Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: google/gemma-7b
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: coding_llamaduo_60k_v0.2
|
| 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 |
+
# coding_llamaduo_60k_v0.2
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.3326
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- total_eval_batch_size: 16
|
| 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 |
+
| 0.7499 | 1.0 | 126 | 1.2580 |
|
| 61 |
+
| 0.6058 | 2.0 | 252 | 1.1687 |
|
| 62 |
+
| 0.5571 | 3.0 | 378 | 1.1492 |
|
| 63 |
+
| 0.5118 | 4.0 | 504 | 1.1551 |
|
| 64 |
+
| 0.4711 | 5.0 | 630 | 1.1767 |
|
| 65 |
+
| 0.4287 | 6.0 | 756 | 1.1948 |
|
| 66 |
+
| 0.3943 | 7.0 | 882 | 1.2383 |
|
| 67 |
+
| 0.3612 | 8.0 | 1008 | 1.2904 |
|
| 68 |
+
| 0.3457 | 9.0 | 1134 | 1.3253 |
|
| 69 |
+
| 0.3328 | 10.0 | 1260 | 1.3326 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.7.1
|
| 75 |
+
- Transformers 4.40.1
|
| 76 |
+
- Pytorch 2.2.2+cu121
|
| 77 |
+
- Datasets 2.19.0
|
| 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 200068904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3430977fbf67d56dea82f8eb026d5d3d24e08a481959da1f646cd6eff46fca
|
| 3 |
size 200068904
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 3.8899222565240177e+18,
|
| 4 |
+
"train_loss": 1.363766341266178,
|
| 5 |
+
"train_runtime": 8098.2535,
|
| 6 |
+
"train_samples": 60531,
|
| 7 |
+
"train_samples_per_second": 4.97,
|
| 8 |
+
"train_steps_per_second": 0.156
|
| 9 |
+
}
|
runs/Apr23_22-36-57_deep-diver-main-ordinary-zebra-1-0-0/events.out.tfevents.1713926426.deep-diver-main-ordinary-zebra-1-0-0.520.0
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 sha256:10b6e287b3a6cb3f928613155dee2b20705a605137df2bde40eb9975f8e21804
|
| 3 |
+
size 61802
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 3.8899222565240177e+18,
|
| 4 |
+
"train_loss": 1.363766341266178,
|
| 5 |
+
"train_runtime": 8098.2535,
|
| 6 |
+
"train_samples": 60531,
|
| 7 |
+
"train_samples_per_second": 4.97,
|
| 8 |
+
"train_steps_per_second": 0.156
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1881 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1260,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007936507936507936,
|
| 13 |
+
"grad_norm": 300.0,
|
| 14 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 15 |
+
"loss": 44.0514,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03968253968253968,
|
| 20 |
+
"grad_norm": 294.0,
|
| 21 |
+
"learning_rate": 7.936507936507936e-06,
|
| 22 |
+
"loss": 44.4732,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07936507936507936,
|
| 27 |
+
"grad_norm": 172.0,
|
| 28 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 29 |
+
"loss": 39.0478,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11904761904761904,
|
| 34 |
+
"grad_norm": 61.5,
|
| 35 |
+
"learning_rate": 2.380952380952381e-05,
|
| 36 |
+
"loss": 27.5033,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15873015873015872,
|
| 41 |
+
"grad_norm": 19.625,
|
| 42 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 43 |
+
"loss": 19.8771,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1984126984126984,
|
| 48 |
+
"grad_norm": 12.6875,
|
| 49 |
+
"learning_rate": 3.968253968253968e-05,
|
| 50 |
+
"loss": 18.3177,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23809523809523808,
|
| 55 |
+
"grad_norm": 5.875,
|
| 56 |
+
"learning_rate": 4.761904761904762e-05,
|
| 57 |
+
"loss": 16.5284,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2777777777777778,
|
| 62 |
+
"grad_norm": 3.015625,
|
| 63 |
+
"learning_rate": 5.555555555555556e-05,
|
| 64 |
+
"loss": 15.6508,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.31746031746031744,
|
| 69 |
+
"grad_norm": 3.828125,
|
| 70 |
+
"learning_rate": 6.349206349206349e-05,
|
| 71 |
+
"loss": 14.7333,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.35714285714285715,
|
| 76 |
+
"grad_norm": 7.34375,
|
| 77 |
+
"learning_rate": 7.142857142857143e-05,
|
| 78 |
+
"loss": 14.189,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3968253968253968,
|
| 83 |
+
"grad_norm": 19.0,
|
| 84 |
+
"learning_rate": 7.936507936507937e-05,
|
| 85 |
+
"loss": 11.8511,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4365079365079365,
|
| 90 |
+
"grad_norm": 16.625,
|
| 91 |
+
"learning_rate": 8.730158730158731e-05,
|
| 92 |
+
"loss": 5.6454,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.47619047619047616,
|
| 97 |
+
"grad_norm": 2.203125,
|
| 98 |
+
"learning_rate": 9.523809523809524e-05,
|
| 99 |
+
"loss": 1.7925,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5158730158730159,
|
| 104 |
+
"grad_norm": 2.265625,
|
| 105 |
+
"learning_rate": 0.00010317460317460319,
|
| 106 |
+
"loss": 1.4147,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5555555555555556,
|
| 111 |
+
"grad_norm": 0.74609375,
|
| 112 |
+
"learning_rate": 0.00011111111111111112,
|
| 113 |
+
"loss": 1.2306,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5952380952380952,
|
| 118 |
+
"grad_norm": 2.046875,
|
| 119 |
+
"learning_rate": 0.00011904761904761905,
|
| 120 |
+
"loss": 1.1237,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6349206349206349,
|
| 125 |
+
"grad_norm": 2.0,
|
| 126 |
+
"learning_rate": 0.00012698412698412698,
|
| 127 |
+
"loss": 1.0467,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6746031746031746,
|
| 132 |
+
"grad_norm": 7.90625,
|
| 133 |
+
"learning_rate": 0.00013492063492063494,
|
| 134 |
+
"loss": 0.9706,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7142857142857143,
|
| 139 |
+
"grad_norm": 1.5078125,
|
| 140 |
+
"learning_rate": 0.00014285714285714287,
|
| 141 |
+
"loss": 0.944,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.753968253968254,
|
| 146 |
+
"grad_norm": 2.765625,
|
| 147 |
+
"learning_rate": 0.0001507936507936508,
|
| 148 |
+
"loss": 0.9101,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7936507936507936,
|
| 153 |
+
"grad_norm": 2.140625,
|
| 154 |
+
"learning_rate": 0.00015873015873015873,
|
| 155 |
+
"loss": 0.8892,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8333333333333334,
|
| 160 |
+
"grad_norm": 1.640625,
|
| 161 |
+
"learning_rate": 0.0001666666666666667,
|
| 162 |
+
"loss": 0.8475,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.873015873015873,
|
| 167 |
+
"grad_norm": 27.125,
|
| 168 |
+
"learning_rate": 0.00017460317460317462,
|
| 169 |
+
"loss": 0.8386,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9126984126984127,
|
| 174 |
+
"grad_norm": 1.8828125,
|
| 175 |
+
"learning_rate": 0.00018253968253968255,
|
| 176 |
+
"loss": 0.8187,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9523809523809523,
|
| 181 |
+
"grad_norm": 1.6015625,
|
| 182 |
+
"learning_rate": 0.00019047619047619048,
|
| 183 |
+
"loss": 0.7724,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9920634920634921,
|
| 188 |
+
"grad_norm": 1.6640625,
|
| 189 |
+
"learning_rate": 0.00019841269841269844,
|
| 190 |
+
"loss": 0.7499,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"eval_loss": 1.2579786777496338,
|
| 196 |
+
"eval_runtime": 1.0146,
|
| 197 |
+
"eval_samples_per_second": 1.971,
|
| 198 |
+
"eval_steps_per_second": 0.986,
|
| 199 |
+
"step": 126
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.0317460317460316,
|
| 203 |
+
"grad_norm": 0.453125,
|
| 204 |
+
"learning_rate": 0.00019999386012995552,
