Model save
Browse files- README.md +69 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
- runs/Mar14_07-24-42_333df911e7ea/events.out.tfevents.1710401246.333df911e7ea.52523.0 +2 -2
- runs/Mar14_07-24-42_333df911e7ea/events.out.tfevents.1710404227.333df911e7ea.52523.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1318 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: jan-hq/LlamaCorn-1.1B-Chat
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: TinyJensen-1.1B-Chat
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# TinyJensen-1.1B-Chat
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [jan-hq/LlamaCorn-1.1B-Chat](https://huggingface.co/jan-hq/LlamaCorn-1.1B-Chat) on the generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.8771
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 5e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 16
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 5
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.8226 | 1.0 | 207 | 0.8232 |
|
| 58 |
+
| 0.6608 | 2.0 | 414 | 0.7941 |
|
| 59 |
+
| 0.526 | 3.0 | 621 | 0.8186 |
|
| 60 |
+
| 0.4388 | 4.0 | 829 | 0.8643 |
|
| 61 |
+
| 0.3888 | 4.99 | 1035 | 0.8771 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.37.2
|
| 67 |
+
- Pytorch 2.1.2+cu121
|
| 68 |
+
- Datasets 2.14.6
|
| 69 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_loss": 0.8771134614944458,
|
| 4 |
+
"eval_runtime": 9.8335,
|
| 5 |
+
"eval_samples": 854,
|
| 6 |
+
"eval_samples_per_second": 23.593,
|
| 7 |
+
"eval_steps_per_second": 5.898,
|
| 8 |
+
"train_loss": 0.5910406330357427,
|
| 9 |
+
"train_runtime": 2967.3423,
|
| 10 |
+
"train_samples": 13225,
|
| 11 |
+
"train_samples_per_second": 5.586,
|
| 12 |
+
"train_steps_per_second": 0.349
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_loss": 0.8771134614944458,
|
| 4 |
+
"eval_runtime": 9.8335,
|
| 5 |
+
"eval_samples": 854,
|
| 6 |
+
"eval_samples_per_second": 23.593,
|
| 7 |
+
"eval_steps_per_second": 5.898
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.37.2"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2200119864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df65ac037e1d51022a63155d6fbe0dca8906a94ed5f96079c4f2d1f75ab8cf5c
|
| 3 |
size 2200119864
|
runs/Mar14_07-24-42_333df911e7ea/events.out.tfevents.1710401246.333df911e7ea.52523.0
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:cb811536445436e0a1df92b3cab9563c4566703bae745364152ddc08560c813b
|
| 3 |
+
size 38776
|
runs/Mar14_07-24-42_333df911e7ea/events.out.tfevents.1710404227.333df911e7ea.52523.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e216932db0d6b6c5b481342e683316da0855dc6cea7e1af7466ec77062381365
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"train_loss": 0.5910406330357427,
|
| 4 |
+
"train_runtime": 2967.3423,
|
| 5 |
+
"train_samples": 13225,
|
| 6 |
+
"train_samples_per_second": 5.586,
|
| 7 |
+
"train_steps_per_second": 0.349
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.9939686369119425,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1035,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4.807692307692308e-07,
|
| 14 |
+
"loss": 1.4009,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 2.403846153846154e-06,
|
| 20 |
+
"loss": 1.2871,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 4.807692307692308e-06,
|
| 26 |
+
"loss": 1.1951,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 7.211538461538461e-06,
|
| 32 |
+
"loss": 1.1289,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 9.615384615384616e-06,
|
| 38 |
+
"loss": 1.1274,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.12,
|
| 43 |
+
"learning_rate": 1.2019230769230771e-05,
|
| 44 |
+
"loss": 1.0066,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.14,
|
| 49 |
+
"learning_rate": 1.4423076923076923e-05,
|
| 50 |
+
"loss": 0.9923,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17,
|
| 55 |
+
"learning_rate": 1.682692307692308e-05,
|
| 56 |
+
"loss": 1.0136,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.19,
|
| 61 |
+
"learning_rate": 1.923076923076923e-05,
|
| 62 |
+
"loss": 1.0153,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.22,
|
| 67 |
+
"learning_rate": 2.1634615384615387e-05,
|
| 68 |
+
"loss": 0.9874,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.24,
|
| 73 |
+
"learning_rate": 2.4038461538461542e-05,
|
| 74 |
+
"loss": 0.9887,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.27,
|
| 79 |
+
"learning_rate": 2.6442307692307694e-05,
|
| 80 |
+
"loss": 0.9289,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.29,
|
| 85 |
+
"learning_rate": 2.8846153846153845e-05,
|
| 86 |
+
"loss": 0.9279,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.31,
|
