Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- runs/Sep29_12-00-25_86690ac8d1bf/events.out.tfevents.1727625900.86690ac8d1bf.575.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +890 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-7b
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: gemma
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma7b-gpt4o_100k_coding-k
|
| 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 |
+
# gemma7b-gpt4o_100k_coding-k
|
| 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: 1.4680
|
| 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: 0.0003
|
| 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: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 0.7674 | 1.0 | 598 | 1.4680 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.1.dev0
|
| 66 |
+
- Transformers 4.45.1
|
| 67 |
+
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 9.117045735743816e+17,
|
| 4 |
+
"train_loss": 1.9824217689475885,
|
| 5 |
+
"train_runtime": 7933.7629,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 2.411,
|
| 8 |
+
"train_steps_per_second": 0.075
|
| 9 |
+
}
|
runs/Sep29_12-00-25_86690ac8d1bf/events.out.tfevents.1727625900.86690ac8d1bf.575.0
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:a884d2575e0b356fd443f97f54f3e6aa12391a5b62024030b3175134064efe0a
|
| 3 |
+
size 32518
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 9.117045735743816e+17,
|
| 4 |
+
"train_loss": 1.9824217689475885,
|
| 5 |
+
"train_runtime": 7933.7629,
|
| 6 |
+
"train_samples": 116368,
|
| 7 |
+
"train_samples_per_second": 2.411,
|
| 8 |
+
"train_steps_per_second": 0.075
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,890 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 598,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0016722408026755853,
|
| 13 |
+
"grad_norm": 108.1450424194336,
|
| 14 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 15 |
+
"loss": 23.7219,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008361204013377926,
|
| 20 |
+
"grad_norm": 80.87652587890625,
|
| 21 |
+
"learning_rate": 2.4999999999999998e-05,
|
| 22 |
+
"loss": 22.4468,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.016722408026755852,
|
| 27 |
+
"grad_norm": 25.19646644592285,
|
| 28 |
+
"learning_rate": 4.9999999999999996e-05,
|
| 29 |
+
"loss": 18.8421,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02508361204013378,
|
| 34 |
+
"grad_norm": 7.7148966789245605,
|
| 35 |
+
"learning_rate": 7.5e-05,
|
| 36 |
+
"loss": 15.947,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.033444816053511704,
|
| 41 |
+
"grad_norm": 6.524266719818115,
|
| 42 |
+
"learning_rate": 9.999999999999999e-05,
|
| 43 |
+
"loss": 14.4621,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04180602006688963,
|
| 48 |
+
"grad_norm": 3.7445762157440186,
|
| 49 |
+
"learning_rate": 0.000125,
|
| 50 |
+
"loss": 13.5317,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05016722408026756,
|
| 55 |
+
"grad_norm": 2.5251731872558594,
|
| 56 |
+
"learning_rate": 0.00015,
|
| 57 |
+
"loss": 13.0802,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05852842809364549,
|
| 62 |
+
"grad_norm": 3.446436882019043,
|
| 63 |
+
"learning_rate": 0.000175,
|
| 64 |
+
"loss": 12.5052,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06688963210702341,
|
| 69 |
+
"grad_norm": 5.8851447105407715,
|
| 70 |
+
"learning_rate": 0.00019999999999999998,
|
| 71 |
+
"loss": 11.5731,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07525083612040134,
|
| 76 |
+
"grad_norm": 11.619170188903809,
|
| 77 |
+
"learning_rate": 0.000225,
|
| 78 |
+
"loss": 9.873,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08361204013377926,
|
| 83 |
+
"grad_norm": 20.056072235107422,
|
| 84 |
+
"learning_rate": 0.00025,
|
| 85 |
+
"loss": 7.4632,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09197324414715718,
|
| 90 |
+
"grad_norm": 9.337392807006836,
|
| 91 |
+
"learning_rate": 0.00027499999999999996,
|
| 92 |
+
"loss": 3.5644,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.10033444816053512,
|
| 97 |
+
"grad_norm": 5.715840816497803,
|
| 98 |
+
"learning_rate": 0.0003,
|
| 99 |
+
"loss": 2.2307,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.10869565217391304,
|
| 104 |
+
"grad_norm": 3.3433170318603516,
|
| 105 |
+
"learning_rate": 0.0002999360698660697,
|
| 106 |
+
"loss": 1.735,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.11705685618729098,
