Model save
Browse files- README.md +78 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Aug10_01-50-35_e8f6cb577ded/events.out.tfevents.1723254790.e8f6cb577ded.87185.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2019 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
3 |
+
datasets:
|
4 |
+
- generator
|
5 |
+
library_name: peft
|
6 |
+
license: llama3
|
7 |
+
tags:
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
+
- generated_from_trainer
|
11 |
+
model-index:
|
12 |
+
- name: llama3-8b-coding-gpt4o-100k
|
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 |
+
# llama3-8b-coding-gpt4o-100k
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.5174
|
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: 0.002
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 8
|
48 |
+
- gradient_accumulation_steps: 2
|
49 |
+
- total_train_batch_size: 128
|
50 |
+
- total_eval_batch_size: 64
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: cosine
|
53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
54 |
+
- num_epochs: 10
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
60 |
+
| 0.4861 | 1.0 | 135 | 1.2495 |
|
61 |
+
| 0.458 | 2.0 | 270 | 1.2390 |
|
62 |
+
| 0.4423 | 3.0 | 405 | 1.2549 |
|
63 |
+
| 0.4244 | 4.0 | 540 | 1.2665 |
|
64 |
+
| 0.4051 | 5.0 | 675 | 1.2714 |
|
65 |
+
| 0.3815 | 6.0 | 810 | 1.2959 |
|
66 |
+
| 0.3546 | 7.0 | 945 | 1.3560 |
|
67 |
+
| 0.3233 | 8.0 | 1080 | 1.4125 |
|
68 |
+
| 0.2969 | 9.0 | 1215 | 1.4809 |
|
69 |
+
| 0.2818 | 10.0 | 1350 | 1.5174 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- PEFT 0.12.0
|
75 |
+
- Transformers 4.44.0
|
76 |
+
- Pytorch 2.2.0+cu121
|
77 |
+
- Datasets 2.20.0
|
78 |
+
- 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 2155922488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8917d4c48cb421134d8fee0d433f26f32d32dfd62fc4729fb61364bcc2fe2ae5
|
3 |
size 2155922488
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 7.982333171800736e+18,
|
4 |
+
"train_loss": 0.3983345487382677,
|
5 |
+
"train_runtime": 11606.8402,
|
6 |
+
"train_samples": 116368,
|
7 |
+
"train_samples_per_second": 14.865,
|
8 |
+
"train_steps_per_second": 0.116
|
9 |
+
}
|
runs/Aug10_01-50-35_e8f6cb577ded/events.out.tfevents.1723254790.e8f6cb577ded.87185.0
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 sha256:4f508566b0010a302ec433c9685e3db5dd40fec22cf4ceac0a46dd38597dd2ce
|
3 |
+
size 66109
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 7.982333171800736e+18,
|
4 |
+
"train_loss": 0.3983345487382677,
|
5 |
+
"train_runtime": 11606.8402,
|
6 |
+
"train_samples": 116368,
|
7 |
+
"train_samples_per_second": 14.865,
|
8 |
+
"train_steps_per_second": 0.116
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2019 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1350,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.007407407407407408,
|
13 |
+
"grad_norm": 1.5567783117294312,
|
14 |
+
"learning_rate": 1.4814814814814815e-05,
|
15 |
+
"loss": 1.5566,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.037037037037037035,
|
20 |
+
"grad_norm": 1.6362663507461548,
|
21 |
+
"learning_rate": 7.407407407407407e-05,
|
22 |
+
"loss": 1.5121,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07407407407407407,
|
27 |
+
"grad_norm": 0.9970850944519043,
|
28 |
+
"learning_rate": 0.00014814814814814815,
|
29 |
+
"loss": 1.2449,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1111111111111111,
|
34 |
+
"grad_norm": 0.688450813293457,
|
35 |
+
"learning_rate": 0.0002222222222222222,
|
36 |
+
"loss": 0.8674,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.14814814814814814,
|
41 |
+
"grad_norm": 0.4350931942462921,
|
42 |
+
"learning_rate": 0.0002962962962962963,
|
43 |
+
"loss": 0.7491,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18518518518518517,
|
48 |
+
"grad_norm": 0.377754271030426,
|
49 |
+
"learning_rate": 0.00037037037037037035,
|
50 |
+
"loss": 0.6649,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2222222222222222,
|
55 |
+
"grad_norm": 0.19140222668647766,
|
56 |
+
"learning_rate": 0.0004444444444444444,
|
57 |
+
"loss": 0.6335,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.25925925925925924,
|
62 |
+
"grad_norm": 0.16032004356384277,
|
63 |
+
"learning_rate": 0.0005185185185185185,
|
64 |
+
"loss": 0.6068,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2962962962962963,
|
69 |
+
"grad_norm": 0.15596596896648407,
|
70 |
+
"learning_rate": 0.0005925925925925926,
|
71 |
+
"loss": 0.5878,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.3333333333333333,
|
76 |
+
"grad_norm": 0.12440178543329239,
|
77 |
+
"learning_rate": 0.0006666666666666666,
|
78 |
+
"loss": 0.564,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.37037037037037035,
|
83 |
+
"grad_norm": 0.13573868572711945,
|
84 |
+
"learning_rate": 0.0007407407407407407,
|
85 |
+
"loss": 0.56,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.4074074074074074,
|
90 |
+
"grad_norm": 0.10565729439258575,
|
91 |
+
"learning_rate": 0.0008148148148148148,
|
92 |
+
"loss": 0.5418,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4444444444444444,
|
97 |
+
"grad_norm": 0.11647824943065643,
|
98 |
+
"learning_rate": 0.0008888888888888888,
|
99 |
+
"loss": 0.5356,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.48148148148148145,
|
104 |
+
"grad_norm": 0.10235206037759781,
|
105 |
+
"learning_rate": 0.0009629629629629629,
|
106 |
+
"loss": 0.5294,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5185185185185185,
|
111 |
+
"grad_norm": 0.17172235250473022,
|
112 |
+
"learning_rate": 0.001037037037037037,
|
113 |
+
"loss": 0.5216,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5555555555555556,
|
118 |
+
"grad_norm": 0.12478260695934296,
|
119 |
+
"learning_rate": 0.0011111111111111111,
|
120 |
+
"loss": 0.5218,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5925925925925926,
|
125 |
+
"grad_norm": 0.11295782774686813,
|
126 |
+
"learning_rate": 0.0011851851851851852,
|
127 |
+
"loss": 0.5144,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6296296296296297,
|
132 |
+
"grad_norm": 0.1066703274846077,
|
133 |
+
"learning_rate": 0.0012592592592592592,
|
134 |
+
"loss": 0.5154,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6666666666666666,
|
139 |
+
"grad_norm": 0.0921861082315445,
|
140 |
+
"learning_rate": 0.0013333333333333333,
|
141 |
+
"loss": 0.5003,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.7037037037037037,
|
146 |
+
"grad_norm": 0.09984983503818512,
|
147 |
+
"learning_rate": 0.0014074074074074076,
|
148 |
+
"loss": 0.5042,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7407407407407407,
|
153 |
+
"grad_norm": 0.13562288880348206,
|
154 |
+
"learning_rate": 0.0014814814814814814,
|
155 |
+
"loss": 0.5003,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7777777777777778,
|
160 |
+
"grad_norm": 0.09528646618127823,
|
161 |
+
"learning_rate": 0.0015555555555555557,
|
162 |
+
"loss": 0.4996,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8148148148148148,
|
167 |
+
"grad_norm": 0.14511393010616302,
|
168 |
+
"learning_rate": 0.0016296296296296295,
|
169 |
+
"loss": 0.4929,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.8518518518518519,
|
174 |
+
"grad_norm": 0.0997464582324028,
|
175 |
+
"learning_rate": 0.0017037037037037038,
|
176 |
+
"loss": 0.4906,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8888888888888888,
|
181 |
+
"grad_norm": 0.14288371801376343,
|
182 |
+
"learning_rate": 0.0017777777777777776,
|
183 |
+
"loss": 0.4924,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9259259259259259,
|
188 |
+
"grad_norm": 0.12957949936389923,
|
189 |
+
"learning_rate": 0.001851851851851852,
|
190 |
+
"loss": 0.4879,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9629629629629629,
|
195 |
+
"grad_norm": 0.10427533835172653,
|
196 |
+
"learning_rate": 0.0019259259259259258,
|
197 |
+
"loss": 0.4856,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.0,
|
202 |
+
"grad_norm": 0.11492197960615158,
|
203 |
+