| 91 |
+
"learning_rate": 3.125e-05,
|
| 92 |
+
"loss": 0.9228,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.34,
|
| 97 |
+
"learning_rate": 3.365384615384616e-05,
|
| 98 |
+
"loss": 0.9526,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.36,
|
| 103 |
+
"learning_rate": 3.605769230769231e-05,
|
| 104 |
+
"loss": 0.9023,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.39,
|
| 109 |
+
"learning_rate": 3.846153846153846e-05,
|
| 110 |
+
"loss": 0.9244,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.41,
|
| 115 |
+
"learning_rate": 4.0865384615384615e-05,
|
| 116 |
+
"loss": 0.885,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.43,
|
| 121 |
+
"learning_rate": 4.326923076923077e-05,
|
| 122 |
+
"loss": 0.917,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.46,
|
| 127 |
+
"learning_rate": 4.5673076923076925e-05,
|
| 128 |
+
"loss": 0.9262,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.48,
|
| 133 |
+
"learning_rate": 4.8076923076923084e-05,
|
| 134 |
+
"loss": 0.8931,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.51,
|
| 139 |
+
"learning_rate": 4.999985766556415e-05,
|
| 140 |
+
"loss": 0.8588,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.53,
|
| 145 |
+
"learning_rate": 4.999487613048386e-05,
|
| 146 |
+
"loss": 0.8868,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.55,
|
| 151 |
+
"learning_rate": 4.998277949425564e-05,
|
| 152 |
+
"loss": 0.8861,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.58,
|
| 157 |
+
"learning_rate": 4.9963571200336876e-05,
|
| 158 |
+
"loss": 0.8955,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.6,
|
| 163 |
+
"learning_rate": 4.9937256716606394e-05,
|
| 164 |
+
"loss": 0.8693,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.63,
|
| 169 |
+
"learning_rate": 4.9903843533808e-05,
|
| 170 |
+
"loss": 0.8645,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.65,
|
| 175 |
+
"learning_rate": 4.986334116341812e-05,
|
| 176 |
+
"loss": 0.8622,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.68,
|
| 181 |
+
"learning_rate": 4.981576113493827e-05,
|
| 182 |
+
"loss": 0.8166,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.7,
|
| 187 |
+
"learning_rate": 4.976111699261301e-05,
|
| 188 |
+
"loss": 0.8387,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.72,
|
| 193 |
+
"learning_rate": 4.9699424291574436e-05,
|
| 194 |
+
"loss": 0.8268,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.75,
|
| 199 |
+
"learning_rate": 4.9630700593414206e-05,
|
| 200 |
+
"loss": 0.8282,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.77,
|
| 205 |
+
"learning_rate": 4.955496546118439e-05,
|
| 206 |
+
"loss": 0.8482,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.8,
|
| 211 |
+
"learning_rate": 4.947224045382866e-05,
|
| 212 |
+
"loss": 0.8075,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.82,
|
| 217 |
+
"learning_rate": 4.938254912004522e-05,
|
| 218 |
+
"loss": 0.8612,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.84,
|
| 223 |
+
"learning_rate": 4.92859169915834e-05,
|
| 224 |
+
"loss": 0.8528,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.87,
|
| 229 |
+
"learning_rate": 4.9182371575975736e-05,
|
| 230 |
+
"loss": 0.8368,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.89,
|
| 235 |
+
"learning_rate": 4.907194234870759e-05,
|
| 236 |
+
"loss": 0.8273,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.92,
|
| 241 |
+
"learning_rate": 4.8954660744826575e-05,
|
| 242 |
+
"loss": 0.8127,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.94,
|
| 247 |
+
"learning_rate": 4.883056014999423e-05,
|
| 248 |
+
"loss": 0.8429,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.97,
|
| 253 |
+
"learning_rate": 4.8699675890982345e-05,
|
| 254 |
+
"loss": 0.8408,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.99,
|
| 259 |
+
"learning_rate": 4.8562045225616736e-05,
|
| 260 |
+
"loss": 0.8226,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.0,
|
| 265 |
+
"eval_loss": 0.8232178688049316,
|
| 266 |
+
"eval_runtime": 9.8377,
|
| 267 |
+
"eval_samples_per_second": 23.583,
|
| 268 |
+
"eval_steps_per_second": 5.896,
|
| 269 |
+
"step": 207
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.01,
|
| 273 |
+
"learning_rate": 4.8417707332171385e-05,
|
| 274 |
+
"loss": 0.7622,
|
| 275 |
+
"step": 210
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.04,
|
| 279 |
+
"learning_rate": 4.826670329821584e-05,
|
| 280 |
+
"loss": 0.6629,
|
| 281 |
+
"step": 215
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.06,
|
| 285 |
+
"learning_rate": 4.810907610891914e-05,
|
| 286 |
+
"loss": 0.6781,
|
| 287 |
+
"step": 220
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.09,
|
| 291 |
+