|
| 205 |
+
"loss": 0.7176,
|
| 206 |
+
"step": 130
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0714285714285714,
|
| 210 |
+
"grad_norm": 0.5078125,
|
| 211 |
+
"learning_rate": 0.00019996891820008164,
|
| 212 |
+
"loss": 0.7074,
|
| 213 |
+
"step": 135
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.1111111111111112,
|
| 217 |
+
"grad_norm": 0.609375,
|
| 218 |
+
"learning_rate": 0.00019992479525042303,
|
| 219 |
+
"loss": 0.6984,
|
| 220 |
+
"step": 140
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.1507936507936507,
|
| 224 |
+
"grad_norm": 7.375,
|
| 225 |
+
"learning_rate": 0.0001998614997468427,
|
| 226 |
+
"loss": 0.6891,
|
| 227 |
+
"step": 145
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.1904761904761905,
|
| 231 |
+
"grad_norm": 0.90625,
|
| 232 |
+
"learning_rate": 0.0001997790438338385,
|
| 233 |
+
"loss": 0.6864,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.2301587301587302,
|
| 238 |
+
"grad_norm": 0.306640625,
|
| 239 |
+
"learning_rate": 0.00019967744333221278,
|
| 240 |
+
"loss": 0.6766,
|
| 241 |
+
"step": 155
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.2698412698412698,
|
| 245 |
+
"grad_norm": 8.1875,
|
| 246 |
+
"learning_rate": 0.00019955671773603696,
|
| 247 |
+
"loss": 0.6776,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.3095238095238095,
|
| 252 |
+
"grad_norm": 2.203125,
|
| 253 |
+
"learning_rate": 0.0001994168902089112,
|
| 254 |
+
"loss": 0.6565,
|
| 255 |
+
"step": 165
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.3492063492063493,
|
| 259 |
+
"grad_norm": 0.80859375,
|
| 260 |
+
"learning_rate": 0.00019925798757952,
|
| 261 |
+
"loss": 0.6495,
|
| 262 |
+
"step": 170
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.3888888888888888,
|
| 266 |
+
"grad_norm": 1.90625,
|
| 267 |
+
"learning_rate": 0.00019908004033648453,
|
| 268 |
+
"loss": 0.6625,
|
| 269 |
+
"step": 175
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.4285714285714286,
|
| 273 |
+
"grad_norm": 1.0234375,
|
| 274 |
+
"learning_rate": 0.00019888308262251285,
|
| 275 |
+
"loss": 0.6444,
|
| 276 |
+
"step": 180
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.4682539682539684,
|
| 280 |
+
"grad_norm": 0.9609375,
|
| 281 |
+
"learning_rate": 0.00019866715222784895,
|
| 282 |
+
"loss": 0.635,
|
| 283 |
+
"step": 185
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.507936507936508,
|
| 287 |
+
"grad_norm": 1.953125,
|
| 288 |
+
"learning_rate": 0.0001984322905830219,
|
| 289 |
+
"loss": 0.6417,
|
| 290 |
+
"step": 190
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.5476190476190477,
|
| 294 |
+
"grad_norm": 1.0859375,
|
| 295 |
+
"learning_rate": 0.0001981785427508966,
|
| 296 |
+
"loss": 0.6381,
|
| 297 |
+
"step": 195
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.5873015873015874,
|
| 301 |
+
"grad_norm": 0.69140625,
|
| 302 |
+
"learning_rate": 0.00019790595741802757,
|
| 303 |
+
"loss": 0.6256,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.626984126984127,
|
| 308 |
+
"grad_norm": 0.30078125,
|
| 309 |
+
"learning_rate": 0.00019761458688531756,
|
| 310 |
+
"loss": 0.6247,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.6666666666666665,
|
| 315 |
+
"grad_norm": 0.921875,
|
| 316 |
+
"learning_rate": 0.00019730448705798239,
|
| 317 |
+
"loss": 0.6244,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.7063492063492065,
|
| 322 |
+
"grad_norm": 0.6328125,
|
| 323 |
+
"learning_rate": 0.0001969757174348246,
|
| 324 |
+
"loss": 0.6094,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.746031746031746,
|
| 329 |
+
"grad_norm": 0.76953125,
|
| 330 |
+
"learning_rate": 0.0001966283410968174,
|
| 331 |
+
"loss": 0.6156,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.7857142857142856,
|
| 336 |
+
"grad_norm": 1.1484375,
|
| 337 |
+
"learning_rate": 0.0001962624246950012,
|
| 338 |
+
"loss": 0.6037,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.8253968253968254,
|
| 343 |
+
"grad_norm": 0.984375,
|
| 344 |
+
"learning_rate": 0.0001958780384376955,
|
| 345 |
+
"loss": 0.6068,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.8650793650793651,
|
| 350 |
+
"grad_norm": 0.640625,
|
| 351 |
+
"learning_rate": 0.00019547525607702774,
|
| 352 |
+
"loss": 0.5994,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.9047619047619047,
|
| 357 |
+
"grad_norm": 1.8203125,
|
| 358 |
+
"learning_rate": 0.0001950541548947829,
|
| 359 |
+
"loss": 0.6115,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.9444444444444444,
|
| 364 |
+
"grad_norm": 0.30078125,
|
| 365 |
+
"learning_rate": 0.00019461481568757506,
|
| 366 |
+
"loss": 0.598,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.9841269841269842,
|
| 371 |
+
"grad_norm": 0.396484375,
|
| 372 |
+
"learning_rate": 0.00019415732275134513,
|
| 373 |
+
"loss": 0.6058,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.0,
|
| 378 |
+
"eval_loss": 1.1687145233154297,
|
| 379 |
+
"eval_runtime": 1.0157,
|
| 380 |
+
"eval_samples_per_second": 1.969,
|
| 381 |
+
"eval_steps_per_second": 0.985,
|
| 382 |
+
"step": 252
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.0238095238095237,
|
| 386 |
+
"grad_norm": 0.458984375,
|
| 387 |
+
"learning_rate": 0.0001936817638651871,
|
| 388 |
+
"loss": 0.5677,
|
| 389 |
+
"step": 255
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.0634920634920633,
|
| 393 |
+
"grad_norm": 0.5078125,
|
| 394 |
+
"learning_rate": 0.0001931882302745057,
|
| 395 |
+
"loss": 0.5648,
|
| 396 |
+
"step": 260
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.1031746031746033,
|
| 400 |
+
"grad_norm": 0.66796875,
|
| 401 |
+
"learning_rate": 0.00019267681667350928,
|
| 402 |
+
"loss": 0.5502,
|
| 403 |
+
"step": 265
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.142857142857143,
|
| 407 |
+
"grad_norm": 0.48828125,
|
| 408 |
+
"learning_rate": 0.00019214762118704076,
|
| 409 |
+
"loss": 0.5573,
|
| 410 |
+
"step": 270
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.1825396825396823,
|
| 414 |
+
"grad_norm": 0.26953125,
|
| 415 |
+
"learning_rate": 0.00019160074535175058,
|
| 416 |
+
"loss": 0.5622,
|
| 417 |
+
"step": 275
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.2222222222222223,
|
| 421 |
+
"grad_norm": 0.291015625,
|
| 422 |
+
"learning_rate": 0.0001910362940966147,
|
| 423 |
+
"loss": 0.5586,
|
| 424 |
+
"step": 280
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.261904761904762,
|
| 428 |
+
"grad_norm": 0.3984375,
|
| 429 |
+
"learning_rate": 0.00019045437572280194,
|
| 430 |
+
"loss": 0.5545,
|
| 431 |
+
"step": 285
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.3015873015873014,
|
| 435 |
+
"grad_norm": 0.34765625,
|
| 436 |
+
"learning_rate": 0.0001898551018828944,
|
| 437 |
+
"loss": 0.5489,
|
| 438 |
+
"step": 290
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.3412698412698414,
|
| 442 |
+
"grad_norm": 0.275390625,
|
| 443 |
+
"learning_rate": 0.0001892385875594645,
|
| 444 |
+
"loss": 0.5577,
|
| 445 |
+
"step": 295
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.380952380952381,
|
| 449 |
+
"grad_norm": 0.2578125,
|
| 450 |
+
"learning_rate": 0.00018860495104301345,
|
| 451 |
+
"loss": 0.5462,
|
| 452 |
+
"step": 300
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.4206349206349205,
|
| 456 |
+
"grad_norm": 0.38671875,
|
| 457 |
+
"learning_rate": 0.0001879543139092747,
