hugodk-sch
commited on
Model save
Browse files- README.md +70 -0
- adapter_model.safetensors +1 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1995 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
+
- generated_from_trainer
|
7 |
+
base_model: NorLLM-AI/NorMistral-7B
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
model-index:
|
11 |
+
- name: norllm-ai-normistral-7b-sft-qlora
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# norllm-ai-normistral-7b-sft-qlora
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [NorLLM-AI/NorMistral-7B](https://huggingface.co/NorLLM-AI/NorMistral-7B) on the generator dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.4403
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0002
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- distributed_type: multi-GPU
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 8
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- num_epochs: 5
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.7274 | 1.0 | 274 | 1.9432 |
|
58 |
+
| 1.1514 | 2.0 | 549 | 1.7111 |
|
59 |
+
| 0.645 | 3.0 | 823 | 1.5109 |
|
60 |
+
| 0.4291 | 4.0 | 1098 | 1.4415 |
|
61 |
+
| 0.3392 | 4.99 | 1370 | 1.4403 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- PEFT 0.10.0
|
67 |
+
- Transformers 4.39.0.dev0
|
68 |
+
- Pytorch 2.1.2+cu121
|
69 |
+
- Datasets 2.14.6
|
70 |
+
- 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:fc3e5e1f31fce526b019aaea0f5e020a78b105cc28acb9108258c5d58098e08e
|
3 |
size 83946192
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"train_loss": 1.004000898782354,
|
4 |
+
"train_runtime": 10982.2688,
|
5 |
+
"train_samples": 4208,
|
6 |
+
"train_samples_per_second": 0.998,
|
7 |
+
"train_steps_per_second": 0.125
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"train_loss": 1.004000898782354,
|
4 |
+
"train_runtime": 10982.2688,
|
5 |
+
"train_samples": 4208,
|
6 |
+
"train_samples_per_second": 0.998,
|
7 |
+
"train_steps_per_second": 0.125
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1995 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.990892531876138,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1370,
|
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": 0.1083984375,
|
14 |
+
"learning_rate": 1.4598540145985402e-06,
|
15 |
+
"loss": 2.234,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02,
|
20 |
+
"grad_norm": 0.09521484375,
|
21 |
+
"learning_rate": 7.2992700729927e-06,
|
22 |
+
"loss": 2.1882,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.04,
|
27 |
+
"grad_norm": 0.095703125,
|
28 |
+
"learning_rate": 1.45985401459854e-05,
|
29 |
+
"loss": 2.2055,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.05,
|
34 |
+
"grad_norm": 0.111328125,
|
35 |
+
"learning_rate": 2.1897810218978105e-05,
|
36 |
+
"loss": 2.176,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.07,
|
41 |
+
"grad_norm": 0.109375,
|
42 |
+
"learning_rate": 2.91970802919708e-05,
|
43 |
+
"loss": 2.1559,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09,
|
48 |
+
"grad_norm": 0.11962890625,
|
49 |
+
"learning_rate": 3.649635036496351e-05,
|
50 |
+
"loss": 2.16,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11,
|
55 |
+
"grad_norm": 0.1123046875,
|
56 |
+
"learning_rate": 4.379562043795621e-05,
|
57 |
+
"loss": 2.1681,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.13,
|
62 |
+
"grad_norm": 0.11572265625,
|
63 |
+
"learning_rate": 5.109489051094891e-05,
|
64 |
+
"loss": 2.0763,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.15,
|
69 |
+
"grad_norm": 0.1171875,
|
70 |
+
"learning_rate": 5.83941605839416e-05,
|
71 |
+
"loss": 2.114,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.16,
|
76 |
+
"grad_norm": 0.109375,
|
77 |
+
"learning_rate": 6.56934306569343e-05,
|
78 |
+
"loss": 2.0984,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.18,
|
83 |
+
"grad_norm": 0.111328125,
|
84 |
+
"learning_rate": 7.299270072992701e-05,
|
85 |
+
"loss": 2.0837,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.2,
|
90 |
+
"grad_norm": 0.1328125,
|
91 |
+
"learning_rate": 8.029197080291971e-05,
|
92 |
+
"loss": 2.0903,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.22,
|
97 |
+
"grad_norm": 0.1123046875,
|
98 |
+
"learning_rate": 8.759124087591242e-05,
|
99 |
+
"loss": 2.0727,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.24,
|
104 |
+
"grad_norm": 0.1201171875,
|
105 |
+
"learning_rate": 9.489051094890511e-05,
|
106 |
+
"loss": 2.0506,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.26,
|
111 |
+
"grad_norm": 0.1181640625,
|
112 |
+
"learning_rate": 0.00010218978102189782,
|
113 |
+
"loss": 2.0916,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.27,
|
118 |
+
"grad_norm": 0.1337890625,
|
119 |
+
"learning_rate": 0.00010948905109489052,
|
120 |
+
"loss": 2.0582,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.29,
|
125 |
+
"grad_norm": 0.1279296875,
|
126 |
+
"learning_rate": 0.0001167883211678832,
|
127 |
+
"loss": 2.0502,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.31,
|
132 |
+
"grad_norm": 0.12451171875,
|
133 |
+
"learning_rate": 0.0001240875912408759,
|
134 |
+
"loss": 2.0715,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.33,
|
139 |
+
"grad_norm": 0.1298828125,
|
140 |
+
"learning_rate": 0.0001313868613138686,
|
141 |
+
"loss": 1.9955,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.35,
|
146 |
+
"grad_norm": 0.146484375,
|
147 |
+
"learning_rate": 0.00013868613138686133,
|
148 |
+
"loss": 2.0099,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.36,
|
153 |
+
"grad_norm": 0.1376953125,
|
154 |
+
"learning_rate": 0.00014598540145985403,
|
155 |
+
"loss": 2.0107,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.38,
|
160 |
+
"grad_norm": 0.1533203125,
|
161 |
+
"learning_rate": 0.00015328467153284672,
|
162 |
+
"loss": 1.9787,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.4,
|
167 |
+
"grad_norm": 0.1689453125,
|
168 |
+
"learning_rate": 0.00016058394160583942,
|
169 |
+
"loss": 1.992,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.42,
|
174 |
+
"grad_norm": 0.1748046875,
|
175 |
+
"learning_rate": 0.00016788321167883211,
|
176 |
+
"loss": 2.0616,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.44,
|
181 |
+
"grad_norm": 0.1748046875,
|
182 |
+
"learning_rate": 0.00017518248175182484,
|
183 |
+
"loss": 2.0284,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.46,
|
188 |
+
"grad_norm": 0.197265625,
|
189 |
+
"learning_rate": 0.00018248175182481753,
|
190 |
+
"loss": 1.9884,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.47,
|
195 |
+
"grad_norm": 0.2578125,
|
196 |
+
"learning_rate": 0.00018978102189781023,
|
197 |
+
"loss": 1.995,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.49,
|
202 |
+
"grad_norm": 0.2294921875,
|
203 |
+
"learning_rate": 0.00019708029197080293,
|
204 |
+
"loss": 2.0103,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.51,
|
209 |
+
"grad_norm": 0.2021484375,
|
210 |
+
"learning_rate": 0.00019999707864731247,
|
211 |