"learning_rate": 4.7944870634813525e-05,
|
| 292 |
+
"loss": 0.6815,
|
| 293 |
+
"step": 225
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.11,
|
| 297 |
+
"learning_rate": 4.7774133619021514e-05,
|
| 298 |
+
"loss": 0.6885,
|
| 299 |
+
"step": 230
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.13,
|
| 303 |
+
"learning_rate": 4.759691366394989e-05,
|
| 304 |
+
"loss": 0.6674,
|
| 305 |
+
"step": 235
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.16,
|
| 309 |
+
"learning_rate": 4.741326121745441e-05,
|
| 310 |
+
"loss": 0.7042,
|
| 311 |
+
"step": 240
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.18,
|
| 315 |
+
"learning_rate": 4.722322855847921e-05,
|
| 316 |
+
"loss": 0.6955,
|
| 317 |
+
"step": 245
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.21,
|
| 321 |
+
"learning_rate": 4.702686978217495e-05,
|
| 322 |
+
"loss": 0.6949,
|
| 323 |
+
"step": 250
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.23,
|
| 327 |
+
"learning_rate": 4.682424078449995e-05,
|
| 328 |
+
"loss": 0.6823,
|
| 329 |
+
"step": 255
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.25,
|
| 333 |
+
"learning_rate": 4.6615399246308756e-05,
|
| 334 |
+
"loss": 0.6692,
|
| 335 |
+
"step": 260
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.28,
|
| 339 |
+
"learning_rate": 4.6400404616932505e-05,
|
| 340 |
+
"loss": 0.6632,
|
| 341 |
+
"step": 265
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.3,
|
| 345 |
+
"learning_rate": 4.617931809725599e-05,
|
| 346 |
+
"loss": 0.6618,
|
| 347 |
+
"step": 270
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.33,
|
| 351 |
+
"learning_rate": 4.595220262229601e-05,
|
| 352 |
+
"loss": 0.7224,
|
| 353 |
+
"step": 275
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.35,
|
| 357 |
+
"learning_rate": 4.571912284328626e-05,
|
| 358 |
+
"loss": 0.7081,
|
| 359 |
+
"step": 280
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.38,
|
| 363 |
+
"learning_rate": 4.5480145109273384e-05,
|
| 364 |
+
"loss": 0.6746,
|
| 365 |
+
"step": 285
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.4,
|
| 369 |
+
"learning_rate": 4.5235337448230034e-05,
|
| 370 |
+
"loss": 0.6857,
|
| 371 |
+
"step": 290
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.42,
|
| 375 |
+
"learning_rate": 4.498476954768981e-05,
|
| 376 |
+
"loss": 0.6835,
|
| 377 |
+
"step": 295
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.45,
|
| 381 |
+
"learning_rate": 4.4728512734909844e-05,
|
| 382 |
+
"loss": 0.6893,
|
| 383 |
+
"step": 300
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.47,
|
| 387 |
+
"learning_rate": 4.446663995656661e-05,
|
| 388 |
+
"loss": 0.6608,
|
| 389 |
+
"step": 305
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.5,
|
| 393 |
+
"learning_rate": 4.419922575799078e-05,
|
| 394 |
+
"loss": 0.6919,
|
| 395 |
+
"step": 310
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.52,
|
| 399 |
+
"learning_rate": 4.39263462619469e-05,
|
| 400 |
+
"loss": 0.6883,
|
| 401 |
+
"step": 315
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.54,
|
| 405 |
+
"learning_rate": 4.364807914696421e-05,
|
| 406 |
+
"loss": 0.681,
|
| 407 |
+
"step": 320
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.57,
|
| 411 |
+
"learning_rate": 4.3364503625224376e-05,
|
| 412 |
+
"loss": 0.6898,
|
| 413 |
+
"step": 325
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.59,
|
| 417 |
+
"learning_rate": 4.307570042001283e-05,
|
| 418 |
+
"loss": 0.6589,
|
| 419 |
+
"step": 330
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.62,
|
| 423 |
+
"learning_rate": 4.2781751742739885e-05,
|
| 424 |
+
"loss": 0.6924,
|
| 425 |
+
"step": 335
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.64,
|
| 429 |
+
"learning_rate": 4.248274126953819e-05,
|
| 430 |
+
"loss": 0.6666,
|
| 431 |
+
"step": 340
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.66,
|
| 435 |
+
"learning_rate": 4.217875411744334e-05,
|
| 436 |
+
"loss": 0.6759,
|
| 437 |
+
"step": 345
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.69,
|
| 441 |
+
"learning_rate": 4.186987682016422e-05,
|
| 442 |
+
"loss": 0.6894,
|
| 443 |
+
"step": 350
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.71,
|
| 447 |
+
"learning_rate": 4.155619730345015e-05,
|
| 448 |
+
"loss": 0.6898,
|
| 449 |
+
"step": 355
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.74,
|
| 453 |
+
"learning_rate": 4.123780486006167e-05,
|
| 454 |
+
"loss": 0.6721,
|
| 455 |
+
"step": 360
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.76,
|
| 459 |
+
"learning_rate": 4.09147901243523e-05,
|
| 460 |
+
"loss": 0.6616,
|
| 461 |
+
"step": 365
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.79,
|
| 465 |
+
"learning_rate": 4.058724504646834e-05,
