 |
+
"loss": 1.6591,
|
514 |
+
"step": 350
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.34,
|
518 |
+
"grad_norm": 0.62109375,
|
519 |
+
"learning_rate": 0.00018311021378306563,
|
520 |
+
"loss": 1.6217,
|
521 |
+
"step": 355
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.36,
|
525 |
+
"grad_norm": 0.6015625,
|
526 |
+
"learning_rate": 0.0001823676581429833,
|
527 |
+
"loss": 1.5634,
|
528 |
+
"step": 360
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.38,
|
532 |
+
"grad_norm": 0.5078125,
|
533 |
+
"learning_rate": 0.00018161070267624937,
|
534 |
+
"loss": 1.7062,
|
535 |
+
"step": 365
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.4,
|
539 |
+
"grad_norm": 0.55078125,
|
540 |
+
"learning_rate": 0.0001808394797166919,
|
541 |
+
"loss": 1.6042,
|
542 |
+
"step": 370
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.42,
|
546 |
+
"grad_norm": 0.51171875,
|
547 |
+
"learning_rate": 0.00018005412409243606,
|
548 |
+
"loss": 1.6031,
|
549 |
+
"step": 375
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.44,
|
553 |
+
"grad_norm": 0.56640625,
|
554 |
+
"learning_rate": 0.00017925477310233316,
|
555 |
+
"loss": 1.4434,
|
556 |
+
"step": 380
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.46,
|
560 |
+
"grad_norm": 0.63671875,
|
561 |
+
"learning_rate": 0.00017844156649195759,
|
562 |
+
"loss": 1.4816,
|
563 |
+
"step": 385
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.48,
|
567 |
+
"grad_norm": 0.5703125,
|
568 |
+
"learning_rate": 0.0001776146464291757,
|
569 |
+
"loss": 1.5563,
|
570 |
+
"step": 390
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.5,
|
574 |
+
"grad_norm": 0.640625,
|
575 |
+
"learning_rate": 0.00017677415747929174,
|
576 |
+
"loss": 1.5238,
|
577 |
+
"step": 395
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.52,
|
581 |
+
"grad_norm": 0.6328125,
|
582 |
+
"learning_rate": 0.00017592024657977432,
|
583 |
+
"loss": 1.5693,
|
584 |
+
"step": 400
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.53,
|
588 |
+
"grad_norm": 0.5625,
|
589 |
+
"learning_rate": 0.00017505306301456822,
|
590 |
+
"loss": 1.5205,
|
591 |
+
"step": 405
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.55,
|
595 |
+
"grad_norm": 0.58984375,
|
596 |
+
"learning_rate": 0.00017417275838799596,
|
597 |
+
"loss": 1.537,
|
598 |
+
"step": 410
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.57,
|
602 |
+
"grad_norm": 0.6484375,
|
603 |
+
"learning_rate": 0.0001732794865982539,
|
604 |
+
"loss": 1.4182,
|
605 |
+
"step": 415
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.59,
|
609 |
+
"grad_norm": 0.609375,
|
610 |
+
"learning_rate": 0.00017237340381050703,
|
611 |
+
"loss": 1.4714,
|
612 |
+
"step": 420
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.61,
|
616 |
+
"grad_norm": 0.578125,
|
617 |
+
"learning_rate": 0.00017145466842958764,
|
618 |
+
"loss": 1.4167,
|
619 |
+
"step": 425
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.63,
|
623 |
+
"grad_norm": 0.6796875,
|
624 |
+
"learning_rate": 0.00017052344107230241,
|
625 |
+
"loss": 1.4556,
|
626 |
+
"step": 430
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.65,
|
630 |
+
"grad_norm": 0.64453125,
|
631 |
+
"learning_rate": 0.00016957988453935276,
|
632 |
+
"loss": 1.3048,
|
633 |
+
"step": 435
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.67,
|
637 |
+
"grad_norm": 0.5859375,
|
638 |
+
"learning_rate": 0.0001686241637868734,
|
639 |
+
"loss": 1.4648,
|
640 |
+
"step": 440
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.69,
|
644 |
+
"grad_norm": 0.609375,
|
645 |
+
"learning_rate": 0.00016765644589759396,
|
646 |
+
"loss": 1.3969,
|
647 |
+
"step": 445
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.7,
|
651 |
+
"grad_norm": 0.65625,
|
652 |
+
"learning_rate": 0.00016667690005162916,
|
653 |
+
"loss": 1.5284,
|
654 |
+
"step": 450
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.72,
|
658 |
+
"grad_norm": 0.7265625,
|
659 |
+
"learning_rate": 0.00016568569749690208,
|
660 |
+
"loss": 1.3291,
|
661 |
+
"step": 455
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.74,
|
665 |
+
"grad_norm": 0.6484375,
|
666 |
+
"learning_rate": 0.00016468301151920575,
|
667 |
+
"loss": 1.3605,
|
668 |
+
"step": 460
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.76,
|
672 |
+
"grad_norm": 0.61328125,
|
673 |
+
"learning_rate": 0.00016366901741190882,
|
674 |
+
"loss": 1.4962,
|
675 |
+
"step": 465
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.78,
|
679 |
+
"grad_norm": 0.703125,
|
680 |
+
"learning_rate": 0.00016264389244531014,
|
681 |
+
"loss": 1.3618,
|
682 |
+
"step": 470
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.8,
|
686 |
+
"grad_norm": 0.64453125,
|
687 |
+
"learning_rate": 0.0001616078158356475,
|
688 |
+
"loss": 1.391,
|
689 |
+
"step": 475
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.82,
|
693 |
+
"grad_norm": 0.75,
|
694 |
+
"learning_rate": 0.00016056096871376667,