|
| 111 |
+
"grad_norm": 1.1295098066329956,
|
| 112 |
+
"learning_rate": 0.0002997443339584391,
|
| 113 |
+
"loss": 1.4312,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1254180602006689,
|
| 118 |
+
"grad_norm": 1.1192564964294434,
|
| 119 |
+
"learning_rate": 0.0002994249557131383,
|
| 120 |
+
"loss": 1.26,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.13377926421404682,
|
| 125 |
+
"grad_norm": 0.5016701817512512,
|
| 126 |
+
"learning_rate": 0.00029897820736875393,
|
| 127 |
+
"loss": 1.18,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14214046822742474,
|
| 132 |
+
"grad_norm": 1.4025403261184692,
|
| 133 |
+
"learning_rate": 0.0002984044697343724,
|
| 134 |
+
"loss": 1.1377,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1505016722408027,
|
| 139 |
+
"grad_norm": 0.6089034080505371,
|
| 140 |
+
"learning_rate": 0.00029770423186497794,
|
| 141 |
+
"loss": 1.0823,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1588628762541806,
|
| 146 |
+
"grad_norm": 0.8872767090797424,
|
| 147 |
+
"learning_rate": 0.0002968780906445808,
|
| 148 |
+
"loss": 1.0462,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.16722408026755853,
|
| 153 |
+
"grad_norm": 1.0498641729354858,
|
| 154 |
+
"learning_rate": 0.00029592675027743253,
|
| 155 |
+
"loss": 1.0203,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.17558528428093645,
|
| 160 |
+
"grad_norm": 1.5126526355743408,
|
| 161 |
+
"learning_rate": 0.00029485102168776096,
|
| 162 |
+
"loss": 1.0039,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.18394648829431437,
|
| 167 |
+
"grad_norm": 1.2154971361160278,
|
| 168 |
+
"learning_rate": 0.0002936518218285368,
|
| 169 |
+
"loss": 0.9897,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.19230769230769232,
|
| 174 |
+
"grad_norm": 0.8289320468902588,
|
| 175 |
+
"learning_rate": 0.0002923301728998616,
|
| 176 |
+
"loss": 0.9631,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.20066889632107024,
|
| 181 |
+
"grad_norm": 1.4787485599517822,
|
| 182 |
+
"learning_rate": 0.0002908872014776423,
|
| 183 |
+
"loss": 0.9517,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.20903010033444816,
|
| 188 |
+
"grad_norm": 1.2933125495910645,
|
| 189 |
+
"learning_rate": 0.0002893241375532959,
|
| 190 |
+
"loss": 0.9611,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.21739130434782608,
|
| 195 |
+
"grad_norm": 1.0930614471435547,
|
| 196 |
+
"learning_rate": 0.00028764231348530267,
|
| 197 |
+
"loss": 0.9246,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.225752508361204,
|
| 202 |
+
"grad_norm": 1.1177003383636475,
|
| 203 |
+
"learning_rate": 0.00028584316286350164,
|
| 204 |
+
"loss": 0.9513,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.23411371237458195,
|
| 209 |
+
"grad_norm": 1.164829969406128,
|
| 210 |
+
"learning_rate": 0.0002839282192870955,
|
| 211 |
+
"loss": 0.9224,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24247491638795987,
|
| 216 |
+
"grad_norm": 0.5613699555397034,
|
| 217 |
+
"learning_rate": 0.00028189911505740843,
|
| 218 |
+
"loss": 0.9142,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2508361204013378,
|
| 223 |
+
"grad_norm": 0.8771304488182068,
|
| 224 |
+
"learning_rate": 0.0002797575797865093,
|
| 225 |
+
"loss": 0.9032,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2591973244147157,
|
| 230 |
+
"grad_norm": 1.156224250793457,
|
| 231 |
+
"learning_rate": 0.0002775054389228871,
|
| 232 |
+
"loss": 0.8969,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.26755852842809363,
|
| 237 |
+
"grad_norm": 1.482100486755371,
|
| 238 |
+
"learning_rate": 0.0002751446121954359,
|
| 239 |
+
"loss": 0.8972,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27591973244147155,
|
| 244 |
+
"grad_norm": 1.0462350845336914,
|
| 245 |
+
"learning_rate": 0.00027267711197707386,
|
| 246 |
+
"loss": 0.8902,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.2842809364548495,
|
| 251 |
+
"grad_norm": 0.8120772838592529,
|
| 252 |
+
"learning_rate": 0.0002701050415693934,
|
| 253 |
+
"loss": 0.8766,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.29264214046822745,
|
| 258 |
+
"grad_norm": 0.8219690322875977,
|
| 259 |
+
"learning_rate": 0.0002674305934098032,
|
| 260 |
+
"loss": 0.8838,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3010033444816054,
|
| 265 |
+
"grad_norm": 0.643622875213623,
|
| 266 |
+
"learning_rate": 0.00026465604720269026,
|
| 267 |
+