|
| 466 |
+
"loss": 0.6631,
|
| 467 |
+
"step": 370
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.81,
|
| 471 |
+
"learning_rate": 4.025526286617411e-05,
|
| 472 |
+
"loss": 0.692,
|
| 473 |
+
"step": 375
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.83,
|
| 477 |
+
"learning_rate": 3.991893808631011e-05,
|
| 478 |
+
"loss": 0.6706,
|
| 479 |
+
"step": 380
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.86,
|
| 483 |
+
"learning_rate": 3.957836644589159e-05,
|
| 484 |
+
"loss": 0.6777,
|
| 485 |
+
"step": 385
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.88,
|
| 489 |
+
"learning_rate": 3.9233644892855285e-05,
|
| 490 |
+
"loss": 0.6605,
|
| 491 |
+
"step": 390
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.91,
|
| 495 |
+
"learning_rate": 3.8884871556461966e-05,
|
| 496 |
+
"loss": 0.6911,
|
| 497 |
+
"step": 395
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.93,
|
| 501 |
+
"learning_rate": 3.8532145719362734e-05,
|
| 502 |
+
"loss": 0.6618,
|
| 503 |
+
"step": 400
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.95,
|
| 507 |
+
"learning_rate": 3.817556778933698e-05,
|
| 508 |
+
"loss": 0.6912,
|
| 509 |
+
"step": 405
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.98,
|
| 513 |
+
"learning_rate": 3.781523927071006e-05,
|
| 514 |
+
"loss": 0.6608,
|
| 515 |
+
"step": 410
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.0,
|
| 519 |
+
"eval_loss": 0.7941169738769531,
|
| 520 |
+
"eval_runtime": 9.8325,
|
| 521 |
+
"eval_samples_per_second": 23.595,
|
| 522 |
+
"eval_steps_per_second": 5.899,
|
| 523 |
+
"step": 414
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.0,
|
| 527 |
+
"learning_rate": 3.745126273545886e-05,
|
| 528 |
+
"loss": 0.6317,
|
| 529 |
+
"step": 415
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.03,
|
| 533 |
+
"learning_rate": 3.7083741794013385e-05,
|
| 534 |
+
"loss": 0.5188,
|
| 535 |
+
"step": 420
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.05,
|
| 539 |
+
"learning_rate": 3.671278106576278e-05,
|
| 540 |
+
"loss": 0.5433,
|
| 541 |
+
"step": 425
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.07,
|
| 545 |
+
"learning_rate": 3.6338486149274107e-05,
|
| 546 |
+
"loss": 0.5177,
|
| 547 |
+
"step": 430
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.1,
|
| 551 |
+
"learning_rate": 3.596096359223241e-05,
|
| 552 |
+
"loss": 0.5095,
|
| 553 |
+
"step": 435
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.12,
|
| 557 |
+
"learning_rate": 3.5580320861110625e-05,
|
| 558 |
+
"loss": 0.4915,
|
| 559 |
+
"step": 440
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.15,
|
| 563 |
+
"learning_rate": 3.519666631057789e-05,
|
| 564 |
+
"loss": 0.5216,
|
| 565 |
+
"step": 445
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.17,
|
| 569 |
+
"learning_rate": 3.481010915265504e-05,
|
| 570 |
+
"loss": 0.5118,
|
| 571 |
+
"step": 450
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.2,
|
| 575 |
+
"learning_rate": 3.442075942562608e-05,
|
| 576 |
+
"loss": 0.505,
|
| 577 |
+
"step": 455
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.22,
|
| 581 |
+
"learning_rate": 3.402872796271438e-05,
|
| 582 |
+
"loss": 0.5103,
|
| 583 |
+
"step": 460
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.24,
|
| 587 |
+
"learning_rate": 3.363412636053269e-05,
|
| 588 |
+
"loss": 0.532,
|
| 589 |
+
"step": 465
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.27,
|
| 593 |
+
"learning_rate": 3.323706694731572e-05,
|
| 594 |
+
"loss": 0.5151,
|
| 595 |
+
"step": 470
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.29,
|
| 599 |
+
"learning_rate": 3.2837662750944535e-05,
|
| 600 |
+
"loss": 0.5199,
|
| 601 |
+
"step": 475
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.32,
|
| 605 |
+
"learning_rate": 3.243602746677179e-05,
|
| 606 |
+
"loss": 0.5261,
|
| 607 |
+
"step": 480
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.34,
|
| 611 |
+
"learning_rate": 3.2032275425256916e-05,
|
| 612 |
+
"loss": 0.5052,
|
| 613 |
+
"step": 485
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.36,
|
| 617 |
+
"learning_rate": 3.1626521559420556e-05,
|
| 618 |
+
"loss": 0.508,
|
| 619 |
+
"step": 490
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.39,
|
| 623 |
+
"learning_rate": 3.121888137212742e-05,
|
| 624 |
+
"loss": 0.5308,
|
| 625 |
+
"step": 495
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.41,
|
| 629 |
+
"learning_rate": 3.0809470903207036e-05,
|
| 630 |
+
"loss": 0.5024,
|
| 631 |
+
"step": 500
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.44,
|
| 635 |
+
"learning_rate": 3.0398406696421473e-05,
|
| 636 |
+
"loss": 0.5069,
|
| 637 |
+
"step": 505