"learning_rate": 0.002,
|
204 |
+
"loss": 0.4861,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.0,
|
209 |
+
"eval_loss": 1.2494666576385498,
|
210 |
+
"eval_runtime": 1.452,
|
211 |
+
"eval_samples_per_second": 2.755,
|
212 |
+
"eval_steps_per_second": 0.689,
|
213 |
+
"step": 135
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.037037037037037,
|
217 |
+
"grad_norm": 0.20287227630615234,
|
218 |
+
"learning_rate": 0.0019999164298554373,
|
219 |
+
"loss": 0.4759,
|
220 |
+
"step": 140
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.074074074074074,
|
224 |
+
"grad_norm": 0.10903054475784302,
|
225 |
+
"learning_rate": 0.0019996657333896874,
|
226 |
+
"loss": 0.4752,
|
227 |
+
"step": 145
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.1111111111111112,
|
231 |
+
"grad_norm": 0.09817971289157867,
|
232 |
+
"learning_rate": 0.00199924795250423,
|
233 |
+
"loss": 0.4771,
|
234 |
+
"step": 150
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.1481481481481481,
|
238 |
+
"grad_norm": 0.10313747823238373,
|
239 |
+
"learning_rate": 0.001998663157027083,
|
240 |
+
"loss": 0.471,
|
241 |
+
"step": 155
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 1.1851851851851851,
|
245 |
+
"grad_norm": 0.10586988180875778,
|
246 |
+
"learning_rate": 0.001997911444701132,
|
247 |
+
"loss": 0.4675,
|
248 |
+
"step": 160
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.2222222222222223,
|
252 |
+
"grad_norm": 0.10676765441894531,
|
253 |
+
"learning_rate": 0.001996992941167792,
|
254 |
+
"loss": 0.4743,
|
255 |
+
"step": 165
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 1.2592592592592593,
|
259 |
+
"grad_norm": 0.09956058114767075,
|
260 |
+
"learning_rate": 0.0019959077999460095,
|
261 |
+
"loss": 0.4682,
|
262 |
+
"step": 170
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 1.2962962962962963,
|
266 |
+
"grad_norm": 0.08940426260232925,
|
267 |
+
"learning_rate": 0.0019946562024066015,
|
268 |
+
"loss": 0.4667,
|
269 |
+
"step": 175
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.3333333333333333,
|
273 |
+
"grad_norm": 0.09569676965475082,
|
274 |
+
"learning_rate": 0.001993238357741943,
|
275 |
+
"loss": 0.4742,
|
276 |
+
"step": 180
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 1.3703703703703702,
|
280 |
+
"grad_norm": 0.1325625479221344,
|
281 |
+
"learning_rate": 0.0019916545029310014,
|
282 |
+
"loss": 0.4735,
|
283 |
+
"step": 185
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 1.4074074074074074,
|
287 |
+
"grad_norm": 0.09514327347278595,
|
288 |
+
"learning_rate": 0.0019899049026997273,
|
289 |
+
"loss": 0.473,
|
290 |
+
"step": 190
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.4444444444444444,
|
294 |
+
"grad_norm": 0.10093410313129425,
|
295 |
+
"learning_rate": 0.001987989849476809,
|
296 |
+
"loss": 0.4693,
|
297 |
+
"step": 195
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.4814814814814814,
|
301 |
+
"grad_norm": 0.10901673138141632,
|
302 |
+
"learning_rate": 0.0019859096633447963,
|
303 |
+
"loss": 0.4666,
|
304 |
+
"step": 200
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.5185185185185186,
|
308 |
+
"grad_norm": 0.10339543968439102,
|
309 |
+
"learning_rate": 0.001983664691986601,
|
310 |
+
"loss": 0.4712,
|
311 |
+
"step": 205
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.5555555555555556,
|
315 |
+
"grad_norm": 0.0933491587638855,
|
316 |
+
"learning_rate": 0.001981255310627385,
|
317 |
+
"loss": 0.4692,
|
318 |
+
"step": 210
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.5925925925925926,
|
322 |
+
"grad_norm": 0.09102772176265717,
|
323 |
+
"learning_rate": 0.0019786819219718443,
|
324 |
+
"loss": 0.4666,
|
325 |
+
"step": 215
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.6296296296296298,
|
329 |
+
"grad_norm": 0.08935283869504929,
|
330 |
+
"learning_rate": 0.0019759449561369035,
|
331 |
+
"loss": 0.4605,
|
332 |
+
"step": 220
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.6666666666666665,
|
336 |
+
"grad_norm": 0.10174907743930817,
|
337 |
+
"learning_rate": 0.0019730448705798237,
|
338 |
+
"loss": 0.465,
|
339 |
+
"step": 225
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.7037037037037037,
|
343 |
+
"grad_norm": 0.09616223722696304,
|
344 |
+
"learning_rate": 0.0019699821500217436,
|
345 |
+
"loss": 0.4684,
|
346 |
+
"step": 230
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.7407407407407407,
|
350 |
+
"grad_norm": 0.09224896878004074,
|
351 |
+
"learning_rate": 0.001966757306366662,
|
352 |
+
"loss": 0.468,
|
353 |
+
"step": 235
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.7777777777777777,
|
357 |
+
"grad_norm": 0.09403350204229355,
|
358 |
+
"learning_rate": 0.0019633708786158804,
|
359 |
+
"loss": 0.4658,
|
360 |
+
"step": 240
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.8148148148148149,
|
364 |
+
"grad_norm": 0.09764115512371063,
|
365 |
+
"learning_rate": 0.001959823432777912,
|
366 |
+
"loss": 0.4682,
|
367 |
+
"step": 245
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.8518518518518519,
|
371 |
+
"grad_norm": 0.08690910041332245,
|
372 |
+
"learning_rate": 0.0019561155617738796,
|
373 |
+
"loss": 0.4679,
|
374 |
+
"step": 250
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.8888888888888888,
|
378 |
+
"grad_norm": 0.10882115364074707,
|
379 |
+
"learning_rate": 0.0019522478853384153,
|
380 |
+
"loss": 0.46,
|
381 |
+
"step": 255
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.925925925925926,
|
385 |
+
"grad_norm": 0.10638313740491867,
|
386 |
+
"learning_rate": 0.0019482210499160765,
|
387 |
+
"loss": 0.4601,
|
388 |
+
"step": 260
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.9629629629629628,
|
392 |
+
"grad_norm": 0.1394616961479187,
|
393 |
+
"learning_rate": 0.0019440357285533,
|
394 |
+
"loss": 0.4649,
|
395 |
+
"step": 265
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.0,
|
399 |
+
"grad_norm": 0.11232441663742065,
|
400 |
+
"learning_rate": 0.0019396926207859084,
|
401 |
+
"loss": 0.458,
|
402 |
+
"step": 270
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.0,
|
406 |
+
"eval_loss": 1.2390342950820923,
|
407 |
+
"eval_runtime": 1.4571,
|
408 |
+
"eval_samples_per_second": 2.745,
|
409 |
+
"eval_steps_per_second": 0.686,
|
410 |
+
"step": 270
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.037037037037037,
|
414 |
+
"grad_norm": 0.11058547347784042,
|
415 |
+
"learning_rate": 0.0019351924525221897,
|
416 |
+
"loss": 0.4336,
|
417 |
+
"step": 275
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 2.074074074074074,
|
421 |
+
"grad_norm": 0.10051153600215912,
|
422 |
+
"learning_rate": 0.0019305359759215685,
|
423 |
+
"loss": 0.4345,
|
424 |
+
"step": 280
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 2.111111111111111,
|
428 |
+
"grad_norm": 0.09568148106336594,
|
429 |
+
"learning_rate": 0.0019257239692688907,
|
430 |
+
"loss": 0.4356,
|
431 |
+
"step": 285
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 2.148148148148148,
|
435 |
+
"grad_norm": 0.09497468173503876,
|
436 |
+
"learning_rate": 0.0019207572368443383,
|
437 |
+
"loss": 0.44,
|
438 |
+
"step": 290
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 2.185185185185185,
|
442 |
+
"grad_norm": 0.10157410800457001,
|
443 |
+
"learning_rate": 0.001915636608789006,
|
444 |
+
"loss": 0.439,
|
445 |
+
"step": 295
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 2.2222222222222223,
|
449 |
+
"grad_norm": 0.1098947674036026,
|
450 |
+
"learning_rate": 0.0019103629409661467,
|
451 |
+
"loss": 0.44,
|
452 |
+
"step": 300
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.259259259259259,
|
456 |
+
"grad_norm": 0.09858433902263641,
|
457 |
+
"learning_rate": 0.0019049371148181253,
|
458 |
+
"loss": 0.4466,
|
459 |
+
"step": 305
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 2.2962962962962963,
|
463 |
+
"grad_norm": 0.09663781523704529,
|
464 |
+
"learning_rate": 0.0018993600372190932,
|
465 |
+
"loss": 0.4408,
|
466 |
+
"step": 310
