24/08/05 Train End Commit
Browse files- README.md +69 -8
- model.safetensors +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +3 -0
- scheduler.pt +1 -1
- trainer_state.json +1445 -5
README.md
CHANGED
@@ -1,10 +1,71 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: Jiayi-Pan/Tiny-Vicuna-1B
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: vicuna_1b_stage1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/momorami-kaist/medusa_test/runs/ku8hga4l)
|
16 |
+
# vicuna_1b_stage1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Jiayi-Pan/Tiny-Vicuna-1B](https://huggingface.co/Jiayi-Pan/Tiny-Vicuna-1B) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.9673
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0005
|
40 |
+
- train_batch_size: 2
|
41 |
+
- eval_batch_size: 2
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 8
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- lr_scheduler_warmup_steps: 40
|
48 |
+
- num_epochs: 1
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 3.3461 | 0.0170 | 40 | 3.5421 |
|
55 |
+
| 3.2004 | 0.0340 | 80 | 3.1581 |
|
56 |
+
| 3.0095 | 0.0510 | 120 | 3.0506 |
|
57 |
+
| 2.714 | 0.0681 | 160 | 3.0168 |
|
58 |
+
| 2.9508 | 0.0851 | 200 | 2.9764 |
|
59 |
+
| 2.9774 | 0.1021 | 240 | 2.9598 |
|
60 |
+
| 2.8688 | 0.1191 | 280 | 2.9551 |
|
61 |
+
| 2.8195 | 0.1361 | 320 | 2.9420 |
|
62 |
+
| 2.8471 | 0.1531 | 360 | 2.9328 |
|
63 |
+
| 2.9252 | 0.1701 | 400 | 2.9673 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.43.0
|
69 |
+
- Pytorch 2.3.1
|
70 |
+
- Datasets 2.15.0
|
71 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2897445048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d85661692b6291fa2a41089f42d3bf749225e56c8dfbd3b7fd329521e4f3c223
|
3 |
size 2897445048
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 698764714
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcbeff40bfd7f17c7b13436a81b46ca10e8027fca89ea3e23d4e9fae246af1f5
|
3 |
size 698764714
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b79470bbff7b03707dd1c00c4396c80f7644ed00cf4550ac4fc2d2e061e57335
|
3 |
+
size 2897493098
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4316c2cc91b0a7d79df989d3702d957e8d8964baa1b466b18af3b6a5b4d70131
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "./vicuna_1b_stage1/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 40,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1159,6 +1159,1446 @@
|
|
1159 |
"eval_samples_per_second": 4.9,
|
1160 |
"eval_steps_per_second": 2.45,
|
1161 |
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1162 |
}
|
1163 |
],
|
1164 |
"logging_steps": 1,
|
@@ -1187,7 +2627,7 @@
|
|
1187 |
"attributes": {}
|
1188 |
}
|
1189 |
},
|
1190 |
-
"total_flos":
|
1191 |
"train_batch_size": 2,
|
1192 |
"trial_name": null,
|
1193 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.932816982269287,
|
3 |
+
"best_model_checkpoint": "./vicuna_1b_stage1/checkpoint-360",
|
4 |
+
"epoch": 0.15312632922160782,
|
5 |
"eval_steps": 40,
|
6 |
+
"global_step": 360,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1159 |
"eval_samples_per_second": 4.9,
|
1160 |
"eval_steps_per_second": 2.45,
|
1161 |
"step": 160
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.06848149723521905,
|
1165 |
+
"grad_norm": 0.234375,
|
1166 |
+
"learning_rate": 0.0004966255641053594,
|
1167 |
+
"loss": 3.0074,
|
1168 |
+
"step": 161
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 0.06890684814972352,
|
1172 |
+
"grad_norm": 0.232421875,
|
1173 |
+
"learning_rate": 0.0004965696862563215,
|
1174 |
+
"loss": 2.7767,
|
1175 |
+
"step": 162
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 0.06933219906422798,
|
1179 |
+
"grad_norm": 0.22265625,
|
1180 |
+
"learning_rate": 0.00049651335274879,
|
1181 |
+
"loss": 3.1079,
|
1182 |
+
"step": 163
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.06975754997873246,
|
1186 |
+
"grad_norm": 0.25,
|
1187 |
+
"learning_rate": 0.0004964565636868685,
|
1188 |
+
"loss": 3.0311,
|
1189 |
+
"step": 164
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 0.07018290089323692,
|
1193 |
+
"grad_norm": 0.21484375,
|
1194 |
+
"learning_rate": 0.000496399319175503,
|
1195 |
+
"loss": 2.8768,
|
1196 |
+
"step": 165
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.07060825180774138,
|
1200 |
+
"grad_norm": 0.2119140625,
|
1201 |
+
"learning_rate": 0.0004963416193204805,
|
1202 |
+
"loss": 2.8893,
|
1203 |
+
"step": 166
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.07103360272224585,
|
1207 |
+
"grad_norm": 0.2236328125,
|
1208 |
+
"learning_rate": 0.0004962834642284299,
|
1209 |
+
"loss": 3.0358,
|
1210 |
+
"step": 167
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 0.07145895363675032,
|
1214 |
+
"grad_norm": 0.2412109375,
|
1215 |
+
"learning_rate": 0.0004962248540068214,
|
1216 |
+
"loss": 2.9668,
|
1217 |
+
"step": 168
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 0.07188430455125479,
|
1221 |
+
"grad_norm": 0.248046875,
|
1222 |
+
"learning_rate": 0.000496165788763966,
|
1223 |
+
"loss": 3.1232,
|
1224 |
+
"step": 169
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 0.07230965546575925,
|
1228 |
+
"grad_norm": 0.251953125,
|
1229 |
+
"learning_rate": 0.0004961062686090157,
|
1230 |
+
"loss": 2.8973,
|
1231 |
+
"step": 170
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 0.07273500638026371,
|
1235 |
+
"grad_norm": 0.220703125,
|
1236 |
+
"learning_rate": 0.0004960462936519634,
|
1237 |
+
"loss": 2.972,
|
1238 |
+
"step": 171
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.07316035729476818,
|
1242 |
+
"grad_norm": 0.2314453125,
|
1243 |
+
"learning_rate": 0.0004959858640036421,
|
1244 |
+
"loss": 2.7401,
|
1245 |
+
"step": 172
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.07358570820927265,
|
1249 |
+
"grad_norm": 0.287109375,
|
1250 |
+
"learning_rate": 0.0004959249797757252,
|
1251 |
+