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 2.46,
|
| 641 |
+
"learning_rate": 2.9985805766289817e-05,
|
| 642 |
+
"loss": 0.5265,
|
| 643 |
+
"step": 510
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 2.48,
|
| 647 |
+
"learning_rate": 2.9571785564778455e-05,
|
| 648 |
+
"loss": 0.5138,
|
| 649 |
+
"step": 515
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.51,
|
| 653 |
+
"learning_rate": 2.9156463947866985e-05,
|
| 654 |
+
"loss": 0.515,
|
| 655 |
+
"step": 520
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.53,
|
| 659 |
+
"learning_rate": 2.8739959141999023e-05,
|
| 660 |
+
"loss": 0.5211,
|
| 661 |
+
"step": 525
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.56,
|
| 665 |
+
"learning_rate": 2.8322389710427548e-05,
|
| 666 |
+
"loss": 0.5184,
|
| 667 |
+
"step": 530
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.58,
|
| 671 |
+
"learning_rate": 2.7903874519464474e-05,
|
| 672 |
+
"loss": 0.5256,
|
| 673 |
+
"step": 535
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.61,
|
| 677 |
+
"learning_rate": 2.748453270464381e-05,
|
| 678 |
+
"loss": 0.5132,
|
| 679 |
+
"step": 540
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.63,
|
| 683 |
+
"learning_rate": 2.7064483636808313e-05,
|
| 684 |
+
"loss": 0.4917,
|
| 685 |
+
"step": 545
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.65,
|
| 689 |
+
"learning_rate": 2.6643846888129048e-05,
|
| 690 |
+
"loss": 0.5044,
|
| 691 |
+
"step": 550
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.68,
|
| 695 |
+
"learning_rate": 2.622274219806773e-05,
|
| 696 |
+
"loss": 0.5055,
|
| 697 |
+
"step": 555
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.7,
|
| 701 |
+
"learning_rate": 2.5801289439291388e-05,
|
| 702 |
+
"loss": 0.4964,
|
| 703 |
+
"step": 560
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.73,
|
| 707 |
+
"learning_rate": 2.5379608583549097e-05,
|
| 708 |
+
"loss": 0.5157,
|
| 709 |
+
"step": 565
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.75,
|
| 713 |
+
"learning_rate": 2.4957819667520596e-05,
|
| 714 |
+
"loss": 0.5169,
|
| 715 |
+
"step": 570
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 2.77,
|
| 719 |
+
"learning_rate": 2.4536042758646315e-05,
|
| 720 |
+
"loss": 0.5232,
|
| 721 |
+
"step": 575
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.8,
|
| 725 |
+
"learning_rate": 2.4114397920948657e-05,
|
| 726 |
+
"loss": 0.517,
|
| 727 |
+
"step": 580
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.82,
|
| 731 |
+
"learning_rate": 2.369300518085438e-05,
|
| 732 |
+
"loss": 0.5095,
|
| 733 |
+
"step": 585
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.85,
|
| 737 |
+
"learning_rate": 2.327198449302752e-05,
|
| 738 |
+
"loss": 0.5329,
|
| 739 |
+
"step": 590
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.87,
|
| 743 |
+
"learning_rate": 2.2851455706222817e-05,
|
| 744 |
+
"loss": 0.5225,
|
| 745 |
+
"step": 595
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.9,
|
| 749 |
+
"learning_rate": 2.24315385291693e-05,
|
| 750 |
+
"loss": 0.5118,
|
| 751 |
+
"step": 600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.92,
|
| 755 |
+
"learning_rate": 2.201235249649369e-05,
|
| 756 |
+
"loss": 0.502,
|
| 757 |
+
"step": 605
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.94,
|
| 761 |
+
"learning_rate": 2.1594016934693424e-05,
|
| 762 |
+
"loss": 0.5114,
|
| 763 |
+
"step": 610
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.97,
|
| 767 |
+
"learning_rate": 2.117665092816885e-05,
|
| 768 |
+
"loss": 0.5244,
|
| 769 |
+
"step": 615
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.99,
|
| 773 |
+
"learning_rate": 2.0760373285324415e-05,
|
| 774 |
+
"loss": 0.526,
|
| 775 |
+
"step": 620
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.0,
|
| 779 |
+
"eval_loss": 0.8185678720474243,
|
| 780 |
+
"eval_runtime": 9.84,
|
| 781 |
+
"eval_samples_per_second": 23.577,
|
| 782 |
+
"eval_steps_per_second": 5.894,
|
| 783 |
+
"step": 621
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.02,
|
| 787 |
+
"learning_rate": 2.0345302504748355e-05,
|
| 788 |
+
"loss": 0.4593,
|
| 789 |
+
"step": 625
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.04,
|
| 793 |
+
"learning_rate": 1.993155674148058e-05,
|
| 794 |
+
"loss": 0.4372,
|
| 795 |
+
"step": 630
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.06,
|
| 799 |
+
"learning_rate": 1.9519253773378455e-05,
|
| 800 |
+
"loss": 0.4451,
|
| 801 |
+
"step": 635
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.09,
|
| 805 |
+
"learning_rate": 1.9108510967589784e-05,
|
| 806 |
+
"loss": 0.4319,
|
| 807 |
+
"step": 640
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.11,
|
| 811 |
+
"learning_rate": 1.8699445247142864e-05,