|
| 458 |
+
"loss": 0.557,
|
| 459 |
+
"step": 305
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.4603174603174605,
|
| 463 |
+
"grad_norm": 0.44921875,
|
| 464 |
+
"learning_rate": 0.00018728680099588748,
|
| 465 |
+
"loss": 0.5531,
|
| 466 |
+
"step": 310
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.5,
|
| 470 |
+
"grad_norm": 0.27734375,
|
| 471 |
+
"learning_rate": 0.00018660254037844388,
|
| 472 |
+
"loss": 0.5597,
|
| 473 |
+
"step": 315
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.5396825396825395,
|
| 477 |
+
"grad_norm": 0.71484375,
|
| 478 |
+
"learning_rate": 0.00018590166334591531,
|
| 479 |
+
"loss": 0.5578,
|
| 480 |
+
"step": 320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.5793650793650795,
|
| 484 |
+
"grad_norm": 0.375,
|
| 485 |
+
"learning_rate": 0.000185184304375462,
|
| 486 |
+
"loss": 0.5546,
|
| 487 |
+
"step": 325
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.619047619047619,
|
| 491 |
+
"grad_norm": 0.2109375,
|
| 492 |
+
"learning_rate": 0.0001844506011066308,
|
| 493 |
+
"loss": 0.5532,
|
| 494 |
+
"step": 330
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.6587301587301586,
|
| 498 |
+
"grad_norm": 0.349609375,
|
| 499 |
+
"learning_rate": 0.00018370069431494646,
|
| 500 |
+
"loss": 0.5509,
|
| 501 |
+
"step": 335
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.6984126984126986,
|
| 505 |
+
"grad_norm": 0.27734375,
|
| 506 |
+
"learning_rate": 0.00018293472788490095,
|
| 507 |
+
"loss": 0.5479,
|
| 508 |
+
"step": 340
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.738095238095238,
|
| 512 |
+
"grad_norm": 0.279296875,
|
| 513 |
+
"learning_rate": 0.00018215284878234642,
|
| 514 |
+
"loss": 0.5505,
|
| 515 |
+
"step": 345
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.7777777777777777,
|
| 519 |
+
"grad_norm": 0.28125,
|
| 520 |
+
"learning_rate": 0.00018135520702629675,
|
| 521 |
+
"loss": 0.5466,
|
| 522 |
+
"step": 350
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.817460317460317,
|
| 526 |
+
"grad_norm": 0.373046875,
|
| 527 |
+
"learning_rate": 0.0001805419556601437,
|
| 528 |
+
"loss": 0.5548,
|
| 529 |
+
"step": 355
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.857142857142857,
|
| 533 |
+
"grad_norm": 0.25,
|
| 534 |
+
"learning_rate": 0.00017971325072229226,
|
| 535 |
+
"loss": 0.5521,
|
| 536 |
+
"step": 360
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.8968253968253967,
|
| 540 |
+
"grad_norm": 0.318359375,
|
| 541 |
+
"learning_rate": 0.0001788692512162216,
|
| 542 |
+
"loss": 0.5413,
|
| 543 |
+
"step": 365
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.9365079365079367,
|
| 547 |
+
"grad_norm": 0.390625,
|
| 548 |
+
"learning_rate": 0.00017801011907997725,
|
| 549 |
+
"loss": 0.5546,
|
| 550 |
+
"step": 370
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.9761904761904763,
|
| 554 |
+
"grad_norm": 0.26171875,
|
| 555 |
+
"learning_rate": 0.0001771360191551,
|
| 556 |
+
"loss": 0.5571,
|
| 557 |
+
"step": 375
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 3.0,
|
| 561 |
+
"eval_loss": 1.1491789817810059,
|
| 562 |
+
"eval_runtime": 1.0142,
|
| 563 |
+
"eval_samples_per_second": 1.972,
|
| 564 |
+
"eval_steps_per_second": 0.986,
|
| 565 |
+
"step": 378
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 3.015873015873016,
|
| 569 |
+
"grad_norm": 0.30859375,
|
| 570 |
+
"learning_rate": 0.00017624711915499764,
|
| 571 |
+
"loss": 0.5262,
|
| 572 |
+
"step": 380
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.0555555555555554,
|
| 576 |
+
"grad_norm": 0.2734375,
|
| 577 |
+
"learning_rate": 0.00017534358963276607,
|
| 578 |
+
"loss": 0.5035,
|
| 579 |
+
"step": 385
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.0952380952380953,
|
| 583 |
+
"grad_norm": 0.203125,
|
| 584 |
+
"learning_rate": 0.00017442560394846516,
|
| 585 |
+
"loss": 0.5017,
|
| 586 |
+
"step": 390
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 3.134920634920635,
|
| 590 |
+
"grad_norm": 0.21484375,
|
| 591 |
+
"learning_rate": 0.00017349333823585617,
|
| 592 |
+
"loss": 0.5052,
|
| 593 |
+
"step": 395
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.1746031746031744,
|
| 597 |
+
"grad_norm": 0.232421875,
|
| 598 |
+
"learning_rate": 0.00017254697136860703,
|
| 599 |
+
"loss": 0.5056,
|
| 600 |
+
"step": 400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.2142857142857144,
|
| 604 |
+
"grad_norm": 0.333984375,
|
| 605 |
+
"learning_rate": 0.00017158668492597186,
|
| 606 |
+
"loss": 0.5199,
|
| 607 |
+
"step": 405
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 3.253968253968254,
|
| 611 |
+
"grad_norm": 0.2216796875,
|
| 612 |
+
"learning_rate": 0.00017061266315795146,
|
| 613 |
+
"loss": 0.5038,
|
| 614 |
+
"step": 410
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.2936507936507935,
|
| 618 |
+
"grad_norm": 0.333984375,
|
| 619 |
+
"learning_rate": 0.0001696250929499412,
|
| 620 |
+
"loss": 0.501,
|
| 621 |
+
"step": 415
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 3.3333333333333335,
|
| 625 |
+
"grad_norm": 0.79296875,
|
| 626 |
+
"learning_rate": 0.0001686241637868734,
|
| 627 |
+
"loss": 0.5044,
|
| 628 |
+
"step": 420
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 3.373015873015873,
|
| 632 |
+
"grad_norm": 0.4296875,
|
| 633 |
+
"learning_rate": 0.0001676100677168608,
|
| 634 |
+
"loss": 0.4998,
|
| 635 |
+
"step": 425
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.4126984126984126,
|
| 639 |
+
"grad_norm": 0.265625,
|
| 640 |
+
"learning_rate": 0.00016658299931434858,
|
| 641 |
+
"loss": 0.5172,
|
| 642 |
+
"step": 430
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 3.4523809523809526,
|
| 646 |
+
"grad_norm": 0.212890625,
|
| 647 |
+
"learning_rate": 0.000165543155642781,
|
| 648 |
+
"loss": 0.5082,
|
| 649 |
+
"step": 435
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.492063492063492,
|
| 653 |
+
"grad_norm": 0.22265625,
|
| 654 |
+
"learning_rate": 0.00016449073621679127,
|
| 655 |
+
"loss": 0.5016,
|
| 656 |
+
"step": 440
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.5317460317460316,
|
| 660 |
+
"grad_norm": 0.1865234375,
|
| 661 |
+
"learning_rate": 0.0001634259429639203,
|
| 662 |
+
"loss": 0.5109,
|
| 663 |
+
"step": 445
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.571428571428571,
|
| 667 |
+
"grad_norm": 0.197265625,
|
| 668 |
+
"learning_rate": 0.00016234898018587337,
|
| 669 |
+
"loss": 0.5178,
|
| 670 |
+
"step": 450
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 3.611111111111111,
|
| 674 |
+
"grad_norm": 0.267578125,
|
| 675 |
+
"learning_rate": 0.0001612600545193203,
|
| 676 |
+
"loss": 0.5163,
|
| 677 |
+
"step": 455
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.6507936507936507,
|
| 681 |
+
"grad_norm": 0.29296875,
|
| 682 |
+
"learning_rate": 0.00016015937489624848,
|
| 683 |
+
"loss": 0.5078,
|
| 684 |
+
"step": 460
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.6904761904761907,
|
| 688 |
+
"grad_norm": 0.25,
|
| 689 |
+
"learning_rate": 0.00015904715250387498,
|
| 690 |
+
"loss": 0.508,
|
| 691 |
+
"step": 465
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.7301587301587302,
|
| 695 |
+
"grad_norm": 0.2890625,
|
| 696 |
+
"learning_rate": 0.00015792360074412613,
|
| 697 |
+
"loss": 0.5055,
|
| 698 |
+
"step": 470