+
"loss": 1.9678,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.53,
|
216 |
+
"grad_norm": 0.255859375,
|
217 |
+
"learning_rate": 0.0001999792265545627,
|
218 |
+
"loss": 2.0033,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.55,
|
223 |
+
"grad_norm": 0.25,
|
224 |
+
"learning_rate": 0.00019994514823658906,
|
225 |
+
"loss": 1.9277,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.56,
|
230 |
+
"grad_norm": 0.259765625,
|
231 |
+
"learning_rate": 0.00019989484922416502,
|
232 |
+
"loss": 2.0091,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.58,
|
237 |
+
"grad_norm": 0.25,
|
238 |
+
"learning_rate": 0.0001998283376806175,
|
239 |
+
"loss": 1.9636,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.6,
|
244 |
+
"grad_norm": 0.25390625,
|
245 |
+
"learning_rate": 0.00019974562440050177,
|
246 |
+
"loss": 1.9385,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.62,
|
251 |
+
"grad_norm": 0.259765625,
|
252 |
+
"learning_rate": 0.00019964672280784954,
|
253 |
+
"loss": 1.9536,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.64,
|
258 |
+
"grad_norm": 0.244140625,
|
259 |
+
"learning_rate": 0.00019953164895399042,
|
260 |
+
"loss": 1.9552,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.66,
|
265 |
+
"grad_norm": 0.28125,
|
266 |
+
"learning_rate": 0.00019940042151494675,
|
267 |
+
"loss": 1.8901,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.67,
|
272 |
+
"grad_norm": 0.283203125,
|
273 |
+
"learning_rate": 0.0001992530617884026,
|
274 |
+
"loss": 1.9541,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.69,
|
279 |
+
"grad_norm": 0.26953125,
|
280 |
+
"learning_rate": 0.00019908959369024728,
|
281 |
+
"loss": 1.9515,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.71,
|
286 |
+
"grad_norm": 0.279296875,
|
287 |
+
"learning_rate": 0.00019891004375069377,
|
288 |
+
"loss": 1.896,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.73,
|
293 |
+
"grad_norm": 0.279296875,
|
294 |
+
"learning_rate": 0.0001987144411099731,
|
295 |
+
"loss": 1.9335,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.75,
|
300 |
+
"grad_norm": 0.380859375,
|
301 |
+
"learning_rate": 0.00019850281751360497,
|
302 |
+
"loss": 1.8805,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.77,
|
307 |
+
"grad_norm": 0.296875,
|
308 |
+
"learning_rate": 0.00019827520730724543,
|
309 |
+
"loss": 1.8663,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.78,
|
314 |
+
"grad_norm": 0.3125,
|
315 |
+
"learning_rate": 0.00019803164743111302,
|
316 |
+
"loss": 1.8169,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.8,
|
321 |
+
"grad_norm": 0.3359375,
|
322 |
+
"learning_rate": 0.0001977721774139933,
|
323 |
+
"loss": 1.861,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.82,
|
328 |
+
"grad_norm": 0.296875,
|
329 |
+
"learning_rate": 0.00019749683936682352,
|
330 |
+
"loss": 1.8507,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.84,
|
335 |
+
"grad_norm": 0.3046875,
|
336 |
+
"learning_rate": 0.00019720567797585817,
|
337 |
+
"loss": 1.8928,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.86,
|
342 |
+
"grad_norm": 0.296875,
|
343 |
+
"learning_rate": 0.00019689874049541673,
|
344 |
+
"loss": 1.8767,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.87,
|
349 |
+
"grad_norm": 0.318359375,
|
350 |
+
"learning_rate": 0.00019657607674021424,
|
351 |
+
"loss": 1.9053,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.89,
|
356 |
+
"grad_norm": 0.32421875,
|
357 |
+
"learning_rate": 0.00019623773907727682,
|
358 |
+
"loss": 1.7781,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.91,
|
363 |
+
"grad_norm": 0.302734375,
|
364 |
+
"learning_rate": 0.00019588378241744254,
|
365 |
+
"loss": 1.8099,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.93,
|
370 |
+
"grad_norm": 0.302734375,
|
371 |
+
"learning_rate": 0.00019551426420644967,
|
372 |
+
"loss": 1.8546,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.95,
|
377 |
+
"grad_norm": 0.369140625,
|
378 |
+
"learning_rate": 0.00019512924441561348,
|
379 |
+
"loss": 1.8158,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.97,
|
384 |
+
"grad_norm": 0.318359375,
|
385 |
+
"learning_rate": 0.00019472878553209312,
|
386 |
+
"loss": 1.7982,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.98,
|
391 |
+
"grad_norm": 0.39453125,
|
392 |
+
"learning_rate": 0.0001943129525487502,
|
393 |
+
"loss": 1.7274,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.0,
|
398 |
+
"eval_loss": 1.9431506395339966,
|
399 |
+
"eval_runtime": 74.7123,
|
400 |
+
"eval_samples_per_second": 3.667,
|
401 |
+
"eval_steps_per_second": 0.468,
|
402 |
+
"step": 274
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.0,
|
406 |
+
"grad_norm": 0.55078125,
|
407 |
+
"learning_rate": 0.00019388181295360078,
|
408 |
+
"loss": 1.7478,
|
409 |
+
"step": 275
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.02,
|
413 |
+
"grad_norm": 0.439453125,
|
414 |
+
"learning_rate": 0.00019343543671886218,
|
415 |
+
"loss": 1.61,
|
416 |
+
"step": 280
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.04,
|
420 |
+
"grad_norm": 0.435546875,
|
421 |
+
"learning_rate": 0.00019297389628959702,
|
422 |
+
"loss": 1.6174,
|
423 |
+
"step": 285
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.06,
|
427 |
+
"grad_norm": 0.412109375,
|
428 |
+
"learning_rate": 0.00019249726657195532,
|
429 |
+
"loss": 1.6191,
|
430 |
+
"step": 290
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.07,
|
434 |
+
"grad_norm": 0.392578125,
|
435 |
+
"learning_rate": 0.00019200562492101798,
|
436 |
+
"loss": 1.6129,
|
437 |
+
"step": 295
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.09,
|
441 |
+
"grad_norm": 0.41015625,
|
442 |
+
"learning_rate": 0.00019149905112824197,
|
443 |
+
"loss": 1.6052,
|
444 |
+
"step": 300
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.11,
|
448 |
+
"grad_norm": 0.44921875,
|
449 |
+
"learning_rate": 0.00019097762740851061,
|
450 |
+
"loss": 1.4974,
|
451 |
+
"step": 305
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.13,
|
455 |
+
"grad_norm": 0.4375,
|
456 |
+
"learning_rate": 0.0001904414383867907,
|
457 |
+
"loss": 1.598,
|
458 |
+
"step": 310
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.15,
|
462 |
+
"grad_norm": 0.4609375,
|
463 |
+
"learning_rate": 0.00018989057108439777,
|
464 |
+
"loss": 1.5788,
|
465 |
+
"step": 315
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.17,
|
469 |
+
"grad_norm": 0.373046875,
|
470 |
+
"learning_rate": 0.0001893251149048732,
|
471 |
+
"loss": 1.6078,
|
472 |
+
"step": 320
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.18,
|
476 |
+
"grad_norm": 0.55078125,
|
477 |
+
"learning_rate": 0.0001887451616194743,
|
478 |
+
"loss": 1.527,
|
479 |
+
"step": 325
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.2,
|
483 |
+
"grad_norm": 0.482421875,
|
484 |
+
"learning_rate": 0.0001881508053522801,
|
485 |
+
"loss": 1.4852,
|
486 |
+
"step": 330
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.22,
|
490 |
+