"loss": 3.1016,
|
1252 |
+
"step": 173
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 0.07401105912377712,
|
1256 |
+
"grad_norm": 0.2197265625,
|
1257 |
+
"learning_rate": 0.0004958636410807262,
|
1258 |
+
"loss": 2.9953,
|
1259 |
+
"step": 174
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 0.07443641003828158,
|
1263 |
+
"grad_norm": 0.205078125,
|
1264 |
+
"learning_rate": 0.0004958018480319986,
|
1265 |
+
"loss": 3.1185,
|
1266 |
+
"step": 175
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 0.07486176095278604,
|
1270 |
+
"grad_norm": 0.26171875,
|
1271 |
+
"learning_rate": 0.0004957396007437352,
|
1272 |
+
"loss": 2.9158,
|
1273 |
+
"step": 176
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 0.07528711186729052,
|
1277 |
+
"grad_norm": 0.208984375,
|
1278 |
+
"learning_rate": 0.0004956768993309683,
|
1279 |
+
"loss": 2.9062,
|
1280 |
+
"step": 177
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.07571246278179498,
|
1284 |
+
"grad_norm": 0.2294921875,
|
1285 |
+
"learning_rate": 0.00049561374390957,
|
1286 |
+
"loss": 2.9196,
|
1287 |
+
"step": 178
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.07613781369629945,
|
1291 |
+
"grad_norm": 0.2294921875,
|
1292 |
+
"learning_rate": 0.0004955501345962506,
|
1293 |
+
"loss": 2.8288,
|
1294 |
+
"step": 179
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 0.07656316461080391,
|
1298 |
+
"grad_norm": 0.2099609375,
|
1299 |
+
"learning_rate": 0.0004954860715085594,
|
1300 |
+
"loss": 2.8086,
|
1301 |
+
"step": 180
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 0.07698851552530837,
|
1305 |
+
"grad_norm": 0.216796875,
|
1306 |
+
"learning_rate": 0.0004954215547648847,
|
1307 |
+
"loss": 2.9331,
|
1308 |
+
"step": 181
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 0.07741386643981285,
|
1312 |
+
"grad_norm": 0.2275390625,
|
1313 |
+
"learning_rate": 0.0004953565844844526,
|
1314 |
+
"loss": 2.9668,
|
1315 |
+
"step": 182
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 0.07783921735431731,
|
1319 |
+
"grad_norm": 0.234375,
|
1320 |
+
"learning_rate": 0.0004952911607873276,
|
1321 |
+
"loss": 2.9912,
|
1322 |
+
"step": 183
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.07826456826882178,
|
1326 |
+
"grad_norm": 0.259765625,
|
1327 |
+
"learning_rate": 0.0004952252837944123,
|
1328 |
+
"loss": 3.3231,
|
1329 |
+
"step": 184
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.07868991918332624,
|
1333 |
+
"grad_norm": 0.2138671875,
|
1334 |
+
"learning_rate": 0.0004951589536274465,
|
1335 |
+
"loss": 2.8044,
|
1336 |
+
"step": 185
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.07911527009783072,
|
1340 |
+
"grad_norm": 0.2314453125,
|
1341 |
+
"learning_rate": 0.000495092170409008,
|
1342 |
+
"loss": 2.9173,
|
1343 |
+
"step": 186
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 0.07954062101233518,
|
1347 |
+
"grad_norm": 0.236328125,
|
1348 |
+
"learning_rate": 0.0004950249342625114,
|
1349 |
+
"loss": 2.9855,
|
1350 |
+
"step": 187
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 0.07996597192683964,
|
1354 |
+
"grad_norm": 0.25390625,
|
1355 |
+
"learning_rate": 0.0004949572453122085,
|
1356 |
+
"loss": 2.9776,
|
1357 |
+
"step": 188
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 0.0803913228413441,
|
1361 |
+
"grad_norm": 0.2265625,
|
1362 |
+
"learning_rate": 0.0004948891036831878,
|
1363 |
+
"loss": 2.8271,
|
1364 |
+
"step": 189
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.08081667375584857,
|
1368 |
+
"grad_norm": 0.2177734375,
|
1369 |
+
"learning_rate": 0.0004948205095013744,
|
1370 |
+
"loss": 3.0117,
|
1371 |
+
"step": 190
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.08124202467035305,
|
1375 |
+
"grad_norm": 0.25390625,
|
1376 |
+
"learning_rate": 0.0004947514628935299,
|
1377 |
+
"loss": 2.9677,
|
1378 |
+
"step": 191
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.08166737558485751,
|
1382 |
+
"grad_norm": 0.2255859375,
|
1383 |
+
"learning_rate": 0.0004946819639872516,
|
1384 |
+
"loss": 2.971,
|
1385 |
+
"step": 192
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 0.08209272649936197,
|
1389 |
+
"grad_norm": 0.298828125,
|
1390 |
+
"learning_rate": 0.0004946120129109729,
|
1391 |
+
"loss": 3.0211,
|
1392 |
+
"step": 193
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.08251807741386644,
|
1396 |
+
"grad_norm": 0.255859375,
|
1397 |
+
"learning_rate": 0.0004945416097939628,
|
1398 |
+
"loss": 2.964,
|
1399 |
+
"step": 194
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 0.0829434283283709,
|
1403 |
+
"grad_norm": 0.271484375,
|
1404 |
+
"learning_rate": 0.0004944707547663255,
|
1405 |
+
"loss": 3.1499,
|
1406 |
+
"step": 195
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.08336877924287538,
|
1410 |
+
"grad_norm": 0.28125,
|
1411 |
+
"learning_rate": 0.0004943994479590005,
|
1412 |
+
"loss": 3.0077,
|
1413 |
+
"step": 196
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.08379413015737984,
|
1417 |
+
"grad_norm": 0.283203125,
|
1418 |
+
"learning_rate": 0.0004943276895037621,
|
1419 |
+
"loss": 3.0179,
|
1420 |
+
"step": 197
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.0842194810718843,
|
1424 |
+
"grad_norm": 0.275390625,
|
1425 |
+
"learning_rate": 0.0004942554795332191,
|
1426 |
+
"loss": 2.9786,
|
1427 |
+
"step": 198
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 0.08464483198638877,
|
1431 |
+
"grad_norm": 0.228515625,
|
1432 |
+
"learning_rate": 0.0004941828181808151,
|
1433 |
+
"loss": 2.8511,
|
1434 |
+
"step": 199
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.08507018290089324,
|
1438 |
+
"grad_norm": 0.205078125,
|
1439 |
+
"learning_rate": 0.0004941097055808276,
|
1440 |
+
"loss": 2.9508,
|
1441 |
+
"step": 200
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 0.08507018290089324,
|
1445 |
+
"eval_loss": 2.9764404296875,
|
1446 |
+