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.7698412698412698,
|
| 702 |
+
"grad_norm": 0.19140625,
|
| 703 |
+
"learning_rate": 0.00015678893519269197,
|
| 704 |
+
"loss": 0.5083,
|
| 705 |
+
"step": 475
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.8095238095238093,
|
| 709 |
+
"grad_norm": 0.322265625,
|
| 710 |
+
"learning_rate": 0.00015564337355766412,
|
| 711 |
+
"loss": 0.5121,
|
| 712 |
+
"step": 480
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.8492063492063493,
|
| 716 |
+
"grad_norm": 0.2109375,
|
| 717 |
+
"learning_rate": 0.00015448713563776374,
|
| 718 |
+
"loss": 0.4984,
|
| 719 |
+
"step": 485
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.888888888888889,
|
| 723 |
+
"grad_norm": 0.412109375,
|
| 724 |
+
"learning_rate": 0.00015332044328016914,
|
| 725 |
+
"loss": 0.5044,
|
| 726 |
+
"step": 490
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 3.928571428571429,
|
| 730 |
+
"grad_norm": 0.44140625,
|
| 731 |
+
"learning_rate": 0.0001521435203379498,
|
| 732 |
+
"loss": 0.5127,
|
| 733 |
+
"step": 495
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 3.9682539682539684,
|
| 737 |
+
"grad_norm": 0.54296875,
|
| 738 |
+
"learning_rate": 0.0001509565926271159,
|
| 739 |
+
"loss": 0.5118,
|
| 740 |
+
"step": 500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.0,
|
| 744 |
+
"eval_loss": 1.155090570449829,
|
| 745 |
+
"eval_runtime": 1.0165,
|
| 746 |
+
"eval_samples_per_second": 1.968,
|
| 747 |
+
"eval_steps_per_second": 0.984,
|
| 748 |
+
"step": 504
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.007936507936508,
|
| 752 |
+
"grad_norm": 0.97265625,
|
| 753 |
+
"learning_rate": 0.00014975988788329064,
|
| 754 |
+
"loss": 0.4977,
|
| 755 |
+
"step": 505
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 4.0476190476190474,
|
| 759 |
+
"grad_norm": 0.515625,
|
| 760 |
+
"learning_rate": 0.00014855363571801523,
|
| 761 |
+
"loss": 0.4642,
|
| 762 |
+
"step": 510
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 4.087301587301587,
|
| 766 |
+
"grad_norm": 0.251953125,
|
| 767 |
+
"learning_rate": 0.00014733806757469286,
|
| 768 |
+
"loss": 0.457,
|
| 769 |
+
"step": 515
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.1269841269841265,
|
| 773 |
+
"grad_norm": 0.51953125,
|
| 774 |
+
"learning_rate": 0.000146113416684182,
|
| 775 |
+
"loss": 0.4674,
|
| 776 |
+
"step": 520
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 4.166666666666667,
|
| 780 |
+
"grad_norm": 0.259765625,
|
| 781 |
+
"learning_rate": 0.00014487991802004623,
|
| 782 |
+
"loss": 0.4608,
|
| 783 |
+
"step": 525
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.2063492063492065,
|
| 787 |
+
"grad_norm": 0.45703125,
|
| 788 |
+
"learning_rate": 0.00014363780825347005,
|
| 789 |
+
"loss": 0.4601,
|
| 790 |
+
"step": 530
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 4.246031746031746,
|
| 794 |
+
"grad_norm": 0.408203125,
|
| 795 |
+
"learning_rate": 0.00014238732570784866,
|
| 796 |
+
"loss": 0.4656,
|
| 797 |
+
"step": 535
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 4.285714285714286,
|
| 801 |
+
"grad_norm": 0.263671875,
|
| 802 |
+
"learning_rate": 0.00014112871031306119,
|
| 803 |
+
"loss": 0.4661,
|
| 804 |
+
"step": 540
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 4.325396825396825,
|
| 808 |
+
"grad_norm": 0.42578125,
|
| 809 |
+
"learning_rate": 0.00013986220355943494,
|
| 810 |
+
"loss": 0.4652,
|
| 811 |
+
"step": 545
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.365079365079365,
|
| 815 |
+
"grad_norm": 0.5,
|
| 816 |
+
"learning_rate": 0.00013858804845141116,
|
| 817 |
+
"loss": 0.4667,
|
| 818 |
+
"step": 550
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.404761904761905,
|
| 822 |
+
"grad_norm": 0.205078125,
|
| 823 |
+
"learning_rate": 0.0001373064894609194,
|
| 824 |
+
"loss": 0.469,
|
| 825 |
+
"step": 555
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.444444444444445,
|
| 829 |
+
"grad_norm": 0.59375,
|
| 830 |
+
"learning_rate": 0.00013601777248047105,
|
| 831 |
+
"loss": 0.4654,
|
| 832 |
+
"step": 560
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 4.484126984126984,
|
| 836 |
+
"grad_norm": 0.298828125,
|
| 837 |
+
"learning_rate": 0.00013472214477597977,
|
| 838 |
+
"loss": 0.4662,
|
| 839 |
+
"step": 565
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 4.523809523809524,
|
| 843 |
+
"grad_norm": 0.28515625,
|
| 844 |
+
"learning_rate": 0.00013341985493931877,
|
| 845 |
+
"loss": 0.4669,
|
| 846 |
+
"step": 570
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 4.563492063492063,
|
| 850 |
+
"grad_norm": 0.3125,
|
| 851 |
+
"learning_rate": 0.00013211115284062335,
|
| 852 |
+
"loss": 0.465,
|
| 853 |
+
"step": 575
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 4.603174603174603,
|
| 857 |
+
"grad_norm": 0.30859375,
|
| 858 |
+
"learning_rate": 0.00013079628958034855,
|
| 859 |
+
"loss": 0.4696,
|
| 860 |
+
"step": 580
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 4.642857142857143,
|
| 864 |
+
"grad_norm": 0.38671875,
|
| 865 |
+
"learning_rate": 0.00012947551744109043,
|
| 866 |
+
"loss": 0.4837,
|
| 867 |
+
"step": 585
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 4.682539682539683,
|
| 871 |
+
"grad_norm": 0.75390625,
|
| 872 |
+
"learning_rate": 0.00012814908983918073,
|
| 873 |
+
"loss": 0.4752,
|
| 874 |
+
"step": 590
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 4.722222222222222,
|
| 878 |
+
"grad_norm": 0.59375,
|
| 879 |
+
"learning_rate": 0.00012681726127606376,
|
| 880 |
+
"loss": 0.4678,
|
| 881 |
+
"step": 595
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 4.761904761904762,
|
| 885 |
+
"grad_norm": 0.306640625,
|
| 886 |
+
"learning_rate": 0.0001254802872894655,
|
| 887 |
+
"loss": 0.4753,
|
| 888 |
+
"step": 600
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 4.801587301587301,
|
| 892 |
+
"grad_norm": 0.333984375,
|
| 893 |
+
"learning_rate": 0.00012413842440436333,
|
| 894 |
+
"loss": 0.473,
|
| 895 |
+
"step": 605
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 4.841269841269841,
|
| 899 |
+
"grad_norm": 0.353515625,
|
| 900 |
+
"learning_rate": 0.000122791930083767,
|
| 901 |
+
"loss": 0.4646,
|
| 902 |
+
"step": 610
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.880952380952381,
|
| 906 |
+
"grad_norm": 0.224609375,
|
| 907 |
+
"learning_rate": 0.00012144106267931876,
|
| 908 |
+
"loss": 0.4715,
|
| 909 |
+
"step": 615
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.920634920634921,
|
| 913 |
+
"grad_norm": 0.2734375,
|
| 914 |
+
"learning_rate": 0.00012008608138172393,
|
| 915 |
+
"loss": 0.4704,
|
| 916 |
+
"step": 620
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.9603174603174605,
|
| 920 |
+
"grad_norm": 0.31640625,
|
| 921 |
+
"learning_rate": 0.00011872724617101969,
|
| 922 |
+
"loss": 0.4657,
|
| 923 |
+
"step": 625
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 5.0,
|
| 927 |
+
"grad_norm": 0.224609375,
|
| 928 |
+
"learning_rate": 0.00011736481776669306,
|
| 929 |
+
"loss": 0.4711,
|
| 930 |
+
"step": 630
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.0,
|
| 934 |
+
"eval_loss": 1.1766771078109741,
|
| 935 |
+
"eval_runtime": 1.015,
|
| 936 |
+
"eval_samples_per_second": 1.971,
|
| 937 |
+
"eval_steps_per_second": 0.985,
|
| 938 |
+
"step": 630
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 5.0396825396825395,