"grad_norm": 0.458984375,
|
491 |
+
"learning_rate": 0.00018754214256491562,
|
492 |
+
"loss": 1.5538,
|
493 |
+
"step": 335
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.24,
|
497 |
+
"grad_norm": 0.439453125,
|
498 |
+
"learning_rate": 0.0001869192720408963,
|
499 |
+
"loss": 1.5196,
|
500 |
+
"step": 340
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.26,
|
504 |
+
"grad_norm": 0.49609375,
|
505 |
+
"learning_rate": 0.00018628229486959596,
|
506 |
+
"loss": 1.495,
|
507 |
+
"step": 345
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.28,
|
511 |
+
"grad_norm": 0.443359375,
|
512 |
+
"learning_rate": 0.00018563131442984044,
|
513 |
+
"loss": 1.465,
|
514 |
+
"step": 350
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.29,
|
518 |
+
"grad_norm": 0.447265625,
|
519 |
+
"learning_rate": 0.00018496643637312942,
|
520 |
+
"loss": 1.3923,
|
521 |
+
"step": 355
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.31,
|
525 |
+
"grad_norm": 0.455078125,
|
526 |
+
"learning_rate": 0.00018428776860648994,
|
527 |
+
"loss": 1.5173,
|
528 |
+
"step": 360
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.33,
|
532 |
+
"grad_norm": 0.494140625,
|
533 |
+
"learning_rate": 0.0001835954212749632,
|
534 |
+
"loss": 1.4434,
|
535 |
+
"step": 365
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.35,
|
539 |
+
"grad_norm": 0.4765625,
|
540 |
+
"learning_rate": 0.0001828895067437287,
|
541 |
+
"loss": 1.4619,
|
542 |
+
"step": 370
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.37,
|
546 |
+
"grad_norm": 0.55078125,
|
547 |
+
"learning_rate": 0.0001821701395798677,
|
548 |
+
"loss": 1.3675,
|
549 |
+
"step": 375
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.38,
|
553 |
+
"grad_norm": 0.58984375,
|
554 |
+
"learning_rate": 0.00018143743653376942,
|
555 |
+
"loss": 1.4109,
|
556 |
+
"step": 380
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.4,
|
560 |
+
"grad_norm": 0.55078125,
|
561 |
+
"learning_rate": 0.0001806915165201831,
|
562 |
+
"loss": 1.3592,
|
563 |
+
"step": 385
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.42,
|
567 |
+
"grad_norm": 0.466796875,
|
568 |
+
"learning_rate": 0.00017993250059891838,
|
569 |
+
"loss": 1.3634,
|
570 |
+
"step": 390
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.44,
|
574 |
+
"grad_norm": 0.55859375,
|
575 |
+
"learning_rate": 0.00017916051195519797,
|
576 |
+
"loss": 1.2936,
|
577 |
+
"step": 395
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.46,
|
581 |
+
"grad_norm": 0.48828125,
|
582 |
+
"learning_rate": 0.00017837567587966507,
|
583 |
+
"loss": 1.4582,
|
584 |
+
"step": 400
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.48,
|
588 |
+
"grad_norm": 0.5078125,
|
589 |
+
"learning_rate": 0.00017757811974804927,
|
590 |
+
"loss": 1.3851,
|
591 |
+
"step": 405
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.49,
|
595 |
+
"grad_norm": 0.5234375,
|
596 |
+
"learning_rate": 0.00017676797300049393,
|
597 |
+
"loss": 1.4325,
|
598 |
+
"step": 410
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.51,
|
602 |
+
"grad_norm": 0.55859375,
|
603 |
+
"learning_rate": 0.0001759453671205487,
|
604 |
+
"loss": 1.3731,
|
605 |
+
"step": 415
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.53,
|
609 |
+
"grad_norm": 0.44921875,
|
610 |
+
"learning_rate": 0.00017511043561382997,
|
611 |
+
"loss": 1.5819,
|
612 |
+
"step": 420
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.55,
|
616 |
+
"grad_norm": 0.4921875,
|
617 |
+
"learning_rate": 0.0001742633139863538,
|
618 |
+
"loss": 1.4186,
|
619 |
+
"step": 425
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.57,
|
623 |
+
"grad_norm": 0.5859375,
|
624 |
+
"learning_rate": 0.00017340413972254367,
|
625 |
+
"loss": 1.2765,
|
626 |
+
"step": 430
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.58,
|
630 |
+
"grad_norm": 0.498046875,
|
631 |
+
"learning_rate": 0.00017253305226291724,
|
632 |
+
"loss": 1.2749,
|
633 |
+
"step": 435
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.6,
|
637 |
+
"grad_norm": 0.60546875,
|
638 |
+
"learning_rate": 0.00017165019298145585,
|
639 |
+
"loss": 1.3995,
|
640 |
+
"step": 440
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.62,
|
644 |
+
"grad_norm": 0.55078125,
|
645 |
+
"learning_rate": 0.00017075570516266012,
|
646 |
+
"loss": 1.3697,
|
647 |
+
"step": 445
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.64,
|
651 |
+
"grad_norm": 0.58984375,
|
652 |
+
"learning_rate": 0.00016984973397829524,
|
653 |
+
"loss": 1.2694,
|
654 |
+
"step": 450
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.66,
|
658 |
+
"grad_norm": 0.5390625,
|
659 |
+
"learning_rate": 0.0001689324264638304,
|
660 |
+
"loss": 1.3461,
|
661 |
+
"step": 455
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.68,
|
665 |
+
"grad_norm": 0.5859375,
|
666 |
+
"learning_rate": 0.00016800393149457539,
|
667 |
+
"loss": 1.2316,
|
668 |
+
"step": 460
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.69,
|
672 |
+
"grad_norm": 0.6015625,
|
673 |
+
"learning_rate": 0.0001670643997615189,
|
674 |
+
"loss": 1.2794,
|
675 |
+
"step": 465
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.71,
|
679 |
+
"grad_norm": 0.53125,
|
680 |
+
"learning_rate": 0.0001661139837468717,
|
681 |
+
"loss": 1.185,
|
682 |
+
"step": 470
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.73,
|
686 |
+
"grad_norm": 0.58203125,
|
687 |
+
"learning_rate": 0.00016515283769931972,
|
688 |
+
"loss": 1.2398,
|
689 |
+
"step": 475
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.75,
|
693 |
+
"grad_norm": 0.55859375,
|
694 |
+
"learning_rate": 0.0001641811176089899,
|
695 |
+
"loss": 1.2424,
|
696 |
+
"step": 480
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.77,
|
700 |
+
"grad_norm": 0.60546875,
|
701 |
+
"learning_rate": 0.00016319898118213365,
|
702 |
+
"loss": 1.24,
|
703 |
+
"step": 485
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.79,
|
707 |
+
"grad_norm": 0.58984375,
|
708 |
+
"learning_rate": 0.00016220658781553176,
|
709 |
+
"loss": 1.2045,
|
710 |
+
"step": 490
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.8,
|
714 |
+
"grad_norm": 0.60546875,
|
715 |
+
"learning_rate": 0.00016120409857062507,
|
716 |
+
"loss": 1.2237,
|
717 |
+
"step": 495
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.82,
|
721 |
+
"grad_norm": 0.61328125,
|
722 |
+
"learning_rate": 0.0001601916761473747,
|
723 |
+
"loss": 1.329,
|
724 |
+
"step": 500
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 1.84,
|
728 |
+
"grad_norm": 0.7265625,
|
729 |
+
"learning_rate": 0.00015916948485785647,
|
730 |
+
"loss": 1.0863,
|
731 |
+
"step": 505
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 1.86,
|
735 |
+
"grad_norm": 0.55078125,
|
736 |
+
"learning_rate": 0.0001581376905995939,
|
737 |
+
"loss": 1.2565,
|
738 |
+
"step": 510
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 1.88,
|
742 |
+
"grad_norm": 0.59765625,
|
743 |
+
"learning_rate": 0.0001570964608286336,
|
744 |
+
"loss": 1.127,
|
745 |
+
"step": 515