|
695 |
+
"loss": 1.2776,
|
696 |
+
"step": 480
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.84,
|
700 |
+
"grad_norm": 0.64453125,
|
701 |
+
"learning_rate": 0.00015950353409345517,
|
702 |
+
"loss": 1.4267,
|
703 |
+
"step": 485
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.86,
|
707 |
+
"grad_norm": 0.609375,
|
708 |
+
"learning_rate": 0.0001584356968394471,
|
709 |
+
"loss": 1.2524,
|
710 |
+
"step": 490
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.88,
|
714 |
+
"grad_norm": 0.63671875,
|
715 |
+
"learning_rate": 0.0001573576436351046,
|
716 |
+
"loss": 1.3176,
|
717 |
+
"step": 495
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.89,
|
721 |
+
"grad_norm": 0.7578125,
|
722 |
+
"learning_rate": 0.00015626956294978103,
|
723 |
+
"loss": 1.2975,
|
724 |
+
"step": 500
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 1.91,
|
728 |
+
"grad_norm": 0.70703125,
|
729 |
+
"learning_rate": 0.0001551716450058719,
|
730 |
+
"loss": 1.2803,
|
731 |
+
"step": 505
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 1.93,
|
735 |
+
"grad_norm": 0.59375,
|
736 |
+
"learning_rate": 0.00015406408174555976,
|
737 |
+
"loss": 1.3139,
|
738 |
+
"step": 510
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 1.95,
|
742 |
+
"grad_norm": 0.74609375,
|
743 |
+
"learning_rate": 0.0001529470667972579,
|
744 |
+
"loss": 1.2867,
|
745 |
+
"step": 515
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.97,
|
749 |
+
"grad_norm": 0.70703125,
|
750 |
+
"learning_rate": 0.00015182079544175955,
|
751 |
+
"loss": 1.3683,
|
752 |
+
"step": 520
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.99,
|
756 |
+
"grad_norm": 0.82421875,
|
757 |
+
"learning_rate": 0.0001506854645780983,
|
758 |
+
"loss": 1.2293,
|
759 |
+
"step": 525
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 2.0,
|
763 |
+
"eval_loss": 1.9121202230453491,
|
764 |
+
"eval_runtime": 67.9476,
|
765 |
+
"eval_samples_per_second": 3.9,
|
766 |
+
"eval_steps_per_second": 0.5,
|
767 |
+
"step": 528
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.01,
|
771 |
+
"grad_norm": 0.796875,
|
772 |
+
"learning_rate": 0.00014954127268912526,
|
773 |
+
"loss": 1.1291,
|
774 |
+
"step": 530
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.03,
|
778 |
+
"grad_norm": 0.765625,
|
779 |
+
"learning_rate": 0.0001483884198068096,
|
780 |
+
"loss": 1.045,
|
781 |
+
"step": 535
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.05,
|
785 |
+
"grad_norm": 0.8125,
|
786 |
+
"learning_rate": 0.0001472271074772683,
|
787 |
+
"loss": 0.9242,
|
788 |
+
"step": 540
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.06,
|
792 |
+
"grad_norm": 0.89453125,
|
793 |
+
"learning_rate": 0.00014605753872553093,
|
794 |
+
"loss": 1.0677,
|
795 |
+
"step": 545
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.08,
|
799 |
+
"grad_norm": 0.81640625,
|
800 |
+
"learning_rate": 0.00014487991802004623,
|
801 |
+
"loss": 0.9137,
|
802 |
+
"step": 550
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.1,
|
806 |
+
"grad_norm": 0.78515625,
|
807 |
+
"learning_rate": 0.00014369445123693596,
|
808 |
+
"loss": 0.9222,
|
809 |
+
"step": 555
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.12,
|
813 |
+
"grad_norm": 0.7734375,
|
814 |
+
"learning_rate": 0.000142501345624003,
|
815 |
+
"loss": 0.89,
|
816 |
+
"step": 560
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.14,
|
820 |
+
"grad_norm": 0.72265625,
|
821 |
+
"learning_rate": 0.00014130080976449948,
|
822 |
+
"loss": 1.0561,
|
823 |
+
"step": 565
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.16,
|
827 |
+
"grad_norm": 0.76953125,
|
828 |
+
"learning_rate": 0.00014009305354066137,
|
829 |
+
"loss": 1.0657,
|
830 |
+
"step": 570
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.18,
|
834 |
+
"grad_norm": 0.671875,
|
835 |
+
"learning_rate": 0.0001388782880970162,
|
836 |
+
"loss": 0.8967,
|
837 |
+
"step": 575
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.2,
|
841 |
+
"grad_norm": 0.8359375,
|
842 |
+
"learning_rate": 0.00013765672580346987,
|
843 |
+
"loss": 0.9202,
|
844 |
+
"step": 580
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.22,
|
848 |
+
"grad_norm": 0.92578125,
|
849 |
+
"learning_rate": 0.00013642858021817943,
|
850 |
+
"loss": 0.8938,
|
851 |
+
"step": 585
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.23,
|
855 |
+
"grad_norm": 0.875,
|
856 |
+
"learning_rate": 0.00013519406605021797,
|
857 |
+
"loss": 0.9264,
|
858 |
+
"step": 590
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.25,
|
862 |
+
"grad_norm": 0.765625,
|
863 |
+
"learning_rate": 0.00013395339912203829,
|
864 |
+
"loss": 0.9314,
|
865 |
+
"step": 595
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.27,
|
869 |
+
"grad_norm": 0.84375,
|
870 |
+
"learning_rate": 0.00013270679633174218,
|
871 |
+
"loss": 0.7482,
|
872 |
+
"step": 600
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.29,