|
| 942 |
+
"grad_norm": 0.2890625,
|
| 943 |
+
"learning_rate": 0.0001159990575776563,
|
| 944 |
+
"loss": 0.4228,
|
| 945 |
+
"step": 635
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 5.079365079365079,
|
| 949 |
+
"grad_norm": 0.3125,
|
| 950 |
+
"learning_rate": 0.00011463022765209088,
|
| 951 |
+
"loss": 0.4163,
|
| 952 |
+
"step": 640
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 5.119047619047619,
|
| 956 |
+
"grad_norm": 0.353515625,
|
| 957 |
+
"learning_rate": 0.00011325859062716795,
|
| 958 |
+
"loss": 0.4213,
|
| 959 |
+
"step": 645
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 5.158730158730159,
|
| 963 |
+
"grad_norm": 0.365234375,
|
| 964 |
+
"learning_rate": 0.00011188440967865641,
|
| 965 |
+
"loss": 0.4319,
|
| 966 |
+
"step": 650
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.198412698412699,
|
| 970 |
+
"grad_norm": 0.3203125,
|
| 971 |
+
"learning_rate": 0.00011050794847042731,
|
| 972 |
+
"loss": 0.4258,
|
| 973 |
+
"step": 655
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 5.238095238095238,
|
| 977 |
+
"grad_norm": 0.26953125,
|
| 978 |
+
"learning_rate": 0.00010912947110386484,
|
| 979 |
+
"loss": 0.4237,
|
| 980 |
+
"step": 660
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 5.277777777777778,
|
| 984 |
+
"grad_norm": 0.5078125,
|
| 985 |
+
"learning_rate": 0.0001077492420671931,
|
| 986 |
+
"loss": 0.4238,
|
| 987 |
+
"step": 665
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 5.317460317460317,
|
| 991 |
+
"grad_norm": 0.22265625,
|
| 992 |
+
"learning_rate": 0.00010636752618472887,
|
| 993 |
+
"loss": 0.4225,
|
| 994 |
+
"step": 670
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 5.357142857142857,
|
| 998 |
+
"grad_norm": 0.2451171875,
|
| 999 |
+
"learning_rate": 0.00010498458856606972,
|
| 1000 |
+
"loss": 0.4214,
|
| 1001 |
+
"step": 675
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.396825396825397,
|
| 1005 |
+
"grad_norm": 0.283203125,
|
| 1006 |
+
"learning_rate": 0.00010360069455522765,
|
| 1007 |
+
"loss": 0.425,
|
| 1008 |
+
"step": 680
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 5.436507936507937,
|
| 1012 |
+
"grad_norm": 0.43359375,
|
| 1013 |
+
"learning_rate": 0.00010221610967971735,
|
| 1014 |
+
"loss": 0.4281,
|
| 1015 |
+
"step": 685
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 5.476190476190476,
|
| 1019 |
+
"grad_norm": 0.275390625,
|
| 1020 |
+
"learning_rate": 0.00010083109959960973,
|
| 1021 |
+
"loss": 0.427,
|
| 1022 |
+
"step": 690
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 5.515873015873016,
|
| 1026 |
+
"grad_norm": 0.2099609375,
|
| 1027 |
+
"learning_rate": 9.944593005655947e-05,
|
| 1028 |
+
"loss": 0.4299,
|
| 1029 |
+
"step": 695
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 5.555555555555555,
|
| 1033 |
+
"grad_norm": 0.216796875,
|
| 1034 |
+
"learning_rate": 9.806086682281758e-05,
|
| 1035 |
+
"loss": 0.4413,
|
| 1036 |
+
"step": 700
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 5.595238095238095,
|
| 1040 |
+
"grad_norm": 0.2158203125,
|
| 1041 |
+
"learning_rate": 9.667617565023735e-05,
|
| 1042 |
+
"loss": 0.4352,
|
| 1043 |
+
"step": 705
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 5.634920634920634,
|
| 1047 |
+
"grad_norm": 0.2578125,
|
| 1048 |
+
"learning_rate": 9.529212221928483e-05,
|
| 1049 |
+
"loss": 0.4337,
|
| 1050 |
+
"step": 710
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 5.674603174603175,
|
| 1054 |
+
"grad_norm": 0.2294921875,
|
| 1055 |
+
"learning_rate": 9.390897208806266e-05,
|
| 1056 |
+
"loss": 0.4242,
|
| 1057 |
+
"step": 715
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 5.714285714285714,
|
| 1061 |
+
"grad_norm": 0.365234375,
|
| 1062 |
+
"learning_rate": 9.252699064135758e-05,
|
| 1063 |
+
"loss": 0.4286,
|
| 1064 |
+
"step": 720
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 5.753968253968254,
|
| 1068 |
+
"grad_norm": 0.5078125,
|
| 1069 |
+
"learning_rate": 9.114644303972096e-05,
|
| 1070 |
+
"loss": 0.4349,
|
| 1071 |
+
"step": 725
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 5.7936507936507935,
|
| 1075 |
+
"grad_norm": 0.318359375,
|
| 1076 |
+
"learning_rate": 8.976759416859256e-05,
|
| 1077 |
+
"loss": 0.4311,
|
| 1078 |
+
"step": 730
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 5.833333333333333,
|
| 1082 |
+
"grad_norm": 0.2470703125,
|
| 1083 |
+
"learning_rate": 8.839070858747697e-05,
|
| 1084 |
+
"loss": 0.4257,
|
| 1085 |
+
"step": 735
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 5.8730158730158735,
|
| 1089 |
+
"grad_norm": 0.236328125,
|
| 1090 |
+
"learning_rate": 8.701605047918276e-05,
|
| 1091 |
+
"loss": 0.4332,
|
| 1092 |
+
"step": 740
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 5.912698412698413,
|
| 1096 |
+
"grad_norm": 0.2255859375,
|
| 1097 |
+
"learning_rate": 8.564388359913356e-05,
|
| 1098 |
+
"loss": 0.4309,
|
| 1099 |
+
"step": 745
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 5.9523809523809526,
|
| 1103 |
+
"grad_norm": 0.2138671875,
|
| 1104 |
+
"learning_rate": 8.427447122476148e-05,
|
| 1105 |
+
"loss": 0.4311,
|
| 1106 |
+
"step": 750
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 5.992063492063492,
|
| 1110 |
+
"grad_norm": 0.244140625,
|
| 1111 |
+
"learning_rate": 8.290807610499206e-05,
|
| 1112 |
+
"loss": 0.4287,
|
| 1113 |
+
"step": 755
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.0,
|
| 1117 |
+
"eval_loss": 1.1948192119598389,
|
| 1118 |
+
"eval_runtime": 1.0151,
|
| 1119 |
+
"eval_samples_per_second": 1.97,
|
| 1120 |
+
"eval_steps_per_second": 0.985,
|
| 1121 |
+
"step": 756
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 6.031746031746032,
|
| 1125 |
+
"grad_norm": 0.265625,
|
| 1126 |
+
"learning_rate": 8.154496040983073e-05,
|
| 1127 |
+
"loss": 0.3917,
|
| 1128 |
+
"step": 760
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 6.071428571428571,
|
| 1132 |
+
"grad_norm": 0.322265625,
|
| 1133 |
+
"learning_rate": 8.018538568006027e-05,
|
| 1134 |
+
"loss": 0.3851,
|
| 1135 |
+
"step": 765
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 6.111111111111111,
|
| 1139 |
+
"grad_norm": 0.267578125,
|
| 1140 |
+
"learning_rate": 7.882961277705895e-05,
|
| 1141 |
+
"loss": 0.3846,
|
| 1142 |
+
"step": 770
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 6.150793650793651,
|
| 1146 |
+
"grad_norm": 0.392578125,
|
| 1147 |
+
"learning_rate": 7.747790183274922e-05,
|
| 1148 |
+
"loss": 0.3897,
|
| 1149 |
+
"step": 775
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.190476190476191,
|
| 1153 |
+
"grad_norm": 0.25,
|
| 1154 |
+
"learning_rate": 7.613051219968623e-05,
|
| 1155 |
+
"loss": 0.3894,
|
| 1156 |
+
"step": 780
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.23015873015873,
|
| 1160 |
+
"grad_norm": 0.30859375,
|
| 1161 |
+
"learning_rate": 7.478770240129579e-05,
|
| 1162 |
+
"loss": 0.386,
|
| 1163 |
+
"step": 785
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 6.26984126984127,
|
| 1167 |
+
"grad_norm": 0.29296875,
|
| 1168 |
+
"learning_rate": 7.344973008227161e-05,
|
| 1169 |
+
"loss": 0.383,
|
| 1170 |
+
"step": 790
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 6.309523809523809,
|
| 1174 |
+
"grad_norm": 0.265625,
|
| 1175 |
+
"learning_rate": 7.211685195914097e-05,
|
| 1176 |
+
"loss": 0.3867,
|
| 1177 |
+
"step": 795