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 2.3333333333333335,
|
470 |
+
"grad_norm": 0.100925512611866,
|
471 |
+
"learning_rate": 0.0018936326403234123,
|
472 |
+
"loss": 0.4393,
|
473 |
+
"step": 315
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 2.3703703703703702,
|
477 |
+
"grad_norm": 0.10806870460510254,
|
478 |
+
"learning_rate": 0.0018877558814098562,
|
479 |
+
"loss": 0.4393,
|
480 |
+
"step": 320
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 2.4074074074074074,
|
484 |
+
"grad_norm": 0.10387130826711655,
|
485 |
+
"learning_rate": 0.001881730742721608,
|
486 |
+
"loss": 0.4445,
|
487 |
+
"step": 325
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 2.4444444444444446,
|
491 |
+
"grad_norm": 0.09329431504011154,
|
492 |
+
"learning_rate": 0.0018755582313020908,
|
493 |
+
"loss": 0.439,
|
494 |
+
"step": 330
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 2.4814814814814814,
|
498 |
+
"grad_norm": 0.09396202117204666,
|
499 |
+
"learning_rate": 0.0018692393788266478,
|
500 |
+
"loss": 0.4379,
|
501 |
+
"step": 335
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 2.5185185185185186,
|
505 |
+
"grad_norm": 0.10305757075548172,
|
506 |
+
"learning_rate": 0.0018627752414301084,
|
507 |
+
"loss": 0.4412,
|
508 |
+
"step": 340
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 2.5555555555555554,
|
512 |
+
"grad_norm": 0.1034080982208252,
|
513 |
+
"learning_rate": 0.0018561668995302665,
|
514 |
+
"loss": 0.4445,
|
515 |
+
"step": 345
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.5925925925925926,
|
519 |
+
"grad_norm": 0.09808813035488129,
|
520 |
+
"learning_rate": 0.0018494154576472975,
|
521 |
+
"loss": 0.4454,
|
522 |
+
"step": 350
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 2.6296296296296298,
|
526 |
+
"grad_norm": 0.0979294404387474,
|
527 |
+
"learning_rate": 0.0018425220442191495,
|
528 |
+
"loss": 0.4498,
|
529 |
+
"step": 355
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 2.6666666666666665,
|
533 |
+
"grad_norm": 0.09154608845710754,
|
534 |
+
"learning_rate": 0.0018354878114129364,
|
535 |
+
"loss": 0.4416,
|
536 |
+
"step": 360
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 2.7037037037037037,
|
540 |
+
"grad_norm": 0.0931951180100441,
|
541 |
+
"learning_rate": 0.0018283139349323631,
|
542 |
+
"loss": 0.4439,
|
543 |
+
"step": 365
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 2.7407407407407405,
|
547 |
+
"grad_norm": 0.09334207326173782,
|
548 |
+
"learning_rate": 0.0018210016138212187,
|
549 |
+
"loss": 0.4443,
|
550 |
+
"step": 370
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 2.7777777777777777,
|
554 |
+
"grad_norm": 0.092356376349926,
|
555 |
+
"learning_rate": 0.0018135520702629675,
|
556 |
+
"loss": 0.4429,
|
557 |
+
"step": 375
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 2.814814814814815,
|
561 |
+
"grad_norm": 0.09269876778125763,
|
562 |
+
"learning_rate": 0.0018059665493764742,
|
563 |
+
"loss": 0.4443,
|
564 |
+
"step": 380
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 2.851851851851852,
|
568 |
+
"grad_norm": 0.10383119434118271,
|
569 |
+
"learning_rate": 0.0017982463190078929,
|
570 |
+
"loss": 0.4436,
|
571 |
+
"step": 385
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.888888888888889,
|
575 |
+
"grad_norm": 0.0941496342420578,
|
576 |
+
"learning_rate": 0.0017903926695187593,
|
577 |
+
"loss": 0.4456,
|
578 |
+
"step": 390
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.925925925925926,
|
582 |
+
"grad_norm": 0.09286876022815704,
|
583 |
+
"learning_rate": 0.0017824069135703197,
|
584 |
+
"loss": 0.445,
|
585 |
+
"step": 395
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 2.962962962962963,
|
589 |
+
"grad_norm": 0.09152144938707352,
|
590 |
+
"learning_rate": 0.0017742903859041324,
|
591 |
+
"loss": 0.4499,
|
592 |
+
"step": 400
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 3.0,
|
596 |
+
"grad_norm": 0.09554123133420944,
|
597 |
+
"learning_rate": 0.001766044443118978,
|
598 |
+
"loss": 0.4423,
|
599 |
+
"step": 405
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 3.0,
|
603 |
+
"eval_loss": 1.2548832893371582,
|
604 |
+
"eval_runtime": 1.4432,
|
605 |
+
"eval_samples_per_second": 2.772,
|
606 |
+
"eval_steps_per_second": 0.693,
|
607 |
+
"step": 405
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 3.037037037037037,
|
611 |
+
"grad_norm": 0.0980718806385994,
|
612 |
+
"learning_rate": 0.001757670463444118,
|
613 |
+
"loss": 0.4156,
|
614 |
+
"step": 410
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 3.074074074074074,
|
618 |
+
"grad_norm": 0.09404606372117996,
|
619 |
+
"learning_rate": 0.0017491698465089362,
|
620 |
+
"loss": 0.4121,
|
621 |
+
"step": 415
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 3.111111111111111,
|
625 |
+
"grad_norm": 0.11583345383405685,
|
626 |
+
"learning_rate": 0.0017405440131090047,
|
627 |
+
"loss": 0.4172,
|
628 |
+
"step": 420
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 3.148148148148148,
|
632 |
+
"grad_norm": 0.09314367175102234,
|
633 |
+
"learning_rate": 0.0017317944049686123,
|
634 |
+
"loss": 0.4166,
|
635 |
+
"step": 425
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 3.185185185185185,
|
639 |
+
"grad_norm": 0.1007940024137497,
|
640 |
+
"learning_rate": 0.001722922484499793,
|
641 |
+
"loss": 0.4123,
|
642 |
+
"step": 430
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 3.2222222222222223,
|
646 |
+
"grad_norm": 0.0978422611951828,
|
647 |
+
"learning_rate": 0.0017139297345578992,
|
648 |
+
"loss": 0.4199,
|
649 |
+
"step": 435
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 3.259259259259259,
|
653 |
+
"grad_norm": 0.09395431727170944,
|
654 |
+
"learning_rate": 0.0017048176581937562,
|
655 |
+
"loss": 0.4133,
|
656 |
+
"step": 440
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 3.2962962962962963,
|
660 |
+
"grad_norm": 0.09783247113227844,
|
661 |
+
"learning_rate": 0.0016955877784024418,
|
662 |
+
"loss": 0.4253,
|
663 |
+
"step": 445
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 3.3333333333333335,
|
667 |
+
"grad_norm": 0.0955362394452095,
|
668 |
+
"learning_rate": 0.0016862416378687337,
|
669 |
+
"loss": 0.4204,
|
670 |
+
"step": 450
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 3.3703703703703702,
|
674 |
+
"grad_norm": 0.09792539477348328,
|
675 |
+
"learning_rate": 0.001676780798709262,
|
676 |
+
"loss": 0.4232,
|
677 |
+
"step": 455
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 3.4074074074074074,
|
681 |
+
"grad_norm": 0.09116431325674057,
|
682 |
+
"learning_rate": 0.0016672068422114196,
|
683 |
+
"loss": 0.4211,
|
684 |
+
"step": 460
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 3.4444444444444446,
|
688 |
+
"grad_norm": 0.1013198271393776,
|
689 |
+
"learning_rate": 0.0016575213685690638,
|
690 |
+
"loss": 0.4202,
|
691 |
+
"step": 465
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 3.4814814814814814,
|
695 |
+
"grad_norm": 0.09579209238290787,
|
696 |
+
"learning_rate": 0.0016477259966150588,
|
697 |
+
"loss": 0.4268,
|
698 |
+
"step": 470
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 3.5185185185185186,
|
702 |
+
"grad_norm": 0.09915994852781296,
|
703 |
+
"learning_rate": 0.001637822363550706,
|
704 |
+
"loss": 0.4274,
|
705 |
+
"step": 475
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 3.5555555555555554,
|
709 |
+
"grad_norm": 0.09255506843328476,
|
710 |
+
"learning_rate": 0.0016278121246720988,
|
711 |
+
"loss": 0.4237,
|
712 |
+
"step": 480
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 3.5925925925925926,
|
716 |
+
"grad_norm": 0.09609281271696091,
|
717 |
+
"learning_rate": 0.001617696953093457,
|
718 |
+
"loss": 0.4287,
|
719 |
+
"step": 485
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 3.6296296296296298,
|
723 |
+
"grad_norm": 0.10273302346467972,
|
724 |
+
"learning_rate": 0.0016074785394674836,
|
725 |
+
"loss": 0.4301,
|
726 |
+
"step": 490
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 3.6666666666666665,
|