|
876 |
+
"grad_norm": 0.83203125,
|
877 |
+
"learning_rate": 0.00013145447561516138,
|
878 |
+
"loss": 0.8059,
|
879 |
+
"step": 605
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.31,
|
883 |
+
"grad_norm": 0.81640625,
|
884 |
+
"learning_rate": 0.00013019665590775716,
|
885 |
+
"loss": 0.8082,
|
886 |
+
"step": 610
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.33,
|
890 |
+
"grad_norm": 0.98046875,
|
891 |
+
"learning_rate": 0.0001289335571063453,
|
892 |
+
"loss": 0.7883,
|
893 |
+
"step": 615
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.35,
|
897 |
+
"grad_norm": 0.73046875,
|
898 |
+
"learning_rate": 0.0001276654000306527,
|
899 |
+
"loss": 0.7813,
|
900 |
+
"step": 620
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.37,
|
904 |
+
"grad_norm": 0.76953125,
|
905 |
+
"learning_rate": 0.00012639240638471317,
|
906 |
+
"loss": 0.9305,
|
907 |
+
"step": 625
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.39,
|
911 |
+
"grad_norm": 0.59765625,
|
912 |
+
"learning_rate": 0.0001251147987181079,
|
913 |
+
"loss": 0.7705,
|
914 |
+
"step": 630
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.41,
|
918 |
+
"grad_norm": 0.9375,
|
919 |
+
"learning_rate": 0.00012383280038705884,
|
920 |
+
"loss": 0.8381,
|
921 |
+
"step": 635
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.42,
|
925 |
+
"grad_norm": 0.70703125,
|
926 |
+
"learning_rate": 0.00012254663551538046,
|
927 |
+
"loss": 0.9174,
|
928 |
+
"step": 640
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.44,
|
932 |
+
"grad_norm": 0.9453125,
|
933 |
+
"learning_rate": 0.00012125652895529766,
|
934 |
+
"loss": 0.9508,
|
935 |
+
"step": 645
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.46,
|
939 |
+
"grad_norm": 0.78515625,
|
940 |
+
"learning_rate": 0.00011996270624813642,
|
941 |
+
"loss": 0.9384,
|
942 |
+
"step": 650
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.48,
|
946 |
+
"grad_norm": 0.8828125,
|
947 |
+
"learning_rate": 0.00011866539358489345,
|
948 |
+
"loss": 0.7756,
|
949 |
+
"step": 655
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 2.5,
|
953 |
+
"grad_norm": 0.88671875,
|
954 |
+
"learning_rate": 0.00011736481776669306,
|
955 |
+
"loss": 0.8655,
|
956 |
+
"step": 660
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 2.52,
|
960 |
+
"grad_norm": 0.73046875,
|
961 |
+
"learning_rate": 0.00011606120616513648,
|
962 |
+
"loss": 0.8007,
|
963 |
+
"step": 665
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 2.54,
|
967 |
+
"grad_norm": 0.7734375,
|
968 |
+
"learning_rate": 0.00011475478668255222,
|
969 |
+
"loss": 0.9225,
|
970 |
+
"step": 670
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 2.56,
|
974 |
+
"grad_norm": 0.86328125,
|
975 |
+
"learning_rate": 0.00011344578771215319,
|
976 |
+
"loss": 0.7905,
|
977 |
+
"step": 675
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.58,
|
981 |
+
"grad_norm": 0.82421875,
|
982 |
+
"learning_rate": 0.0001121344380981082,
|
983 |
+
"loss": 0.8412,
|
984 |
+
"step": 680
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 2.59,
|
988 |
+
"grad_norm": 0.69921875,
|
989 |
+
"learning_rate": 0.00011082096709553442,
|
990 |
+
"loss": 0.8604,
|
991 |
+
"step": 685
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 2.61,
|
995 |
+
"grad_norm": 0.828125,
|
996 |
+
"learning_rate": 0.00010950560433041826,
|
997 |
+
"loss": 0.8263,
|
998 |
+
"step": 690
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 2.63,
|
1002 |
+
"grad_norm": 0.78515625,
|
1003 |
+
"learning_rate": 0.00010818857975947128,
|
1004 |
+
"loss": 0.8888,
|
1005 |
+
"step": 695
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 2.65,
|
1009 |
+
"grad_norm": 0.7109375,
|
1010 |
+
"learning_rate": 0.0001068701236299281,
|
1011 |
+
"loss": 0.868,
|
1012 |
+
"step": 700
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 2.67,
|
1016 |
+
"grad_norm": 0.765625,
|
1017 |
+
"learning_rate": 0.00010555046643929403,
|
1018 |
+
"loss": 0.8699,
|
1019 |
+
"step": 705
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 2.69,
|
1023 |
+
"grad_norm": 0.73828125,
|
1024 |
+
"learning_rate": 0.00010422983889504831,
|
1025 |
+
"loss": 0.7818,
|
1026 |
+
"step": 710
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 2.71,
|
1030 |
+
"grad_norm": 0.81640625,
|
1031 |
+
"learning_rate": 0.00010290847187431113,
|
1032 |
+
"loss": 0.8963,
|
1033 |
+
"step": 715
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.73,
|
1037 |
+
"grad_norm": 0.58203125,
|
1038 |
+
"learning_rate": 0.00010158659638348081,
|
1039 |
+
"loss": 0.659,
|
1040 |
+
"step": 720
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.75,
|
1044 |
+
"grad_norm": 0.74609375,
|
1045 |
+
"learning_rate": 0.00010026444351784822,
|
1046 |
+
"loss": 0.7786,
|
1047 |
+
"step": 725
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 2.77,
|
1051 |
+
"grad_norm": 0.87109375,
|
1052 |
+
"learning_rate": 9.894224442119607e-05,