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.89,
|
749 |
+
"grad_norm": 0.625,
|
750 |
+
"learning_rate": 0.0001560459645323678,
|
751 |
+
"loss": 1.147,
|
752 |
+
"step": 520
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.91,
|
756 |
+
"grad_norm": 0.62890625,
|
757 |
+
"learning_rate": 0.0001549863722021084,
|
758 |
+
"loss": 1.1599,
|
759 |
+
"step": 525
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 1.93,
|
763 |
+
"grad_norm": 0.65234375,
|
764 |
+
"learning_rate": 0.00015391785580541698,
|
765 |
+
"loss": 1.1667,
|
766 |
+
"step": 530
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 1.95,
|
770 |
+
"grad_norm": 0.6015625,
|
771 |
+
"learning_rate": 0.00015284058875819504,
|
772 |
+
"loss": 1.2302,
|
773 |
+
"step": 535
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 1.97,
|
777 |
+
"grad_norm": 0.66796875,
|
778 |
+
"learning_rate": 0.00015175474589653942,
|
779 |
+
"loss": 1.1781,
|
780 |
+
"step": 540
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 1.99,
|
784 |
+
"grad_norm": 0.734375,
|
785 |
+
"learning_rate": 0.00015066050344836706,
|
786 |
+
"loss": 1.1514,
|
787 |
+
"step": 545
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 2.0,
|
791 |
+
"eval_loss": 1.7110929489135742,
|
792 |
+
"eval_runtime": 74.7203,
|
793 |
+
"eval_samples_per_second": 3.667,
|
794 |
+
"eval_steps_per_second": 0.468,
|
795 |
+
"step": 549
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.0,
|
799 |
+
"grad_norm": 0.53515625,
|
800 |
+
"learning_rate": 0.00014955803900481389,
|
801 |
+
"loss": 1.0657,
|
802 |
+
"step": 550
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.02,
|
806 |
+
"grad_norm": 0.8125,
|
807 |
+
"learning_rate": 0.0001484475314914125,
|
808 |
+
"loss": 0.9519,
|
809 |
+
"step": 555
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.04,
|
813 |
+
"grad_norm": 0.66796875,
|
814 |
+
"learning_rate": 0.00014732916113905335,
|
815 |
+
"loss": 0.8776,
|
816 |
+
"step": 560
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.06,
|
820 |
+
"grad_norm": 0.76171875,
|
821 |
+
"learning_rate": 0.0001462031094547339,
|
822 |
+
"loss": 0.9081,
|
823 |
+
"step": 565
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.08,
|
827 |
+
"grad_norm": 0.703125,
|
828 |
+
"learning_rate": 0.0001450695591921008,
|
829 |
+
"loss": 0.9279,
|
830 |
+
"step": 570
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.09,
|
834 |
+
"grad_norm": 0.73828125,
|
835 |
+
"learning_rate": 0.00014392869432178971,
|
836 |
+
"loss": 0.7395,
|
837 |
+
"step": 575
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.11,
|
841 |
+
"grad_norm": 0.671875,
|
842 |
+
"learning_rate": 0.00014278070000156768,
|
843 |
+
"loss": 0.9795,
|
844 |
+
"step": 580
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.13,
|
848 |
+
"grad_norm": 0.72265625,
|
849 |
+
"learning_rate": 0.00014162576254628267,
|
850 |
+
"loss": 0.8563,
|
851 |
+
"step": 585
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.15,
|
855 |
+
"grad_norm": 0.73046875,
|
856 |
+
"learning_rate": 0.00014046406939762545,
|
857 |
+
"loss": 0.8419,
|
858 |
+
"step": 590
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.17,
|
862 |
+
"grad_norm": 0.70703125,
|
863 |
+
"learning_rate": 0.00013929580909370862,
|
864 |
+
"loss": 0.82,
|
865 |
+
"step": 595
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.19,
|
869 |
+
"grad_norm": 0.67578125,
|
870 |
+
"learning_rate": 0.00013812117123846747,
|
871 |
+
"loss": 0.9267,
|
872 |
+
"step": 600
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.2,
|
876 |
+
"grad_norm": 0.69921875,
|
877 |
+
"learning_rate": 0.0001369403464708884,
|
878 |
+
"loss": 0.8248,
|
879 |
+
"step": 605
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.22,
|
883 |
+
"grad_norm": 0.73046875,
|
884 |
+
"learning_rate": 0.00013575352643406844,
|
885 |
+
"loss": 0.8331,
|
886 |
+
"step": 610
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.24,
|
890 |
+
"grad_norm": 0.69140625,
|
891 |
+
"learning_rate": 0.00013456090374411284,
|
892 |
+
"loss": 0.8908,
|
893 |
+
"step": 615
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.26,
|
897 |
+
"grad_norm": 0.734375,
|
898 |
+
"learning_rate": 0.00013336267195887398,
|
899 |
+
"loss": 0.8693,
|
900 |
+
"step": 620
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.28,
|
904 |
+
"grad_norm": 0.953125,
|
905 |
+
"learning_rate": 0.00013215902554653772,
|
906 |
+
"loss": 0.8886,
|
907 |
+
"step": 625
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.3,
|
911 |
+
"grad_norm": 0.8046875,
|
912 |
+
"learning_rate": 0.00013095015985406215,
|
913 |
+
"loss": 0.7254,
|
914 |
+
"step": 630
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.31,
|
918 |
+
"grad_norm": 0.7421875,
|
919 |
+
"learning_rate": 0.00012973627107547346,
|
920 |
+
"loss": 0.8929,
|
921 |
+
"step": 635
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.33,
|
925 |
+
"grad_norm": 0.8671875,
|
926 |
+
"learning_rate": 0.00012851755622002444,
|
927 |
+
"loss": 0.7416,
|
928 |
+
"step": 640
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.35,
|
932 |
+
"grad_norm": 0.6796875,
|
933 |
+
"learning_rate": 0.0001272942130802207,
|
934 |
+
"loss": 0.7426,
|
935 |
+
"step": 645
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.37,
|
939 |
+
"grad_norm": 0.73046875,
|
940 |
+
"learning_rate": 0.00012606644019971968,
|
941 |
+
"loss": 0.7973,
|
942 |
+
"step": 650
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.39,
|
946 |
+
"grad_norm": 0.7265625,
|
947 |
+
"learning_rate": 0.00012483443684110793,
|
948 |
+
"loss": 0.7846,
|
949 |
+
"step": 655
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 2.4,
|
953 |
+
"grad_norm": 0.7265625,
|
954 |
+
"learning_rate": 0.00012359840295356151,
|
955 |
+
"loss": 0.9146,
|
956 |
+
"step": 660
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 2.42,
|
960 |
+
"grad_norm": 0.734375,
|
961 |
+
"learning_rate": 0.00012235853914039515,
|
962 |
+
"loss": 0.8241,
|
963 |
+
"step": 665
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 2.44,
|
967 |
+
"grad_norm": 0.6640625,
|
968 |
+
"learning_rate": 0.0001211150466265049,
|
969 |
+
"loss": 0.811,
|
970 |
+
"step": 670
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 2.46,
|
974 |
+
"grad_norm": 0.66015625,
|
975 |
+
"learning_rate": 0.00011986812722571039,
|
976 |
+
"loss": 0.7336,
|
977 |
+
"step": 675
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.48,
|
981 |
+
"grad_norm": 0.6875,
|
982 |
+
"learning_rate": 0.00011861798330800125,
|
983 |
+
"loss": 0.727,
|
984 |
+
"step": 680
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 2.5,
|
988 |
+
"grad_norm": 0.7578125,
|
989 |
+
"learning_rate": 0.00011736481776669306,
|
990 |
+
"loss": 0.6652,
|
991 |
+
"step": 685
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 2.51,
|
995 |
+
"grad_norm": 0.625,
|
996 |
+
"learning_rate": 0.00011610883398549879,
|
997 |
+
"loss": 0.6868,
|
998 |
+
"step": 690
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 2.53,
|
1002 |
+
