Model save
Browse files- README.md +76 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Aug30_16-06-25_938RL43/events.out.tfevents.1725027260.938RL43.754039.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1566 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
+
datasets:
|
4 |
+
- generator
|
5 |
+
library_name: peft
|
6 |
+
license: llama3.1
|
7 |
+
tags:
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
+
- generated_from_trainer
|
11 |
+
model-index:
|
12 |
+
- name: hansken_human_hql
|
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 |
+
# hansken_human_hql
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2892
|
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: 1
|
44 |
+
- eval_batch_size: 1
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- gradient_accumulation_steps: 8
|
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: 20
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 0.4508 | 0.9976 | 102 | 0.4433 |
|
59 |
+
| 0.302 | 1.9951 | 204 | 0.3140 |
|
60 |
+
| 0.2692 | 2.9927 | 306 | 0.2616 |
|
61 |
+
| 0.177 | 4.0 | 409 | 0.2431 |
|
62 |
+
| 0.1616 | 4.9976 | 511 | 0.2362 |
|
63 |
+
| 0.1358 | 5.9951 | 613 | 0.2394 |
|
64 |
+
| 0.1199 | 6.9927 | 715 | 0.2474 |
|
65 |
+
| 0.1051 | 8.0 | 818 | 0.2625 |
|
66 |
+
| 0.0945 | 8.9976 | 920 | 0.2797 |
|
67 |
+
| 0.0843 | 9.9951 | 1022 | 0.2892 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- PEFT 0.12.0
|
73 |
+
- Transformers 4.44.0
|
74 |
+
- Pytorch 2.1.2+cu121
|
75 |
+
- Datasets 2.20.0
|
76 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22336ad6031f16fcf852a9fc6e36c81ef128033fc8de69ca86c761c7f6007c1c
|
3 |
size 167832240
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.995110024449877,
|
3 |
+
"total_flos": 7.585797735459062e+17,
|
4 |
+
"train_loss": 0.2326957560244605,
|
5 |
+
"train_runtime": 28787.7929,
|
6 |
+
"train_samples": 11408,
|
7 |
+
"train_samples_per_second": 0.568,
|
8 |
+
"train_steps_per_second": 0.071
|
9 |
+
}
|
runs/Aug30_16-06-25_938RL43/events.out.tfevents.1725027260.938RL43.754039.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6c6b183c0496ca525244a9f8029c075a0bdb7065b3d65c833c78b0b7f3100b9
|
3 |
+
size 52935
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.995110024449877,
|
3 |
+
"total_flos": 7.585797735459062e+17,
|
4 |
+
"train_loss": 0.2326957560244605,
|
5 |
+
"train_runtime": 28787.7929,
|
6 |
+
"train_samples": 11408,
|
7 |
+
"train_samples_per_second": 0.568,
|
8 |
+
"train_steps_per_second": 0.071
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1566 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.23624150454998016,
|
3 |
+
"best_model_checkpoint": "data/hansken_human_hql/checkpoint-511",
|
4 |
+
"epoch": 9.995110024449877,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1022,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.009779951100244499,
|
13 |
+
"grad_norm": 1.0709587335586548,
|
14 |
+
"learning_rate": 9.80392156862745e-07,
|
15 |
+
"loss": 1.4707,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0488997555012225,
|
20 |
+
"grad_norm": 1.1860318183898926,
|
21 |
+
"learning_rate": 4.901960784313726e-06,
|
22 |
+
"loss": 1.4227,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.097799511002445,
|
27 |
+
"grad_norm": 1.145372986793518,
|
28 |
+
"learning_rate": 9.803921568627451e-06,
|
29 |
+
"loss": 1.444,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1466992665036675,
|
34 |
+
"grad_norm": 1.0051456689834595,
|
35 |
+
"learning_rate": 1.4705882352941177e-05,
|
36 |
+
"loss": 1.3414,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.19559902200489,
|
41 |
+
"grad_norm": 0.5133008360862732,
|
42 |
+
"learning_rate": 1.9607843137254903e-05,
|
43 |
+
"loss": 1.2116,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24449877750611246,
|
48 |
+
"grad_norm": 0.41832494735717773,
|
49 |
+
"learning_rate": 2.4509803921568626e-05,
|
50 |
+
"loss": 1.1424,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.293398533007335,
|
55 |
+
"grad_norm": 0.41829216480255127,
|
56 |
+
"learning_rate": 2.9411764705882354e-05,
|
57 |
+
"loss": 1.143,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3422982885085575,
|
62 |
+
"grad_norm": 0.35495856404304504,
|
63 |
+
"learning_rate": 3.431372549019608e-05,
|
64 |
+
"loss": 1.0472,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.39119804400978,
|
69 |
+
"grad_norm": 0.40399229526519775,
|
70 |
+
"learning_rate": 3.9215686274509805e-05,
|
71 |
+
"loss": 0.9879,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4400977995110024,
|
76 |
+
"grad_norm": 0.31430941820144653,
|
77 |
+
"learning_rate": 4.411764705882353e-05,
|
78 |
+
"loss": 0.9467,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4889975550122249,
|
83 |
+
"grad_norm": 0.29712405800819397,
|
84 |
+
"learning_rate": 4.901960784313725e-05,
|
85 |
+
"loss": 0.885,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5378973105134475,
|
90 |
+
"grad_norm": 0.40078112483024597,
|
91 |
+
"learning_rate": 5.392156862745098e-05,
|
92 |
+
"loss": 0.7973,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.58679706601467,
|
97 |
+
"grad_norm": 0.34199750423431396,
|
98 |
+
"learning_rate": 5.882352941176471e-05,
|
99 |
+
"loss": 0.776,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6356968215158925,
|
104 |
+
"grad_norm": 0.4243955910205841,
|
105 |
+
"learning_rate": 6.372549019607843e-05,
|
106 |
+
"loss": 0.651,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.684596577017115,
|
111 |
+
"grad_norm": 0.30432572960853577,
|
112 |
+
"learning_rate": 6.862745098039216e-05,
|
113 |
+
"loss": 0.5769,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7334963325183375,
|
118 |
+
"grad_norm": 0.27279356122016907,
|
119 |
+
"learning_rate": 7.352941176470589e-05,
|
120 |
+
"loss": 0.5436,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.78239608801956,
|
125 |
+
"grad_norm": 0.2576221823692322,
|
126 |
+
"learning_rate": 7.843137254901961e-05,
|
127 |
+
"loss": 0.501,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8312958435207825,
|
132 |
+
"grad_norm": 0.22290439903736115,
|
133 |
+
"learning_rate": 8.333333333333334e-05,
|
134 |
+
"loss": 0.4915,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.8801955990220048,
|
139 |
+
"grad_norm": 0.21740856766700745,
|
140 |
+