730 |
+
"grad_norm": 0.09646812826395035,
|
731 |
+
"learning_rate": 0.0015971585917027862,
|
732 |
+
"loss": 0.4282,
|
733 |
+
"step": 495
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 3.7037037037037037,
|
737 |
+
"grad_norm": 0.09089499711990356,
|
738 |
+
"learning_rate": 0.001586738834678418,
|
739 |
+
"loss": 0.425,
|
740 |
+
"step": 500
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 3.7407407407407405,
|
744 |
+
"grad_norm": 0.08903223276138306,
|
745 |
+
"learning_rate": 0.0015762210099555802,
|
746 |
+
"loss": 0.4222,
|
747 |
+
"step": 505
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 3.7777777777777777,
|
751 |
+
"grad_norm": 0.09616349637508392,
|
752 |
+
"learning_rate": 0.0015656068754865387,
|
753 |
+
"loss": 0.4243,
|
754 |
+
"step": 510
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 3.814814814814815,
|
758 |
+
"grad_norm": 0.0883878841996193,
|
759 |
+
"learning_rate": 0.001554898205320797,
|
760 |
+
"loss": 0.4278,
|
761 |
+
"step": 515
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 3.851851851851852,
|
765 |
+
"grad_norm": 0.0974721610546112,
|
766 |
+
"learning_rate": 0.0015440967893085827,
|
767 |
+
"loss": 0.4239,
|
768 |
+
"step": 520
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 3.888888888888889,
|
772 |
+
"grad_norm": 0.09724871814250946,
|
773 |
+
"learning_rate": 0.0015332044328016914,
|
774 |
+
"loss": 0.4269,
|
775 |
+
"step": 525
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 3.925925925925926,
|
779 |
+
"grad_norm": 0.09783729910850525,
|
780 |
+
"learning_rate": 0.0015222229563517384,
|
781 |
+
"loss": 0.4289,
|
782 |
+
"step": 530
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 3.962962962962963,
|
786 |
+
"grad_norm": 0.09811478108167648,
|
787 |
+
"learning_rate": 0.0015111541954058731,
|
788 |
+
"loss": 0.4265,
|
789 |
+
"step": 535
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 4.0,
|
793 |
+
"grad_norm": 0.09431273490190506,
|
794 |
+
"learning_rate": 0.0015,
|
795 |
+
"loss": 0.4244,
|
796 |
+
"step": 540
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 4.0,
|
800 |
+
"eval_loss": 1.266510009765625,
|
801 |
+
"eval_runtime": 1.4433,
|
802 |
+
"eval_samples_per_second": 2.771,
|
803 |
+
"eval_steps_per_second": 0.693,
|
804 |
+
"step": 540
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 4.037037037037037,
|
808 |
+
"grad_norm": 0.09484298527240753,
|
809 |
+
"learning_rate": 0.0014887622344495642,
|
810 |
+
"loss": 0.3886,
|
811 |
+
"step": 545
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 4.074074074074074,
|
815 |
+
"grad_norm": 0.09763394296169281,
|
816 |
+
"learning_rate": 0.001477442777037949,
|
817 |
+
"loss": 0.3867,
|
818 |
+
"step": 550
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 4.111111111111111,
|
822 |
+
"grad_norm": 0.09587694704532623,
|
823 |
+
"learning_rate": 0.001466043519702539,
|
824 |
+
"loss": 0.3934,
|
825 |
+
"step": 555
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 4.148148148148148,
|
829 |
+
"grad_norm": 0.09805364161729813,
|
830 |
+
"learning_rate": 0.0014545663677185006,
|
831 |
+
"loss": 0.3913,
|
832 |
+
"step": 560
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 4.185185185185185,
|
836 |
+
"grad_norm": 0.09342525154352188,
|
837 |
+
"learning_rate": 0.0014430132393803352,
|
838 |
+
"loss": 0.3962,
|
839 |
+
"step": 565
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 4.222222222222222,
|
843 |
+
"grad_norm": 0.09320686757564545,
|
844 |
+
"learning_rate": 0.0014313860656812536,
|
845 |
+
"loss": 0.393,
|
846 |
+
"step": 570
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 4.2592592592592595,
|
850 |
+
"grad_norm": 0.09312278032302856,
|
851 |
+
"learning_rate": 0.001419686789990429,
|
852 |
+
"loss": 0.3956,
|
853 |
+
"step": 575
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 4.296296296296296,
|
857 |
+
"grad_norm": 0.09693987667560577,
|
858 |
+
"learning_rate": 0.0014079173677281835,
|
859 |
+
"loss": 0.4003,
|
860 |
+
"step": 580
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 4.333333333333333,
|
864 |
+
"grad_norm": 0.09647519141435623,
|
865 |
+
"learning_rate": 0.001396079766039157,
|
866 |
+
"loss": 0.4026,
|
867 |
+
"step": 585
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 4.37037037037037,
|
871 |
+
"grad_norm": 0.09753508865833282,
|
872 |
+
"learning_rate": 0.0013841759634635176,
|
873 |
+
"loss": 0.4047,
|
874 |
+
"step": 590
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 4.407407407407407,
|
878 |
+
"grad_norm": 0.09481139481067657,
|
879 |
+
"learning_rate": 0.00137220794960627,
|
880 |
+
"loss": 0.4028,
|
881 |
+
"step": 595
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 4.444444444444445,
|
885 |
+
"grad_norm": 0.0947929173707962,
|
886 |
+
"learning_rate": 0.0013601777248047106,
|
887 |
+
"loss": 0.4018,
|
888 |
+
"step": 600
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 4.481481481481482,
|
892 |
+
"grad_norm": 0.10154122114181519,
|
893 |
+
"learning_rate": 0.0013480872997940906,
|
894 |
+
"loss": 0.4019,
|
895 |
+
"step": 605
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 4.518518518518518,
|
899 |
+
"grad_norm": 0.09206040948629379,
|
900 |
+
"learning_rate": 0.0013359386953715423,
|
901 |
+
"loss": 0.401,
|
902 |
+
"step": 610
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 4.555555555555555,
|
906 |
+
"grad_norm": 0.0979878157377243,
|
907 |
+
"learning_rate": 0.0013237339420583212,
|
908 |
+
"loss": 0.4046,
|
909 |
+
"step": 615
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 4.592592592592593,
|
913 |
+
"grad_norm": 0.09499992430210114,
|
914 |
+
"learning_rate": 0.0013114750797604247,
|
915 |
+
"loss": 0.4092,
|
916 |
+
"step": 620
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 4.62962962962963,
|
920 |
+
"grad_norm": 0.096099354326725,
|
921 |
+
"learning_rate": 0.0012991641574276419,
|
922 |
+
"loss": 0.4066,
|
923 |
+
"step": 625
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 4.666666666666667,
|
927 |
+
"grad_norm": 0.09620559960603714,
|
928 |
+
"learning_rate": 0.0012868032327110904,
|
929 |
+
"loss": 0.4075,
|
930 |
+
"step": 630
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 4.703703703703704,
|
934 |
+
"grad_norm": 0.09676729887723923,
|
935 |
+
"learning_rate": 0.0012743943716193016,
|
936 |
+
"loss": 0.4026,
|
937 |
+
"step": 635
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 4.7407407407407405,
|
941 |
+
"grad_norm": 0.09284202009439468,
|
942 |
+
"learning_rate": 0.0012619396481729059,
|
943 |
+
"loss": 0.4055,
|
944 |
+
"step": 640
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 4.777777777777778,
|
948 |
+
"grad_norm": 0.09661979228258133,
|
949 |
+
"learning_rate": 0.0012494411440579815,
|
950 |
+
"loss": 0.4068,
|
951 |
+
"step": 645
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 4.814814814814815,
|
955 |
+
"grad_norm": 0.09566741436719894,
|
956 |
+
"learning_rate": 0.001236900948278119,
|
957 |
+
"loss": 0.4021,
|
958 |
+
"step": 650
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 4.851851851851852,
|
962 |
+
"grad_norm": 0.09348838031291962,
|
963 |
+
"learning_rate": 0.0012243211568052678,
|
964 |
+
"loss": 0.4024,
|
965 |
+
"step": 655
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 4.888888888888889,
|
969 |
+
"grad_norm": 0.09663164615631104,
|
970 |
+
"learning_rate": 0.0012117038722294108,
|
971 |
+
"loss": 0.4062,
|
972 |
+
"step": 660
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 4.925925925925926,
|
976 |
+
"grad_norm": 0.09402230381965637,
|
977 |
+
"learning_rate": 0.0011990512034071405,
|
978 |
+
"loss": 0.4028,
|
979 |
+
"step": 665
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 4.962962962962963,
|
983 |
+
"grad_norm": 0.10056190937757492,
|
984 |
+
"learning_rate": 0.0011863652651091822,
|
985 |
+
"loss": 0.4074,
|
986 |
+
"step": 670
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 5.0,
|
990 |
+
"grad_norm": 0.09207284450531006,
|
991 |
+
"learning_rate": 0.0011736481776669307,