"grad_norm": 0.734375,
|
1003 |
+
"learning_rate": 0.00011485023580552039,
|
1004 |
+
"loss": 0.7602,
|
1005 |
+
"step": 695
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 2.55,
|
1009 |
+
"grad_norm": 0.73046875,
|
1010 |
+
"learning_rate": 0.00011358922749216614,
|
1011 |
+
"loss": 0.7176,
|
1012 |
+
"step": 700
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 2.57,
|
1016 |
+
"grad_norm": 0.73828125,
|
1017 |
+
"learning_rate": 0.00011232601370199936,
|
1018 |
+
"loss": 0.7167,
|
1019 |
+
"step": 705
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 2.59,
|
1023 |
+
"grad_norm": 0.76953125,
|
1024 |
+
"learning_rate": 0.00011106079944952317,
|
1025 |
+
"loss": 0.7278,
|
1026 |
+
"step": 710
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 2.6,
|
1030 |
+
"grad_norm": 0.75390625,
|
1031 |
+
"learning_rate": 0.00010979379007390782,
|
1032 |
+
"loss": 0.778,
|
1033 |
+
"step": 715
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.62,
|
1037 |
+
"grad_norm": 0.73046875,
|
1038 |
+
"learning_rate": 0.00010852519120566475,
|
1039 |
+
"loss": 0.7099,
|
1040 |
+
"step": 720
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.64,
|
1044 |
+
"grad_norm": 0.671875,
|
1045 |
+
"learning_rate": 0.00010725520873327361,
|
1046 |
+
"loss": 0.781,
|
1047 |
+
"step": 725
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 2.66,
|
1051 |
+
"grad_norm": 0.71875,
|
1052 |
+
"learning_rate": 0.00010598404876976749,
|
1053 |
+
"loss": 0.6719,
|
1054 |
+
"step": 730
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 2.68,
|
1058 |
+
"grad_norm": 0.7890625,
|
1059 |
+
"learning_rate": 0.00010471191761928146,
|
1060 |
+
"loss": 0.8674,
|
1061 |
+
"step": 735
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 2.7,
|
1065 |
+
"grad_norm": 0.73828125,
|
1066 |
+
"learning_rate": 0.00010343902174357039,
|
1067 |
+
"loss": 0.6813,
|
1068 |
+
"step": 740
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 2.71,
|
1072 |
+
"grad_norm": 0.703125,
|
1073 |
+
"learning_rate": 0.00010216556772850094,
|
1074 |
+
"loss": 0.795,
|
1075 |
+
"step": 745
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 2.73,
|
1079 |
+
"grad_norm": 0.7109375,
|
1080 |
+
"learning_rate": 0.00010089176225052354,
|
1081 |
+
"loss": 0.6741,
|
1082 |
+
"step": 750
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 2.75,
|
1086 |
+
"grad_norm": 0.71484375,
|
1087 |
+
"learning_rate": 9.96178120431296e-05,
|
1088 |
+
"loss": 0.6977,
|
1089 |
+
"step": 755
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.77,
|
1093 |
+
"grad_norm": 0.734375,
|
1094 |
+
"learning_rate": 9.83439238632996e-05,
|
1095 |
+
"loss": 0.6683,
|
1096 |
+
"step": 760
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 2.79,
|
1100 |
+
"grad_norm": 0.65625,
|
1101 |
+
"learning_rate": 9.707030445794715e-05,
|
1102 |
+
"loss": 0.6262,
|
1103 |
+
"step": 765
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 2.81,
|
1107 |
+
"grad_norm": 0.78125,
|
1108 |
+
"learning_rate": 9.579716053036479e-05,
|
1109 |
+
"loss": 0.6627,
|
1110 |
+
"step": 770
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.82,
|
1114 |
+
"grad_norm": 0.765625,
|
1115 |
+
"learning_rate": 9.452469870667713e-05,
|
1116 |
+
"loss": 0.7535,
|
1117 |
+
"step": 775
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 2.84,
|
1121 |
+
"grad_norm": 0.6640625,
|
1122 |
+
"learning_rate": 9.325312550230581e-05,
|
1123 |
+
"loss": 0.7468,
|
1124 |
+
"step": 780
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 2.86,
|
1128 |
+
"grad_norm": 0.59765625,
|
1129 |
+
"learning_rate": 9.198264728845332e-05,
|
1130 |
+
"loss": 0.6141,
|
1131 |
+
"step": 785
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 2.88,
|
1135 |
+
"grad_norm": 0.8125,
|
1136 |
+
"learning_rate": 9.071347025860958e-05,
|
1137 |
+
"loss": 0.6955,
|
1138 |
+
"step": 790
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 2.9,
|
1142 |
+
"grad_norm": 0.65234375,
|
1143 |
+
"learning_rate": 8.944580039508748e-05,
|
1144 |
+
"loss": 0.6839,
|
1145 |
+
"step": 795
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.91,
|
1149 |
+
"grad_norm": 0.71875,
|
1150 |
+
"learning_rate": 8.81798434355931e-05,
|
1151 |
+
"loss": 0.6004,
|
1152 |
+
"step": 800
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 2.93,
|
1156 |
+
"grad_norm": 0.69140625,
|
1157 |
+
"learning_rate": 8.69158048398349e-05,
|
1158 |
+
"loss": 0.7424,
|
1159 |
+
"step": 805
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 2.95,
|
1163 |
+
"grad_norm": 0.703125,
|
1164 |
+
"learning_rate": 8.565388975617873e-05,
|
1165 |
+
"loss": 0.6301,
|
1166 |
+
"step": 810
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 2.97,
|
1170 |
+
"grad_norm": 0.6875,
|
1171 |
+
"learning_rate": 8.439430298835304e-05,
|
1172 |
+
"loss": 0.74,
|
1173 |
+
"step": 815
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 2.99,
|
1177 |
+
"grad_norm": 0.7578125,
|
1178 |
+
"learning_rate": 8.313724896220994e-05,
|
1179 |
+
"loss": 0.645,
|
1180 |
+
"step": 820
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 3.0,
|
1184 |
+
"eval_loss": 1.5109344720840454,
|
1185 |
+
"eval_runtime": 74.6963,
|
1186 |
+
"eval_samples_per_second": 3.668,
|
1187 |
+
"eval_steps_per_second": 0.469,
|
1188 |
+
"step": 823
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 3.01,
|
1192 |
+
"grad_norm": 0.59765625,
|
1193 |
+
"learning_rate": 8.188293169254775e-05,
|
1194 |
+
"loss": 0.5792,
|
1195 |
+
"step": 825
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"epoch": 3.02,
|
1199 |
+
"grad_norm": 0.8359375,
|
1200 |
+
"learning_rate": 8.063155475000037e-05,
|
1201 |
+
"loss": 0.6678,
|
1202 |
+
"step": 830
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 3.04,
|
1206 |
+
"grad_norm": 0.71875,
|
1207 |
+
"learning_rate": 7.938332122799834e-05,
|
1208 |
+
"loss": 0.3506,
|
1209 |
+
"step": 835
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 3.06,
|
1213 |
+
"grad_norm": 0.828125,
|
1214 |
+
"learning_rate": 7.813843370980787e-05,
|
1215 |
+
"loss": 0.4464,
|
1216 |
+
"step": 840
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 3.08,
|
1220 |
+
"grad_norm": 0.6640625,
|
1221 |
+
"learning_rate": 7.68970942356521e-05,
|
1222 |
+
"loss": 0.4639,
|
1223 |
+
"step": 845
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 3.1,
|
1227 |
+
"grad_norm": 0.66015625,
|
1228 |
+
"learning_rate": 7.565950426992096e-05,
|
1229 |
+
"loss": 0.4815,
|
1230 |
+
"step": 850
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 3.11,
|
1234 |
+
"grad_norm": 0.6953125,
|
1235 |
+
"learning_rate": 7.442586466847441e-05,
|
1236 |
+
"loss": 0.4089,
|
1237 |
+
"step": 855
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 3.13,
|
1241 |
+
"grad_norm": 0.67578125,
|
1242 |
+
"learning_rate": 7.319637564604412e-05,
|
1243 |
+
"loss": 0.4647,
|
1244 |
+
"step": 860
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 3.15,
|
1248 |
+
"grad_norm": 0.734375,
|
1249 |
+
"learning_rate": 7.197123674373942e-05,
|
1250 |
+
"loss": 0.4837,
|