"learning_rate": 8.823529411764706e-05,
|
141 |
+
"loss": 0.4487,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.9290953545232273,
|
146 |
+
"grad_norm": 0.21560043096542358,
|
147 |
+
"learning_rate": 9.313725490196079e-05,
|
148 |
+
"loss": 0.4351,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9779951100244498,
|
153 |
+
"grad_norm": 0.2607389986515045,
|
154 |
+
"learning_rate": 9.80392156862745e-05,
|
155 |
+
"loss": 0.4508,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9975550122249389,
|
160 |
+
"eval_loss": 0.44326770305633545,
|
161 |
+
"eval_runtime": 398.4802,
|
162 |
+
"eval_samples_per_second": 1.029,
|
163 |
+
"eval_steps_per_second": 1.029,
|
164 |
+
"step": 102
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.0268948655256724,
|
168 |
+
"grad_norm": 0.21888603270053864,
|
169 |
+
"learning_rate": 0.00010294117647058823,
|
170 |
+
"loss": 0.3968,
|
171 |
+
"step": 105
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.075794621026895,
|
175 |
+
"grad_norm": 0.21742066740989685,
|
176 |
+
"learning_rate": 0.00010784313725490196,
|
177 |
+
"loss": 0.3785,
|
178 |
+
"step": 110
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 1.1246943765281174,
|
182 |
+
"grad_norm": 0.2523965537548065,
|
183 |
+
"learning_rate": 0.0001127450980392157,
|
184 |
+
"loss": 0.4034,
|
185 |
+
"step": 115
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.17359413202934,
|
189 |
+
"grad_norm": 0.2155005782842636,
|
190 |
+
"learning_rate": 0.00011764705882352942,
|
191 |
+
"loss": 0.3766,
|
192 |
+
"step": 120
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.2224938875305624,
|
196 |
+
"grad_norm": 0.25576308369636536,
|
197 |
+
"learning_rate": 0.00012254901960784316,
|
198 |
+
"loss": 0.364,
|
199 |
+
"step": 125
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 1.271393643031785,
|
203 |
+
"grad_norm": 0.2288295179605484,
|
204 |
+
"learning_rate": 0.00012745098039215687,
|
205 |
+
"loss": 0.3451,
|
206 |
+
"step": 130
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.3202933985330074,
|
210 |
+
"grad_norm": 0.2045079469680786,
|
211 |
+
"learning_rate": 0.0001323529411764706,
|
212 |
+
"loss": 0.3425,
|
213 |
+
"step": 135
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.36919315403423,
|
217 |
+
"grad_norm": 0.2297014445066452,
|
218 |
+
"learning_rate": 0.0001372549019607843,
|
219 |
+
"loss": 0.3658,
|
220 |
+
"step": 140
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.4180929095354524,
|
224 |
+
"grad_norm": 0.2170581817626953,
|
225 |
+
"learning_rate": 0.00014215686274509804,
|
226 |
+
"loss": 0.3482,
|
227 |
+
"step": 145
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.466992665036675,
|
231 |
+
"grad_norm": 0.2250969409942627,
|
232 |
+
"learning_rate": 0.00014705882352941178,
|
233 |
+
"loss": 0.3353,
|
234 |
+
"step": 150
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.5158924205378974,
|
238 |
+
"grad_norm": 0.23191578686237335,
|
239 |
+
"learning_rate": 0.00015196078431372549,
|
240 |
+
"loss": 0.3271,
|
241 |
+
"step": 155
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 1.56479217603912,
|
245 |
+
"grad_norm": 0.2477528601884842,
|
246 |
+
"learning_rate": 0.00015686274509803922,
|
247 |
+
"loss": 0.3549,
|
248 |
+
"step": 160
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.6136919315403424,
|
252 |
+
"grad_norm": 0.20846064388751984,
|
253 |
+
"learning_rate": 0.00016176470588235295,
|
254 |
+
"loss": 0.3171,
|
255 |
+
"step": 165
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 1.662591687041565,
|
259 |
+
"grad_norm": 0.21829602122306824,
|
260 |
+
"learning_rate": 0.0001666666666666667,
|
261 |
+
"loss": 0.3642,
|
262 |
+
"step": 170
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 1.7114914425427874,
|
266 |
+
"grad_norm": 0.22842282056808472,
|
267 |
+
"learning_rate": 0.0001715686274509804,
|
268 |
+
"loss": 0.3116,
|
269 |
+
"step": 175
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.76039119804401,
|
273 |
+
"grad_norm": 0.24106037616729736,
|
274 |
+
"learning_rate": 0.00017647058823529413,
|
275 |
+
"loss": 0.3066,
|
276 |
+
"step": 180
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 1.8092909535452324,
|
280 |
+
"grad_norm": 0.25696486234664917,
|
281 |
+
"learning_rate": 0.00018137254901960786,
|
282 |
+
"loss": 0.3053,
|
283 |
+
"step": 185
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 1.858190709046455,
|
287 |
+
"grad_norm": 0.22010771930217743,
|
288 |
+
"learning_rate": 0.00018627450980392157,
|
289 |
+
"loss": 0.3233,
|
290 |
+
"step": 190
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.9070904645476774,
|
294 |
+
"grad_norm": 0.2373352199792862,
|
295 |
+
"learning_rate": 0.0001911764705882353,
|
296 |
+
"loss": 0.3102,
|
297 |
+
"step": 195
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.9559902200488999,
|
301 |
+
"grad_norm": 0.21177123486995697,
|
302 |
+
"learning_rate": 0.000196078431372549,
|
303 |
+
"loss": 0.302,
|
304 |
+
"step": 200
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.9951100244498776,
|
308 |
+
"eval_loss": 0.3139691650867462,
|
309 |
+
"eval_runtime": 387.4792,
|
310 |
+
"eval_samples_per_second": 1.058,
|
311 |
+
"eval_steps_per_second": 1.058,
|
312 |
+
"step": 204
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 2.0048899755501224,
|
316 |
+
"grad_norm": 0.2193712592124939,
|
317 |
+
"learning_rate": 0.00019999985360565867,
|
318 |
+
"loss": 0.2813,
|
319 |
+
"step": 205
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 2.053789731051345,
|
323 |
+
"grad_norm": 0.3371932804584503,
|
324 |
+
"learning_rate": 0.00019999472984871732,
|
325 |
+
"loss": 0.2844,
|
326 |
+
"step": 210
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.1026894865525674,
|
330 |
+
"grad_norm": 0.23578821122646332,
|
331 |
+
"learning_rate": 0.00019998228680332932,
|
332 |
+
"loss": 0.263,
|
333 |
+
"step": 215
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 2.15158924205379,
|
337 |
+
"grad_norm": 0.27435311675071716,
|
338 |
+
"learning_rate": 0.00019996252538028507,
|
339 |
+
"loss": 0.2752,
|
340 |
+
"step": 220
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 2.2004889975550124,
|
344 |
+
"grad_norm": 0.24362725019454956,
|
345 |
+
"learning_rate": 0.00019993544702605638,
|
346 |
+
"loss": 0.2572,
|
347 |
+