|
992 |
+
"loss": 0.4051,
|
993 |
+
"step": 675
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 5.0,
|
997 |
+
"eval_loss": 1.271437644958496,
|
998 |
+
"eval_runtime": 1.4527,
|
999 |
+
"eval_samples_per_second": 2.753,
|
1000 |
+
"eval_steps_per_second": 0.688,
|
1001 |
+
"step": 675
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 5.037037037037037,
|
1005 |
+
"grad_norm": 0.10166580975055695,
|
1006 |
+
"learning_rate": 0.0011609020666180573,
|
1007 |
+
"loss": 0.369,
|
1008 |
+
"step": 680
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 5.074074074074074,
|
1012 |
+
"grad_norm": 0.10062967240810394,
|
1013 |
+
"learning_rate": 0.001148129062351249,
|
1014 |
+
"loss": 0.3679,
|
1015 |
+
"step": 685
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 5.111111111111111,
|
1019 |
+
"grad_norm": 0.09751473367214203,
|
1020 |
+
"learning_rate": 0.0011353312997501312,
|
1021 |
+
"loss": 0.3679,
|
1022 |
+
"step": 690
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 5.148148148148148,
|
1026 |
+
"grad_norm": 0.0990433469414711,
|
1027 |
+
"learning_rate": 0.0011225109178364455,
|
1028 |
+
"loss": 0.3685,
|
1029 |
+
"step": 695
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 5.185185185185185,
|
1033 |
+
"grad_norm": 0.099190853536129,
|
1034 |
+
"learning_rate": 0.0011096700594125316,
|
1035 |
+
"loss": 0.3736,
|
1036 |
+
"step": 700
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 5.222222222222222,
|
1040 |
+
"grad_norm": 0.1061362773180008,
|
1041 |
+
"learning_rate": 0.0010968108707031792,
|
1042 |
+
"loss": 0.3751,
|
1043 |
+
"step": 705
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 5.2592592592592595,
|
1047 |
+
"grad_norm": 0.11798923462629318,
|
1048 |
+
"learning_rate": 0.0010839355009969068,
|
1049 |
+
"loss": 0.3757,
|
1050 |
+
"step": 710
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 5.296296296296296,
|
1054 |
+
"grad_norm": 0.09905427694320679,
|
1055 |
+
"learning_rate": 0.00107104610228673,
|
1056 |
+
"loss": 0.375,
|
1057 |
+
"step": 715
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 5.333333333333333,
|
1061 |
+
"grad_norm": 0.1025015115737915,
|
1062 |
+
"learning_rate": 0.0010581448289104759,
|
1063 |
+
"loss": 0.3763,
|
1064 |
+
"step": 720
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 5.37037037037037,
|
1068 |
+
"grad_norm": 0.1149529442191124,
|
1069 |
+
"learning_rate": 0.0010452338371907063,
|
1070 |
+
"loss": 0.3882,
|
1071 |
+
"step": 725
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 5.407407407407407,
|
1075 |
+
"grad_norm": 0.12777069211006165,
|
1076 |
+
"learning_rate": 0.0010323152850743107,
|
1077 |
+
"loss": 0.3812,
|
1078 |
+
"step": 730
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 5.444444444444445,
|
1082 |
+
"grad_norm": 0.10847526788711548,
|
1083 |
+
"learning_rate": 0.0010193913317718243,
|
1084 |
+
"loss": 0.3832,
|
1085 |
+
"step": 735
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 5.481481481481482,
|
1089 |
+
"grad_norm": 0.11118727922439575,
|
1090 |
+
"learning_rate": 0.0010064641373965393,
|
1091 |
+
"loss": 0.384,
|
1092 |
+
"step": 740
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 5.518518518518518,
|
1096 |
+
"grad_norm": 0.12322206795215607,
|
1097 |
+
"learning_rate": 0.0009935358626034607,
|
1098 |
+
"loss": 0.3826,
|
1099 |
+
"step": 745
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 5.555555555555555,
|
1103 |
+
"grad_norm": 0.1018897145986557,
|
1104 |
+
"learning_rate": 0.0009806086682281757,
|
1105 |
+
"loss": 0.3828,
|
1106 |
+
"step": 750
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 5.592592592592593,
|
1110 |
+
"grad_norm": 0.10415022075176239,
|
1111 |
+
"learning_rate": 0.0009676847149256894,
|
1112 |
+
"loss": 0.3834,
|
1113 |
+
"step": 755
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 5.62962962962963,
|
1117 |
+
"grad_norm": 0.10056640207767487,
|
1118 |
+
"learning_rate": 0.0009547661628092937,
|
1119 |
+
"loss": 0.379,
|
1120 |
+
"step": 760
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 5.666666666666667,
|
1124 |
+
"grad_norm": 0.13305579125881195,
|
1125 |
+
"learning_rate": 0.0009418551710895242,
|
1126 |
+
"loss": 0.3836,
|
1127 |
+
"step": 765
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 5.703703703703704,
|
1131 |
+
"grad_norm": 0.1132049411535263,
|
1132 |
+
"learning_rate": 0.0009289538977132702,
|
1133 |
+
"loss": 0.3815,
|
1134 |
+
"step": 770
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 5.7407407407407405,
|
1138 |
+
"grad_norm": 0.12073713541030884,
|
1139 |
+
"learning_rate": 0.000916064499003093,
|
1140 |
+
"loss": 0.384,
|
1141 |
+
"step": 775
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 5.777777777777778,
|
1145 |
+
"grad_norm": 0.0997130498290062,
|
1146 |
+
"learning_rate": 0.000903189129296821,
|
1147 |
+
"loss": 0.3836,
|
1148 |
+
"step": 780
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 5.814814814814815,
|
1152 |
+
"grad_norm": 0.1098228394985199,
|
1153 |
+
"learning_rate": 0.0008903299405874684,
|
1154 |
+
"loss": 0.3901,
|
1155 |
+
"step": 785
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 5.851851851851852,
|
1159 |
+
"grad_norm": 0.10409754514694214,
|
1160 |
+
"learning_rate": 0.0008774890821635547,
|
1161 |
+
"loss": 0.3806,
|
1162 |
+
"step": 790
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 5.888888888888889,
|
1166 |
+
"grad_norm": 0.09349874407052994,
|
1167 |
+
"learning_rate": 0.0008646687002498692,
|
1168 |
+
"loss": 0.3821,
|
1169 |
+
"step": 795
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 5.925925925925926,
|
1173 |
+
"grad_norm": 0.0936858206987381,
|
1174 |
+
"learning_rate": 0.0008518709376487514,
|
1175 |
+
"loss": 0.3842,
|
1176 |
+
"step": 800
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 5.962962962962963,
|
1180 |
+
"grad_norm": 0.09671808034181595,
|
1181 |
+
"learning_rate": 0.0008390979333819426,
|
1182 |
+
"loss": 0.3813,
|
1183 |
+
"step": 805
|
1184 |
+
},
|
1185 |
+
{
|
1186 |
+
"epoch": 6.0,
|
1187 |
+
"grad_norm": 0.10419617593288422,
|
1188 |
+
"learning_rate": 0.0008263518223330697,
|
1189 |
+
"loss": 0.3815,
|
1190 |
+
"step": 810
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 6.0,
|
1194 |
+
"eval_loss": 1.2959271669387817,
|
1195 |
+
"eval_runtime": 1.4543,
|
1196 |
+
"eval_samples_per_second": 2.75,
|
1197 |
+
"eval_steps_per_second": 0.688,
|
1198 |
+
"step": 810
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 6.037037037037037,
|
1202 |
+
"grad_norm": 0.10344818234443665,
|
1203 |
+
"learning_rate": 0.0008136347348908179,
|
1204 |
+
"loss": 0.3456,
|
1205 |
+
"step": 815
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 6.074074074074074,
|
1209 |
+
"grad_norm": 0.11311297118663788,
|
1210 |
+
"learning_rate": 0.0008009487965928596,
|
1211 |
+
"loss": 0.3457,
|
1212 |
+
"step": 820
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 6.111111111111111,
|
1216 |
+
"grad_norm": 0.1126752719283104,
|
1217 |
+
"learning_rate": 0.0007882961277705895,
|
1218 |
+
"loss": 0.3446,
|
1219 |
+
"step": 825
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"epoch": 6.148148148148148,
|
1223 |
+
"grad_norm": 0.10734600573778152,
|
1224 |
+
"learning_rate": 0.0007756788431947326,
|
1225 |
+
"loss": 0.3441,
|
1226 |
+
"step": 830
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 6.185185185185185,
|
1230 |
+
"grad_norm": 0.10664735734462738,
|
1231 |
+
"learning_rate": 0.0007630990517218807,
|
1232 |
+
"loss": 0.3464,
|
1233 |
+
"step": 835
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 6.222222222222222,
|
1237 |
+
"grad_norm": 0.10784178227186203,
|
1238 |
+
"learning_rate": 0.0007505588559420188,
|
1239 |
+
"loss": 0.3484,
|
1240 |
+
"step": 840
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 6.2592592592592595,
|
1244 |
+
"grad_norm": 0.09735342860221863,
|
1245 |
+
"learning_rate": 0.0007380603518270941,
|
1246 |
+
"loss": 0.3473,
|
1247 |
+
"step": 845
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 6.296296296296296,