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 6.349206349206349,
|
| 1181 |
+
"grad_norm": 0.263671875,
|
| 1182 |
+
"learning_rate": 7.078932377100877e-05,
|
| 1183 |
+
"loss": 0.393,
|
| 1184 |
+
"step": 800
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 6.388888888888889,
|
| 1188 |
+
"grad_norm": 0.345703125,
|
| 1189 |
+
"learning_rate": 6.94674002304887e-05,
|
| 1190 |
+
"loss": 0.3856,
|
| 1191 |
+
"step": 805
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 6.428571428571429,
|
| 1195 |
+
"grad_norm": 0.2255859375,
|
| 1196 |
+
"learning_rate": 6.815133497483157e-05,
|
| 1197 |
+
"loss": 0.397,
|
| 1198 |
+
"step": 810
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 6.468253968253968,
|
| 1202 |
+
"grad_norm": 0.302734375,
|
| 1203 |
+
"learning_rate": 6.684138051726012e-05,
|
| 1204 |
+
"loss": 0.3879,
|
| 1205 |
+
"step": 815
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 6.507936507936508,
|
| 1209 |
+
"grad_norm": 0.248046875,
|
| 1210 |
+
"learning_rate": 6.553778819851926e-05,
|
| 1211 |
+
"loss": 0.3852,
|
| 1212 |
+
"step": 820
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.5476190476190474,
|
| 1216 |
+
"grad_norm": 0.24609375,
|
| 1217 |
+
"learning_rate": 6.424080813865138e-05,
|
| 1218 |
+
"loss": 0.3956,
|
| 1219 |
+
"step": 825
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 6.587301587301587,
|
| 1223 |
+
"grad_norm": 0.4296875,
|
| 1224 |
+
"learning_rate": 6.295068918900586e-05,
|
| 1225 |
+
"loss": 0.394,
|
| 1226 |
+
"step": 830
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 6.6269841269841265,
|
| 1230 |
+
"grad_norm": 0.2392578125,
|
| 1231 |
+
"learning_rate": 6.16676788844919e-05,
|
| 1232 |
+
"loss": 0.3904,
|
| 1233 |
+
"step": 835
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 6.666666666666667,
|
| 1237 |
+
"grad_norm": 0.33984375,
|
| 1238 |
+
"learning_rate": 6.039202339608432e-05,
|
| 1239 |
+
"loss": 0.395,
|
| 1240 |
+
"step": 840
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 6.7063492063492065,
|
| 1244 |
+
"grad_norm": 0.326171875,
|
| 1245 |
+
"learning_rate": 5.912396748359046e-05,
|
| 1246 |
+
"loss": 0.3892,
|
| 1247 |
+
"step": 845
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 6.746031746031746,
|
| 1251 |
+
"grad_norm": 0.337890625,
|
| 1252 |
+
"learning_rate": 5.786375444868828e-05,
|
| 1253 |
+
"loss": 0.3945,
|
| 1254 |
+
"step": 850
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 6.785714285714286,
|
| 1258 |
+
"grad_norm": 0.443359375,
|
| 1259 |
+
"learning_rate": 5.6611626088244194e-05,
|
| 1260 |
+
"loss": 0.3948,
|
| 1261 |
+
"step": 855
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 6.825396825396825,
|
| 1265 |
+
"grad_norm": 0.314453125,
|
| 1266 |
+
"learning_rate": 5.5367822647919424e-05,
|
| 1267 |
+
"loss": 0.3953,
|
| 1268 |
+
"step": 860
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 6.865079365079366,
|
| 1272 |
+
"grad_norm": 0.283203125,
|
| 1273 |
+
"learning_rate": 5.4132582776074126e-05,
|
| 1274 |
+
"loss": 0.3983,
|
| 1275 |
+
"step": 865
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 6.904761904761905,
|
| 1279 |
+
"grad_norm": 0.236328125,
|
| 1280 |
+
"learning_rate": 5.290614347797802e-05,
|
| 1281 |
+
"loss": 0.3862,
|
| 1282 |
+
"step": 870
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 6.944444444444445,
|
| 1286 |
+
"grad_norm": 0.2431640625,
|
| 1287 |
+
"learning_rate": 5.168874007033615e-05,
|
| 1288 |
+
"loss": 0.39,
|
| 1289 |
+
"step": 875
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.984126984126984,
|
| 1293 |
+
"grad_norm": 0.232421875,
|
| 1294 |
+
"learning_rate": 5.048060613613888e-05,
|
| 1295 |
+
"loss": 0.3943,
|
| 1296 |
+
"step": 880
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 7.0,
|
| 1300 |
+
"eval_loss": 1.2383077144622803,
|
| 1301 |
+
"eval_runtime": 1.0141,
|
| 1302 |
+
"eval_samples_per_second": 1.972,
|
| 1303 |
+
"eval_steps_per_second": 0.986,
|
| 1304 |
+
"step": 882
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 7.023809523809524,
|
| 1308 |
+
"grad_norm": 0.2216796875,
|
| 1309 |
+
"learning_rate": 4.92819734798441e-05,
|
| 1310 |
+
"loss": 0.3718,
|
| 1311 |
+
"step": 885
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 7.063492063492063,
|
| 1315 |
+
"grad_norm": 0.41015625,
|
| 1316 |
+
"learning_rate": 4.809307208290114e-05,
|
| 1317 |
+
"loss": 0.3505,
|
| 1318 |
+
"step": 890
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 7.103174603174603,
|
| 1322 |
+
"grad_norm": 0.236328125,
|
| 1323 |
+
"learning_rate": 4.691413005962415e-05,
|
| 1324 |
+
"loss": 0.3559,
|
| 1325 |
+
"step": 895
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 7.142857142857143,
|
| 1329 |
+
"grad_norm": 0.248046875,
|
| 1330 |
+
"learning_rate": 4.574537361342407e-05,
|
| 1331 |
+
"loss": 0.3581,
|
| 1332 |
+
"step": 900
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 7.182539682539683,
|
| 1336 |
+
"grad_norm": 0.224609375,
|
| 1337 |
+
"learning_rate": 4.458702699340667e-05,
|
| 1338 |
+
"loss": 0.3601,
|
| 1339 |
+
"step": 905
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 7.222222222222222,
|
| 1343 |
+
"grad_norm": 0.259765625,
|
| 1344 |
+
"learning_rate": 4.343931245134616e-05,
|
| 1345 |
+
"loss": 0.3587,
|
| 1346 |
+
"step": 910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 7.261904761904762,
|
| 1350 |
+
"grad_norm": 0.240234375,
|
| 1351 |
+
"learning_rate": 4.23024501990417e-05,
|
| 1352 |
+
"loss": 0.3589,
|
| 1353 |
+
"step": 915
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 7.301587301587301,
|
| 1357 |
+
"grad_norm": 0.26171875,
|
| 1358 |
+
"learning_rate": 4.117665836606549e-05,
|
| 1359 |
+
"loss": 0.3595,
|
| 1360 |
+
"step": 920
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 7.341269841269841,
|
| 1364 |
+
"grad_norm": 0.259765625,
|
| 1365 |
+
"learning_rate": 4.00621529579101e-05,
|
| 1366 |
+
"loss": 0.359,
|
| 1367 |
+
"step": 925
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 7.380952380952381,
|
| 1371 |
+
"grad_norm": 0.24609375,
|
| 1372 |
+
"learning_rate": 3.89591478145437e-05,
|
| 1373 |
+
"loss": 0.3637,
|
| 1374 |
+
"step": 930
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 7.420634920634921,
|
| 1378 |
+
"grad_norm": 0.26953125,
|
| 1379 |
+
"learning_rate": 3.786785456938049e-05,
|
| 1380 |
+
"loss": 0.3667,
|
| 1381 |
+
"step": 935
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 7.4603174603174605,
|
| 1385 |
+
"grad_norm": 0.26171875,
|
| 1386 |
+
"learning_rate": 3.6788482608674826e-05,
|
| 1387 |
+
"loss": 0.3566,
|
| 1388 |
+
"step": 940
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 7.5,
|
| 1392 |
+
"grad_norm": 0.248046875,
|
| 1393 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 1394 |
+
"loss": 0.3538,
|
| 1395 |
+
"step": 945
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 7.5396825396825395,
|
| 1399 |
+
"grad_norm": 0.2392578125,
|
| 1400 |
+
"learning_rate": 3.4666328609242725e-05,
|
| 1401 |
+
"loss": 0.3564,
|
| 1402 |
+
"step": 950
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 7.579365079365079,
|
| 1406 |
+
"grad_norm": 0.2421875,
|
| 1407 |
+
"learning_rate": 3.362395374785283e-05,
|
| 1408 |
+
"loss": 0.3588,
|
| 1409 |
+
"step": 955
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 7.619047619047619,
|
| 1413 |
+
"grad_norm": 0.25390625,
|