"step": 225
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 2.249388753056235,
|
351 |
+
"grad_norm": 0.24360118806362152,
|
352 |
+
"learning_rate": 0.0001999010537226905,
|
353 |
+
"loss": 0.3191,
|
354 |
+
"step": 230
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 2.2982885085574574,
|
358 |
+
"grad_norm": 0.2612737715244293,
|
359 |
+
"learning_rate": 0.0001998593479876652,
|
360 |
+
"loss": 0.2506,
|
361 |
+
"step": 235
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 2.34718826405868,
|
365 |
+
"grad_norm": 0.21556636691093445,
|
366 |
+
"learning_rate": 0.00019981033287370443,
|
367 |
+
"loss": 0.2416,
|
368 |
+
"step": 240
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.3960880195599024,
|
372 |
+
"grad_norm": 0.22406277060508728,
|
373 |
+
"learning_rate": 0.00019975401196855482,
|
374 |
+
"loss": 0.273,
|
375 |
+
"step": 245
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 2.444987775061125,
|
379 |
+
"grad_norm": 0.3020350933074951,
|
380 |
+
"learning_rate": 0.00019969038939472315,
|
381 |
+
"loss": 0.2457,
|
382 |
+
"step": 250
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 2.4938875305623474,
|
386 |
+
"grad_norm": 0.20698243379592896,
|
387 |
+
"learning_rate": 0.00019961946980917456,
|
388 |
+
"loss": 0.2569,
|
389 |
+
"step": 255
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 2.54278728606357,
|
393 |
+
"grad_norm": 0.4294751286506653,
|
394 |
+
"learning_rate": 0.00019954125840299165,
|
395 |
+
"loss": 0.2246,
|
396 |
+
"step": 260
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 2.591687041564792,
|
400 |
+
"grad_norm": 0.37185847759246826,
|
401 |
+
"learning_rate": 0.00019945576090099452,
|
402 |
+
"loss": 0.229,
|
403 |
+
"step": 265
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 2.640586797066015,
|
407 |
+
"grad_norm": 0.2863105237483978,
|
408 |
+
"learning_rate": 0.00019936298356132176,
|
409 |
+
"loss": 0.2338,
|
410 |
+
"step": 270
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.689486552567237,
|
414 |
+
"grad_norm": 0.19301028549671173,
|
415 |
+
"learning_rate": 0.00019926293317497245,
|
416 |
+
"loss": 0.2167,
|
417 |
+
"step": 275
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 2.73838630806846,
|
421 |
+
"grad_norm": 0.22075964510440826,
|
422 |
+
"learning_rate": 0.00019915561706530883,
|
423 |
+
"loss": 0.2367,
|
424 |
+
"step": 280
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 2.787286063569682,
|
428 |
+
"grad_norm": 0.22829142212867737,
|
429 |
+
"learning_rate": 0.0001990410430875205,
|
430 |
+
"loss": 0.245,
|
431 |
+
"step": 285
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 2.836185819070905,
|
435 |
+
"grad_norm": 0.1982724666595459,
|
436 |
+
"learning_rate": 0.00019891921962804943,
|
437 |
+
"loss": 0.217,
|
438 |
+
"step": 290
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 2.885085574572127,
|
442 |
+
"grad_norm": 0.23672354221343994,
|
443 |
+
"learning_rate": 0.00019879015560397587,
|
444 |
+
"loss": 0.2298,
|
445 |
+
"step": 295
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 2.93398533007335,
|
449 |
+
"grad_norm": 0.21391943097114563,
|
450 |
+
"learning_rate": 0.00019865386046236596,
|
451 |
+
"loss": 0.2326,
|
452 |
+
"step": 300
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.982885085574572,
|
456 |
+
"grad_norm": 0.19821615517139435,
|
457 |
+
"learning_rate": 0.00019851034417958,
|
458 |
+
"loss": 0.2692,
|
459 |
+
"step": 305
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.9926650366748166,
|
463 |
+
"eval_loss": 0.2616053521633148,
|
464 |
+
"eval_runtime": 387.9813,
|
465 |
+
"eval_samples_per_second": 1.057,
|
466 |
+
"eval_steps_per_second": 1.057,
|
467 |
+
"step": 306
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 3.031784841075795,
|
471 |
+
"grad_norm": 0.22108572721481323,
|
472 |
+
"learning_rate": 0.0001983596172605423,
|
473 |
+
"loss": 0.2104,
|
474 |
+
"step": 310
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 3.0806845965770173,
|
478 |
+
"grad_norm": 0.24487629532814026,
|
479 |
+
"learning_rate": 0.00019820169073797228,
|
480 |
+
"loss": 0.1942,
|
481 |
+
"step": 315
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 3.12958435207824,
|
485 |
+
"grad_norm": 0.2110164612531662,
|
486 |
+
"learning_rate": 0.0001980365761715769,
|
487 |
+
"loss": 0.1833,
|
488 |
+
"step": 320
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 3.178484107579462,
|
492 |
+
"grad_norm": 0.20861805975437164,
|
493 |
+
"learning_rate": 0.0001978642856472045,
|
494 |
+
"loss": 0.1981,
|
495 |
+
"step": 325
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 3.227383863080685,
|
499 |
+
"grad_norm": 0.1969948559999466,
|
500 |
+
"learning_rate": 0.0001976848317759601,
|
501 |
+
"loss": 0.1868,
|
502 |
+
"step": 330
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 3.276283618581907,
|
506 |
+
"grad_norm": 0.19443638622760773,
|
507 |
+
"learning_rate": 0.0001974982276932824,
|
508 |
+
"loss": 0.1902,
|
509 |
+
"step": 335
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 3.32518337408313,
|
513 |
+
"grad_norm": 0.30058181285858154,
|
514 |
+
"learning_rate": 0.00019730448705798239,
|
515 |
+
"loss": 0.2241,
|
516 |
+
"step": 340
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 3.374083129584352,
|
520 |
+
"grad_norm": 0.21647138893604279,
|
521 |
+
"learning_rate": 0.00019710362405124334,
|
522 |
+
"loss": 0.1838,
|
523 |
+
"step": 345
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 3.422982885085575,
|
527 |
+
"grad_norm": 0.19676022231578827,
|
528 |
+
"learning_rate": 0.00019689565337558288,
|
529 |
+
"loss": 0.1961,
|
530 |
+
"step": 350
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 3.471882640586797,
|
534 |
+
"grad_norm": 0.2371009737253189,
|
535 |
+
"learning_rate": 0.00019668059025377703,
|
536 |
+
"loss": 0.2052,
|
537 |
+
"step": 355
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 3.52078239608802,
|
541 |
+
"grad_norm": 0.21014133095741272,
|
542 |
+
"learning_rate": 0.00019645845042774553,
|
543 |
+
"loss": 0.1987,
|
544 |
+
"step": 360
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 3.569682151589242,
|
548 |
+
"grad_norm": 0.2178957760334015,
|
549 |
+
"learning_rate": 0.00019622925015739997,
|
550 |
+
"loss": 0.1903,
|
551 |
+
"step": 365