1251 |
+
"step": 865
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 3.17,
|
1255 |
+
"grad_norm": 0.71875,
|
1256 |
+
"learning_rate": 7.075064679666294e-05,
|
1257 |
+
"loss": 0.5208,
|
1258 |
+
"step": 870
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 3.19,
|
1262 |
+
"grad_norm": 0.703125,
|
1263 |
+
"learning_rate": 6.953480390164e-05,
|
1264 |
+
"loss": 0.4568,
|
1265 |
+
"step": 875
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 3.21,
|
1269 |
+
"grad_norm": 0.7890625,
|
1270 |
+
"learning_rate": 6.832390538506868e-05,
|
1271 |
+
"loss": 0.5692,
|
1272 |
+
"step": 880
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 3.22,
|
1276 |
+
"grad_norm": 0.72265625,
|
1277 |
+
"learning_rate": 6.711814777089427e-05,
|
1278 |
+
"loss": 0.4652,
|
1279 |
+
"step": 885
|
1280 |
+
},
|
1281 |
+
{
|
1282 |
+
"epoch": 3.24,
|
1283 |
+
"grad_norm": 0.74609375,
|
1284 |
+
"learning_rate": 6.591772674871434e-05,
|
1285 |
+
"loss": 0.5665,
|
1286 |
+
"step": 890
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 3.26,
|
1290 |
+
"grad_norm": 0.69921875,
|
1291 |
+
"learning_rate": 6.472283714201919e-05,
|
1292 |
+
"loss": 0.5147,
|
1293 |
+
"step": 895
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 3.28,
|
1297 |
+
"grad_norm": 0.70703125,
|
1298 |
+
"learning_rate": 6.353367287657262e-05,
|
1299 |
+
"loss": 0.5033,
|
1300 |
+
"step": 900
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 3.3,
|
1304 |
+
"grad_norm": 0.75,
|
1305 |
+
"learning_rate": 6.235042694893862e-05,
|
1306 |
+
"loss": 0.5159,
|
1307 |
+
"step": 905
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 3.32,
|
1311 |
+
"grad_norm": 0.59765625,
|
1312 |
+
"learning_rate": 6.117329139515894e-05,
|
1313 |
+
"loss": 0.4865,
|
1314 |
+
"step": 910
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 3.33,
|
1318 |
+
"grad_norm": 0.6953125,
|
1319 |
+
"learning_rate": 6.000245725958618e-05,
|
1320 |
+
"loss": 0.4963,
|
1321 |
+
"step": 915
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.35,
|
1325 |
+
"grad_norm": 0.69140625,
|
1326 |
+
"learning_rate": 5.883811456387821e-05,
|
1327 |
+
"loss": 0.4766,
|
1328 |
+
"step": 920
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 3.37,
|
1332 |
+
"grad_norm": 0.671875,
|
1333 |
+
"learning_rate": 5.7680452276158457e-05,
|
1334 |
+
"loss": 0.4681,
|
1335 |
+
"step": 925
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 3.39,
|
1339 |
+
"grad_norm": 0.73046875,
|
1340 |
+
"learning_rate": 5.6529658280346906e-05,
|
1341 |
+
"loss": 0.4764,
|
1342 |
+
"step": 930
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 3.41,
|
1346 |
+
"grad_norm": 0.62109375,
|
1347 |
+
"learning_rate": 5.5385919345667715e-05,
|
1348 |
+
"loss": 0.4547,
|
1349 |
+
"step": 935
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 3.42,
|
1353 |
+
"grad_norm": 0.6953125,
|
1354 |
+
"learning_rate": 5.424942109633692e-05,
|
1355 |
+
"loss": 0.5382,
|
1356 |
+
"step": 940
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 3.44,
|
1360 |
+
"grad_norm": 0.85546875,
|
1361 |
+
"learning_rate": 5.3120347981436444e-05,
|
1362 |
+
"loss": 0.4404,
|
1363 |
+
"step": 945
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 3.46,
|
1367 |
+
"grad_norm": 0.703125,
|
1368 |
+
"learning_rate": 5.199888324497907e-05,
|
1369 |
+
"loss": 0.5514,
|
1370 |
+
"step": 950
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 3.48,
|
1374 |
+
"grad_norm": 0.60546875,
|
1375 |
+
"learning_rate": 5.088520889616828e-05,
|
1376 |
+
"loss": 0.5287,
|
1377 |
+
"step": 955
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 3.5,
|
1381 |
+
"grad_norm": 0.72265625,
|
1382 |
+
"learning_rate": 4.9779505679859096e-05,
|
1383 |
+
"loss": 0.4759,
|
1384 |
+
"step": 960
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 3.52,
|
1388 |
+
"grad_norm": 0.73828125,
|
1389 |
+
"learning_rate": 4.8681953047223914e-05,
|
1390 |
+
"loss": 0.5279,
|
1391 |
+
"step": 965
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 3.53,
|
1395 |
+
"grad_norm": 0.71484375,
|
1396 |
+
"learning_rate": 4.759272912662822e-05,
|
1397 |
+
"loss": 0.4184,
|
1398 |
+
"step": 970
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 3.55,
|
1402 |
+
"grad_norm": 0.57421875,
|
1403 |
+
"learning_rate": 4.651201069472125e-05,
|
1404 |
+
"loss": 0.4301,
|
1405 |
+
"step": 975
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 3.57,
|
1409 |
+
"grad_norm": 0.734375,
|
1410 |
+
"learning_rate": 4.543997314774553e-05,
|
1411 |
+
"loss": 0.4781,
|
1412 |
+
"step": 980
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 3.59,
|
1416 |
+
"grad_norm": 0.64453125,
|
1417 |
+
"learning_rate": 4.437679047307116e-05,
|
1418 |
+
"loss": 0.5563,
|
1419 |
+
"step": 985
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 3.61,
|
1423 |
+
"grad_norm": 0.6640625,
|
1424 |
+
"learning_rate": 4.332263522095815e-05,
|
1425 |
+
"loss": 0.4216,
|
1426 |
+
"step": 990
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 3.62,
|
1430 |
+
"grad_norm": 0.72265625,
|
1431 |
+
"learning_rate": 4.227767847655205e-05,
|
1432 |
+
"loss": 0.5113,
|
1433 |
+
"step": 995
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 3.64,
|
1437 |
+
"grad_norm": 0.6015625,
|
1438 |
+
"learning_rate": 4.124208983211799e-05,
|
1439 |
+
"loss": 0.5323,
|
1440 |
+
"step": 1000
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 3.66,
|
1444 |
+
"grad_norm": 0.71875,
|
1445 |
+
"learning_rate": 4.021603735951608e-05,
|
1446 |
+
"loss": 0.5079,
|
1447 |
+
"step": 1005
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 3.68,
|
1451 |
+
"grad_norm": 0.703125,
|
1452 |
+
"learning_rate": 3.919968758292425e-05,
|
1453 |
+
"loss": 0.4655,
|
1454 |
+
"step": 1010
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 3.7,
|
1458 |
+
"grad_norm": 0.71875,
|
1459 |
+
"learning_rate": 3.8193205451811995e-05,
|
1460 |
+
"loss": 0.5073,
|
1461 |
+
"step": 1015
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 3.72,
|
1465 |
+
"grad_norm": 0.609375,
|
1466 |
+
"learning_rate": 3.719675431416972e-05,
|
1467 |
+
"loss": 0.4882,
|
1468 |
+
"step": 1020
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 3.73,
|
1472 |
+
"grad_norm": 0.640625,
|
1473 |
+
"learning_rate": 3.62104958899982e-05,
|
1474 |
+
"loss": 0.4177,
|
1475 |
+
"step": 1025
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 3.75,
|
1479 |
+
"grad_norm": 0.671875,
|
1480 |
+
"learning_rate": 3.5234590245061684e-05,
|
1481 |
+
"loss": 0.5276,
|
1482 |
+
"step": 1030
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 3.77,
|
1486 |
+
"grad_norm": 0.69921875,
|
1487 |
+
"learning_rate": 3.426919576491024e-05,
|
1488 |
+
"loss": 0.357,
|
1489 |
+
"step": 1035
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 3.79,
|
1493 |
+
"grad_norm": 0.671875,
|
1494 |
+
"learning_rate": 3.3314469129174364e-05,
|
1495 |
+
"loss": 0.4146,
|
1496 |
+
"step": 1040
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 3.81,
|
1500 |
+
"grad_norm": 0.64453125,
|
1501 |
+