|
1053 |
+
"loss": 0.7708,
|
1054 |
+
"step": 730
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 2.78,
|
1058 |
+
"grad_norm": 0.71875,
|
1059 |
+
"learning_rate": 9.762023024538926e-05,
|
1060 |
+
"loss": 0.7358,
|
1061 |
+
"step": 735
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 2.8,
|
1065 |
+
"grad_norm": 0.77734375,
|
1066 |
+
"learning_rate": 9.629863210996419e-05,
|
1067 |
+
"loss": 0.859,
|
1068 |
+
"step": 740
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 2.82,
|
1072 |
+
"grad_norm": 0.79296875,
|
1073 |
+
"learning_rate": 9.49776810617235e-05,
|
1074 |
+
"loss": 0.6883,
|
1075 |
+
"step": 745
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 2.84,
|
1079 |
+
"grad_norm": 0.82421875,
|
1080 |
+
"learning_rate": 9.365760803434355e-05,
|
1081 |
+
"loss": 0.6727,
|
1082 |
+
"step": 750
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 2.86,
|
1086 |
+
"grad_norm": 0.7734375,
|
1087 |
+
"learning_rate": 9.233864380800178e-05,
|
1088 |
+
"loss": 0.7685,
|
1089 |
+
"step": 755
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.88,
|
1093 |
+
"grad_norm": 0.87890625,
|
1094 |
+
"learning_rate": 9.102101896903084e-05,
|
1095 |
+
"loss": 0.8278,
|
1096 |
+
"step": 760
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 2.9,
|
1100 |
+
"grad_norm": 0.83203125,
|
1101 |
+
"learning_rate": 8.970496386960656e-05,
|
1102 |
+
"loss": 0.7174,
|
1103 |
+
"step": 765
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 2.92,
|
1107 |
+
"grad_norm": 0.82421875,
|
1108 |
+
"learning_rate": 8.839070858747697e-05,
|
1109 |
+
"loss": 0.7189,
|
1110 |
+
"step": 770
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.94,
|
1114 |
+
"grad_norm": 0.80078125,
|
1115 |
+
"learning_rate": 8.707848288573926e-05,
|
1116 |
+
"loss": 0.6564,
|
1117 |
+
"step": 775
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 2.95,
|
1121 |
+
"grad_norm": 0.79296875,
|
1122 |
+
"learning_rate": 8.57685161726715e-05,
|
1123 |
+
"loss": 0.6793,
|
1124 |
+
"step": 780
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 2.97,
|
1128 |
+
"grad_norm": 0.70703125,
|
1129 |
+
"learning_rate": 8.446103746162698e-05,
|
1130 |
+
"loss": 0.8086,
|
1131 |
+
"step": 785
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 2.99,
|
1135 |
+
"grad_norm": 0.7734375,
|
1136 |
+
"learning_rate": 8.315627533099696e-05,
|
1137 |
+
"loss": 0.6985,
|
1138 |
+
"step": 790
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 3.0,
|
1142 |
+
"eval_loss": 1.6915704011917114,
|
1143 |
+
"eval_runtime": 67.8527,
|
1144 |
+
"eval_samples_per_second": 3.906,
|
1145 |
+
"eval_steps_per_second": 0.501,
|
1146 |
+
"step": 792
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 3.01,
|
1150 |
+
"grad_norm": 0.73046875,
|
1151 |
+
"learning_rate": 8.185445788424974e-05,
|
1152 |
+
"loss": 0.5262,
|
1153 |
+
"step": 795
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 3.03,
|
1157 |
+
"grad_norm": 0.703125,
|
1158 |
+
"learning_rate": 8.055581271005292e-05,
|
1159 |
+
"loss": 0.57,
|
1160 |
+
"step": 800
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 3.05,
|
1164 |
+
"grad_norm": 0.84375,
|
1165 |
+
"learning_rate": 7.92605668424853e-05,
|
1166 |
+
"loss": 0.4825,
|
1167 |
+
"step": 805
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 3.07,
|
1171 |
+
"grad_norm": 0.73828125,
|
1172 |
+
"learning_rate": 7.796894672134594e-05,
|
1173 |
+
"loss": 0.5857,
|
1174 |
+
"step": 810
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"epoch": 3.09,
|
1178 |
+
"grad_norm": 0.76171875,
|
1179 |
+
"learning_rate": 7.668117815256729e-05,
|
1180 |
+
"loss": 0.4708,
|
1181 |
+
"step": 815
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 3.11,
|
1185 |
+
"grad_norm": 0.78515625,
|
1186 |
+
"learning_rate": 7.539748626873866e-05,
|
1187 |
+
"loss": 0.5465,
|
1188 |
+
"step": 820
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 3.12,
|
1192 |
+
"grad_norm": 0.80859375,
|
1193 |
+
"learning_rate": 7.411809548974792e-05,
|
1194 |
+
"loss": 0.5395,
|
1195 |
+
"step": 825
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 3.14,
|
1199 |
+
"grad_norm": 0.6640625,
|
1200 |
+
"learning_rate": 7.28432294835474e-05,
|
1201 |
+
"loss": 0.5176,
|
1202 |
+
"step": 830
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 3.16,
|
1206 |
+
"grad_norm": 0.640625,
|
1207 |
+
"learning_rate": 7.157311112705149e-05,
|
1208 |
+
"loss": 0.5352,
|
1209 |
+
"step": 835
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 3.18,
|
1213 |
+
"grad_norm": 0.796875,
|
1214 |
+
"learning_rate": 7.030796246717255e-05,
|
1215 |
+
"loss": 0.5097,
|
1216 |
+
"step": 840
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 3.2,
|
1220 |
+
"grad_norm": 0.78515625,
|
1221 |
+
"learning_rate": 6.904800468200143e-05,
|
1222 |
+
"loss": 0.4998,
|
1223 |
+
"step": 845
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 3.22,
|
1227 |
+
"grad_norm": 0.73828125,
|
1228 |
+