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 3.618581907090465,
|
555 |
+
"grad_norm": 0.21497862040996552,
|
556 |
+
"learning_rate": 0.0001959930062194534,
|
557 |
+
"loss": 0.2,
|
558 |
+
"step": 370
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 3.667481662591687,
|
562 |
+
"grad_norm": 0.22582682967185974,
|
563 |
+
"learning_rate": 0.00019574973590619243,
|
564 |
+
"loss": 0.1868,
|
565 |
+
"step": 375
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 3.71638141809291,
|
569 |
+
"grad_norm": 0.1827058047056198,
|
570 |
+
"learning_rate": 0.00019549945702421144,
|
571 |
+
"loss": 0.2172,
|
572 |
+
"step": 380
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 3.765281173594132,
|
576 |
+
"grad_norm": 0.19827835261821747,
|
577 |
+
"learning_rate": 0.00019524218789310912,
|
578 |
+
"loss": 0.1785,
|
579 |
+
"step": 385
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 3.8141809290953548,
|
583 |
+
"grad_norm": 0.2121572494506836,
|
584 |
+
"learning_rate": 0.0001949779473441478,
|
585 |
+
"loss": 0.1795,
|
586 |
+
"step": 390
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 3.863080684596577,
|
590 |
+
"grad_norm": 0.20197761058807373,
|
591 |
+
"learning_rate": 0.0001947067547188747,
|
592 |
+
"loss": 0.19,
|
593 |
+
"step": 395
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 3.9119804400977998,
|
597 |
+
"grad_norm": 0.21854069828987122,
|
598 |
+
"learning_rate": 0.00019442862986770646,
|
599 |
+
"loss": 0.1886,
|
600 |
+
"step": 400
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 3.960880195599022,
|
604 |
+
"grad_norm": 0.20974552631378174,
|
605 |
+
"learning_rate": 0.0001941435931484761,
|
606 |
+
"loss": 0.177,
|
607 |
+
"step": 405
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 4.0,
|
611 |
+
"eval_loss": 0.24309584498405457,
|
612 |
+
"eval_runtime": 399.7773,
|
613 |
+
"eval_samples_per_second": 1.026,
|
614 |
+
"eval_steps_per_second": 1.026,
|
615 |
+
"step": 409
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 4.009779951100245,
|
619 |
+
"grad_norm": 0.19041913747787476,
|
620 |
+
"learning_rate": 0.0001938516654249428,
|
621 |
+
"loss": 0.1709,
|
622 |
+
"step": 410
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 4.058679706601467,
|
626 |
+
"grad_norm": 0.22610776126384735,
|
627 |
+
"learning_rate": 0.00019355286806526493,
|
628 |
+
"loss": 0.158,
|
629 |
+
"step": 415
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 4.10757946210269,
|
633 |
+
"grad_norm": 0.2044234424829483,
|
634 |
+
"learning_rate": 0.00019324722294043558,
|
635 |
+
"loss": 0.1522,
|
636 |
+
"step": 420
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 4.156479217603912,
|
640 |
+
"grad_norm": 0.2402704805135727,
|
641 |
+
"learning_rate": 0.00019293475242268223,
|
642 |
+
"loss": 0.1509,
|
643 |
+
"step": 425
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 4.205378973105135,
|
647 |
+
"grad_norm": 0.20224688947200775,
|
648 |
+
"learning_rate": 0.0001926154793838288,
|
649 |
+
"loss": 0.1565,
|
650 |
+
"step": 430
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 4.254278728606357,
|
654 |
+
"grad_norm": 0.21887710690498352,
|
655 |
+
"learning_rate": 0.00019228942719362143,
|
656 |
+
"loss": 0.1551,
|
657 |
+
"step": 435
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 4.30317848410758,
|
661 |
+
"grad_norm": 0.20886527001857758,
|
662 |
+
"learning_rate": 0.00019195661971801827,
|
663 |
+
"loss": 0.1568,
|
664 |
+
"step": 440
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 4.352078239608802,
|
668 |
+
"grad_norm": 0.21612216532230377,
|
669 |
+
"learning_rate": 0.00019161708131744222,
|
670 |
+
"loss": 0.1516,
|
671 |
+
"step": 445
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 4.400977995110025,
|
675 |
+
"grad_norm": 0.20036669075489044,
|
676 |
+
"learning_rate": 0.00019127083684499806,
|
677 |
+
"loss": 0.1529,
|
678 |
+
"step": 450
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 4.449877750611247,
|
682 |
+
"grad_norm": 0.3197900950908661,
|
683 |
+
"learning_rate": 0.00019091791164465305,
|
684 |
+
"loss": 0.1854,
|
685 |
+
"step": 455
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 4.49877750611247,
|
689 |
+
"grad_norm": 0.18851010501384735,
|
690 |
+
"learning_rate": 0.00019055833154938207,
|
691 |
+
"loss": 0.1574,
|
692 |
+
"step": 460
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 4.547677261613692,
|
696 |
+
"grad_norm": 0.214978888630867,
|
697 |
+
"learning_rate": 0.00019019212287927663,
|
698 |
+
"loss": 0.1555,
|
699 |
+
"step": 465
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 4.596577017114915,
|
703 |
+
"grad_norm": 0.21155217289924622,
|
704 |
+
"learning_rate": 0.00018981931243961824,
|
705 |
+
"loss": 0.176,
|
706 |
+
"step": 470
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 4.645476772616137,
|
710 |
+
"grad_norm": 0.18137674033641815,
|
711 |
+
"learning_rate": 0.00018943992751891653,
|
712 |
+
"loss": 0.1575,
|
713 |
+
"step": 475
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 4.69437652811736,
|
717 |
+
"grad_norm": 0.24663567543029785,
|
718 |
+
"learning_rate": 0.00018905399588691163,
|
719 |
+
"loss": 0.1568,
|
720 |
+
"step": 480
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 4.743276283618582,
|
724 |
+
"grad_norm": 0.19319510459899902,
|
725 |
+
"learning_rate": 0.0001886615457925417,
|
726 |
+
"loss": 0.1547,
|
727 |
+
"step": 485
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 4.792176039119805,
|
731 |
+
"grad_norm": 0.18611547350883484,
|
732 |
+
"learning_rate": 0.00018826260596187505,
|
733 |
+
"loss": 0.1755,
|
734 |
+
"step": 490
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 4.841075794621027,
|
738 |
+
"grad_norm": 0.47814473509788513,
|
739 |
+
"learning_rate": 0.00018785720559600752,
|
740 |
+
"loss": 0.1647,
|
741 |
+
"step": 495
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 4.88997555012225,
|
745 |
+
"grad_norm": 0.19350242614746094,
|
746 |
+
"learning_rate": 0.00018744537436892516,
|
747 |
+
"loss": 0.155,
|
748 |
+
"step": 500
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 4.938875305623472,
|
752 |
+
"grad_norm": 0.19956329464912415,
|
753 |
+
"learning_rate": 0.00018702714242533204,
|
754 |
+
"loss": 0.156,
|
755 |
+
"step": 505
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 4.987775061124695,