|
| 812 |
+
"loss": 0.428,
|
| 813 |
+
"step": 645
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.14,
|
| 817 |
+
"learning_rate": 1.829217305766289e-05,
|
| 818 |
+
"loss": 0.4323,
|
| 819 |
+
"step": 650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.16,
|
| 823 |
+
"learning_rate": 1.7886810334224192e-05,
|
| 824 |
+
"loss": 0.445,
|
| 825 |
+
"step": 655
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.18,
|
| 829 |
+
"learning_rate": 1.7483472468347982e-05,
|
| 830 |
+
"loss": 0.444,
|
| 831 |
+
"step": 660
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.21,
|
| 835 |
+
"learning_rate": 1.7082274275154675e-05,
|
| 836 |
+
"loss": 0.436,
|
| 837 |
+
"step": 665
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 3.23,
|
| 841 |
+
"learning_rate": 1.668332996068034e-05,
|
| 842 |
+
"loss": 0.4187,
|
| 843 |
+
"step": 670
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.26,
|
| 847 |
+
"learning_rate": 1.6286753089366532e-05,
|
| 848 |
+
"loss": 0.4405,
|
| 849 |
+
"step": 675
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.28,
|
| 853 |
+
"learning_rate": 1.5892656551732814e-05,
|
| 854 |
+
"loss": 0.4232,
|
| 855 |
+
"step": 680
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.31,
|
| 859 |
+
"learning_rate": 1.5501152532241005e-05,
|
| 860 |
+
"loss": 0.4287,
|
| 861 |
+
"step": 685
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 3.33,
|
| 865 |
+
"learning_rate": 1.5112352477360537e-05,
|
| 866 |
+
"loss": 0.4121,
|
| 867 |
+
"step": 690
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 3.35,
|
| 871 |
+
"learning_rate": 1.472636706384382e-05,
|
| 872 |
+
"loss": 0.4355,
|
| 873 |
+
"step": 695
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.38,
|
| 877 |
+
"learning_rate": 1.4343306167220708e-05,
|
| 878 |
+
"loss": 0.4082,
|
| 879 |
+
"step": 700
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 3.4,
|
| 883 |
+
"learning_rate": 1.3963278830521104e-05,
|
| 884 |
+
"loss": 0.4251,
|
| 885 |
+
"step": 705
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.43,
|
| 889 |
+
"learning_rate": 1.3586393233234501e-05,
|
| 890 |
+
"loss": 0.4102,
|
| 891 |
+
"step": 710
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.45,
|
| 895 |
+
"learning_rate": 1.3212756660515338e-05,
|
| 896 |
+
"loss": 0.4297,
|
| 897 |
+
"step": 715
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.47,
|
| 901 |
+
"learning_rate": 1.2842475472642968e-05,
|
| 902 |
+
"loss": 0.4329,
|
| 903 |
+
"step": 720
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 3.5,
|
| 907 |
+
"learning_rate": 1.2475655074744855e-05,
|
| 908 |
+
"loss": 0.4319,
|
| 909 |
+
"step": 725
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.52,
|
| 913 |
+
"learning_rate": 1.2112399886791747e-05,
|
| 914 |
+
"loss": 0.4318,
|
| 915 |
+
"step": 730
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 3.55,
|
| 919 |
+
"learning_rate": 1.1752813313873213e-05,
|
| 920 |
+
"loss": 0.4498,
|
| 921 |
+
"step": 735
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.57,
|
| 925 |
+
"learning_rate": 1.139699771676207e-05,
|
| 926 |
+
"loss": 0.4213,
|
| 927 |
+
"step": 740
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.59,
|
| 931 |
+
"learning_rate": 1.10450543827762e-05,
|
| 932 |
+
"loss": 0.4203,
|
| 933 |
+
"step": 745
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.62,
|
| 937 |
+
"learning_rate": 1.0697083496945765e-05,
|
| 938 |
+
"loss": 0.4355,
|
| 939 |
+
"step": 750
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.64,
|
| 943 |
+
"learning_rate": 1.0353184113494386e-05,
|
| 944 |
+
"loss": 0.4253,
|
| 945 |
+
"step": 755
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.67,
|
| 949 |
+
"learning_rate": 1.0013454127642069e-05,
|
| 950 |
+
"loss": 0.4225,
|
| 951 |
+
"step": 760
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 3.69,
|
| 955 |
+
"learning_rate": 9.677990247738159e-06,
|
| 956 |
+
"loss": 0.4248,
|
| 957 |
+
"step": 765
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 3.72,
|
| 961 |
+
"learning_rate": 9.346887967732057e-06,
|
| 962 |
+
"loss": 0.4145,
|
| 963 |
+
"step": 770
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 3.74,
|
| 967 |
+
"learning_rate": 9.020241539989746e-06,
|
| 968 |
+
"loss": 0.4261,
|
| 969 |
+
"step": 775
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.76,
|
| 973 |
+
"learning_rate": 8.698143948463652e-06,
|
| 974 |
+
"loss": 0.424,
|
| 975 |
+
"step": 780
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.79,
|
| 979 |
+
"learning_rate": 8.380686882223618e-06,
|
| 980 |
+
"loss": 0.4398,
|
| 981 |
+
"step": 785
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.81,
|
| 985 |
+