|
1251 |
+
"grad_norm": 0.10385815799236298,
|
1252 |
+
"learning_rate": 0.0007256056283806986,
|
1253 |
+
"loss": 0.3493,
|
1254 |
+
"step": 850
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 6.333333333333333,
|
1258 |
+
"grad_norm": 0.10252544283866882,
|
1259 |
+
"learning_rate": 0.0007131967672889101,
|
1260 |
+
"loss": 0.3531,
|
1261 |
+
"step": 855
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 6.37037037037037,
|
1265 |
+
"grad_norm": 0.10720902681350708,
|
1266 |
+
"learning_rate": 0.0007008358425723586,
|
1267 |
+
"loss": 0.3543,
|
1268 |
+
"step": 860
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 6.407407407407407,
|
1272 |
+
"grad_norm": 0.1041482537984848,
|
1273 |
+
"learning_rate": 0.0006885249202395753,
|
1274 |
+
"loss": 0.3508,
|
1275 |
+
"step": 865
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 6.444444444444445,
|
1279 |
+
"grad_norm": 0.10373668372631073,
|
1280 |
+
"learning_rate": 0.000676266057941679,
|
1281 |
+
"loss": 0.3534,
|
1282 |
+
"step": 870
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 6.481481481481482,
|
1286 |
+
"grad_norm": 0.10245037823915482,
|
1287 |
+
"learning_rate": 0.0006640613046284581,
|
1288 |
+
"loss": 0.3521,
|
1289 |
+
"step": 875
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 6.518518518518518,
|
1293 |
+
"grad_norm": 0.10254081338644028,
|
1294 |
+
"learning_rate": 0.0006519127002059096,
|
1295 |
+
"loss": 0.3538,
|
1296 |
+
"step": 880
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 6.555555555555555,
|
1300 |
+
"grad_norm": 0.10260630398988724,
|
1301 |
+
"learning_rate": 0.0006398222751952898,
|
1302 |
+
"loss": 0.3537,
|
1303 |
+
"step": 885
|
1304 |
+
},
|
1305 |
+
{
|
1306 |
+
"epoch": 6.592592592592593,
|
1307 |
+
"grad_norm": 0.10130611807107925,
|
1308 |
+
"learning_rate": 0.0006277920503937303,
|
1309 |
+
"loss": 0.3515,
|
1310 |
+
"step": 890
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 6.62962962962963,
|
1314 |
+
"grad_norm": 0.10895968973636627,
|
1315 |
+
"learning_rate": 0.0006158240365364823,
|
1316 |
+
"loss": 0.3578,
|
1317 |
+
"step": 895
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 6.666666666666667,
|
1321 |
+
"grad_norm": 0.09870075434446335,
|
1322 |
+
"learning_rate": 0.0006039202339608432,
|
1323 |
+
"loss": 0.3512,
|
1324 |
+
"step": 900
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 6.703703703703704,
|
1328 |
+
"grad_norm": 0.10364022850990295,
|
1329 |
+
"learning_rate": 0.0005920826322718165,
|
1330 |
+
"loss": 0.3537,
|
1331 |
+
"step": 905
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 6.7407407407407405,
|
1335 |
+
"grad_norm": 0.10551033914089203,
|
1336 |
+
"learning_rate": 0.000580313210009571,
|
1337 |
+
"loss": 0.3566,
|
1338 |
+
"step": 910
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 6.777777777777778,
|
1342 |
+
"grad_norm": 0.10657215118408203,
|
1343 |
+
"learning_rate": 0.0005686139343187468,
|
1344 |
+
"loss": 0.3552,
|
1345 |
+
"step": 915
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 6.814814814814815,
|
1349 |
+
"grad_norm": 0.10223071277141571,
|
1350 |
+
"learning_rate": 0.0005569867606196651,
|
1351 |
+
"loss": 0.3584,
|
1352 |
+
"step": 920
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 6.851851851851852,
|
1356 |
+
"grad_norm": 0.10146836936473846,
|
1357 |
+
"learning_rate": 0.0005454336322814994,
|
1358 |
+
"loss": 0.3535,
|
1359 |
+
"step": 925
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 6.888888888888889,
|
1363 |
+
"grad_norm": 0.1027546152472496,
|
1364 |
+
"learning_rate": 0.0005339564802974615,
|
1365 |
+
"loss": 0.3501,
|
1366 |
+
"step": 930
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"epoch": 6.925925925925926,
|
1370 |
+
"grad_norm": 0.10245343297719955,
|
1371 |
+
"learning_rate": 0.0005225572229620509,
|
1372 |
+
"loss": 0.3512,
|
1373 |
+
"step": 935
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 6.962962962962963,
|
1377 |
+
"grad_norm": 0.10256995260715485,
|
1378 |
+
"learning_rate": 0.0005112377655504359,
|
1379 |
+
"loss": 0.3543,
|
1380 |
+
"step": 940
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 7.0,
|
1384 |
+
"grad_norm": 0.10365499556064606,
|
1385 |
+
"learning_rate": 0.0005000000000000002,
|
1386 |
+
"loss": 0.3546,
|
1387 |
+
"step": 945
|
1388 |
+
},
|
1389 |
+
{
|
1390 |
+
"epoch": 7.0,
|
1391 |
+
"eval_loss": 1.3559757471084595,
|
1392 |
+
"eval_runtime": 1.4533,
|
1393 |
+
"eval_samples_per_second": 2.752,
|
1394 |
+
"eval_steps_per_second": 0.688,
|
1395 |
+
"step": 945
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 7.037037037037037,
|
1399 |
+
"grad_norm": 0.11704354733228683,
|
1400 |
+
"learning_rate": 0.0004888458045941269,
|
1401 |
+
"loss": 0.32,
|
1402 |
+
"step": 950
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 7.074074074074074,
|
1406 |
+
"grad_norm": 0.11646736413240433,
|
1407 |
+
"learning_rate": 0.0004777770436482617,
|
1408 |
+
"loss": 0.3177,
|
1409 |
+
"step": 955
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 7.111111111111111,
|
1413 |
+
"grad_norm": 0.11117232590913773,
|
1414 |
+
"learning_rate": 0.000466795567198309,
|
1415 |
+
"loss": 0.3144,
|
1416 |
+
"step": 960
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 7.148148148148148,
|
1420 |
+
"grad_norm": 0.10937786102294922,
|
1421 |
+
"learning_rate": 0.0004559032106914173,
|
1422 |
+
"loss": 0.3212,
|
1423 |
+
"step": 965
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 7.185185185185185,
|
1427 |
+
"grad_norm": 0.11477228999137878,
|
1428 |
+
"learning_rate": 0.0004451017946792032,
|
1429 |
+
"loss": 0.3219,
|
1430 |
+
"step": 970
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 7.222222222222222,
|
1434 |
+
"grad_norm": 0.10524013638496399,
|
1435 |
+
"learning_rate": 0.0004343931245134616,
|
1436 |
+
"loss": 0.3167,
|
1437 |
+
"step": 975
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 7.2592592592592595,
|
1441 |
+
"grad_norm": 0.10898813605308533,
|
1442 |
+
"learning_rate": 0.0004237789900444197,
|
1443 |
+
"loss": 0.3204,
|
1444 |
+
"step": 980
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 7.296296296296296,
|
1448 |
+
"grad_norm": 0.11245737224817276,
|
1449 |
+
"learning_rate": 0.0004132611653215822,
|
1450 |
+
"loss": 0.3216,
|
1451 |
+
"step": 985
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 7.333333333333333,
|
1455 |
+
"grad_norm": 0.1109575405716896,
|
1456 |
+
"learning_rate": 0.00040284140829721405,
|
1457 |
+
"loss": 0.3211,
|
1458 |
+
"step": 990
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 7.37037037037037,
|
1462 |
+
"grad_norm": 0.10827223211526871,
|
1463 |
+
"learning_rate": 0.00039252146053251637,
|
1464 |
+
"loss": 0.3224,
|
1465 |
+
"step": 995
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 7.407407407407407,
|
1469 |
+
"grad_norm": 0.11438044160604477,
|
1470 |
+
"learning_rate": 0.00038230304690654306,
|
1471 |
+
"loss": 0.3243,
|
1472 |
+
"step": 1000
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 7.444444444444445,
|
1476 |
+
"grad_norm": 0.1066223755478859,
|
1477 |
+
"learning_rate": 0.00037218787532790164,
|
1478 |
+
"loss": 0.3253,
|
1479 |
+
"step": 1005
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 7.481481481481482,
|
1483 |
+
"grad_norm": 0.11840826272964478,
|
1484 |
+
"learning_rate": 0.0003621776364492939,
|
1485 |
+
"loss": 0.327,
|
1486 |
+
"step": 1010
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 7.518518518518518,
|
1490 |
+
"grad_norm": 0.1115390807390213,
|
1491 |
+
"learning_rate": 0.0003522740033849411,
|
1492 |
+
"loss": 0.3261,
|
1493 |
+
"step": 1015
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 7.555555555555555,
|
1497 |
+
"grad_norm": 0.1104753240942955,
|
1498 |
+
"learning_rate": 0.0003424786314309365,
|
1499 |
+
"loss": 0.3225,
|
1500 |
+
"step": 1020
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 7.592592592592593,
|
1504 |
+
"grad_norm": 0.10727293789386749,
|
1505 |
+
"learning_rate": 0.00033279315778858033,
|
1506 |
+