|
759 |
+
"grad_norm": 0.20709875226020813,
|
760 |
+
"learning_rate": 0.00018660254037844388,
|
761 |
+
"loss": 0.1616,
|
762 |
+
"step": 510
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 4.997555012224939,
|
766 |
+
"eval_loss": 0.23624150454998016,
|
767 |
+
"eval_runtime": 387.7068,
|
768 |
+
"eval_samples_per_second": 1.058,
|
769 |
+
"eval_steps_per_second": 1.058,
|
770 |
+
"step": 511
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 5.036674816625917,
|
774 |
+
"grad_norm": 0.22790652513504028,
|
775 |
+
"learning_rate": 0.00018617159930774715,
|
776 |
+
"loss": 0.1377,
|
777 |
+
"step": 515
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 5.08557457212714,
|
781 |
+
"grad_norm": 0.21796418726444244,
|
782 |
+
"learning_rate": 0.00018573435075672424,
|
783 |
+
"loss": 0.1326,
|
784 |
+
"step": 520
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 5.134474327628362,
|
788 |
+
"grad_norm": 0.19105204939842224,
|
789 |
+
"learning_rate": 0.00018529082673054457,
|
790 |
+
"loss": 0.1303,
|
791 |
+
"step": 525
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 5.183374083129585,
|
795 |
+
"grad_norm": 0.2682870328426361,
|
796 |
+
"learning_rate": 0.00018484105969372182,
|
797 |
+
"loss": 0.1316,
|
798 |
+
"step": 530
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 5.232273838630807,
|
802 |
+
"grad_norm": 0.18370023369789124,
|
803 |
+
"learning_rate": 0.00018438508256773785,
|
804 |
+
"loss": 0.1323,
|
805 |
+
"step": 535
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 5.28117359413203,
|
809 |
+
"grad_norm": 0.24072639644145966,
|
810 |
+
"learning_rate": 0.00018392292872863267,
|
811 |
+
"loss": 0.1332,
|
812 |
+
"step": 540
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 5.330073349633252,
|
816 |
+
"grad_norm": 0.19523735344409943,
|
817 |
+
"learning_rate": 0.00018345463200456164,
|
818 |
+
"loss": 0.1344,
|
819 |
+
"step": 545
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 5.378973105134475,
|
823 |
+
"grad_norm": 0.24865508079528809,
|
824 |
+
"learning_rate": 0.0001829802266733193,
|
825 |
+
"loss": 0.1359,
|
826 |
+
"step": 550
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 5.427872860635697,
|
830 |
+
"grad_norm": 0.2039840966463089,
|
831 |
+
"learning_rate": 0.00018249974745983023,
|
832 |
+
"loss": 0.1337,
|
833 |
+
"step": 555
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 5.47677261613692,
|
837 |
+
"grad_norm": 0.20024679601192474,
|
838 |
+
"learning_rate": 0.00018201322953360758,
|
839 |
+
"loss": 0.154,
|
840 |
+
"step": 560
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 5.525672371638142,
|
844 |
+
"grad_norm": 0.1976476013660431,
|
845 |
+
"learning_rate": 0.0001815207085061784,
|
846 |
+
"loss": 0.1353,
|
847 |
+
"step": 565
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 5.574572127139365,
|
851 |
+
"grad_norm": 0.1974327266216278,
|
852 |
+
"learning_rate": 0.00018102222042847737,
|
853 |
+
"loss": 0.1373,
|
854 |
+
"step": 570
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 5.623471882640587,
|
858 |
+
"grad_norm": 0.27005520462989807,
|
859 |
+
"learning_rate": 0.00018051780178820765,
|
860 |
+
"loss": 0.1437,
|
861 |
+
"step": 575
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 5.67237163814181,
|
865 |
+
"grad_norm": 0.20781448483467102,
|
866 |
+
"learning_rate": 0.00018000748950717038,
|
867 |
+
"loss": 0.1322,
|
868 |
+
"step": 580
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 5.721271393643032,
|
872 |
+
"grad_norm": 0.20179703831672668,
|
873 |
+
"learning_rate": 0.000179491320938562,
|
874 |
+
"loss": 0.1378,
|
875 |
+
"step": 585
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 5.770171149144255,
|
879 |
+
"grad_norm": 0.22105282545089722,
|
880 |
+
"learning_rate": 0.00017896933386423998,
|
881 |
+
"loss": 0.136,
|
882 |
+
"step": 590
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 5.819070904645477,
|
886 |
+
"grad_norm": 0.4113224446773529,
|
887 |
+
"learning_rate": 0.00017844156649195759,
|
888 |
+
"loss": 0.1495,
|
889 |
+
"step": 595
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 5.8679706601467,
|
893 |
+
"grad_norm": 0.20451286435127258,
|
894 |
+
"learning_rate": 0.00017790805745256704,
|
895 |
+
"loss": 0.1318,
|
896 |
+
"step": 600
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 5.916870415647922,
|
900 |
+
"grad_norm": 0.18566569685935974,
|
901 |
+
"learning_rate": 0.0001773688457971919,
|
902 |
+
"loss": 0.1359,
|
903 |
+
"step": 605
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 5.965770171149144,
|
907 |
+
"grad_norm": 0.1862591803073883,
|
908 |
+
"learning_rate": 0.0001768239709943686,
|
909 |
+
"loss": 0.1358,
|
910 |
+
"step": 610
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 5.995110024449878,
|
914 |
+
"eval_loss": 0.23938237130641937,
|
915 |
+
"eval_runtime": 387.8478,
|
916 |
+
"eval_samples_per_second": 1.057,
|
917 |
+
"eval_steps_per_second": 1.057,
|
918 |
+
"step": 613
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 6.014669926650367,
|
922 |
+
"grad_norm": 0.16670842468738556,
|
923 |
+
"learning_rate": 0.0001762734729271575,
|
924 |
+
"loss": 0.1275,
|
925 |
+
"step": 615
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 6.06356968215159,
|
929 |
+
"grad_norm": 0.23901741206645966,
|
930 |
+
"learning_rate": 0.00017571739189022365,
|
931 |
+
"loss": 0.1113,
|
932 |
+
"step": 620
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 6.112469437652812,
|
936 |
+
"grad_norm": 0.19317218661308289,
|
937 |
+
"learning_rate": 0.00017515576858688722,
|
938 |
+
"loss": 0.1101,
|
939 |
+
"step": 625
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 6.161369193154035,
|
943 |
+
"grad_norm": 0.21369099617004395,
|
944 |
+
"learning_rate": 0.00017458864412614434,
|
945 |
+
"loss": 0.1122,
|
946 |
+
"step": 630
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 6.210268948655257,
|
950 |
+
"grad_norm": 0.21011659502983093,
|
951 |
+
"learning_rate": 0.00017401606001965782,
|
952 |
+
"loss": 0.1136,
|
953 |
+
"step": 635
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 6.25916870415648,
|
957 |
+
"grad_norm": 0.1860456019639969,
|
958 |
+
"learning_rate": 0.00017343805817871886,
|
959 |
+
"loss": 0.1305,
|
960 |
+
"step": 640