"learning_rate": 6.779345804214088e-05,
|
1229 |
+
"loss": 0.491,
|
1230 |
+
"step": 850
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 3.24,
|
1234 |
+
"grad_norm": 0.66796875,
|
1235 |
+
"learning_rate": 6.654454187219649e-05,
|
1236 |
+
"loss": 0.5098,
|
1237 |
+
"step": 855
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 3.26,
|
1241 |
+
"grad_norm": 0.609375,
|
1242 |
+
"learning_rate": 6.530147451243377e-05,
|
1243 |
+
"loss": 0.5362,
|
1244 |
+
"step": 860
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 3.28,
|
1248 |
+
"grad_norm": 0.875,
|
1249 |
+
"learning_rate": 6.406447328060709e-05,
|
1250 |
+
"loss": 0.5549,
|
1251 |
+
"step": 865
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 3.3,
|
1255 |
+
"grad_norm": 0.67578125,
|
1256 |
+
"learning_rate": 6.283375443396726e-05,
|
1257 |
+
"loss": 0.4999,
|
1258 |
+
"step": 870
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 3.31,
|
1262 |
+
"grad_norm": 0.64453125,
|
1263 |
+
"learning_rate": 6.160953313145463e-05,
|
1264 |
+
"loss": 0.471,
|
1265 |
+
"step": 875
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 3.33,
|
1269 |
+
"grad_norm": 0.6640625,
|
1270 |
+
"learning_rate": 6.039202339608432e-05,
|
1271 |
+
"loss": 0.4818,
|
1272 |
+
"step": 880
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 3.35,
|
1276 |
+
"grad_norm": 0.75,
|
1277 |
+
"learning_rate": 5.918143807752972e-05,
|
1278 |
+
"loss": 0.5522,
|
1279 |
+
"step": 885
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 3.37,
|
1283 |
+
"grad_norm": 0.7890625,
|
1284 |
+
"learning_rate": 5.797798881491138e-05,
|
1285 |
+
"loss": 0.4821,
|
1286 |
+
"step": 890
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 3.39,
|
1290 |
+
"grad_norm": 0.7578125,
|
1291 |
+
"learning_rate": 5.678188599979753e-05,
|
1292 |
+
"loss": 0.5222,
|
1293 |
+
"step": 895
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 3.41,
|
1297 |
+
"grad_norm": 0.7734375,
|
1298 |
+
"learning_rate": 5.559333873942259e-05,
|
1299 |
+
"loss": 0.4699,
|
1300 |
+
"step": 900
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 3.43,
|
1304 |
+
"grad_norm": 0.69921875,
|
1305 |
+
"learning_rate": 5.44125548201301e-05,
|
1306 |
+
"loss": 0.4958,
|
1307 |
+
"step": 905
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 3.45,
|
1311 |
+
"grad_norm": 0.66015625,
|
1312 |
+
"learning_rate": 5.3239740671046864e-05,
|
1313 |
+
"loss": 0.6005,
|
1314 |
+
"step": 910
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 3.47,
|
1318 |
+
"grad_norm": 0.6953125,
|
1319 |
+
"learning_rate": 5.207510132799436e-05,
|
1320 |
+
"loss": 0.5334,
|
1321 |
+
"step": 915
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.48,
|
1325 |
+
"grad_norm": 0.80859375,
|
1326 |
+
"learning_rate": 5.091884039764321e-05,
|
1327 |
+
"loss": 0.481,
|
1328 |
+
"step": 920
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 3.5,
|
1332 |
+
"grad_norm": 0.79296875,
|
1333 |
+
"learning_rate": 4.9771160021918305e-05,
|
1334 |
+
"loss": 0.5972,
|
1335 |
+
"step": 925
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 3.52,
|
1339 |
+
"grad_norm": 0.66796875,
|
1340 |
+
"learning_rate": 4.8632260842659393e-05,
|
1341 |
+
"loss": 0.5062,
|
1342 |
+
"step": 930
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 3.54,
|
1346 |
+
"grad_norm": 0.765625,
|
1347 |
+
"learning_rate": 4.7502341966544e-05,
|
1348 |
+
"loss": 0.5411,
|
1349 |
+
"step": 935
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 3.56,
|
1353 |
+
"grad_norm": 0.765625,
|
1354 |
+
"learning_rate": 4.638160093027908e-05,
|
1355 |
+
"loss": 0.4579,
|
1356 |
+
"step": 940
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 3.58,
|
1360 |
+
"grad_norm": 0.703125,
|
1361 |
+
"learning_rate": 4.527023366606679e-05,
|
1362 |
+
"loss": 0.5362,
|
1363 |
+
"step": 945
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 3.6,
|
1367 |
+
"grad_norm": 0.859375,
|
1368 |
+
"learning_rate": 4.416843446735077e-05,
|
1369 |
+
"loss": 0.5176,
|
1370 |
+
"step": 950
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 3.62,
|
1374 |
+
"grad_norm": 0.83984375,
|
1375 |
+
"learning_rate": 4.3076395954849236e-05,
|
1376 |
+
"loss": 0.5847,
|
1377 |
+
"step": 955
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 3.64,
|
1381 |
+
"grad_norm": 0.6015625,
|
1382 |
+
"learning_rate": 4.19943090428802e-05,
|
1383 |
+
"loss": 0.4638,
|
1384 |
+
"step": 960
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 3.66,
|
1388 |
+
"grad_norm": 0.859375,
|
1389 |
+
"learning_rate": 4.092236290598499e-05,
|
1390 |
+
"loss": 0.5305,
|
1391 |
+
"step": 965
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 3.67,
|
1395 |
+
"grad_norm": 0.69140625,
|
1396 |
+
"learning_rate": 3.986074494585619e-05,
|
1397 |
+
"loss": 0.4742,
|
1398 |
+
"step": 970
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 3.69,
|
1402 |
+
"grad_norm": 0.68359375,
|
1403 |
+
"learning_rate": 3.880964075857535e-05,
|
1404 |