"loss": 0.882,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3093645484949833,
|
| 272 |
+
"grad_norm": 1.0544142723083496,
|
| 273 |
+
"learning_rate": 0.0002617837679761962,
|
| 274 |
+
"loss": 0.8643,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3177257525083612,
|
| 279 |
+
"grad_norm": 0.718562126159668,
|
| 280 |
+
"learning_rate": 0.0002588162040662628,
|
| 281 |
+
"loss": 0.8456,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.32608695652173914,
|
| 286 |
+
"grad_norm": 1.0501580238342285,
|
| 287 |
+
"learning_rate": 0.0002557558850296661,
|
| 288 |
+
"loss": 0.866,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.33444816053511706,
|
| 293 |
+
"grad_norm": 1.50191330909729,
|
| 294 |
+
"learning_rate": 0.00025260541948781784,
|
| 295 |
+
"loss": 0.8682,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.342809364548495,
|
| 300 |
+
"grad_norm": 2.241793394088745,
|
| 301 |
+
"learning_rate": 0.00024936749290317196,
|
| 302 |
+
"loss": 0.858,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3511705685618729,
|
| 307 |
+
"grad_norm": 0.8153356313705444,
|
| 308 |
+
"learning_rate": 0.00024604486529013106,
|
| 309 |
+
"loss": 0.8508,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3595317725752508,
|
| 314 |
+
"grad_norm": 1.1809695959091187,
|
| 315 |
+
"learning_rate": 0.00024264036886240603,
|
| 316 |
+
"loss": 0.845,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.36789297658862874,
|
| 321 |
+
"grad_norm": 0.45723193883895874,
|
| 322 |
+
"learning_rate": 0.00023915690561883125,
|
| 323 |
+
"loss": 0.8446,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3762541806020067,
|
| 328 |
+
"grad_norm": 1.4294965267181396,
|
| 329 |
+
"learning_rate": 0.00023559744486969622,
|
| 330 |
+
"loss": 0.8342,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.38461538461538464,
|
| 335 |
+
"grad_norm": 0.41016700863838196,
|
| 336 |
+
"learning_rate": 0.00023196502070569963,
|
| 337 |
+
"loss": 0.8355,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.39297658862876256,
|
| 342 |
+
"grad_norm": 0.39777177572250366,
|
| 343 |
+
"learning_rate": 0.00022826272941168556,
|
| 344 |
+
"loss": 0.8328,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4013377926421405,
|
| 349 |
+
"grad_norm": 0.9254685044288635,
|
| 350 |
+
"learning_rate": 0.00022449372682736428,
|
| 351 |
+
"loss": 0.8285,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4096989966555184,
|
| 356 |
+
"grad_norm": 0.9923207759857178,
|
| 357 |
+
"learning_rate": 0.00022066122565726914,
|
| 358 |
+
"loss": 0.8205,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4180602006688963,
|
| 363 |
+
"grad_norm": 1.5853259563446045,
|
| 364 |
+
"learning_rate": 0.00021676849273224132,
|
| 365 |
+
"loss": 0.8431,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.42642140468227424,
|
| 370 |
+
"grad_norm": 0.5669292211532593,
|
| 371 |
+
"learning_rate": 0.00021281884622477757,
|
| 372 |
+
"loss": 0.828,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.43478260869565216,
|
| 377 |
+
"grad_norm": 0.7299262285232544,
|
| 378 |
+
"learning_rate": 0.00020881565282061386,
|
| 379 |
+
"loss": 0.82,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4431438127090301,
|
| 384 |
+
"grad_norm": 2.6832640171051025,
|
| 385 |
+
"learning_rate": 0.00020476232484895653,
|
| 386 |
+
"loss": 0.8197,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.451505016722408,
|
| 391 |
+
"grad_norm": 1.040622591972351,
|
| 392 |
+
"learning_rate": 0.00020066231737380684,
|
| 393 |
+
"loss": 0.8163,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.459866220735786,
|
| 398 |
+
"grad_norm": 0.9296326637268066,
|
| 399 |
+
"learning_rate": 0.00019651912524885814,
|
| 400 |
+
"loss": 0.8207,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.4682274247491639,
|
| 405 |
+
"grad_norm": 1.341401219367981,
|
| 406 |
+
"learning_rate": 0.00019233628013847636,
|
| 407 |
+
"loss": 0.7954,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.4765886287625418,
|
| 412 |
+
"grad_norm": 1.4546632766723633,
|
| 413 |
+
"learning_rate": 0.00018811734750730306,
|
| 414 |
+
"loss": 0.8087,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.48494983277591974,
|
| 419 |
+
"grad_norm": 2.639110803604126,
|
| 420 |
+
"learning_rate": 0.000183865923581047,
|
| 421 |
+
"loss": 0.82,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.49331103678929766,
|
| 426 |
+
"grad_norm": 1.9307732582092285,