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 6.308068459657702,
|
964 |
+
"grad_norm": 0.23417602479457855,
|
965 |
+
"learning_rate": 0.00017285468091117904,
|
966 |
+
"loss": 0.1165,
|
967 |
+
"step": 645
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 6.356968215158924,
|
971 |
+
"grad_norm": 0.189472958445549,
|
972 |
+
"learning_rate": 0.00017226597091835378,
|
973 |
+
"loss": 0.119,
|
974 |
+
"step": 650
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 6.405867970660147,
|
978 |
+
"grad_norm": 0.2460348904132843,
|
979 |
+
"learning_rate": 0.00017167197129189652,
|
980 |
+
"loss": 0.1188,
|
981 |
+
"step": 655
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 6.45476772616137,
|
985 |
+
"grad_norm": 0.20059679448604584,
|
986 |
+
"learning_rate": 0.00017107272551064473,
|
987 |
+
"loss": 0.1194,
|
988 |
+
"step": 660
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 6.503667481662592,
|
992 |
+
"grad_norm": 0.19838838279247284,
|
993 |
+
"learning_rate": 0.00017046827743743726,
|
994 |
+
"loss": 0.1165,
|
995 |
+
"step": 665
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 6.552567237163814,
|
999 |
+
"grad_norm": 0.20280085504055023,
|
1000 |
+
"learning_rate": 0.00016985867131590383,
|
1001 |
+
"loss": 0.1168,
|
1002 |
+
"step": 670
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 6.601466992665037,
|
1006 |
+
"grad_norm": 0.27974265813827515,
|
1007 |
+
"learning_rate": 0.00016924395176722647,
|
1008 |
+
"loss": 0.122,
|
1009 |
+
"step": 675
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 6.65036674816626,
|
1013 |
+
"grad_norm": 0.1994495540857315,
|
1014 |
+
"learning_rate": 0.0001686241637868734,
|
1015 |
+
"loss": 0.1173,
|
1016 |
+
"step": 680
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 6.699266503667482,
|
1020 |
+
"grad_norm": 0.20043040812015533,
|
1021 |
+
"learning_rate": 0.00016799935274130546,
|
1022 |
+
"loss": 0.1183,
|
1023 |
+
"step": 685
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 6.748166259168704,
|
1027 |
+
"grad_norm": 0.19184747338294983,
|
1028 |
+
"learning_rate": 0.00016736956436465573,
|
1029 |
+
"loss": 0.1192,
|
1030 |
+
"step": 690
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 6.797066014669927,
|
1034 |
+
"grad_norm": 0.20747938752174377,
|
1035 |
+
"learning_rate": 0.00016673484475538146,
|
1036 |
+
"loss": 0.1188,
|
1037 |
+
"step": 695
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 6.84596577017115,
|
1041 |
+
"grad_norm": 0.19285354018211365,
|
1042 |
+
"learning_rate": 0.00016609524037289019,
|
1043 |
+
"loss": 0.117,
|
1044 |
+
"step": 700
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 6.894865525672372,
|
1048 |
+
"grad_norm": 0.18242338299751282,
|
1049 |
+
"learning_rate": 0.00016545079803413892,
|
1050 |
+
"loss": 0.1208,
|
1051 |
+
"step": 705
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 6.943765281173594,
|
1055 |
+
"grad_norm": 0.19887416064739227,
|
1056 |
+
"learning_rate": 0.00016480156491020727,
|
1057 |
+
"loss": 0.1227,
|
1058 |
+
"step": 710
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 6.992665036674817,
|
1062 |
+
"grad_norm": 0.19773922860622406,
|
1063 |
+
"learning_rate": 0.00016414758852284478,
|
1064 |
+
"loss": 0.1199,
|
1065 |
+
"step": 715
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 6.992665036674817,
|
1069 |
+
"eval_loss": 0.24741248786449432,
|
1070 |
+
"eval_runtime": 387.335,
|
1071 |
+
"eval_samples_per_second": 1.059,
|
1072 |
+
"eval_steps_per_second": 1.059,
|
1073 |
+
"step": 715
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 7.041564792176039,
|
1077 |
+
"grad_norm": 0.5106807351112366,
|
1078 |
+
"learning_rate": 0.0001634889167409923,
|
1079 |
+
"loss": 0.1051,
|
1080 |
+
"step": 720
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 7.090464547677262,
|
1084 |
+
"grad_norm": 0.18619847297668457,
|
1085 |
+
"learning_rate": 0.0001628255977772784,
|
1086 |
+
"loss": 0.0979,
|
1087 |
+
"step": 725
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 7.139364303178484,
|
1091 |
+
"grad_norm": 0.18676620721817017,
|
1092 |
+
"learning_rate": 0.00016215768018449012,
|
1093 |
+
"loss": 0.1009,
|
1094 |
+
"step": 730
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 7.188264058679707,
|
1098 |
+
"grad_norm": 0.2054695338010788,
|
1099 |
+
"learning_rate": 0.00016148521285201927,
|
1100 |
+
"loss": 0.1002,
|
1101 |
+
"step": 735
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 7.237163814180929,
|
1105 |
+
"grad_norm": 0.20496530830860138,
|
1106 |
+
"learning_rate": 0.00016080824500228367,
|
1107 |
+
"loss": 0.1011,
|
1108 |
+
"step": 740
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 7.286063569682152,
|
1112 |
+
"grad_norm": 0.18679122626781464,
|
1113 |
+
"learning_rate": 0.0001601268261871244,
|
1114 |
+
"loss": 0.1052,
|
1115 |
+
"step": 745
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 7.334963325183374,
|
1119 |
+
"grad_norm": 0.20614224672317505,
|
1120 |
+
"learning_rate": 0.00015944100628417868,
|
1121 |
+
"loss": 0.1021,
|
1122 |
+
"step": 750
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 7.383863080684597,
|
1126 |
+
"grad_norm": 0.20026642084121704,
|
1127 |
+
"learning_rate": 0.00015875083549322908,
|
1128 |
+
"loss": 0.1019,
|
1129 |
+
"step": 755
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 7.432762836185819,
|
1133 |
+
"grad_norm": 0.1852520853281021,
|
1134 |
+
"learning_rate": 0.00015805636433252891,
|
1135 |
+
"loss": 0.1028,
|
1136 |
+
"step": 760
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 7.481662591687042,
|
1140 |
+
"grad_norm": 0.19096429646015167,
|
1141 |
+
"learning_rate": 0.0001573576436351046,
|
1142 |
+
"loss": 0.1031,
|
1143 |
+
"step": 765
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 7.530562347188264,
|
1147 |
+
"grad_norm": 0.18263529241085052,
|
1148 |
+
"learning_rate": 0.00015665472454503483,
|
1149 |
+
"loss": 0.1033,
|
1150 |
+
"step": 770
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 7.579462102689487,
|
1154 |
+
"grad_norm": 0.1884106546640396,
|
1155 |
+
"learning_rate": 0.00015594765851370684,
|
1156 |
+
"loss": 0.1063,
|
1157 |
+
"step": 775
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 7.628361858190709,
|
1161 |
+
"grad_norm": 0.2005338817834854,
|
1162 |
+
"learning_rate": 0.0001552364972960506,