+
"loss": 0.5312,
|
1405 |
+
"step": 975
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 3.71,
|
1409 |
+
"grad_norm": 0.64453125,
|
1410 |
+
"learning_rate": 3.776923410216636e-05,
|
1411 |
+
"loss": 0.4508,
|
1412 |
+
"step": 980
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 3.73,
|
1416 |
+
"grad_norm": 0.69140625,
|
1417 |
+
"learning_rate": 3.673970686447005e-05,
|
1418 |
+
"loss": 0.5022,
|
1419 |
+
"step": 985
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 3.75,
|
1423 |
+
"grad_norm": 0.765625,
|
1424 |
+
"learning_rate": 3.5721239031346066e-05,
|
1425 |
+
"loss": 0.4655,
|
1426 |
+
"step": 990
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 3.77,
|
1430 |
+
"grad_norm": 0.7734375,
|
1431 |
+
"learning_rate": 3.4714008655207e-05,
|
1432 |
+
"loss": 0.3936,
|
1433 |
+
"step": 995
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 3.79,
|
1437 |
+
"grad_norm": 0.82421875,
|
1438 |
+
"learning_rate": 3.37181918238904e-05,
|
1439 |
+
"loss": 0.508,
|
1440 |
+
"step": 1000
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 3.81,
|
1444 |
+
"grad_norm": 0.703125,
|
1445 |
+
"learning_rate": 3.273396262987475e-05,
|
1446 |
+
"loss": 0.4346,
|
1447 |
+
"step": 1005
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 3.83,
|
1451 |
+
"grad_norm": 0.6640625,
|
1452 |
+
"learning_rate": 3.1761493139843735e-05,
|
1453 |
+
"loss": 0.4455,
|
1454 |
+
"step": 1010
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 3.84,
|
1458 |
+
"grad_norm": 0.62109375,
|
1459 |
+
"learning_rate": 3.080095336460491e-05,
|
1460 |
+
"loss": 0.431,
|
1461 |
+
"step": 1015
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 3.86,
|
1465 |
+
"grad_norm": 0.7265625,
|
1466 |
+
"learning_rate": 2.9852511229367865e-05,
|
1467 |
+
"loss": 0.4371,
|
1468 |
+
"step": 1020
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 3.88,
|
1472 |
+
"grad_norm": 0.6875,
|
1473 |
+
"learning_rate": 2.891633254438685e-05,
|
1474 |
+
"loss": 0.4578,
|
1475 |
+
"step": 1025
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 3.9,
|
1479 |
+
"grad_norm": 0.59375,
|
1480 |
+
"learning_rate": 2.7992580975973136e-05,
|
1481 |
+
"loss": 0.5402,
|
1482 |
+
"step": 1030
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 3.92,
|
1486 |
+
"grad_norm": 0.6953125,
|
1487 |
+
"learning_rate": 2.70814180178823e-05,
|
1488 |
+
"loss": 0.4338,
|
1489 |
+
"step": 1035
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 3.94,
|
1493 |
+
"grad_norm": 0.8046875,
|
1494 |
+
"learning_rate": 2.618300296308135e-05,
|
1495 |
+
"loss": 0.4541,
|
1496 |
+
"step": 1040
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 3.96,
|
1500 |
+
"grad_norm": 0.640625,
|
1501 |
+
"learning_rate": 2.529749287590042e-05,
|
1502 |
+
"loss": 0.4433,
|
1503 |
+
"step": 1045
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 3.98,
|
1507 |
+
"grad_norm": 0.640625,
|
1508 |
+
"learning_rate": 2.4425042564574184e-05,
|
1509 |
+
"loss": 0.4724,
|
1510 |
+
"step": 1050
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 4.0,
|
1514 |
+
"grad_norm": 0.8125,
|
1515 |
+
"learning_rate": 2.356580455417776e-05,
|
1516 |
+
"loss": 0.4922,
|
1517 |
+
"step": 1055
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 4.0,
|
1521 |
+
"eval_loss": 1.6053533554077148,
|
1522 |
+
"eval_runtime": 67.9802,
|
1523 |
+
"eval_samples_per_second": 3.898,
|
1524 |
+
"eval_steps_per_second": 0.5,
|
1525 |
+
"step": 1056
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 4.02,
|
1529 |
+
"grad_norm": 0.73828125,
|
1530 |
+
"learning_rate": 2.2719929059961698e-05,
|
1531 |
+
"loss": 0.4008,
|
1532 |
+
"step": 1060
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 4.03,
|
1536 |
+
"grad_norm": 0.5859375,
|
1537 |
+
"learning_rate": 2.1887563961090663e-05,
|
1538 |
+
"loss": 0.3496,
|
1539 |
+
"step": 1065
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 4.05,
|
1543 |
+
"grad_norm": 0.62109375,
|
1544 |
+
"learning_rate": 2.106885477479078e-05,
|
1545 |
+
"loss": 0.486,
|
1546 |
+
"step": 1070
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 4.07,
|
1550 |
+
"grad_norm": 0.671875,
|
1551 |
+
"learning_rate": 2.0263944630909738e-05,
|
1552 |
+
"loss": 0.3697,
|
1553 |
+
"step": 1075
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 4.09,
|
1557 |
+
"grad_norm": 0.65625,
|
1558 |
+
"learning_rate": 1.947297424689414e-05,
|
1559 |
+
"loss": 0.4396,
|
1560 |
+
"step": 1080
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 4.11,
|
1564 |
+
"grad_norm": 0.71484375,
|
1565 |
+
"learning_rate": 1.8696081903188955e-05,
|
1566 |
+
"loss": 0.3916,
|
1567 |
+
"step": 1085
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 4.13,
|
1571 |
+
"grad_norm": 0.6640625,
|
1572 |
+
"learning_rate": 1.7933403419062688e-05,
|
1573 |
+
"loss": 0.4399,
|
1574 |
+
"step": 1090
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 4.15,
|
1578 |
+
"grad_norm": 0.6953125,
|
1579 |
+