"eval_runtime": 63.425,
|
1447 |
+
"eval_samples_per_second": 4.888,
|
1448 |
+
"eval_steps_per_second": 2.444,
|
1449 |
+
"step": 200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.0854955338153977,
|
1453 |
+
"grad_norm": 0.21484375,
|
1454 |
+
"learning_rate": 0.0004940361418683679,
|
1455 |
+
"loss": 2.9608,
|
1456 |
+
"step": 201
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 0.08592088472990217,
|
1460 |
+
"grad_norm": 0.2236328125,
|
1461 |
+
"learning_rate": 0.000493962127179381,
|
1462 |
+
"loss": 2.9396,
|
1463 |
+
"step": 202
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 0.08634623564440663,
|
1467 |
+
"grad_norm": 0.2353515625,
|
1468 |
+
"learning_rate": 0.0004938876616506454,
|
1469 |
+
"loss": 3.1023,
|
1470 |
+
"step": 203
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 0.0867715865589111,
|
1474 |
+
"grad_norm": 0.2099609375,
|
1475 |
+
"learning_rate": 0.0004938127454197728,
|
1476 |
+
"loss": 2.9087,
|
1477 |
+
"step": 204
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 0.08719693747341557,
|
1481 |
+
"grad_norm": 0.2353515625,
|
1482 |
+
"learning_rate": 0.0004937373786252077,
|
1483 |
+
"loss": 2.8974,
|
1484 |
+
"step": 205
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 0.08762228838792004,
|
1488 |
+
"grad_norm": 0.271484375,
|
1489 |
+
"learning_rate": 0.0004936615614062271,
|
1490 |
+
"loss": 3.1185,
|
1491 |
+
"step": 206
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.0880476393024245,
|
1495 |
+
"grad_norm": 0.2392578125,
|
1496 |
+
"learning_rate": 0.0004935852939029407,
|
1497 |
+
"loss": 2.853,
|
1498 |
+
"step": 207
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 0.08847299021692896,
|
1502 |
+
"grad_norm": 0.2421875,
|
1503 |
+
"learning_rate": 0.00049350857625629,
|
1504 |
+
"loss": 2.9159,
|
1505 |
+
"step": 208
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 0.08889834113143344,
|
1509 |
+
"grad_norm": 0.2109375,
|
1510 |
+
"learning_rate": 0.0004934314086080485,
|
1511 |
+
"loss": 2.9314,
|
1512 |
+
"step": 209
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 0.0893236920459379,
|
1516 |
+
"grad_norm": 0.2001953125,
|
1517 |
+
"learning_rate": 0.0004933537911008213,
|
1518 |
+
"loss": 2.8321,
|
1519 |
+
"step": 210
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 0.08974904296044237,
|
1523 |
+
"grad_norm": 0.2314453125,
|
1524 |
+
"learning_rate": 0.000493275723878045,
|
1525 |
+
"loss": 2.7451,
|
1526 |
+
"step": 211
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 0.09017439387494683,
|
1530 |
+
"grad_norm": 0.2236328125,
|
1531 |
+
"learning_rate": 0.0004931972070839869,
|
1532 |
+
"loss": 2.8387,
|
1533 |
+
"step": 212
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.09059974478945129,
|
1537 |
+
"grad_norm": 0.2138671875,
|
1538 |
+
"learning_rate": 0.0004931182408637454,
|
1539 |
+
"loss": 2.9006,
|
1540 |
+
"step": 213
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 0.09102509570395577,
|
1544 |
+
"grad_norm": 0.2216796875,
|
1545 |
+
"learning_rate": 0.0004930388253632493,
|
1546 |
+
"loss": 3.1522,
|
1547 |
+
"step": 214
|
1548 |
+
},
|
1549 |
+
{
|
1550 |
+
"epoch": 0.09145044661846023,
|
1551 |
+
"grad_norm": 0.2470703125,
|
1552 |
+
"learning_rate": 0.0004929589607292578,
|
1553 |
+
"loss": 3.0026,
|
1554 |
+
"step": 215
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 0.0918757975329647,
|
1558 |
+
"grad_norm": 0.2216796875,
|
1559 |
+
"learning_rate": 0.0004928786471093599,
|
1560 |
+
"loss": 2.9921,
|
1561 |
+
"step": 216
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 0.09230114844746916,
|
1565 |
+
"grad_norm": 0.2314453125,
|
1566 |
+
"learning_rate": 0.0004927978846519744,
|
1567 |
+
"loss": 3.0345,
|
1568 |
+
"step": 217
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 0.09272649936197362,
|
1572 |
+
"grad_norm": 0.275390625,
|
1573 |
+
"learning_rate": 0.0004927166735063497,
|
1574 |
+
"loss": 2.8549,
|
1575 |
+
"step": 218
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.0931518502764781,
|
1579 |
+
"grad_norm": 0.2578125,
|
1580 |
+
"learning_rate": 0.0004926350138225632,
|
1581 |
+
"loss": 2.7431,
|
1582 |
+
"step": 219
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 0.09357720119098256,
|
1586 |
+
"grad_norm": 0.2119140625,
|
1587 |
+
"learning_rate": 0.0004925529057515211,
|
1588 |
+
"loss": 3.0491,
|
1589 |
+
"step": 220
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 0.09400255210548703,
|
1593 |
+
"grad_norm": 0.259765625,
|
1594 |
+
"learning_rate": 0.0004924703494449586,
|
1595 |
+
"loss": 3.1514,
|
1596 |
+
"step": 221
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 0.09442790301999149,
|
1600 |
+
"grad_norm": 0.205078125,
|
1601 |
+
"learning_rate": 0.0004923873450554388,
|
1602 |
+
"loss": 3.0525,
|
1603 |
+
"step": 222
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"epoch": 0.09485325393449597,
|
1607 |
+
"grad_norm": 0.271484375,
|
1608 |
+
"learning_rate": 0.0004923038927363531,
|
1609 |
+
"loss": 2.8732,
|
1610 |
+
"step": 223
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 0.09527860484900043,
|
1614 |
+
"grad_norm": 0.2177734375,
|
1615 |
+
"learning_rate": 0.0004922199926419206,
|
1616 |
+
"loss": 2.7112,
|
1617 |
+
"step": 224
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.09570395576350489,
|
1621 |
+
"grad_norm": 0.2265625,
|
1622 |
+
"learning_rate": 0.0004921356449271879,
|
1623 |
+
"loss": 2.9487,
|
1624 |
+
"step": 225
|
1625 |
+
},
|
1626 |
+
{
|
1627 |
+
"epoch": 0.09612930667800935,
|
1628 |
+
"grad_norm": 0.2109375,
|
1629 |
+
"learning_rate": 0.0004920508497480288,
|
1630 |
+
"loss": 3.0753,
|
1631 |
+
"step": 226
|
1632 |
+
},
|
1633 |
+
{
|
1634 |
+
"epoch": 0.09655465759251382,
|
1635 |
+
"grad_norm": 0.2431640625,
|
1636 |
+
"learning_rate": 0.0004919656072611441,
|
1637 |
+
"loss": 2.7704,
|
1638 |
+
"step": 227