"learning_rate": 8.067960709356478e-06,
|
| 986 |
+
"loss": 0.4411,
|
| 987 |
+
"step": 790
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 3.84,
|
| 991 |
+
"learning_rate": 7.760054451241635e-06,
|
| 992 |
+
"loss": 0.4217,
|
| 993 |
+
"step": 795
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.86,
|
| 997 |
+
"learning_rate": 7.4570557572100714e-06,
|
| 998 |
+
"loss": 0.4321,
|
| 999 |
+
"step": 800
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.88,
|
| 1003 |
+
"learning_rate": 7.159050879593843e-06,
|
| 1004 |
+
"loss": 0.4352,
|
| 1005 |
+
"step": 805
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.91,
|
| 1009 |
+
"learning_rate": 6.866124649173295e-06,
|
| 1010 |
+
"loss": 0.4161,
|
| 1011 |
+
"step": 810
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.93,
|
| 1015 |
+
"learning_rate": 6.5783604510289365e-06,
|
| 1016 |
+
"loss": 0.4353,
|
| 1017 |
+
"step": 815
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.96,
|
| 1021 |
+
"learning_rate": 6.295840200804823e-06,
|
| 1022 |
+
"loss": 0.4404,
|
| 1023 |
+
"step": 820
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.98,
|
| 1027 |
+
"learning_rate": 6.018644321390288e-06,
|
| 1028 |
+
"loss": 0.4388,
|
| 1029 |
+
"step": 825
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 4.0,
|
| 1033 |
+
"eval_loss": 0.8642870783805847,
|
| 1034 |
+
"eval_runtime": 9.886,
|
| 1035 |
+
"eval_samples_per_second": 23.467,
|
| 1036 |
+
"eval_steps_per_second": 5.867,
|
| 1037 |
+
"step": 829
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 4.0,
|
| 1041 |
+
"learning_rate": 5.7468517200265276e-06,
|
| 1042 |
+
"loss": 0.4298,
|
| 1043 |
+
"step": 830
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.03,
|
| 1047 |
+
"learning_rate": 5.480539765844725e-06,
|
| 1048 |
+
"loss": 0.4086,
|
| 1049 |
+
"step": 835
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.05,
|
| 1053 |
+
"learning_rate": 5.2197842678419204e-06,
|
| 1054 |
+
"loss": 0.4117,
|
| 1055 |
+
"step": 840
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.08,
|
| 1059 |
+
"learning_rate": 4.9646594533010875e-06,
|
| 1060 |
+
"loss": 0.4236,
|
| 1061 |
+
"step": 845
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 4.1,
|
| 1065 |
+
"learning_rate": 4.71523794666138e-06,
|
| 1066 |
+
"loss": 0.4184,
|
| 1067 |
+
"step": 850
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.13,
|
| 1071 |
+
"learning_rate": 4.471590748844703e-06,
|
| 1072 |
+
"loss": 0.4028,
|
| 1073 |
+
"step": 855
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 4.15,
|
| 1077 |
+
"learning_rate": 4.23378721704443e-06,
|
| 1078 |
+
"loss": 0.3819,
|
| 1079 |
+
"step": 860
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 4.17,
|
| 1083 |
+
"learning_rate": 4.001895044981982e-06,
|
| 1084 |
+
"loss": 0.4075,
|
| 1085 |
+
"step": 865
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 4.2,
|
| 1089 |
+
"learning_rate": 3.7759802436370174e-06,
|
| 1090 |
+
"loss": 0.3985,
|
| 1091 |
+
"step": 870
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 4.22,
|
| 1095 |
+
"learning_rate": 3.5561071224565617e-06,
|
| 1096 |
+
"loss": 0.4108,
|
| 1097 |
+
"step": 875
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 4.25,
|
| 1101 |
+
"learning_rate": 3.342338271048526e-06,
|
| 1102 |
+
"loss": 0.4295,
|
| 1103 |
+
"step": 880
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 4.27,
|
| 1107 |
+
"learning_rate": 3.134734541364817e-06,
|
| 1108 |
+
"loss": 0.4196,
|
| 1109 |
+
"step": 885
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.29,
|
| 1113 |
+
"learning_rate": 2.933355030379048e-06,
|
| 1114 |
+
"loss": 0.3981,
|
| 1115 |
+
"step": 890
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 4.32,
|
| 1119 |
+
"learning_rate": 2.7382570632638854e-06,
|
| 1120 |
+
"loss": 0.4105,
|
| 1121 |
+
"step": 895
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 4.34,
|
| 1125 |
+
"learning_rate": 2.549496177072702e-06,
|
| 1126 |
+
"loss": 0.4149,
|
| 1127 |
+
"step": 900
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 4.37,
|
| 1131 |
+
"learning_rate": 2.3671261049302865e-06,
|
| 1132 |
+
"loss": 0.4132,
|
| 1133 |
+
"step": 905
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 4.39,
|
| 1137 |
+
"learning_rate": 2.1911987607370123e-06,
|
| 1138 |
+
"loss": 0.4011,
|
| 1139 |
+
"step": 910
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 4.41,
|
| 1143 |
+
"learning_rate": 2.021764224390954e-06,
|
| 1144 |
+
"loss": 0.4062,
|
| 1145 |
+
"step": 915
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.44,
|
| 1149 |
+
"learning_rate": 1.8588707275319667e-06,
|
| 1150 |
+
"loss": 0.4021,
|
| 1151 |
+
"step": 920
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 4.46,
|