"learning_rate": 1.7185072128862933e-05,
|
1580 |
+
"loss": 0.486,
|
1581 |
+
"step": 1095
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 4.17,
|
1585 |
+
"grad_norm": 0.6640625,
|
1586 |
+
"learning_rate": 1.6451218858706374e-05,
|
1587 |
+
"loss": 0.4195,
|
1588 |
+
"step": 1100
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 4.19,
|
1592 |
+
"grad_norm": 0.609375,
|
1593 |
+
"learning_rate": 1.573197190360729e-05,
|
1594 |
+
"loss": 0.3948,
|
1595 |
+
"step": 1105
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 4.2,
|
1599 |
+
"grad_norm": 0.70703125,
|
1600 |
+
"learning_rate": 1.5027457005048573e-05,
|
1601 |
+
"loss": 0.4698,
|
1602 |
+
"step": 1110
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 4.22,
|
1606 |
+
"grad_norm": 0.6796875,
|
1607 |
+
"learning_rate": 1.433779732899897e-05,
|
1608 |
+
"loss": 0.3929,
|
1609 |
+
"step": 1115
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 4.24,
|
1613 |
+
"grad_norm": 0.71484375,
|
1614 |
+
"learning_rate": 1.3663113444380905e-05,
|
1615 |
+
"loss": 0.3774,
|
1616 |
+
"step": 1120
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 4.26,
|
1620 |
+
"grad_norm": 0.72265625,
|
1621 |
+
"learning_rate": 1.3003523301992104e-05,
|
1622 |
+
"loss": 0.495,
|
1623 |
+
"step": 1125
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 4.28,
|
1627 |
+
"grad_norm": 0.63671875,
|
1628 |
+
"learning_rate": 1.2359142213884933e-05,
|
1629 |
+
"loss": 0.4335,
|
1630 |
+
"step": 1130
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 4.3,
|
1634 |
+
"grad_norm": 0.640625,
|
1635 |
+
"learning_rate": 1.1730082833207202e-05,
|
1636 |
+
"loss": 0.358,
|
1637 |
+
"step": 1135
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 4.32,
|
1641 |
+
"grad_norm": 0.57421875,
|
1642 |
+
"learning_rate": 1.1116455134507664e-05,
|
1643 |
+
"loss": 0.357,
|
1644 |
+
"step": 1140
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 4.34,
|
1648 |
+
"grad_norm": 0.6875,
|
1649 |
+
"learning_rate": 1.0518366394509804e-05,
|
1650 |
+
"loss": 0.4767,
|
1651 |
+
"step": 1145
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 4.36,
|
1655 |
+
"grad_norm": 0.63671875,
|
1656 |
+
"learning_rate": 9.935921173357442e-06,
|
1657 |
+
"loss": 0.4063,
|
1658 |
+
"step": 1150
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 4.38,
|
1662 |
+
"grad_norm": 0.6484375,
|
1663 |
+
"learning_rate": 9.369221296335006e-06,
|
1664 |
+
"loss": 0.3668,
|
1665 |
+
"step": 1155
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 4.39,
|
1669 |
+
"grad_norm": 0.85546875,
|
1670 |
+
"learning_rate": 8.818365836066101e-06,
|
1671 |
+
"loss": 0.3531,
|
1672 |
+
"step": 1160
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 4.41,
|
1676 |
+
"grad_norm": 0.66015625,
|
1677 |
+
"learning_rate": 8.283451095193229e-06,
|
1678 |
+
"loss": 0.3754,
|
1679 |
+
"step": 1165
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 4.43,
|
1683 |
+
"grad_norm": 0.734375,
|
1684 |
+
"learning_rate": 7.764570589541875e-06,
|
1685 |
+
"loss": 0.4278,
|
1686 |
+
"step": 1170
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 4.45,
|
1690 |
+
"grad_norm": 0.73828125,
|
1691 |
+
"learning_rate": 7.261815031771602e-06,
|
1692 |
+
"loss": 0.4919,
|
1693 |
+
"step": 1175
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 4.47,
|
1697 |
+
"grad_norm": 0.73046875,
|
1698 |
+
"learning_rate": 6.7752723155174226e-06,
|
1699 |
+
"loss": 0.4837,
|
1700 |
+
"step": 1180
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 4.49,
|
1704 |
+
"grad_norm": 0.78125,
|
1705 |
+
"learning_rate": 6.3050275000238414e-06,
|
1706 |
+
"loss": 0.4196,
|
1707 |
+
"step": 1185
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 4.51,
|
1711 |
+
"grad_norm": 0.671875,
|
1712 |
+
"learning_rate": 5.851162795274445e-06,
|
1713 |
+
"loss": 0.4928,
|
1714 |
+
"step": 1190
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 4.53,
|
1718 |
+
"grad_norm": 0.84765625,
|
1719 |
+
"learning_rate": 5.413757547619747e-06,
|
1720 |
+
"loss": 0.4489,
|
1721 |
+
"step": 1195
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 4.55,
|
1725 |
+
"grad_norm": 0.5390625,
|
1726 |
+
"learning_rate": 4.992888225905468e-06,
|
1727 |
+
"loss": 0.4083,
|
1728 |
+
"step": 1200
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 4.56,
|
1732 |
+
"grad_norm": 0.734375,
|
1733 |
+
"learning_rate": 4.5886284081039675e-06,
|
1734 |
+
"loss": 0.5487,
|
1735 |
+
"step": 1205
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 4.58,
|
1739 |
+
"grad_norm": 0.70703125,
|
1740 |
+
"learning_rate": 4.20104876845111e-06,
|
1741 |
+
"loss": 0.3817,
|
1742 |
+
"step": 1210
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 4.6,
|
1746 |
+
"grad_norm": 0.68359375,
|
1747 |
+
"learning_rate": 3.830217065090702e-06,
|
1748 |
+
"loss": 0.4394,
|
1749 |
+
"step": 1215
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 4.62,
|
1753 |
+
"grad_norm": 0.6640625,
|
1754 |
+