"loss": 0.3237,
|
1507 |
+
"step": 1025
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 7.62962962962963,
|
1511 |
+
"grad_norm": 0.11141736060380936,
|
1512 |
+
"learning_rate": 0.0003232192012907381,
|
1513 |
+
"loss": 0.3237,
|
1514 |
+
"step": 1030
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 7.666666666666667,
|
1518 |
+
"grad_norm": 0.10661887377500534,
|
1519 |
+
"learning_rate": 0.0003137583621312665,
|
1520 |
+
"loss": 0.3257,
|
1521 |
+
"step": 1035
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 7.703703703703704,
|
1525 |
+
"grad_norm": 0.11351703852415085,
|
1526 |
+
"learning_rate": 0.000304412221597558,
|
1527 |
+
"loss": 0.3236,
|
1528 |
+
"step": 1040
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 7.7407407407407405,
|
1532 |
+
"grad_norm": 0.10875287652015686,
|
1533 |
+
"learning_rate": 0.0002951823418062439,
|
1534 |
+
"loss": 0.3268,
|
1535 |
+
"step": 1045
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 7.777777777777778,
|
1539 |
+
"grad_norm": 0.1116643026471138,
|
1540 |
+
"learning_rate": 0.0002860702654421011,
|
1541 |
+
"loss": 0.3239,
|
1542 |
+
"step": 1050
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 7.814814814814815,
|
1546 |
+
"grad_norm": 0.10941953957080841,
|
1547 |
+
"learning_rate": 0.0002770775155002071,
|
1548 |
+
"loss": 0.3257,
|
1549 |
+
"step": 1055
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 7.851851851851852,
|
1553 |
+
"grad_norm": 0.10806366801261902,
|
1554 |
+
"learning_rate": 0.00026820559503138797,
|
1555 |
+
"loss": 0.3235,
|
1556 |
+
"step": 1060
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 7.888888888888889,
|
1560 |
+
"grad_norm": 0.1069023609161377,
|
1561 |
+
"learning_rate": 0.0002594559868909956,
|
1562 |
+
"loss": 0.3293,
|
1563 |
+
"step": 1065
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 7.925925925925926,
|
1567 |
+
"grad_norm": 0.10821282863616943,
|
1568 |
+
"learning_rate": 0.000250830153491064,
|
1569 |
+
"loss": 0.3267,
|
1570 |
+
"step": 1070
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 7.962962962962963,
|
1574 |
+
"grad_norm": 0.1114460751414299,
|
1575 |
+
"learning_rate": 0.00024232953655588209,
|
1576 |
+
"loss": 0.3225,
|
1577 |
+
"step": 1075
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 8.0,
|
1581 |
+
"grad_norm": 0.1069159284234047,
|
1582 |
+
"learning_rate": 0.0002339555568810221,
|
1583 |
+
"loss": 0.3233,
|
1584 |
+
"step": 1080
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 8.0,
|
1588 |
+
"eval_loss": 1.4125341176986694,
|
1589 |
+
"eval_runtime": 1.4532,
|
1590 |
+
"eval_samples_per_second": 2.753,
|
1591 |
+
"eval_steps_per_second": 0.688,
|
1592 |
+
"step": 1080
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 8.037037037037036,
|
1596 |
+
"grad_norm": 0.13299891352653503,
|
1597 |
+
"learning_rate": 0.00022570961409586754,
|
1598 |
+
"loss": 0.2956,
|
1599 |
+
"step": 1085
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 8.074074074074074,
|
1603 |
+
"grad_norm": 0.11145825684070587,
|
1604 |
+
"learning_rate": 0.00021759308642968023,
|
1605 |
+
"loss": 0.2952,
|
1606 |
+
"step": 1090
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 8.11111111111111,
|
1610 |
+
"grad_norm": 0.11993227154016495,
|
1611 |
+
"learning_rate": 0.00020960733048124082,
|
1612 |
+
"loss": 0.2951,
|
1613 |
+
"step": 1095
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 8.148148148148149,
|
1617 |
+
"grad_norm": 0.11672375351190567,
|
1618 |
+
"learning_rate": 0.00020175368099210702,
|
1619 |
+
"loss": 0.2961,
|
1620 |
+
"step": 1100
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 8.185185185185185,
|
1624 |
+
"grad_norm": 0.11903874576091766,
|
1625 |
+
"learning_rate": 0.00019403345062352572,
|
1626 |
+
"loss": 0.2981,
|
1627 |
+
"step": 1105
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 8.222222222222221,
|
1631 |
+
"grad_norm": 0.11281085014343262,
|
1632 |
+
"learning_rate": 0.00018644792973703252,
|
1633 |
+
"loss": 0.2983,
|
1634 |
+
"step": 1110
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 8.25925925925926,
|
1638 |
+
"grad_norm": 0.11996857821941376,
|
1639 |
+
"learning_rate": 0.00017899838617878162,
|
1640 |
+
"loss": 0.2993,
|
1641 |
+
"step": 1115
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 8.296296296296296,
|
1645 |
+
"grad_norm": 0.11176000535488129,
|
1646 |
+
"learning_rate": 0.00017168606506763696,
|
1647 |
+
"loss": 0.2972,
|
1648 |
+
"step": 1120
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 8.333333333333334,
|
1652 |
+
"grad_norm": 0.11802016943693161,
|
1653 |
+
"learning_rate": 0.00016451218858706373,
|
1654 |
+
"loss": 0.2977,
|
1655 |
+
"step": 1125
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 8.37037037037037,
|
1659 |
+
"grad_norm": 0.11810103803873062,
|
1660 |
+
"learning_rate": 0.00015747795578085046,
|
1661 |
+
"loss": 0.3002,
|
1662 |
+
"step": 1130
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 8.407407407407407,
|
1666 |
+
"grad_norm": 0.12034923583269119,
|
1667 |
+
"learning_rate": 0.0001505845423527027,
|
1668 |
+
"loss": 0.2961,
|
1669 |
+
"step": 1135
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 8.444444444444445,
|
1673 |
+
"grad_norm": 0.11696241796016693,
|
1674 |
+
"learning_rate": 0.00014383310046973364,
|
1675 |
+
"loss": 0.2977,
|
1676 |
+
"step": 1140
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 8.481481481481481,
|
1680 |
+
"grad_norm": 0.11664384603500366,
|
1681 |
+
"learning_rate": 0.00013722475856989158,
|
1682 |
+
"loss": 0.2952,
|
1683 |
+
"step": 1145
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 8.518518518518519,
|
1687 |
+
"grad_norm": 0.117145836353302,
|
1688 |
+
"learning_rate": 0.00013076062117335218,
|
1689 |
+
"loss": 0.3016,
|
1690 |
+
"step": 1150
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 8.555555555555555,
|
1694 |
+
"grad_norm": 0.11361709982156754,
|
1695 |
+
"learning_rate": 0.00012444176869790924,
|
1696 |
+
"loss": 0.2988,
|
1697 |
+
"step": 1155
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 8.592592592592592,
|
1701 |
+
"grad_norm": 0.1155712679028511,
|
1702 |
+
"learning_rate": 0.00011826925727839199,
|
1703 |
+
"loss": 0.2977,
|
1704 |
+
"step": 1160
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 8.62962962962963,
|
1708 |
+
"grad_norm": 0.1212184950709343,
|
1709 |
+
"learning_rate": 0.00011224411859014417,
|
1710 |
+
"loss": 0.298,
|
1711 |
+
"step": 1165
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 8.666666666666666,
|
1715 |
+
"grad_norm": 0.11797547340393066,
|
1716 |
+
"learning_rate": 0.00010636735967658784,
|
1717 |
+
"loss": 0.3007,
|
1718 |
+
"step": 1170
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 8.703703703703704,
|
1722 |
+
"grad_norm": 0.11559978872537613,
|
1723 |
+
"learning_rate": 0.00010063996278090704,
|
1724 |
+
"loss": 0.2958,
|
1725 |
+
"step": 1175
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 8.74074074074074,
|
1729 |
+
"grad_norm": 0.11640750616788864,
|
1730 |
+
"learning_rate": 9.506288518187466e-05,
|
1731 |
+
"loss": 0.2966,
|
1732 |
+
"step": 1180
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 8.777777777777779,
|
1736 |
+
"grad_norm": 0.11927841603755951,
|
1737 |
+
"learning_rate": 8.963705903385344e-05,
|
1738 |
+
"loss": 0.2953,
|
1739 |
+
"step": 1185
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 8.814814814814815,
|
1743 |
+
"grad_norm": 0.11425163596868515,
|
1744 |
+
"learning_rate": 8.436339121099412e-05,
|
1745 |
+
"loss": 0.2989,
|
1746 |
+
"step": 1190
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 8.851851851851851,
|
1750 |
+
"grad_norm": 0.11373434215784073,
|
1751 |
+
"learning_rate": 7.92427631556617e-05,
|
1752 |
+
"loss": 0.2984,
|
1753 |
+
"step": 1195
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 8.88888888888889,
|
1757 |
+
"grad_norm": 0.11790241301059723,
|
1758 |
+
"learning_rate": 7.427603073110967e-05,
|
1759 |
+
"loss": 0.2972,
|
1760 |
+
"step": 1200
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 8.925925925925926,