| 1155 |
+
"learning_rate": 1.7025646398119988e-06,
|
| 1156 |
+
"loss": 0.4168,
|
| 1157 |
+
"step": 925
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 4.49,
|
| 1161 |
+
"learning_rate": 1.552890455695369e-06,
|
| 1162 |
+
"loss": 0.4246,
|
| 1163 |
+
"step": 930
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 4.51,
|
| 1167 |
+
"learning_rate": 1.409890781792872e-06,
|
| 1168 |
+
"loss": 0.4323,
|
| 1169 |
+
"step": 935
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 4.54,
|
| 1173 |
+
"learning_rate": 1.273606324733284e-06,
|
| 1174 |
+
"loss": 0.4106,
|
| 1175 |
+
"step": 940
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 4.56,
|
| 1179 |
+
"learning_rate": 1.144075879575715e-06,
|
| 1180 |
+
"loss": 0.4058,
|
| 1181 |
+
"step": 945
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 4.58,
|
| 1185 |
+
"learning_rate": 1.0213363187661084e-06,
|
| 1186 |
+
"loss": 0.4094,
|
| 1187 |
+
"step": 950
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 4.61,
|
| 1191 |
+
"learning_rate": 9.054225816410522e-07,
|
| 1192 |
+
"loss": 0.416,
|
| 1193 |
+
"step": 955
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.63,
|
| 1197 |
+
"learning_rate": 7.963676644818507e-07,
|
| 1198 |
+
"loss": 0.4105,
|
| 1199 |
+
"step": 960
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.66,
|
| 1203 |
+
"learning_rate": 6.942026111217359e-07,
|
| 1204 |
+
"loss": 0.4091,
|
| 1205 |
+
"step": 965
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 4.68,
|
| 1209 |
+
"learning_rate": 5.989565041088552e-07,
|
| 1210 |
+
"loss": 0.4039,
|
| 1211 |
+
"step": 970
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 4.7,
|
| 1215 |
+
"learning_rate": 5.106564564275607e-07,
|
| 1216 |
+
"loss": 0.4093,
|
| 1217 |
+
"step": 975
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 4.73,
|
| 1221 |
+
"learning_rate": 4.293276037803551e-07,
|
| 1222 |
+
"loss": 0.4051,
|
| 1223 |
+
"step": 980
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 4.75,
|
| 1227 |
+
"learning_rate": 3.5499309743271535e-07,
|
| 1228 |
+
"loss": 0.4143,
|
| 1229 |
+
"step": 985
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 4.78,
|
| 1233 |
+
"learning_rate": 2.876740976227893e-07,
|
| 1234 |
+
"loss": 0.4265,
|
| 1235 |
+
"step": 990
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 4.8,
|
| 1239 |
+
"learning_rate": 2.2738976753788331e-07,
|
| 1240 |
+
"loss": 0.4004,
|
| 1241 |
+
"step": 995
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.83,
|
| 1245 |
+
"learning_rate": 1.7415726785939834e-07,
|
| 1246 |
+
"loss": 0.4109,
|
| 1247 |
+
"step": 1000
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 4.85,
|
| 1251 |
+
"learning_rate": 1.2799175187786783e-07,
|
| 1252 |
+
"loss": 0.3954,
|
| 1253 |
+
"step": 1005
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 4.87,
|
| 1257 |
+
"learning_rate": 8.89063611793417e-08,
|
| 1258 |
+
"loss": 0.4196,
|
| 1259 |
+
"step": 1010
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 4.9,
|
| 1263 |
+
"learning_rate": 5.691222190451206e-08,
|
| 1264 |
+
"loss": 0.4141,
|
| 1265 |
+
"step": 1015
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 4.92,
|
| 1269 |
+
"learning_rate": 3.2018441581493916e-08,
|
| 1270 |
+
"loss": 0.4125,
|
| 1271 |
+
"step": 1020
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 4.95,
|
| 1275 |
+
"learning_rate": 1.4232106533254575e-08,
|
| 1276 |
+
"loss": 0.4142,
|
| 1277 |
+
"step": 1025
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 4.97,
|
| 1281 |
+
"learning_rate": 3.5582798604244516e-09,
|
| 1282 |
+
"loss": 0.4073,
|
| 1283 |
+
"step": 1030
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.99,
|
| 1287 |
+
"learning_rate": 0.0,
|
| 1288 |
+
"loss": 0.3888,
|
| 1289 |
+
"step": 1035
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 4.99,
|
| 1293 |
+
"eval_loss": 0.8771134614944458,
|
| 1294 |
+
"eval_runtime": 9.8426,
|
| 1295 |
+
"eval_samples_per_second": 23.571,
|
| 1296 |
+
"eval_steps_per_second": 5.893,
|
| 1297 |
+
"step": 1035
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.99,
|
| 1301 |
+
"step": 1035,
|
| 1302 |
+
"total_flos": 2.1046133178499072e+17,
|
| 1303 |
+
"train_loss": 0.5910406330357427,
|
| 1304 |
+
"train_runtime": 2967.3423,
|
| 1305 |
+
"train_samples_per_second": 5.586,
|
| 1306 |
+
"train_steps_per_second": 0.349
|
| 1307 |
+
}
|
| 1308 |
+
],
|
| 1309 |
+
"logging_steps": 5,
|
| 1310 |
+
"max_steps": 1035,
|
| 1311 |
+
"num_input_tokens_seen": 0,
|
| 1312 |
+
"num_train_epochs": 5,
|
| 1313 |
+
"save_steps": 100,
|
| 1314 |
+
"total_flos": 2.1046133178499072e+17,
|
| 1315 |
+
"train_batch_size": 4,
|
| 1316 |
+
"trial_name": null,
|
| 1317 |
+
"trial_params": null
|
| 1318 |
+
}
|