"learning_rate": 3.476198128228736e-06,
|
1755 |
+
"loss": 0.3811,
|
1756 |
+
"step": 1220
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 4.64,
|
1760 |
+
"grad_norm": 0.6328125,
|
1761 |
+
"learning_rate": 3.139053848799556e-06,
|
1762 |
+
"loss": 0.3809,
|
1763 |
+
"step": 1225
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 4.66,
|
1767 |
+
"grad_norm": 0.828125,
|
1768 |
+
"learning_rate": 2.818843167645835e-06,
|
1769 |
+
"loss": 0.3755,
|
1770 |
+
"step": 1230
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 4.68,
|
1774 |
+
"grad_norm": 0.6640625,
|
1775 |
+
"learning_rate": 2.5156220652143404e-06,
|
1776 |
+
"loss": 0.4108,
|
1777 |
+
"step": 1235
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 4.7,
|
1781 |
+
"grad_norm": 0.58984375,
|
1782 |
+
"learning_rate": 2.2294435517691503e-06,
|
1783 |
+
"loss": 0.5031,
|
1784 |
+
"step": 1240
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 4.72,
|
1788 |
+
"grad_norm": 0.63671875,
|
1789 |
+
"learning_rate": 1.960357658124301e-06,
|
1790 |
+
"loss": 0.4176,
|
1791 |
+
"step": 1245
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 4.73,
|
1795 |
+
"grad_norm": 0.64453125,
|
1796 |
+
"learning_rate": 1.7084114268971275e-06,
|
1797 |
+
"loss": 0.3757,
|
1798 |
+
"step": 1250
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 4.75,
|
1802 |
+
"grad_norm": 0.60546875,
|
1803 |
+
"learning_rate": 1.4736489042840973e-06,
|
1804 |
+
"loss": 0.4244,
|
1805 |
+
"step": 1255
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 4.77,
|
1809 |
+
"grad_norm": 0.640625,
|
1810 |
+
"learning_rate": 1.2561111323605712e-06,
|
1811 |
+
"loss": 0.3933,
|
1812 |
+
"step": 1260
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 4.79,
|
1816 |
+
"grad_norm": 0.62109375,
|
1817 |
+
"learning_rate": 1.055836141905553e-06,
|
1818 |
+
"loss": 0.4223,
|
1819 |
+
"step": 1265
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 4.81,
|
1823 |
+
"grad_norm": 0.62890625,
|
1824 |
+
"learning_rate": 8.728589457530855e-07,
|
1825 |
+
"loss": 0.3988,
|
1826 |
+
"step": 1270
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 4.83,
|
1830 |
+
"grad_norm": 0.5078125,
|
1831 |
+
"learning_rate": 7.072115326711704e-07,
|
1832 |
+
"loss": 0.3916,
|
1833 |
+
"step": 1275
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 4.85,
|
1837 |
+
"grad_norm": 0.67578125,
|
1838 |
+
"learning_rate": 5.589228617693288e-07,
|
1839 |
+
"loss": 0.3814,
|
1840 |
+
"step": 1280
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 4.87,
|
1844 |
+
"grad_norm": 0.7578125,
|
1845 |
+
"learning_rate": 4.2801885743588567e-07,
|
1846 |
+
"loss": 0.4261,
|
1847 |
+
"step": 1285
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 4.89,
|
1851 |
+
"grad_norm": 0.62890625,
|
1852 |
+
"learning_rate": 3.145224048057727e-07,
|
1853 |
+
"loss": 0.4018,
|
1854 |
+
"step": 1290
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 4.91,
|
1858 |
+
"grad_norm": 0.60546875,
|
1859 |
+
"learning_rate": 2.1845334575963938e-07,
|
1860 |
+
"loss": 0.4824,
|
1861 |
+
"step": 1295
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 4.92,
|
1865 |
+
"grad_norm": 0.734375,
|
1866 |
+
"learning_rate": 1.3982847545507271e-07,
|
1867 |
+
"loss": 0.4293,
|
1868 |
+
"step": 1300
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 4.94,
|
1872 |
+
"grad_norm": 0.7734375,
|
1873 |
+
"learning_rate": 7.866153939033449e-08,
|
1874 |
+
"loss": 0.3955,
|
1875 |
+
"step": 1305
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 4.96,
|
1879 |
+
"grad_norm": 0.80859375,
|
1880 |
+
"learning_rate": 3.496323100138366e-08,
|
1881 |
+
"loss": 0.3909,
|
1882 |
+
"step": 1310
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 4.98,
|
1886 |
+
"grad_norm": 0.7734375,
|
1887 |
+
"learning_rate": 8.7411897923384e-09,
|
1888 |
+
"loss": 0.4108,
|
1889 |
+
"step": 1315
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 5.0,
|
1893 |
+
"grad_norm": 0.66796875,
|
1894 |
+
"learning_rate": 0.0,
|
1895 |
+
"loss": 0.3396,
|
1896 |
+
"step": 1320
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 5.0,
|
1900 |
+
"eval_loss": 1.6054625511169434,
|
1901 |
+
"eval_runtime": 67.9944,
|
1902 |
+
"eval_samples_per_second": 3.897,
|
1903 |
+
"eval_steps_per_second": 0.5,
|
1904 |
+
"step": 1320
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 5.0,
|
1908 |
+
"step": 1320,
|
1909 |
+
"total_flos": 9.280995169497252e+17,
|
1910 |
+
"train_loss": 1.0955926315350966,
|
1911 |
+
"train_runtime": 10263.5013,
|
1912 |
+
"train_samples_per_second": 1.028,
|
1913 |
+
"train_steps_per_second": 0.129
|
1914 |
+
}
|
1915 |
+
],
|
1916 |
+
"logging_steps": 5,
|
1917 |
+
"max_steps": 1320,
|
1918 |
+
"num_input_tokens_seen": 0,
|
1919 |
+
"num_train_epochs": 5,
|
1920 |
+
"save_steps": 100,
|
1921 |
+
"total_flos": 9.280995169497252e+17,
|
1922 |
+
"train_batch_size": 4,
|
1923 |
+
"trial_name": null,
|
1924 |
+
"trial_params": null
|
1925 |
+
}
|