|
1163 |
+
"loss": 0.1054,
|
1164 |
+
"step": 780
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 7.677261613691932,
|
1168 |
+
"grad_norm": 0.184016153216362,
|
1169 |
+
"learning_rate": 0.0001545212929467503,
|
1170 |
+
"loss": 0.1048,
|
1171 |
+
"step": 785
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 7.726161369193154,
|
1175 |
+
"grad_norm": 0.19765067100524902,
|
1176 |
+
"learning_rate": 0.0001538020978164341,
|
1177 |
+
"loss": 0.1044,
|
1178 |
+
"step": 790
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 7.775061124694377,
|
1182 |
+
"grad_norm": 0.18265607953071594,
|
1183 |
+
"learning_rate": 0.0001530789645478426,
|
1184 |
+
"loss": 0.1051,
|
1185 |
+
"step": 795
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 7.823960880195599,
|
1189 |
+
"grad_norm": 0.19815443456172943,
|
1190 |
+
"learning_rate": 0.00015235194607197508,
|
1191 |
+
"loss": 0.1081,
|
1192 |
+
"step": 800
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 7.872860635696822,
|
1196 |
+
"grad_norm": 0.22219662368297577,
|
1197 |
+
"learning_rate": 0.0001516210956042153,
|
1198 |
+
"loss": 0.1071,
|
1199 |
+
"step": 805
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 7.921760391198044,
|
1203 |
+
"grad_norm": 0.20078670978546143,
|
1204 |
+
"learning_rate": 0.0001508864666404365,
|
1205 |
+
"loss": 0.1075,
|
1206 |
+
"step": 810
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 7.970660146699267,
|
1210 |
+
"grad_norm": 0.17794115841388702,
|
1211 |
+
"learning_rate": 0.00015014811295308543,
|
1212 |
+
"loss": 0.1051,
|
1213 |
+
"step": 815
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 8.0,
|
1217 |
+
"eval_loss": 0.2625426948070526,
|
1218 |
+
"eval_runtime": 387.4946,
|
1219 |
+
"eval_samples_per_second": 1.058,
|
1220 |
+
"eval_steps_per_second": 1.058,
|
1221 |
+
"step": 818
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 8.01955990220049,
|
1225 |
+
"grad_norm": 0.1608039289712906,
|
1226 |
+
"learning_rate": 0.0001494060885872464,
|
1227 |
+
"loss": 0.0994,
|
1228 |
+
"step": 820
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 8.06845965770171,
|
1232 |
+
"grad_norm": 0.2323434203863144,
|
1233 |
+
"learning_rate": 0.00014866044785668563,
|
1234 |
+
"loss": 0.0895,
|
1235 |
+
"step": 825
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 8.117359413202934,
|
1239 |
+
"grad_norm": 0.17606528103351593,
|
1240 |
+
"learning_rate": 0.0001479112453398753,
|
1241 |
+
"loss": 0.0849,
|
1242 |
+
"step": 830
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 8.166259168704157,
|
1246 |
+
"grad_norm": 0.19025173783302307,
|
1247 |
+
"learning_rate": 0.0001471585358759987,
|
1248 |
+
"loss": 0.0886,
|
1249 |
+
"step": 835
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 8.21515892420538,
|
1253 |
+
"grad_norm": 0.1990627497434616,
|
1254 |
+
"learning_rate": 0.00014640237456093634,
|
1255 |
+
"loss": 0.0905,
|
1256 |
+
"step": 840
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 8.2640586797066,
|
1260 |
+
"grad_norm": 0.1725684553384781,
|
1261 |
+
"learning_rate": 0.00014564281674323297,
|
1262 |
+
"loss": 0.0899,
|
1263 |
+
"step": 845
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 8.312958435207824,
|
1267 |
+
"grad_norm": 0.18845060467720032,
|
1268 |
+
"learning_rate": 0.00014487991802004623,
|
1269 |
+
"loss": 0.0886,
|
1270 |
+
"step": 850
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 8.361858190709047,
|
1274 |
+
"grad_norm": 0.23856212198734283,
|
1275 |
+
"learning_rate": 0.00014411373423307714,
|
1276 |
+
"loss": 0.0924,
|
1277 |
+
"step": 855
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 8.41075794621027,
|
1281 |
+
"grad_norm": 0.18084120750427246,
|
1282 |
+
"learning_rate": 0.00014334432146448272,
|
1283 |
+
"loss": 0.0918,
|
1284 |
+
"step": 860
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 8.45965770171149,
|
1288 |
+
"grad_norm": 0.18600909411907196,
|
1289 |
+
"learning_rate": 0.00014257173603277095,
|
1290 |
+
"loss": 0.0913,
|
1291 |
+
"step": 865
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 8.508557457212714,
|
1295 |
+
"grad_norm": 0.1851680874824524,
|
1296 |
+
"learning_rate": 0.00014179603448867835,
|
1297 |
+
"loss": 0.0912,
|
1298 |
+
"step": 870
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 8.557457212713937,
|
1302 |
+
"grad_norm": 0.1818709820508957,
|
1303 |
+
"learning_rate": 0.00014101727361103076,
|
1304 |
+
"loss": 0.0903,
|
1305 |
+
"step": 875
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 8.60635696821516,
|
1309 |
+
"grad_norm": 0.19458520412445068,
|
1310 |
+
"learning_rate": 0.00014023551040258725,
|
1311 |
+
"loss": 0.0916,
|
1312 |
+
"step": 880
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 8.65525672371638,
|
1316 |
+
"grad_norm": 0.17777447402477264,
|
1317 |
+
"learning_rate": 0.00013945080208586775,
|
1318 |
+
"loss": 0.0928,
|
1319 |
+
"step": 885
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 8.704156479217604,
|
1323 |
+
"grad_norm": 0.20647075772285461,
|
1324 |
+
"learning_rate": 0.00013866320609896447,
|
1325 |
+
"loss": 0.0926,
|
1326 |
+
"step": 890
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 8.753056234718827,
|
1330 |
+
"grad_norm": 0.18589670956134796,
|
1331 |
+
"learning_rate": 0.00013787278009133776,
|
1332 |
+
"loss": 0.0934,
|
1333 |
+
"step": 895
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 8.80195599022005,
|
1337 |
+
"grad_norm": 0.19582615792751312,
|
1338 |
+
"learning_rate": 0.00013707958191959608,
|
1339 |
+
"loss": 0.0954,
|
1340 |
+
"step": 900
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 8.85085574572127,
|
1344 |
+
"grad_norm": 0.19688870012760162,
|
1345 |
+
"learning_rate": 0.00013628366964326153,
|
1346 |
+
"loss": 0.0925,
|
1347 |
+
"step": 905
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 8.899755501222494,
|
1351 |
+
"grad_norm": 0.1874823123216629,
|
1352 |
+
"learning_rate": 0.00013548510152051963,
|
1353 |
+
"loss": 0.0939,
|
1354 |
+
"step": 910
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 8.948655256723717,
|
1358 |
+
"grad_norm": 0.1876133382320404,
|
1359 |
+
"learning_rate": 0.00013468393600395525,
|
1360 |
+
"loss": 0.097,
|
1361 |
+
"step": 915
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 8.99755501222494,
|
1365 |
+