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 0.0969800085070183,
|
1642 |
+
"grad_norm": 0.236328125,
|
1643 |
+
"learning_rate": 0.0004918799176240609,
|
1644 |
+
"loss": 3.0108,
|
1645 |
+
"step": 228
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 0.09740535942152276,
|
1649 |
+
"grad_norm": 0.234375,
|
1650 |
+
"learning_rate": 0.0004917937809951331,
|
1651 |
+
"loss": 3.0525,
|
1652 |
+
"step": 229
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 0.09783071033602722,
|
1656 |
+
"grad_norm": 0.2490234375,
|
1657 |
+
"learning_rate": 0.0004917071975335402,
|
1658 |
+
"loss": 3.0414,
|
1659 |
+
"step": 230
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.09825606125053168,
|
1663 |
+
"grad_norm": 0.224609375,
|
1664 |
+
"learning_rate": 0.0004916201673992878,
|
1665 |
+
"loss": 3.099,
|
1666 |
+
"step": 231
|
1667 |
+
},
|
1668 |
+
{
|
1669 |
+
"epoch": 0.09868141216503616,
|
1670 |
+
"grad_norm": 0.2412109375,
|
1671 |
+
"learning_rate": 0.0004915326907532066,
|
1672 |
+
"loss": 2.9573,
|
1673 |
+
"step": 232
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 0.09910676307954062,
|
1677 |
+
"grad_norm": 0.2236328125,
|
1678 |
+
"learning_rate": 0.0004914447677569528,
|
1679 |
+
"loss": 3.0696,
|
1680 |
+
"step": 233
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 0.09953211399404509,
|
1684 |
+
"grad_norm": 0.265625,
|
1685 |
+
"learning_rate": 0.0004913563985730071,
|
1686 |
+
"loss": 2.8594,
|
1687 |
+
"step": 234
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"epoch": 0.09995746490854955,
|
1691 |
+
"grad_norm": 0.26171875,
|
1692 |
+
"learning_rate": 0.0004912675833646752,
|
1693 |
+
"loss": 2.9316,
|
1694 |
+
"step": 235
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 0.10038281582305401,
|
1698 |
+
"grad_norm": 0.244140625,
|
1699 |
+
"learning_rate": 0.0004911783222960865,
|
1700 |
+
"loss": 3.0001,
|
1701 |
+
"step": 236
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.10080816673755849,
|
1705 |
+
"grad_norm": 0.2412109375,
|
1706 |
+
"learning_rate": 0.0004910886155321948,
|
1707 |
+
"loss": 2.6424,
|
1708 |
+
"step": 237
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"epoch": 0.10123351765206295,
|
1712 |
+
"grad_norm": 0.2373046875,
|
1713 |
+
"learning_rate": 0.0004909984632387773,
|
1714 |
+
"loss": 3.0565,
|
1715 |
+
"step": 238
|
1716 |
+
},
|
1717 |
+
{
|
1718 |
+
"epoch": 0.10165886856656742,
|
1719 |
+
"grad_norm": 0.2421875,
|
1720 |
+
"learning_rate": 0.0004909078655824346,
|
1721 |
+
"loss": 2.9444,
|
1722 |
+
"step": 239
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 0.10208421948107188,
|
1726 |
+
"grad_norm": 0.302734375,
|
1727 |
+
"learning_rate": 0.0004908168227305904,
|
1728 |
+
"loss": 2.9774,
|
1729 |
+
"step": 240
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 0.10208421948107188,
|
1733 |
+
"eval_loss": 2.9597935676574707,
|
1734 |
+
"eval_runtime": 63.4756,
|
1735 |
+
"eval_samples_per_second": 4.884,
|
1736 |
+
"eval_steps_per_second": 2.442,
|
1737 |
+
"step": 240
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.10250957039557634,
|
1741 |
+
"grad_norm": 0.2353515625,
|
1742 |
+
"learning_rate": 0.000490725334851491,
|
1743 |
+
"loss": 2.9188,
|
1744 |
+
"step": 241
|
1745 |
+
},
|
1746 |
+
{
|
1747 |
+
"epoch": 0.10293492131008082,
|
1748 |
+
"grad_norm": 0.2578125,
|
1749 |
+
"learning_rate": 0.0004906334021142051,
|
1750 |
+
"loss": 3.0157,
|
1751 |
+
"step": 242
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 0.10336027222458528,
|
1755 |
+
"grad_norm": 0.265625,
|
1756 |
+
"learning_rate": 0.0004905410246886236,
|
1757 |
+
"loss": 3.0665,
|
1758 |
+
"step": 243
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 0.10378562313908975,
|
1762 |
+
"grad_norm": 0.224609375,
|
1763 |
+
"learning_rate": 0.0004904482027454591,
|
1764 |
+
"loss": 2.9233,
|
1765 |
+
"step": 244
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 0.10421097405359421,
|
1769 |
+
"grad_norm": 0.2177734375,
|
1770 |
+
"learning_rate": 0.0004903549364562457,
|
1771 |
+
"loss": 2.8526,
|
1772 |
+
"step": 245
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 0.10463632496809869,
|
1776 |
+
"grad_norm": 0.1884765625,
|
1777 |
+
"learning_rate": 0.0004902612259933387,
|
1778 |
+
"loss": 2.8396,
|
1779 |
+
"step": 246
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.10506167588260315,
|
1783 |
+
"grad_norm": 0.22265625,
|
1784 |
+
"learning_rate": 0.0004901670715299141,
|
1785 |
+
"loss": 2.9525,
|
1786 |
+
"step": 247
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 0.10548702679710761,
|
1790 |
+
"grad_norm": 0.2265625,
|
1791 |
+
"learning_rate": 0.0004900724732399684,
|
1792 |
+
"loss": 2.9864,
|
1793 |
+
"step": 248
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 0.10591237771161208,
|
1797 |
+
"grad_norm": 0.2412109375,
|
1798 |
+
"learning_rate": 0.0004899774312983185,
|
1799 |
+
"loss": 2.8855,
|
1800 |
+
"step": 249
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 0.10633772862611654,
|
1804 |
+
"grad_norm": 0.2333984375,
|
1805 |
+
"learning_rate": 0.000489881945880601,
|
1806 |
+
"loss": 2.9226,
|
1807 |
+
"step": 250
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 0.10676307954062102,
|
1811 |
+
"grad_norm": 0.2490234375,
|
1812 |
+
"learning_rate": 0.000489786017163272,
|
1813 |
+
"loss": 3.2196,
|
1814 |
+
"step": 251
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 0.10718843045512548,
|
1818 |
+
"grad_norm": 0.2255859375,
|
1819 |
+
"learning_rate": 0.0004896896453236069,
|
1820 |
+
"loss": 2.8574,
|
1821 |
+
"step": 252
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.10761378136962994,
|
1825 |
+
"grad_norm": 0.228515625,
|
1826 |
+
"learning_rate": 0.0004895928305397,
|
1827 |
+
"loss": 2.7911,
|
1828 |
+
"step": 253
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"epoch": 0.1080391322841344,
|
1832 |
+
"grad_norm": 0.220703125,
|
1833 |
+