"learning_rate": 3.237056528613624e-05,
|
1502 |
+
"loss": 0.3781,
|
1503 |
+
"step": 1045
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 3.83,
|
1507 |
+
"grad_norm": 0.6328125,
|
1508 |
+
"learning_rate": 3.1437637427582564e-05,
|
1509 |
+
"loss": 0.4652,
|
1510 |
+
"step": 1050
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 3.84,
|
1514 |
+
"grad_norm": 0.67578125,
|
1515 |
+
"learning_rate": 3.0515836963942056e-05,
|
1516 |
+
"loss": 0.5685,
|
1517 |
+
"step": 1055
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 3.86,
|
1521 |
+
"grad_norm": 0.703125,
|
1522 |
+
"learning_rate": 2.960531349971204e-05,
|
1523 |
+
"loss": 0.5038,
|
1524 |
+
"step": 1060
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 3.88,
|
1528 |
+
"grad_norm": 0.62109375,
|
1529 |
+
"learning_rate": 2.8706214809178355e-05,
|
1530 |
+
"loss": 0.4237,
|
1531 |
+
"step": 1065
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 3.9,
|
1535 |
+
"grad_norm": 0.765625,
|
1536 |
+
"learning_rate": 2.7818686812432136e-05,
|
1537 |
+
"loss": 0.6172,
|
1538 |
+
"step": 1070
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 3.92,
|
1542 |
+
"grad_norm": 0.72265625,
|
1543 |
+
"learning_rate": 2.6942873551687587e-05,
|
1544 |
+
"loss": 0.5244,
|
1545 |
+
"step": 1075
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 3.93,
|
1549 |
+
"grad_norm": 0.62890625,
|
1550 |
+
"learning_rate": 2.6078917167904527e-05,
|
1551 |
+
"loss": 0.428,
|
1552 |
+
"step": 1080
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 3.95,
|
1556 |
+
"grad_norm": 0.640625,
|
1557 |
+
"learning_rate": 2.5226957877719436e-05,
|
1558 |
+
"loss": 0.3934,
|
1559 |
+
"step": 1085
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 3.97,
|
1563 |
+
"grad_norm": 0.64453125,
|
1564 |
+
"learning_rate": 2.4387133950688912e-05,
|
1565 |
+
"loss": 0.5376,
|
1566 |
+
"step": 1090
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 3.99,
|
1570 |
+
"grad_norm": 0.62109375,
|
1571 |
+
"learning_rate": 2.3559581686849065e-05,
|
1572 |
+
"loss": 0.4291,
|
1573 |
+
"step": 1095
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 4.0,
|
1577 |
+
"eval_loss": 1.4415178298950195,
|
1578 |
+
"eval_runtime": 74.7485,
|
1579 |
+
"eval_samples_per_second": 3.666,
|
1580 |
+
"eval_steps_per_second": 0.468,
|
1581 |
+
"step": 1098
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 4.01,
|
1585 |
+
"grad_norm": 0.60546875,
|
1586 |
+
"learning_rate": 2.2744435394594497e-05,
|
1587 |
+
"loss": 0.4588,
|
1588 |
+
"step": 1100
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 4.03,
|
1592 |
+
"grad_norm": 0.484375,
|
1593 |
+
"learning_rate": 2.1941827368880796e-05,
|
1594 |
+
"loss": 0.3858,
|
1595 |
+
"step": 1105
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 4.04,
|
1599 |
+
"grad_norm": 0.6171875,
|
1600 |
+
"learning_rate": 2.115188786975336e-05,
|
1601 |
+
"loss": 0.4656,
|
1602 |
+
"step": 1110
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 4.06,
|
1606 |
+
"grad_norm": 0.50390625,
|
1607 |
+
"learning_rate": 2.037474510120676e-05,
|
1608 |
+
"loss": 0.3973,
|
1609 |
+
"step": 1115
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 4.08,
|
1613 |
+
"grad_norm": 0.6015625,
|
1614 |
+
"learning_rate": 1.9610525190377983e-05,
|
1615 |
+
"loss": 0.4184,
|
1616 |
+
"step": 1120
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 4.1,
|
1620 |
+
"grad_norm": 0.61328125,
|
1621 |
+
"learning_rate": 1.885935216707617e-05,
|
1622 |
+
"loss": 0.3977,
|
1623 |
+
"step": 1125
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 4.12,
|
1627 |
+
"grad_norm": 0.70703125,
|
1628 |
+
"learning_rate": 1.8121347943653332e-05,
|
1629 |
+
"loss": 0.4274,
|
1630 |
+
"step": 1130
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 4.13,
|
1634 |
+
"grad_norm": 0.5859375,
|
1635 |
+
"learning_rate": 1.7396632295218317e-05,
|
1636 |
+
"loss": 0.326,
|
1637 |
+
"step": 1135
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 4.15,
|
1641 |
+
"grad_norm": 0.625,
|
1642 |
+
"learning_rate": 1.668532284019789e-05,
|
1643 |
+
"loss": 0.4174,
|
1644 |
+
"step": 1140
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 4.17,
|
1648 |
+
"grad_norm": 0.67578125,
|
1649 |
+
"learning_rate": 1.5987535021247667e-05,
|
1650 |
+
"loss": 0.3984,
|
1651 |
+
"step": 1145
|
1652 |
+
},
|
1653 |
+
{
|
1654 |
+
"epoch": 4.19,
|
1655 |
+
"grad_norm": 0.60546875,
|
1656 |
+
"learning_rate": 1.530338208651627e-05,
|
1657 |
+
"loss": 0.5323,
|
1658 |
+
"step": 1150
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 4.21,
|
1662 |
+
"grad_norm": 0.67578125,
|
1663 |
+
"learning_rate": 1.463297507126562e-05,
|
1664 |
+
"loss": 0.398,
|
1665 |
+
"step": 1155
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 4.23,
|
1669 |
+
"grad_norm": 0.703125,
|
1670 |
+
"learning_rate": 1.3976422779850384e-05,
|
1671 |
+
"loss": 0.3888,
|
1672 |
+
"step": 1160
|
1673 |
+
},
|
1674 |
+
{
|
1675 |
+
"epoch": 4.24,
|
1676 |
+
"grad_norm": 0.56640625,
|
1677 |
+
"learning_rate": 1.3333831768059301e-05,
|
1678 |
+
"loss": 0.3988,
|
1679 |
+
"step": 1165
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 4.26,
|
1683 |
+
"grad_norm": 0.625,
|
1684 |
+
"learning_rate": 1.270530632582191e-05,
|
1685 |
+
"loss": 0.3928,
|
1686 |
+
"step": 1170
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 4.28,
|
1690 |
+
"grad_norm": 0.61328125,
|
1691 |
+
"learning_rate": 1.2090948460282414e-05,
|
1692 |
+
"loss": 0.4208,
|
1693 |
+
"step": 1175
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 4.3,
|
1697 |
+
"grad_norm": 0.58984375,
|
1698 |
+
"learning_rate": 1.149085787924451e-05,
|
1699 |
+
"loss": 0.4415,
|
1700 |
+
"step": 1180
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 4.32,
|
1704 |
+
"grad_norm": 0.7109375,
|
1705 |
+
"learning_rate": 1.0905131974989158e-05,
|
1706 |
+
"loss": 0.3831,
|
1707 |
+
"step": 1185
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 4.34,
|
1711 |
+
"grad_norm": 0.6640625,
|
1712 |
+
"learning_rate": 1.0333865808468202e-05,
|
1713 |
+
"loss": 0.4559,
|
1714 |
+
"step": 1190
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 4.35,
|
1718 |
+
"grad_norm": 0.5625,
|
1719 |
+
"learning_rate": 9.777152093876396e-06,
|
1720 |
+
"loss": 0.3927,
|
1721 |
+
"step": 1195
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 4.37,
|
1725 |
+
"grad_norm": 0.6171875,
|
1726 |
+
"learning_rate": 9.235081183604233e-06,
|
1727 |
+
"loss": 0.4036,
|
1728 |
+
"step": 1200
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 4.39,
|
1732 |
+
"grad_norm": 0.5234375,
|
1733 |
+
"learning_rate": 8.70774105357407e-06,
|
1734 |
+
"loss": 0.3153,
|
1735 |
+
"step": 1205
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 4.41,
|
1739 |
+
"grad_norm": 0.51953125,
|
1740 |
+
"learning_rate": 8.195217288962175e-06,
|
1741 |
+
"loss": 0.2749,
|
1742 |
+
"step": 1210
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 4.43,
|
1746 |
+
"grad_norm": 0.71484375,
|
1747 |
+
"learning_rate": 7.697593070308317e-06,
|
1748 |
+
"loss": 0.4395,
|