| 1414 |
+
"learning_rate": 3.259431444746846e-05,
|
| 1415 |
+
"loss": 0.3617,
|
| 1416 |
+
"step": 960
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 7.658730158730159,
|
| 1420 |
+
"grad_norm": 0.2470703125,
|
| 1421 |
+
"learning_rate": 3.157760826481174e-05,
|
| 1422 |
+
"loss": 0.3616,
|
| 1423 |
+
"step": 965
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 7.698412698412699,
|
| 1427 |
+
"grad_norm": 0.25,
|
| 1428 |
+
"learning_rate": 3.057403027512963e-05,
|
| 1429 |
+
"loss": 0.3531,
|
| 1430 |
+
"step": 970
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 7.738095238095238,
|
| 1434 |
+
"grad_norm": 0.287109375,
|
| 1435 |
+
"learning_rate": 2.9583773034764826e-05,
|
| 1436 |
+
"loss": 0.3547,
|
| 1437 |
+
"step": 975
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 7.777777777777778,
|
| 1441 |
+
"grad_norm": 0.2421875,
|
| 1442 |
+
"learning_rate": 2.8607026544210114e-05,
|
| 1443 |
+
"loss": 0.3609,
|
| 1444 |
+
"step": 980
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 7.817460317460317,
|
| 1448 |
+
"grad_norm": 0.2392578125,
|
| 1449 |
+
"learning_rate": 2.764397821165292e-05,
|
| 1450 |
+
"loss": 0.3588,
|
| 1451 |
+
"step": 985
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 7.857142857142857,
|
| 1455 |
+
"grad_norm": 0.271484375,
|
| 1456 |
+
"learning_rate": 2.669481281701739e-05,
|
| 1457 |
+
"loss": 0.3648,
|
| 1458 |
+
"step": 990
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 7.896825396825397,
|
| 1462 |
+
"grad_norm": 0.251953125,
|
| 1463 |
+
"learning_rate": 2.5759712476510622e-05,
|
| 1464 |
+
"loss": 0.3635,
|
| 1465 |
+
"step": 995
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 7.936507936507937,
|
| 1469 |
+
"grad_norm": 0.2412109375,
|
| 1470 |
+
"learning_rate": 2.4838856607680183e-05,
|
| 1471 |
+
"loss": 0.3568,
|
| 1472 |
+
"step": 1000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 7.976190476190476,
|
| 1476 |
+
"grad_norm": 0.25390625,
|
| 1477 |
+
"learning_rate": 2.3932421894989167e-05,
|
| 1478 |
+
"loss": 0.3612,
|
| 1479 |
+
"step": 1005
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 8.0,
|
| 1483 |
+
"eval_loss": 1.2904332876205444,
|
| 1484 |
+
"eval_runtime": 1.0153,
|
| 1485 |
+
"eval_samples_per_second": 1.97,
|
| 1486 |
+
"eval_steps_per_second": 0.985,
|
| 1487 |
+
"step": 1008
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 8.015873015873016,
|
| 1491 |
+
"grad_norm": 0.26171875,
|
| 1492 |
+
"learning_rate": 2.304058225591581e-05,
|
| 1493 |
+
"loss": 0.354,
|
| 1494 |
+
"step": 1010
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 8.055555555555555,
|
| 1498 |
+
"grad_norm": 0.23828125,
|
| 1499 |
+
"learning_rate": 2.2163508807583998e-05,
|
| 1500 |
+
"loss": 0.3464,
|
| 1501 |
+
"step": 1015
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 8.095238095238095,
|
| 1505 |
+
"grad_norm": 0.259765625,
|
| 1506 |
+
"learning_rate": 2.1301369833931117e-05,
|
| 1507 |
+
"loss": 0.3411,
|
| 1508 |
+
"step": 1020
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 8.134920634920634,
|
| 1512 |
+
"grad_norm": 0.259765625,
|
| 1513 |
+
"learning_rate": 2.045433075341927e-05,
|
| 1514 |
+
"loss": 0.3369,
|
| 1515 |
+
"step": 1025
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 8.174603174603174,
|
| 1519 |
+
"grad_norm": 0.232421875,
|
| 1520 |
+
"learning_rate": 1.962255408729662e-05,
|
| 1521 |
+
"loss": 0.3369,
|
| 1522 |
+
"step": 1030
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 8.214285714285714,
|
| 1526 |
+
"grad_norm": 0.2353515625,
|
| 1527 |
+
"learning_rate": 1.880619942841435e-05,
|
| 1528 |
+
"loss": 0.3391,
|
| 1529 |
+
"step": 1035
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 8.253968253968253,
|
| 1533 |
+
"grad_norm": 0.2470703125,
|
| 1534 |
+
"learning_rate": 1.8005423410605772e-05,
|
| 1535 |
+
"loss": 0.3395,
|
| 1536 |
+
"step": 1040
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 8.293650793650794,
|
| 1540 |
+
"grad_norm": 0.244140625,
|
| 1541 |
+
"learning_rate": 1.7220379678632814e-05,
|
| 1542 |
+
"loss": 0.3409,
|
| 1543 |
+
"step": 1045
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 8.333333333333334,
|
| 1547 |
+
"grad_norm": 0.2412109375,
|
| 1548 |
+
"learning_rate": 1.6451218858706374e-05,
|
| 1549 |
+
"loss": 0.3483,
|
| 1550 |
+
"step": 1050
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 8.373015873015873,
|
| 1554 |
+
"grad_norm": 0.2421875,
|
| 1555 |
+
"learning_rate": 1.5698088529585597e-05,
|
| 1556 |
+
"loss": 0.3459,
|
| 1557 |
+
"step": 1055
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 8.412698412698413,
|
| 1561 |
+
"grad_norm": 0.2412109375,
|
| 1562 |
+
"learning_rate": 1.49611331942621e-05,
|
| 1563 |
+
"loss": 0.336,
|
| 1564 |
+
"step": 1060
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 8.452380952380953,
|
| 1568 |
+
"grad_norm": 0.2578125,
|
| 1569 |
+
"learning_rate": 1.4240494252234049e-05,
|
| 1570 |
+
"loss": 0.3349,
|
| 1571 |
+
"step": 1065
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 8.492063492063492,
|
| 1575 |
+
"grad_norm": 0.2412109375,
|
| 1576 |
+
"learning_rate": 1.3536309972375948e-05,
|
| 1577 |
+
"loss": 0.3463,
|
| 1578 |
+
"step": 1070
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 8.531746031746032,
|
| 1582 |
+
"grad_norm": 0.23828125,
|
| 1583 |
+
"learning_rate": 1.2848715466408967e-05,
|
| 1584 |
+
"loss": 0.3372,
|
| 1585 |
+
"step": 1075
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 8.571428571428571,
|
| 1589 |
+
"grad_norm": 0.2314453125,
|
| 1590 |
+
"learning_rate": 1.2177842662977135e-05,
|
| 1591 |
+
"loss": 0.3346,
|
| 1592 |
+
"step": 1080
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 8.61111111111111,
|
| 1596 |
+
"grad_norm": 0.236328125,
|
| 1597 |
+
"learning_rate": 1.1523820282334219e-05,
|
| 1598 |
+
"loss": 0.3449,
|
| 1599 |
+
"step": 1085
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 8.65079365079365,
|
| 1603 |
+
"grad_norm": 0.234375,
|
| 1604 |
+
"learning_rate": 1.088677381164609e-05,
|
| 1605 |
+
"loss": 0.3368,
|
| 1606 |
+
"step": 1090
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 8.69047619047619,
|
| 1610 |
+
"grad_norm": 0.23828125,
|
| 1611 |
+
"learning_rate": 1.0266825480913611e-05,
|
| 1612 |
+
"loss": 0.3379,
|
| 1613 |
+
"step": 1095
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 8.73015873015873,
|
| 1617 |
+
"grad_norm": 0.2421875,
|
| 1618 |
+
"learning_rate": 9.664094239520372e-06,
|
| 1619 |
+
"loss": 0.348,
|
| 1620 |
+
"step": 1100
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 8.76984126984127,
|
| 1624 |
+
"grad_norm": 0.244140625,
|
| 1625 |
+
"learning_rate": 9.07869573340987e-06,
|
| 1626 |
+
"loss": 0.343,
|
| 1627 |
+
"step": 1105
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 8.80952380952381,
|
| 1631 |
+
"grad_norm": 0.236328125,
|
| 1632 |
+
"learning_rate": 8.510742282896544e-06,
|
| 1633 |
+
"loss": 0.3396,
|
| 1634 |
+
"step": 1110
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 8.84920634920635,
|
| 1638 |
+
"grad_norm": 0.23828125,
|
| 1639 |
+
"learning_rate": 7.960342861114921e-06,
|
| 1640 |
+
"loss": 0.3391,
|
| 1641 |
+
"step": 1115
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 8.88888888888889,
|
| 1645 |
+
"grad_norm": 0.2333984375,
|
| 1646 |
+
"learning_rate": 7.427603073110967e-06,
|
| 1647 |
+
"loss": 0.3405,
|