"learning_rate": 0.0004894955729904642,
|
1834 |
+
"loss": 2.8661,
|
1835 |
+
"step": 254
|
1836 |
+
},
|
1837 |
+
{
|
1838 |
+
"epoch": 0.10846448319863888,
|
1839 |
+
"grad_norm": 0.263671875,
|
1840 |
+
"learning_rate": 0.0004893978728556305,
|
1841 |
+
"loss": 2.8232,
|
1842 |
+
"step": 255
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 0.10888983411314335,
|
1846 |
+
"grad_norm": 0.2275390625,
|
1847 |
+
"learning_rate": 0.0004892997303157477,
|
1848 |
+
"loss": 2.7856,
|
1849 |
+
"step": 256
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 0.10931518502764781,
|
1853 |
+
"grad_norm": 0.203125,
|
1854 |
+
"learning_rate": 0.0004892011455521823,
|
1855 |
+
"loss": 2.7407,
|
1856 |
+
"step": 257
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 0.10974053594215227,
|
1860 |
+
"grad_norm": 0.25,
|
1861 |
+
"learning_rate": 0.0004891021187471183,
|
1862 |
+
"loss": 3.2471,
|
1863 |
+
"step": 258
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.11016588685665674,
|
1867 |
+
"grad_norm": 0.234375,
|
1868 |
+
"learning_rate": 0.0004890026500835561,
|
1869 |
+
"loss": 2.7626,
|
1870 |
+
"step": 259
|
1871 |
+
},
|
1872 |
+
{
|
1873 |
+
"epoch": 0.11059123777116121,
|
1874 |
+
"grad_norm": 0.201171875,
|
1875 |
+
"learning_rate": 0.000488902739745313,
|
1876 |
+
"loss": 2.9364,
|
1877 |
+
"step": 260
|
1878 |
+
},
|
1879 |
+
{
|
1880 |
+
"epoch": 0.11101658868566568,
|
1881 |
+
"grad_norm": 0.26171875,
|
1882 |
+
"learning_rate": 0.0004888023879170222,
|
1883 |
+
"loss": 2.7893,
|
1884 |
+
"step": 261
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 0.11144193960017014,
|
1888 |
+
"grad_norm": 0.287109375,
|
1889 |
+
"learning_rate": 0.000488701594784133,
|
1890 |
+
"loss": 2.7034,
|
1891 |
+
"step": 262
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 0.1118672905146746,
|
1895 |
+
"grad_norm": 0.212890625,
|
1896 |
+
"learning_rate": 0.0004886003605329103,
|
1897 |
+
"loss": 2.9583,
|
1898 |
+
"step": 263
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 0.11229264142917907,
|
1902 |
+
"grad_norm": 0.2421875,
|
1903 |
+
"learning_rate": 0.000488498685350434,
|
1904 |
+
"loss": 2.8145,
|
1905 |
+
"step": 264
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.11271799234368354,
|
1909 |
+
"grad_norm": 0.22265625,
|
1910 |
+
"learning_rate": 0.0004883965694245988,
|
1911 |
+
"loss": 3.0146,
|
1912 |
+
"step": 265
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"epoch": 0.113143343258188,
|
1916 |
+
"grad_norm": 0.2021484375,
|
1917 |
+
"learning_rate": 0.0004882940129441141,
|
1918 |
+
"loss": 2.7569,
|
1919 |
+
"step": 266
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"epoch": 0.11356869417269247,
|
1923 |
+
"grad_norm": 0.2421875,
|
1924 |
+
"learning_rate": 0.00048819101609850335,
|
1925 |
+
"loss": 2.8143,
|
1926 |
+
"step": 267
|
1927 |
+
},
|
1928 |
+
{
|
1929 |
+
"epoch": 0.11399404508719693,
|
1930 |
+
"grad_norm": 0.212890625,
|
1931 |
+
"learning_rate": 0.0004880875790781036,
|
1932 |
+
"loss": 2.8306,
|
1933 |
+
"step": 268
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"epoch": 0.11441939600170141,
|
1937 |
+
"grad_norm": 0.1962890625,
|
1938 |
+
"learning_rate": 0.00048798370207406565,
|
1939 |
+
"loss": 2.8753,
|
1940 |
+
"step": 269
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 0.11484474691620587,
|
1944 |
+
"grad_norm": 0.255859375,
|
1945 |
+
"learning_rate": 0.0004878793852783532,
|
1946 |
+
"loss": 3.0401,
|
1947 |
+
"step": 270
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 0.11527009783071034,
|
1951 |
+
"grad_norm": 0.203125,
|
1952 |
+
"learning_rate": 0.00048777462888374267,
|
1953 |
+
"loss": 2.8367,
|
1954 |
+
"step": 271
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 0.1156954487452148,
|
1958 |
+
"grad_norm": 0.2275390625,
|
1959 |
+
"learning_rate": 0.00048766943308382307,
|
1960 |
+
"loss": 2.9306,
|
1961 |
+
"step": 272
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 0.11612079965971926,
|
1965 |
+
"grad_norm": 0.2314453125,
|
1966 |
+
"learning_rate": 0.000487563798072995,
|
1967 |
+
"loss": 2.8537,
|
1968 |
+
"step": 273
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 0.11654615057422374,
|
1972 |
+
"grad_norm": 0.25,
|
1973 |
+
"learning_rate": 0.00048745772404647117,
|
1974 |
+
"loss": 2.8464,
|
1975 |
+
"step": 274
|
1976 |
+
},
|
1977 |
+
{
|
1978 |
+
"epoch": 0.1169715014887282,
|
1979 |
+
"grad_norm": 0.2294921875,
|
1980 |
+
"learning_rate": 0.0004873512112002754,
|
1981 |
+
"loss": 2.8814,
|
1982 |
+
"step": 275
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 0.11739685240323267,
|
1986 |
+
"grad_norm": 0.2373046875,
|
1987 |
+
"learning_rate": 0.00048724425973124233,
|
1988 |
+
"loss": 3.1535,
|
1989 |
+
"step": 276
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.11782220331773713,
|
1993 |
+
"grad_norm": 0.34765625,
|
1994 |
+
"learning_rate": 0.00048713686983701735,
|
1995 |
+
"loss": 3.2049,
|
1996 |
+
"step": 277
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 0.1182475542322416,
|
2000 |
+
"grad_norm": 0.205078125,
|
2001 |
+
"learning_rate": 0.000487029041716056,
|
2002 |
+
"loss": 2.9109,
|
2003 |
+
"step": 278
|
2004 |
+
},
|
2005 |
+
{
|
2006 |
+
"epoch": 0.11867290514674607,
|
2007 |
+
"grad_norm": 0.283203125,
|
2008 |
+
"learning_rate": 0.0004869207755676236,
|
2009 |
+
"loss": 2.923,
|
2010 |
+
"step": 279
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 0.11909825606125053,
|
2014 |
+
"grad_norm": 0.267578125,
|
2015 |
+
"learning_rate": 0.0004868120715917951,
|
2016 |
+
"loss": 2.8688,
|
2017 |
+
"step": 280
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 0.11909825606125053,
|
2021 |
+
"eval_loss": 2.955108165740967,
|
2022 |
+
"eval_runtime": 63.2425,
|
2023 |
+
"eval_samples_per_second": 4.902,
|
2024 |
+
"eval_steps_per_second": 2.451,
|
2025 |
+
"step": 280
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.119523606975755,