1749 |
+
"step": 1215
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 4.44,
|
1753 |
+
"grad_norm": 0.6796875,
|
1754 |
+
"learning_rate": 7.214949160016115e-06,
|
1755 |
+
"loss": 0.4126,
|
1756 |
+
"step": 1220
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"epoch": 4.46,
|
1760 |
+
"grad_norm": 0.67578125,
|
1761 |
+
"learning_rate": 6.747363889245606e-06,
|
1762 |
+
"loss": 0.4111,
|
1763 |
+
"step": 1225
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 4.48,
|
1767 |
+
"grad_norm": 0.6328125,
|
1768 |
+
"learning_rate": 6.294913145200321e-06,
|
1769 |
+
"loss": 0.3986,
|
1770 |
+
"step": 1230
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 4.5,
|
1774 |
+
"grad_norm": 0.625,
|
1775 |
+
"learning_rate": 5.857670358811096e-06,
|
1776 |
+
"loss": 0.4057,
|
1777 |
+
"step": 1235
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 4.52,
|
1781 |
+
"grad_norm": 0.71875,
|
1782 |
+
"learning_rate": 5.435706492818693e-06,
|
1783 |
+
"loss": 0.478,
|
1784 |
+
"step": 1240
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 4.54,
|
1788 |
+
"grad_norm": 0.640625,
|
1789 |
+
"learning_rate": 5.0290900302566335e-06,
|
1790 |
+
"loss": 0.449,
|
1791 |
+
"step": 1245
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 4.55,
|
1795 |
+
"grad_norm": 0.70703125,
|
1796 |
+
"learning_rate": 4.63788696333678e-06,
|
1797 |
+
"loss": 0.4115,
|
1798 |
+
"step": 1250
|
1799 |
+
},
|
1800 |
+
{
|
1801 |
+
"epoch": 4.57,
|
1802 |
+
"grad_norm": 0.52734375,
|
1803 |
+
"learning_rate": 4.262160782739067e-06,
|
1804 |
+
"loss": 0.3495,
|
1805 |
+
"step": 1255
|
1806 |
+
},
|
1807 |
+
{
|
1808 |
+
"epoch": 4.59,
|
1809 |
+
"grad_norm": 0.640625,
|
1810 |
+
"learning_rate": 3.901972467307191e-06,
|
1811 |
+
"loss": 0.3864,
|
1812 |
+
"step": 1260
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 4.61,
|
1816 |
+
"grad_norm": 0.69921875,
|
1817 |
+
"learning_rate": 3.5573804741519833e-06,
|
1818 |
+
"loss": 0.4566,
|
1819 |
+
"step": 1265
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 4.63,
|
1823 |
+
"grad_norm": 0.51171875,
|
1824 |
+
"learning_rate": 3.2284407291641174e-06,
|
1825 |
+
"loss": 0.4479,
|
1826 |
+
"step": 1270
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 4.64,
|
1830 |
+
"grad_norm": 0.66015625,
|
1831 |
+
"learning_rate": 2.9152066179374603e-06,
|
1832 |
+
"loss": 0.4232,
|
1833 |
+
"step": 1275
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 4.66,
|
1837 |
+
"grad_norm": 0.6328125,
|
1838 |
+
"learning_rate": 2.6177289771049274e-06,
|
1839 |
+
"loss": 0.3441,
|
1840 |
+
"step": 1280
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 4.68,
|
1844 |
+
"grad_norm": 0.68359375,
|
1845 |
+
"learning_rate": 2.33605608608779e-06,
|
1846 |
+
"loss": 0.3774,
|
1847 |
+
"step": 1285
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"epoch": 4.7,
|
1851 |
+
"grad_norm": 0.70703125,
|
1852 |
+
"learning_rate": 2.0702336592602122e-06,
|
1853 |
+
"loss": 0.4859,
|
1854 |
+
"step": 1290
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"epoch": 4.72,
|
1858 |
+
"grad_norm": 0.625,
|
1859 |
+
"learning_rate": 1.8203048385299181e-06,
|
1860 |
+
"loss": 0.4231,
|
1861 |
+
"step": 1295
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 4.74,
|
1865 |
+
"grad_norm": 0.671875,
|
1866 |
+
"learning_rate": 1.5863101863364483e-06,
|
1867 |
+
"loss": 0.441,
|
1868 |
+
"step": 1300
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 4.75,
|
1872 |
+
"grad_norm": 0.734375,
|
1873 |
+
"learning_rate": 1.3682876790681254e-06,
|
1874 |
+
"loss": 0.3982,
|
1875 |
+
"step": 1305
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 4.77,
|
1879 |
+
"grad_norm": 0.71875,
|
1880 |
+
"learning_rate": 1.1662727008984964e-06,
|
1881 |
+
"loss": 0.4582,
|
1882 |
+
"step": 1310
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 4.79,
|
1886 |
+
"grad_norm": 0.5625,
|
1887 |
+
"learning_rate": 9.802980380437588e-07,
|
1888 |
+
"loss": 0.3836,
|
1889 |
+
"step": 1315
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 4.81,
|
1893 |
+
"grad_norm": 0.72265625,
|
1894 |
+
"learning_rate": 8.103938734415839e-07,
|
1895 |
+
"loss": 0.4008,
|
1896 |
+
"step": 1320
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 4.83,
|
1900 |
+
"grad_norm": 0.5859375,
|
1901 |
+
"learning_rate": 6.565877818526245e-07,
|
1902 |
+
"loss": 0.353,
|
1903 |
+
"step": 1325
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 4.85,
|
1907 |
+
"grad_norm": 0.5859375,
|
1908 |
+
"learning_rate": 5.189047253851942e-07,
|
1909 |
+
"loss": 0.4758,
|
1910 |
+
"step": 1330
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 4.86,
|
1914 |
+
"grad_norm": 0.609375,
|
1915 |
+
"learning_rate": 3.973670494440307e-07,
|
1916 |
+
"loss": 0.4848,
|
1917 |
+
"step": 1335
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 4.88,
|
1921 |
+
"grad_norm": 0.5703125,
|
1922 |
+
"learning_rate": 2.919944791037632e-07,
|
1923 |
+
"loss": 0.3638,
|
1924 |
+
"step": 1340
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 4.9,
|
1928 |
+
"grad_norm": 0.6796875,
|
1929 |
+
"learning_rate": 2.0280411590754e-07,
|
1930 |
+
"loss": 0.4863,
|
1931 |
+
"step": 1345
|
1932 |
+
},
|
1933 |
+
{
|
1934 |
+
"epoch": 4.92,
|
1935 |
+
"grad_norm": 0.6484375,
|
1936 |
+
"learning_rate": 1.2981043509159297e-07,
|
1937 |
+
"loss": 0.4502,
|
1938 |
+
"step": 1350
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 4.94,
|
1942 |
+
"grad_norm": 0.7578125,
|
1943 |
+
"learning_rate": 7.302528323589464e-08,
|
1944 |
+
"loss": 0.4023,
|
1945 |
+
"step": 1355
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 4.95,
|
1949 |
+
"grad_norm": 0.65234375,
|
1950 |
+
"learning_rate": 3.2457876341585033e-08,
|
1951 |
+
"loss": 0.4602,
|
1952 |
+
"step": 1360
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 4.97,
|
1956 |
+
"grad_norm": 0.61328125,
|
1957 |
+
"learning_rate": 8.114798335157048e-09,
|
1958 |
+
"loss": 0.4061,
|
1959 |
+
"step": 1365
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 4.99,
|
1963 |
+
"grad_norm": 0.421875,
|
1964 |
+
"learning_rate": 0.0,
|
1965 |
+
"loss": 0.3392,
|
1966 |
+
"step": 1370
|
1967 |
+
},
|
1968 |
+
{
|
1969 |
+
"epoch": 4.99,
|
1970 |
+
"eval_loss": 1.4403423070907593,
|
1971 |
+
"eval_runtime": 74.7328,
|
1972 |
+
"eval_samples_per_second": 3.666,
|
1973 |
+
"eval_steps_per_second": 0.468,
|
1974 |
+
"step": 1370
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 4.99,
|
1978 |
+
"step": 1370,
|
1979 |
+
"total_flos": 9.82065973089534e+17,
|
1980 |
+
"train_loss": 1.004000898782354,
|
1981 |
+
"train_runtime": 10982.2688,
|
1982 |
+
"train_samples_per_second": 0.998,
|
1983 |
+
"train_steps_per_second": 0.125
|
1984 |
+
}
|
1985 |
+
],
|
1986 |
+
"logging_steps": 5,
|
1987 |
+
"max_steps": 1370,
|
1988 |
+
"num_input_tokens_seen": 0,
|
1989 |
+
"num_train_epochs": 5,
|
1990 |
+
"save_steps": 100,
|
1991 |
+
"total_flos": 9.82065973089534e+17,
|
1992 |
+
"train_batch_size": 4,
|
1993 |
+
"trial_name": null,
|
1994 |
+
"trial_params": null
|
1995 |
+
}
|