|
1764 |
+
"grad_norm": 0.11773653328418732,
|
1765 |
+
"learning_rate": 6.946402407843155e-05,
|
1766 |
+
"loss": 0.3012,
|
1767 |
+
"step": 1205
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 8.962962962962964,
|
1771 |
+
"grad_norm": 0.12333875894546509,
|
1772 |
+
"learning_rate": 6.480754747781037e-05,
|
1773 |
+
"loss": 0.2959,
|
1774 |
+
"step": 1210
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 9.0,
|
1778 |
+
"grad_norm": 0.11808749288320541,
|
1779 |
+
"learning_rate": 6.0307379214091684e-05,
|
1780 |
+
"loss": 0.2969,
|
1781 |
+
"step": 1215
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 9.0,
|
1785 |
+
"eval_loss": 1.4809459447860718,
|
1786 |
+
"eval_runtime": 1.4606,
|
1787 |
+
"eval_samples_per_second": 2.739,
|
1788 |
+
"eval_steps_per_second": 0.685,
|
1789 |
+
"step": 1215
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 9.037037037037036,
|
1793 |
+
"grad_norm": 0.1122315376996994,
|
1794 |
+
"learning_rate": 5.596427144670002e-05,
|
1795 |
+
"loss": 0.2797,
|
1796 |
+
"step": 1220
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 9.074074074074074,
|
1800 |
+
"grad_norm": 0.12401442974805832,
|
1801 |
+
"learning_rate": 5.1778950083923526e-05,
|
1802 |
+
"loss": 0.2823,
|
1803 |
+
"step": 1225
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 9.11111111111111,
|
1807 |
+
"grad_norm": 0.11285774409770966,
|
1808 |
+
"learning_rate": 4.775211466158469e-05,
|
1809 |
+
"loss": 0.2825,
|
1810 |
+
"step": 1230
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 9.148148148148149,
|
1814 |
+
"grad_norm": 0.11427191644906998,
|
1815 |
+
"learning_rate": 4.3884438226120426e-05,
|
1816 |
+
"loss": 0.2815,
|
1817 |
+
"step": 1235
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 9.185185185185185,
|
1821 |
+
"grad_norm": 0.11915598809719086,
|
1822 |
+
"learning_rate": 4.017656722208807e-05,
|
1823 |
+
"loss": 0.2806,
|
1824 |
+
"step": 1240
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 9.222222222222221,
|
1828 |
+
"grad_norm": 0.11690084636211395,
|
1829 |
+
"learning_rate": 3.6629121384119666e-05,
|
1830 |
+
"loss": 0.2811,
|
1831 |
+
"step": 1245
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 9.25925925925926,
|
1835 |
+
"grad_norm": 0.11301770061254501,
|
1836 |
+
"learning_rate": 3.324269363333799e-05,
|
1837 |
+
"loss": 0.2811,
|
1838 |
+
"step": 1250
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 9.296296296296296,
|
1842 |
+
"grad_norm": 0.1201760470867157,
|
1843 |
+
"learning_rate": 3.0017849978256518e-05,
|
1844 |
+
"loss": 0.2826,
|
1845 |
+
"step": 1255
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 9.333333333333334,
|
1849 |
+
"grad_norm": 0.11819873005151749,
|
1850 |
+
"learning_rate": 2.6955129420176194e-05,
|
1851 |
+
"loss": 0.2787,
|
1852 |
+
"step": 1260
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 9.37037037037037,
|
1856 |
+
"grad_norm": 0.11501555889844894,
|
1857 |
+
"learning_rate": 2.4055043863096426e-05,
|
1858 |
+
"loss": 0.2803,
|
1859 |
+
"step": 1265
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 9.407407407407407,
|
1863 |
+
"grad_norm": 0.11644010990858078,
|
1864 |
+
"learning_rate": 2.1318078028155885e-05,
|
1865 |
+
"loss": 0.2823,
|
1866 |
+
"step": 1270
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 9.444444444444445,
|
1870 |
+
"grad_norm": 0.11667327582836151,
|
1871 |
+
"learning_rate": 1.874468937261531e-05,
|
1872 |
+
"loss": 0.2836,
|
1873 |
+
"step": 1275
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 9.481481481481481,
|
1877 |
+
"grad_norm": 0.11722666025161743,
|
1878 |
+
"learning_rate": 1.6335308013398887e-05,
|
1879 |
+
"loss": 0.2837,
|
1880 |
+
"step": 1280
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 9.518518518518519,
|
1884 |
+
"grad_norm": 0.11853759735822678,
|
1885 |
+
"learning_rate": 1.4090336655203539e-05,
|
1886 |
+
"loss": 0.2816,
|
1887 |
+
"step": 1285
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 9.555555555555555,
|
1891 |
+
"grad_norm": 0.11931838095188141,
|
1892 |
+
"learning_rate": 1.2010150523190988e-05,
|
1893 |
+
"loss": 0.2831,
|
1894 |
+
"step": 1290
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 9.592592592592592,
|
1898 |
+
"grad_norm": 0.11536389589309692,
|
1899 |
+
"learning_rate": 1.0095097300273027e-05,
|
1900 |
+
"loss": 0.2824,
|
1901 |
+
"step": 1295
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 9.62962962962963,
|
1905 |
+
"grad_norm": 0.11747179180383682,
|
1906 |
+
"learning_rate": 8.345497068998897e-06,
|
1907 |
+
"loss": 0.2849,
|
1908 |
+
"step": 1300
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 9.666666666666666,
|
1912 |
+
"grad_norm": 0.12529109418392181,
|
1913 |
+
"learning_rate": 6.761642258056977e-06,
|
1914 |
+
"loss": 0.2841,
|
1915 |
+
"step": 1305
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 9.703703703703704,
|
1919 |
+
"grad_norm": 0.11867683380842209,
|
1920 |
+
"learning_rate": 5.343797593398536e-06,
|
1921 |
+
"loss": 0.2822,
|
1922 |
+
"step": 1310
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 9.74074074074074,
|
1926 |
+
"grad_norm": 0.11928539723157883,
|
1927 |
+
"learning_rate": 4.092200053990691e-06,
|
1928 |
+
"loss": 0.2809,
|
1929 |
+
"step": 1315
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 9.777777777777779,
|
1933 |
+
"grad_norm": 0.11743851751089096,
|
1934 |
+
"learning_rate": 3.007058832207976e-06,
|
1935 |
+
"loss": 0.2819,
|
1936 |
+
"step": 1320
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 9.814814814814815,
|
1940 |
+
"grad_norm": 0.11580769717693329,
|
1941 |
+
"learning_rate": 2.088555298867978e-06,
|
1942 |
+
"loss": 0.2819,
|
1943 |
+
"step": 1325
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 9.851851851851851,
|
1947 |
+
"grad_norm": 0.11537632346153259,
|
1948 |
+
"learning_rate": 1.3368429729168074e-06,
|
1949 |
+
"loss": 0.2814,
|
1950 |
+
"step": 1330
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 9.88888888888889,
|
1954 |
+
"grad_norm": 0.1173846423625946,
|
1955 |
+
"learning_rate": 7.520474957699585e-07,
|
1956 |
+
"loss": 0.2832,
|
1957 |
+
"step": 1335
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 9.925925925925926,
|
1961 |
+
"grad_norm": 0.11481310427188873,
|
1962 |
+
"learning_rate": 3.3426661031255026e-07,
|
1963 |
+
"loss": 0.285,
|
1964 |
+
"step": 1340
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 9.962962962962964,
|
1968 |
+
"grad_norm": 0.11797128617763519,
|
1969 |
+
"learning_rate": 8.357014456272793e-08,
|
1970 |
+
"loss": 0.2824,
|
1971 |
+
"step": 1345
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 10.0,
|
1975 |
+
"grad_norm": 0.11149542033672333,
|
1976 |
+
"learning_rate": 0.0,
|
1977 |
+
"loss": 0.2818,
|
1978 |
+
"step": 1350
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 10.0,
|
1982 |
+
"eval_loss": 1.517443060874939,
|
1983 |
+
"eval_runtime": 1.4076,
|
1984 |
+
"eval_samples_per_second": 2.842,
|
1985 |
+
"eval_steps_per_second": 0.71,
|
1986 |
+
"step": 1350
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 10.0,
|
1990 |
+
"step": 1350,
|
1991 |
+
"total_flos": 7.982333171800736e+18,
|
1992 |
+
"train_loss": 0.3983345487382677,
|
1993 |
+
"train_runtime": 11606.8402,
|
1994 |
+
"train_samples_per_second": 14.865,
|
1995 |
+
"train_steps_per_second": 0.116
|
1996 |
+
}
|
1997 |
+
],
|
1998 |
+
"logging_steps": 5,
|
1999 |
+
"max_steps": 1350,
|
2000 |
+
"num_input_tokens_seen": 0,
|
2001 |
+
"num_train_epochs": 10,
|
2002 |
+
"save_steps": 100,
|
2003 |
+
"stateful_callbacks": {
|
2004 |
+
"TrainerControl": {
|
2005 |
+
"args": {
|
2006 |
+
"should_epoch_stop": false,
|
2007 |
+
"should_evaluate": false,
|
2008 |
+
"should_log": false,
|
2009 |
+
"should_save": true,
|
2010 |
+
"should_training_stop": true
|
2011 |
+
},
|
2012 |
+
"attributes": {}
|
2013 |
+
}
|
2014 |
+
},
|
2015 |
+
"total_flos": 7.982333171800736e+18,
|
2016 |
+
"train_batch_size": 8,
|
2017 |
+
"trial_name": null,
|
2018 |
+
"trial_params": null
|
2019 |
+
}
|