|
2029 |
+
"grad_norm": 0.21484375,
|
2030 |
+
"learning_rate": 0.0004867029299894543,
|
2031 |
+
"loss": 2.9269,
|
2032 |
+
"step": 281
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.11994895789025946,
|
2036 |
+
"grad_norm": 0.2578125,
|
2037 |
+
"learning_rate": 0.00048659335096229396,
|
2038 |
+
"loss": 2.935,
|
2039 |
+
"step": 282
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.12037430880476394,
|
2043 |
+
"grad_norm": 0.2265625,
|
2044 |
+
"learning_rate": 0.00048648333471281504,
|
2045 |
+
"loss": 2.938,
|
2046 |
+
"step": 283
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.1207996597192684,
|
2050 |
+
"grad_norm": 0.2451171875,
|
2051 |
+
"learning_rate": 0.00048637288144432654,
|
2052 |
+
"loss": 3.1435,
|
2053 |
+
"step": 284
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.12122501063377286,
|
2057 |
+
"grad_norm": 0.263671875,
|
2058 |
+
"learning_rate": 0.0004862619913609452,
|
2059 |
+
"loss": 2.802,
|
2060 |
+
"step": 285
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.12165036154827732,
|
2064 |
+
"grad_norm": 0.2236328125,
|
2065 |
+
"learning_rate": 0.00048615066466759475,
|
2066 |
+
"loss": 2.8115,
|
2067 |
+
"step": 286
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.1220757124627818,
|
2071 |
+
"grad_norm": 0.2255859375,
|
2072 |
+
"learning_rate": 0.000486038901570006,
|
2073 |
+
"loss": 2.8113,
|
2074 |
+
"step": 287
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.12250106337728627,
|
2078 |
+
"grad_norm": 0.275390625,
|
2079 |
+
"learning_rate": 0.0004859267022747159,
|
2080 |
+
"loss": 3.0597,
|
2081 |
+
"step": 288
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.12292641429179073,
|
2085 |
+
"grad_norm": 0.25390625,
|
2086 |
+
"learning_rate": 0.00048581406698906793,
|
2087 |
+
"loss": 2.9627,
|
2088 |
+
"step": 289
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.12335176520629519,
|
2092 |
+
"grad_norm": 0.2119140625,
|
2093 |
+
"learning_rate": 0.000485700995921211,
|
2094 |
+
"loss": 2.9785,
|
2095 |
+
"step": 290
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.12377711612079965,
|
2099 |
+
"grad_norm": 0.2060546875,
|
2100 |
+
"learning_rate": 0.00048558748928009934,
|
2101 |
+
"loss": 2.8078,
|
2102 |
+
"step": 291
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.12420246703530413,
|
2106 |
+
"grad_norm": 0.23046875,
|
2107 |
+
"learning_rate": 0.0004854735472754921,
|
2108 |
+
"loss": 2.7406,
|
2109 |
+
"step": 292
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.1246278179498086,
|
2113 |
+
"grad_norm": 0.1884765625,
|
2114 |
+
"learning_rate": 0.0004853591701179533,
|
2115 |
+
"loss": 2.9503,
|
2116 |
+
"step": 293
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.12505316886431306,
|
2120 |
+
"grad_norm": 0.24609375,
|
2121 |
+
"learning_rate": 0.0004852443580188506,
|
2122 |
+
"loss": 2.9331,
|
2123 |
+
"step": 294
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.12547851977881752,
|
2127 |
+
"grad_norm": 0.2470703125,
|
2128 |
+
"learning_rate": 0.00048512911119035586,
|
2129 |
+
"loss": 3.03,
|
2130 |
+
"step": 295
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.12590387069332198,
|
2134 |
+
"grad_norm": 0.21484375,
|
2135 |
+
"learning_rate": 0.00048501342984544403,
|
2136 |
+
"loss": 2.9366,
|
2137 |
+
"step": 296
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.12632922160782645,
|
2141 |
+
"grad_norm": 0.267578125,
|
2142 |
+
"learning_rate": 0.00048489731419789326,
|
2143 |
+
"loss": 2.9618,
|
2144 |
+
"step": 297
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.1267545725223309,
|
2148 |
+
"grad_norm": 0.208984375,
|
2149 |
+
"learning_rate": 0.00048478076446228414,
|
2150 |
+
"loss": 2.8087,
|
2151 |
+
"step": 298
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.1271799234368354,
|
2155 |
+
"grad_norm": 0.2138671875,
|
2156 |
+
"learning_rate": 0.00048466378085399955,
|
2157 |
+
"loss": 2.933,
|
2158 |
+
"step": 299
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.12760527435133986,
|
2162 |
+
"grad_norm": 0.2099609375,
|
2163 |
+
"learning_rate": 0.0004845463635892241,
|
2164 |
+
"loss": 2.9283,
|
2165 |
+
"step": 300
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.12803062526584433,
|
2169 |
+
"grad_norm": 0.2216796875,
|
2170 |
+
"learning_rate": 0.00048442851288494373,
|
2171 |
+
"loss": 3.0075,
|
2172 |
+
"step": 301
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.1284559761803488,
|
2176 |
+
"grad_norm": 0.259765625,
|
2177 |
+
"learning_rate": 0.00048431022895894556,
|
2178 |
+
"loss": 3.007,
|
2179 |
+
"step": 302
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.12888132709485325,
|
2183 |
+
"grad_norm": 0.2177734375,
|
2184 |
+
"learning_rate": 0.00048419151202981717,
|
2185 |
+
"loss": 3.0046,
|
2186 |
+
"step": 303
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.12930667800935772,
|
2190 |
+
"grad_norm": 0.2353515625,
|
2191 |
+
"learning_rate": 0.0004840723623169462,
|
2192 |
+
"loss": 3.043,
|
2193 |
+
"step": 304
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.12973202892386218,
|
2197 |
+
"grad_norm": 0.220703125,
|
2198 |
+
"learning_rate": 0.00048395278004052035,
|
2199 |
+
"loss": 2.9849,
|
2200 |
+
"step": 305
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.13015737983836664,
|
2204 |
+
"grad_norm": 0.2197265625,
|
2205 |
+
"learning_rate": 0.0004838327654215265,
|
2206 |
+
"loss": 2.6544,
|
2207 |
+
"step": 306
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.1305827307528711,
|
2211 |
+
"grad_norm": 0.26171875,
|
2212 |
+
"learning_rate": 0.0004837123186817507,
|
2213 |
+
"loss": 2.6496,
|
2214 |
+
"step": 307
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.1310080816673756,
|
2218 |
+
"grad_norm": 0.2265625,
|
2219 |
+
"learning_rate": 0.0004835914400437772,
|
2220 |
+
"loss": 3.0452,
|
2221 |
+
"step": 308