| 1648 |
+
"step": 1120
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 8.928571428571429,
|
| 1652 |
+
"grad_norm": 0.2314453125,
|
| 1653 |
+
"learning_rate": 6.9126251355795864e-06,
|
| 1654 |
+
"loss": 0.3378,
|
| 1655 |
+
"step": 1125
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 8.968253968253968,
|
| 1659 |
+
"grad_norm": 0.263671875,
|
| 1660 |
+
"learning_rate": 6.415507857252389e-06,
|
| 1661 |
+
"loss": 0.3457,
|
| 1662 |
+
"step": 1130
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 9.0,
|
| 1666 |
+
"eval_loss": 1.3253473043441772,
|
| 1667 |
+
"eval_runtime": 1.0138,
|
| 1668 |
+
"eval_samples_per_second": 1.973,
|
| 1669 |
+
"eval_steps_per_second": 0.986,
|
| 1670 |
+
"step": 1134
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 9.007936507936508,
|
| 1674 |
+
"grad_norm": 0.232421875,
|
| 1675 |
+
"learning_rate": 5.936346619939271e-06,
|
| 1676 |
+
"loss": 0.3402,
|
| 1677 |
+
"step": 1135
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 9.047619047619047,
|
| 1681 |
+
"grad_norm": 0.248046875,
|
| 1682 |
+
"learning_rate": 5.475233360227516e-06,
|
| 1683 |
+
"loss": 0.3362,
|
| 1684 |
+
"step": 1140
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 9.087301587301587,
|
| 1688 |
+
"grad_norm": 0.232421875,
|
| 1689 |
+
"learning_rate": 5.03225655184194e-06,
|
| 1690 |
+
"loss": 0.3346,
|
| 1691 |
+
"step": 1145
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 9.126984126984127,
|
| 1695 |
+
"grad_norm": 0.228515625,
|
| 1696 |
+
"learning_rate": 4.607501188669394e-06,
|
| 1697 |
+
"loss": 0.3358,
|
| 1698 |
+
"step": 1150
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 9.166666666666666,
|
| 1702 |
+
"grad_norm": 0.232421875,
|
| 1703 |
+
"learning_rate": 4.20104876845111e-06,
|
| 1704 |
+
"loss": 0.333,
|
| 1705 |
+
"step": 1155
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 9.206349206349206,
|
| 1709 |
+
"grad_norm": 0.2373046875,
|
| 1710 |
+
"learning_rate": 3.8129772771456797e-06,
|
| 1711 |
+
"loss": 0.3393,
|
| 1712 |
+
"step": 1160
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 9.246031746031745,
|
| 1716 |
+
"grad_norm": 0.232421875,
|
| 1717 |
+
"learning_rate": 3.4433611739658645e-06,
|
| 1718 |
+
"loss": 0.3409,
|
| 1719 |
+
"step": 1165
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 9.285714285714286,
|
| 1723 |
+
"grad_norm": 0.2373046875,
|
| 1724 |
+
"learning_rate": 3.092271377092215e-06,
|
| 1725 |
+
"loss": 0.34,
|
| 1726 |
+
"step": 1170
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 9.325396825396826,
|
| 1730 |
+
"grad_norm": 0.2353515625,
|
| 1731 |
+
"learning_rate": 2.759775250065899e-06,
|
| 1732 |
+
"loss": 0.3362,
|
| 1733 |
+
"step": 1175
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 9.365079365079366,
|
| 1737 |
+
"grad_norm": 0.23828125,
|
| 1738 |
+
"learning_rate": 2.4459365888638062e-06,
|
| 1739 |
+
"loss": 0.333,
|
| 1740 |
+
"step": 1180
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 9.404761904761905,
|
| 1744 |
+
"grad_norm": 0.2314453125,
|
| 1745 |
+
"learning_rate": 2.150815609657875e-06,
|
| 1746 |
+
"loss": 0.3315,
|
| 1747 |
+
"step": 1185
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 9.444444444444445,
|
| 1751 |
+
"grad_norm": 0.23046875,
|
| 1752 |
+
"learning_rate": 1.874468937261531e-06,
|
| 1753 |
+
"loss": 0.3371,
|
| 1754 |
+
"step": 1190
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 9.484126984126984,
|
| 1758 |
+
"grad_norm": 0.24609375,
|
| 1759 |
+
"learning_rate": 1.6169495942650714e-06,
|
| 1760 |
+
"loss": 0.339,
|
| 1761 |
+
"step": 1195
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 9.523809523809524,
|
| 1765 |
+
"grad_norm": 0.23046875,
|
| 1766 |
+
"learning_rate": 1.378306990862177e-06,
|
| 1767 |
+
"loss": 0.3413,
|
| 1768 |
+
"step": 1200
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 9.563492063492063,
|
| 1772 |
+
"grad_norm": 0.2333984375,
|
| 1773 |
+
"learning_rate": 1.158586915369675e-06,
|
| 1774 |
+
"loss": 0.3313,
|
| 1775 |
+
"step": 1205
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 9.603174603174603,
|
| 1779 |
+
"grad_norm": 0.2333984375,
|
| 1780 |
+
"learning_rate": 9.578315254420767e-07,
|
| 1781 |
+
"loss": 0.339,
|
| 1782 |
+
"step": 1210
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 9.642857142857142,
|
| 1786 |
+
"grad_norm": 0.2392578125,
|
| 1787 |
+
"learning_rate": 7.760793399827937e-07,
|
| 1788 |
+
"loss": 0.3284,
|
| 1789 |
+
"step": 1215
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 9.682539682539682,
|
| 1793 |
+
"grad_norm": 0.23828125,
|
| 1794 |
+
"learning_rate": 6.13365231753571e-07,
|
| 1795 |
+
"loss": 0.3359,
|
| 1796 |
+
"step": 1220
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 9.722222222222221,
|
| 1800 |
+
"grad_norm": 0.228515625,
|
| 1801 |
+
"learning_rate": 4.6972042068341714e-07,
|
| 1802 |
+
"loss": 0.3394,
|
| 1803 |
+
"step": 1225
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 9.761904761904763,
|
| 1807 |
+
"grad_norm": 0.2373046875,
|
| 1808 |
+
"learning_rate": 3.451724678784518e-07,
|
| 1809 |
+
"loss": 0.337,
|
| 1810 |
+
"step": 1230
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 9.801587301587302,
|
| 1814 |
+
"grad_norm": 0.2421875,
|
| 1815 |
+
"learning_rate": 2.397452703337577e-07,
|
| 1816 |
+
"loss": 0.3344,
|
| 1817 |
+
"step": 1235
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 9.841269841269842,
|
| 1821 |
+
"grad_norm": 0.234375,
|
| 1822 |
+
"learning_rate": 1.5345905634827074e-07,
|
| 1823 |
+
"loss": 0.3307,
|
| 1824 |
+
"step": 1240
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 9.880952380952381,
|
| 1828 |
+
"grad_norm": 0.2373046875,
|
| 1829 |
+
"learning_rate": 8.633038164358454e-08,
|
| 1830 |
+
"loss": 0.3361,
|
| 1831 |
+
"step": 1245
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 9.920634920634921,
|
| 1835 |
+
"grad_norm": 0.2392578125,
|
| 1836 |
+
"learning_rate": 3.8372126187413704e-08,
|
| 1837 |
+
"loss": 0.34,
|
| 1838 |
+
"step": 1250
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 9.96031746031746,
|
| 1842 |
+
"grad_norm": 0.2314453125,
|
| 1843 |
+
"learning_rate": 9.593491722270642e-09,
|
| 1844 |
+
"loss": 0.3385,
|
| 1845 |
+
"step": 1255
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 10.0,
|
| 1849 |
+
"grad_norm": 0.2470703125,
|
| 1850 |
+
"learning_rate": 0.0,
|
| 1851 |
+
"loss": 0.3328,
|
| 1852 |
+
"step": 1260
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 10.0,
|
| 1856 |
+
"eval_loss": 1.332617163658142,
|
| 1857 |
+
"eval_runtime": 1.0141,
|
| 1858 |
+
"eval_samples_per_second": 1.972,
|
| 1859 |
+
"eval_steps_per_second": 0.986,
|
| 1860 |
+
"step": 1260
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 10.0,
|
| 1864 |
+
"step": 1260,
|
| 1865 |
+
"total_flos": 3.8899222565240177e+18,
|
| 1866 |
+
"train_loss": 1.363766341266178,
|
| 1867 |
+
"train_runtime": 8098.2535,
|
| 1868 |
+
"train_samples_per_second": 4.97,
|
| 1869 |
+
"train_steps_per_second": 0.156
|
| 1870 |
+
}
|
| 1871 |
+
],
|
| 1872 |
+
"logging_steps": 5,
|
| 1873 |
+
"max_steps": 1260,
|
| 1874 |
+
"num_input_tokens_seen": 0,
|
| 1875 |
+
"num_train_epochs": 10,
|
| 1876 |
+
"save_steps": 100,
|
| 1877 |
+
"total_flos": 3.8899222565240177e+18,
|
| 1878 |
+
"train_batch_size": 4,
|
| 1879 |
+
"trial_name": null,
|
| 1880 |
+
"trial_params": null
|
| 1881 |
+
}
|