"grad_norm": 0.1735718548297882,
|
1366 |
+
"learning_rate": 0.00013388023173627414,
|
1367 |
+
"loss": 0.0945,
|
1368 |
+
"step": 920
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 8.99755501222494,
|
1372 |
+
"eval_loss": 0.27974453568458557,
|
1373 |
+
"eval_runtime": 387.9073,
|
1374 |
+
"eval_samples_per_second": 1.057,
|
1375 |
+
"eval_steps_per_second": 1.057,
|
1376 |
+
"step": 920
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 9.04645476772616,
|
1380 |
+
"grad_norm": 0.1655295491218567,
|
1381 |
+
"learning_rate": 0.00013307404754601013,
|
1382 |
+
"loss": 0.0806,
|
1383 |
+
"step": 925
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 9.095354523227384,
|
1387 |
+
"grad_norm": 0.19395217299461365,
|
1388 |
+
"learning_rate": 0.0001322654424432195,
|
1389 |
+
"loss": 0.0788,
|
1390 |
+
"step": 930
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 9.144254278728607,
|
1394 |
+
"grad_norm": 0.18941174447536469,
|
1395 |
+
"learning_rate": 0.00013145447561516138,
|
1396 |
+
"loss": 0.0793,
|
1397 |
+
"step": 935
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 9.19315403422983,
|
1401 |
+
"grad_norm": 0.20010443031787872,
|
1402 |
+
"learning_rate": 0.00013064120642196548,
|
1403 |
+
"loss": 0.0807,
|
1404 |
+
"step": 940
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 9.24205378973105,
|
1408 |
+
"grad_norm": 0.20777645707130432,
|
1409 |
+
"learning_rate": 0.00012982569439228713,
|
1410 |
+
"loss": 0.08,
|
1411 |
+
"step": 945
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 9.290953545232274,
|
1415 |
+
"grad_norm": 0.173665389418602,
|
1416 |
+
"learning_rate": 0.00012900799921895003,
|
1417 |
+
"loss": 0.0808,
|
1418 |
+
"step": 950
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 9.339853300733497,
|
1422 |
+
"grad_norm": 0.20865468680858612,
|
1423 |
+
"learning_rate": 0.0001281881807545769,
|
1424 |
+
"loss": 0.0808,
|
1425 |
+
"step": 955
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 9.38875305623472,
|
1429 |
+
"grad_norm": 0.18372130393981934,
|
1430 |
+
"learning_rate": 0.0001273662990072083,
|
1431 |
+
"loss": 0.0804,
|
1432 |
+
"step": 960
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 9.43765281173594,
|
1436 |
+
"grad_norm": 0.1785283237695694,
|
1437 |
+
"learning_rate": 0.00012654241413591054,
|
1438 |
+
"loss": 0.0812,
|
1439 |
+
"step": 965
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 9.486552567237164,
|
1443 |
+
"grad_norm": 0.17695043981075287,
|
1444 |
+
"learning_rate": 0.000125716586446372,
|
1445 |
+
"loss": 0.0827,
|
1446 |
+
"step": 970
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 9.535452322738386,
|
1450 |
+
"grad_norm": 0.18287776410579681,
|
1451 |
+
"learning_rate": 0.00012488887638648907,
|
1452 |
+
"loss": 0.083,
|
1453 |
+
"step": 975
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 9.58435207823961,
|
1457 |
+
"grad_norm": 0.20748884975910187,
|
1458 |
+
"learning_rate": 0.00012405934454194146,
|
1459 |
+
"loss": 0.0816,
|
1460 |
+
"step": 980
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 9.63325183374083,
|
1464 |
+
"grad_norm": 0.18160052597522736,
|
1465 |
+
"learning_rate": 0.00012322805163175762,
|
1466 |
+
"loss": 0.0823,
|
1467 |
+
"step": 985
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 9.682151589242054,
|
1471 |
+
"grad_norm": 0.17889925837516785,
|
1472 |
+
"learning_rate": 0.0001223950585038703,
|
1473 |
+
"loss": 0.0822,
|
1474 |
+
"step": 990
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 9.731051344743276,
|
1478 |
+
"grad_norm": 0.1896965056657791,
|
1479 |
+
"learning_rate": 0.00012156042613066258,
|
1480 |
+
"loss": 0.0839,
|
1481 |
+
"step": 995
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 9.7799511002445,
|
1485 |
+
"grad_norm": 0.19203361868858337,
|
1486 |
+
"learning_rate": 0.00012072421560450497,
|
1487 |
+
"loss": 0.0828,
|
1488 |
+
"step": 1000
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 9.82885085574572,
|
1492 |
+
"grad_norm": 0.18262554705142975,
|
1493 |
+
"learning_rate": 0.00011988648813328367,
|
1494 |
+
"loss": 0.0838,
|
1495 |
+
"step": 1005
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 9.877750611246944,
|
1499 |
+
"grad_norm": 0.18471267819404602,
|
1500 |
+
"learning_rate": 0.0001190473050359203,
|
1501 |
+
"loss": 0.084,
|
1502 |
+
"step": 1010
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 9.926650366748166,
|
1506 |
+
"grad_norm": 0.18675756454467773,
|
1507 |
+
"learning_rate": 0.00011820672773788353,
|
1508 |
+
"loss": 0.0835,
|
1509 |
+
"step": 1015
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 9.97555012224939,
|
1513 |
+
"grad_norm": 0.17983846366405487,
|
1514 |
+
"learning_rate": 0.00011736481776669306,
|
1515 |
+
"loss": 0.0843,
|
1516 |
+
"step": 1020
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 9.995110024449877,
|
1520 |
+
"eval_loss": 0.2892283499240875,
|
1521 |
+
"eval_runtime": 389.1699,
|
1522 |
+
"eval_samples_per_second": 1.054,
|
1523 |
+
"eval_steps_per_second": 1.054,
|
1524 |
+
"step": 1022
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 9.995110024449877,
|
1528 |
+
"step": 1022,
|
1529 |
+
"total_flos": 7.585797735459062e+17,
|
1530 |
+
"train_loss": 0.2326957560244605,
|
1531 |
+
"train_runtime": 28787.7929,
|
1532 |
+
"train_samples_per_second": 0.568,
|
1533 |
+
"train_steps_per_second": 0.071
|
1534 |
+
}
|
1535 |
+
],
|
1536 |
+
"logging_steps": 5,
|
1537 |
+
"max_steps": 2040,
|
1538 |
+
"num_input_tokens_seen": 0,
|
1539 |
+
"num_train_epochs": 20,
|
1540 |
+
"save_steps": 50,
|
1541 |
+
"stateful_callbacks": {
|
1542 |
+
"EarlyStoppingCallback": {
|
1543 |
+
"args": {
|
1544 |
+
"early_stopping_patience": 5,
|
1545 |
+
"early_stopping_threshold": 0.0
|
1546 |
+
},
|
1547 |
+
"attributes": {
|
1548 |
+
"early_stopping_patience_counter": 0
|
1549 |
+
}
|
1550 |
+
},
|
1551 |
+
"TrainerControl": {
|
1552 |
+
"args": {
|
1553 |
+
"should_epoch_stop": false,
|
1554 |
+
"should_evaluate": false,
|
1555 |
+
"should_log": false,
|
1556 |
+
"should_save": true,
|
1557 |
+
"should_training_stop": true
|
1558 |
+
},
|
1559 |
+
"attributes": {}
|
1560 |
+
}
|
1561 |
+
},
|
1562 |
+
"total_flos": 7.585797735459062e+17,
|
1563 |
+
"train_batch_size": 1,
|
1564 |
+
"trial_name": null,
|
1565 |
+
"trial_params": null
|
1566 |
+
}
|