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.13143343258188006,
|
2225 |
+
"grad_norm": 0.2001953125,
|
2226 |
+
"learning_rate": 0.00048347012973098876,
|
2227 |
+
"loss": 2.8963,
|
2228 |
+
"step": 309
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.13185878349638452,
|
2232 |
+
"grad_norm": 0.2216796875,
|
2233 |
+
"learning_rate": 0.0004833483879675656,
|
2234 |
+
"loss": 2.6782,
|
2235 |
+
"step": 310
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.132284134410889,
|
2239 |
+
"grad_norm": 0.2314453125,
|
2240 |
+
"learning_rate": 0.0004832262149784854,
|
2241 |
+
"loss": 2.7867,
|
2242 |
+
"step": 311
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.13270948532539345,
|
2246 |
+
"grad_norm": 0.2392578125,
|
2247 |
+
"learning_rate": 0.0004831036109895228,
|
2248 |
+
"loss": 2.8551,
|
2249 |
+
"step": 312
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.1331348362398979,
|
2253 |
+
"grad_norm": 0.294921875,
|
2254 |
+
"learning_rate": 0.0004829805762272487,
|
2255 |
+
"loss": 3.0273,
|
2256 |
+
"step": 313
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.13356018715440238,
|
2260 |
+
"grad_norm": 0.19921875,
|
2261 |
+
"learning_rate": 0.0004828571109190303,
|
2262 |
+
"loss": 2.6733,
|
2263 |
+
"step": 314
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.13398553806890684,
|
2267 |
+
"grad_norm": 0.283203125,
|
2268 |
+
"learning_rate": 0.00048273321529303026,
|
2269 |
+
"loss": 2.9066,
|
2270 |
+
"step": 315
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.1344108889834113,
|
2274 |
+
"grad_norm": 0.2099609375,
|
2275 |
+
"learning_rate": 0.0004826088895782066,
|
2276 |
+
"loss": 2.9175,
|
2277 |
+
"step": 316
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.1348362398979158,
|
2281 |
+
"grad_norm": 0.271484375,
|
2282 |
+
"learning_rate": 0.00048248413400431213,
|
2283 |
+
"loss": 2.8247,
|
2284 |
+
"step": 317
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.13526159081242026,
|
2288 |
+
"grad_norm": 0.208984375,
|
2289 |
+
"learning_rate": 0.0004823589488018939,
|
2290 |
+
"loss": 2.741,
|
2291 |
+
"step": 318
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.13568694172692472,
|
2295 |
+
"grad_norm": 0.2138671875,
|
2296 |
+
"learning_rate": 0.0004822333342022931,
|
2297 |
+
"loss": 2.9368,
|
2298 |
+
"step": 319
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.13611229264142918,
|
2302 |
+
"grad_norm": 0.1865234375,
|
2303 |
+
"learning_rate": 0.0004821072904376442,
|
2304 |
+
"loss": 2.8195,
|
2305 |
+
"step": 320
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.13611229264142918,
|
2309 |
+
"eval_loss": 2.9419751167297363,
|
2310 |
+
"eval_runtime": 63.5584,
|
2311 |
+
"eval_samples_per_second": 4.877,
|
2312 |
+
"eval_steps_per_second": 2.439,
|
2313 |
+
"step": 320
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.13653764355593365,
|
2317 |
+
"grad_norm": 0.2021484375,
|
2318 |
+
"learning_rate": 0.0004819808177408751,
|
2319 |
+
"loss": 2.8478,
|
2320 |
+
"step": 321
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.1369629944704381,
|
2324 |
+
"grad_norm": 0.265625,
|
2325 |
+
"learning_rate": 0.00048185391634570604,
|
2326 |
+
"loss": 2.8875,
|
2327 |
+
"step": 322
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.13738834538494257,
|
2331 |
+
"grad_norm": 0.259765625,
|
2332 |
+
"learning_rate": 0.00048172658648664964,
|
2333 |
+
"loss": 3.2072,
|
2334 |
+
"step": 323
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.13781369629944704,
|
2338 |
+
"grad_norm": 0.25,
|
2339 |
+
"learning_rate": 0.0004815988283990104,
|
2340 |
+
"loss": 2.999,
|
2341 |
+
"step": 324
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.1382390472139515,
|
2345 |
+
"grad_norm": 0.2294921875,
|
2346 |
+
"learning_rate": 0.0004814706423188838,
|
2347 |
+
"loss": 2.7438,
|
2348 |
+
"step": 325
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.13866439812845596,
|
2352 |
+
"grad_norm": 0.189453125,
|
2353 |
+
"learning_rate": 0.0004813420284831569,
|
2354 |
+
"loss": 2.8992,
|
2355 |
+
"step": 326
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.13908974904296045,
|
2359 |
+
"grad_norm": 0.2412109375,
|
2360 |
+
"learning_rate": 0.0004812129871295067,
|
2361 |
+
"loss": 2.6756,
|
2362 |
+
"step": 327
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 0.13951509995746492,
|
2366 |
+
"grad_norm": 0.2080078125,
|
2367 |
+
"learning_rate": 0.0004810835184964003,
|
2368 |
+
"loss": 2.9913,
|
2369 |
+
"step": 328
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 0.13994045087196938,
|
2373 |
+
"grad_norm": 0.2333984375,
|
2374 |
+
"learning_rate": 0.00048095362282309475,
|
2375 |
+
"loss": 2.8021,
|
2376 |
+
"step": 329
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 0.14036580178647384,
|
2380 |
+
"grad_norm": 0.1962890625,
|
2381 |
+
"learning_rate": 0.0004808233003496359,
|
2382 |
+
"loss": 2.8213,
|
2383 |
+
"step": 330
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 0.1407911527009783,
|
2387 |
+
"grad_norm": 0.26171875,
|
2388 |
+
"learning_rate": 0.0004806925513168585,
|
2389 |
+
"loss": 2.9985,
|
2390 |
+
"step": 331
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.14121650361548277,
|
2394 |
+
"grad_norm": 0.24609375,
|
2395 |
+
"learning_rate": 0.0004805613759663857,
|
2396 |
+
"loss": 2.9846,
|
2397 |
+
"step": 332
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.14164185452998723,
|
2401 |
+
"grad_norm": 0.27734375,
|
2402 |
+
"learning_rate": 0.00048042977454062813,
|
2403 |
+
"loss": 2.7196,
|
2404 |
+
"step": 333
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 0.1420672054444917,
|
2408 |
+
"grad_norm": 0.263671875,
|
2409 |
+
"learning_rate": 0.0004802977472827841,
|
2410 |
+
"loss": 2.9264,
|
2411 |
+
"step": 334
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 0.14249255635899616,
|
2415 |
+
"grad_norm": 0.220703125,
|
2416 |
+
"learning_rate": 0.00048016529443683874,
|
2417 |
+
"loss": 3.0284,
|
2418 |
+
"step": 335
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 0.14291790727350065,
|
2422 |
+
"grad_norm": 0.287109375,
|
2423 |
+
"learning_rate": 0.0004800324162475637,
|
2424 |
+
"loss": 3.2964,
|
2425 |
+
"step": 336
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 0.1433432581880051,
|
2429 |
+
"grad_norm": 0.26953125,
|
2430 |
+
"learning_rate": 0.0004798991129605166,
|
2431 |
+
"loss": 2.9651,
|
2432 |
+
"step": 337
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 0.14376860910250958,
|
2436 |
+
"grad_norm": 0.2119140625,
|
2437 |
+
"learning_rate": 0.00047976538482204066,
|
2438 |
+
"loss": 2.5494,
|
2439 |
+
"step": 338
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.14419396001701404,
|
2443 |
+
"grad_norm": 0.2158203125,
|
2444 |
+
"learning_rate": 0.0004796312320792644,
|
2445 |
+
"loss": 2.8722,
|
2446 |
+
"step": 339
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 0.1446193109315185,
|
2450 |
+
"grad_norm": 0.1982421875,
|
2451 |
+
"learning_rate": 0.00047949665498010064,
|
2452 |
+
"loss": 3.0085,
|
2453 |
+
"step": 340
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 0.14504466184602297,
|
2457 |
+
"grad_norm": 0.19921875,
|
2458 |
+
"learning_rate": 0.0004793616537732467,
|
2459 |
+
"loss": 2.8798,
|
2460 |
+
"step": 341
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 0.14547001276052743,
|
2464 |
+
"grad_norm": 0.2138671875,
|
2465 |
+
"learning_rate": 0.0004792262287081836,
|
2466 |
+
"loss": 2.7285,
|
2467 |
+
"step": 342
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 0.1458953636750319,
|
2471 |
+
"grad_norm": 0.203125,
|
2472 |
+
"learning_rate": 0.0004790903800351756,
|
2473 |
+
"loss": 3.018,
|
2474 |
+
"step": 343
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 0.14632071458953635,
|
2478 |
+
"grad_norm": 0.22265625,
|
2479 |
+
"learning_rate": 0.0004789541080052696,
|
2480 |
+
"loss": 2.6753,
|
2481 |
+
"step": 344
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 0.14674606550404085,
|
2485 |
+
"grad_norm": 0.1884765625,
|
2486 |
+
"learning_rate": 0.00047881741287029533,
|
2487 |
+
"loss": 2.7885,
|
2488 |
+
"step": 345
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 0.1471714164185453,
|
2492 |
+
"grad_norm": 0.283203125,
|
2493 |
+
"learning_rate": 0.0004786802948828639,
|
2494 |
+
"loss": 3.039,
|
2495 |
+
"step": 346
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 0.14759676733304977,
|
2499 |
+
"grad_norm": 0.255859375,
|
2500 |
+
"learning_rate": 0.0004785427542963683,
|
2501 |
+
"loss": 2.8223,
|
2502 |
+
"step": 347
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 0.14802211824755424,
|
2506 |
+
"grad_norm": 0.232421875,
|
2507 |
+
"learning_rate": 0.00047840479136498204,
|
2508 |
+
"loss": 2.6399,
|
2509 |
+
"step": 348
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 0.1484474691620587,
|
2513 |
+
"grad_norm": 0.2314453125,
|
2514 |
+
"learning_rate": 0.0004782664063436595,
|
2515 |
+
"loss": 2.7918,
|
2516 |
+
"step": 349
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 0.14887282007656316,
|
2520 |
+
"grad_norm": 0.220703125,
|
2521 |
+
"learning_rate": 0.00047812759948813476,
|
2522 |
+
"loss": 2.8189,
|
2523 |
+
"step": 350
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 0.14929817099106762,
|
2527 |
+
"grad_norm": 0.201171875,
|
2528 |
+
"learning_rate": 0.00047798837105492175,
|
2529 |
+
"loss": 3.1005,
|
2530 |
+
"step": 351
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 0.1497235219055721,
|
2534 |
+
"grad_norm": 0.2197265625,
|
2535 |
+
"learning_rate": 0.0004778487213013133,
|
2536 |
+
"loss": 2.7514,
|
2537 |
+
"step": 352
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 0.15014887282007655,
|
2541 |
+
"grad_norm": 0.2265625,
|
2542 |
+
"learning_rate": 0.00047770865048538076,
|
2543 |
+
"loss": 3.0975,
|
2544 |
+
"step": 353
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 0.15057422373458104,
|
2548 |
+
"grad_norm": 0.22265625,
|
2549 |
+
"learning_rate": 0.0004775681588659738,
|
2550 |
+
"loss": 3.0484,
|
2551 |
+
"step": 354
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 0.1509995746490855,
|
2555 |
+
"grad_norm": 0.216796875,
|
2556 |
+
"learning_rate": 0.0004774272467027196,
|
2557 |
+
"loss": 3.1473,
|
2558 |
+
"step": 355
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 0.15142492556358997,
|
2562 |
+
"grad_norm": 0.240234375,
|
2563 |
+
"learning_rate": 0.00047728591425602254,
|
2564 |
+
"loss": 2.827,
|
2565 |
+
"step": 356
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 0.15185027647809443,
|
2569 |
+
"grad_norm": 0.2060546875,
|
2570 |
+
"learning_rate": 0.00047714416178706355,
|
2571 |
+
"loss": 3.0653,
|
2572 |
+
"step": 357
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 0.1522756273925989,
|
2576 |
+
"grad_norm": 0.2119140625,
|
2577 |
+
"learning_rate": 0.0004770019895578001,
|
2578 |
+
"loss": 2.9329,
|
2579 |
+
"step": 358
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 0.15270097830710336,
|
2583 |
+
"grad_norm": 0.23046875,
|
2584 |
+
"learning_rate": 0.000476859397830965,
|
2585 |
+
"loss": 3.0109,
|
2586 |
+
"step": 359
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 0.15312632922160782,
|
2590 |
+
"grad_norm": 0.24609375,
|
2591 |
+
"learning_rate": 0.00047671638687006644,
|
2592 |
+
"loss": 2.8471,
|
2593 |
+
"step": 360
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 0.15312632922160782,
|
2597 |
+
"eval_loss": 2.932816982269287,
|
2598 |
+
"eval_runtime": 63.2289,
|
2599 |
+
"eval_samples_per_second": 4.903,
|
2600 |
+
"eval_steps_per_second": 2.451,
|
2601 |
+
"step": 360
|
2602 |
}
|
2603 |
],
|
2604 |
"logging_steps": 1,
|
|
|
2627 |
"attributes": {}
|
2628 |
}
|
2629 |
},
|
2630 |
+
"total_flos": 4.894975837863936e+16,
|
2631 |
"train_batch_size": 2,
|
2632 |
"trial_name": null,
|
2633 |
"trial_params": null
|