|
| 427 |
+
"learning_rate": 0.00017958563228105473,
|
| 428 |
+
"loss": 0.8261,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.5016722408026756,
|
| 433 |
+
"grad_norm": 0.8820024132728577,
|
| 434 |
+
"learning_rate": 0.000175280122135274,
|
| 435 |
+
"loss": 0.8188,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5100334448160535,
|
| 440 |
+
"grad_norm": 1.1421868801116943,
|
| 441 |
+
"learning_rate": 0.00017095306316824145,
|
| 442 |
+
"loss": 0.808,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5183946488294314,
|
| 447 |
+
"grad_norm": 1.443213701248169,
|
| 448 |
+
"learning_rate": 0.00016660814377274764,
|
| 449 |
+
"loss": 0.8246,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.5267558528428093,
|
| 454 |
+
"grad_norm": 1.0917268991470337,
|
| 455 |
+
"learning_rate": 0.00016224906756584414,
|
| 456 |
+
"loss": 0.8132,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5351170568561873,
|
| 461 |
+
"grad_norm": 1.4697446823120117,
|
| 462 |
+
"learning_rate": 0.00015787955023187394,
|
| 463 |
+
"loss": 0.7961,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5434782608695652,
|
| 468 |
+
"grad_norm": 0.5695840716362,
|
| 469 |
+
"learning_rate": 0.00015350331635521528,
|
| 470 |
+
"loss": 0.8022,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.5518394648829431,
|
| 475 |
+
"grad_norm": 0.5283718705177307,
|
| 476 |
+
"learning_rate": 0.00014912409624543942,
|
| 477 |
+
"loss": 0.8126,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.560200668896321,
|
| 482 |
+
"grad_norm": 0.604545533657074,
|
| 483 |
+
"learning_rate": 0.000144745622757588,
|
| 484 |
+
"loss": 0.8025,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.568561872909699,
|
| 489 |
+
"grad_norm": 0.5798037648200989,
|
| 490 |
+
"learning_rate": 0.00014037162811028105,
|
| 491 |
+
"loss": 0.7849,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.5769230769230769,
|
| 496 |
+
"grad_norm": 0.8034297227859497,
|
| 497 |
+
"learning_rate": 0.00013600584070436663,
|
| 498 |
+
"loss": 0.7902,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.5852842809364549,
|
| 503 |
+
"grad_norm": 0.454662948846817,
|
| 504 |
+
"learning_rate": 0.0001316519819448257,
|
| 505 |
+
"loss": 0.79,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.5936454849498328,
|
| 510 |
+
"grad_norm": 0.8804046511650085,
|
| 511 |
+
"learning_rate": 0.0001273137630686397,
|
| 512 |
+
"loss": 0.7963,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6020066889632107,
|
| 517 |
+
"grad_norm": 0.7838584780693054,
|
| 518 |
+
"learning_rate": 0.0001229948819813257,
|
| 519 |
+
"loss": 0.7967,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6103678929765887,
|
| 524 |
+
"grad_norm": 1.194453477859497,
|
| 525 |
+
"learning_rate": 0.00011869902010483487,
|
| 526 |
+
"loss": 0.7879,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6187290969899666,
|
| 531 |
+
"grad_norm": 0.972303032875061,
|
| 532 |
+
"learning_rate": 0.00011442983923950197,
|
| 533 |
+
"loss": 0.8019,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6270903010033445,
|
| 538 |
+
"grad_norm": 0.7446233034133911,
|
| 539 |
+
"learning_rate": 0.00011019097844272025,
|
| 540 |
+
"loss": 0.7786,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6354515050167224,
|
| 545 |
+
"grad_norm": 0.754374086856842,
|
| 546 |
+
"learning_rate": 0.00010598605092700247,
|
| 547 |
+
"loss": 0.792,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6438127090301003,
|
| 552 |
+
"grad_norm": 1.5724862813949585,
|
| 553 |
+
"learning_rate": 0.00010181864098007187,
|
| 554 |
+
"loss": 0.7877,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.6521739130434783,
|
| 559 |
+
"grad_norm": 0.7619232535362244,
|
| 560 |
+
"learning_rate": 9.76923009096091e-05,
|
| 561 |
+
"loss": 0.7795,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6605351170568562,
|
| 566 |
+
"grad_norm": 0.7642078995704651,
|
| 567 |
+
"learning_rate": 9.361054801525882e-05,
|
| 568 |
+
"loss": 0.7811,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.6688963210702341,
|
| 573 |
+
"grad_norm": 0.6380756497383118,
|
| 574 |
+
"learning_rate": 8.9576861590477e-05,
|
| 575 |
+
"loss": 0.7793,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.677257525083612,
|
| 580 |
+
"grad_norm": 1.0837666988372803,
|
| 581 |
+
"learning_rate": 8.559467995677535e-05,
|
| 582 |
+
"loss": 0.7833,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.68561872909699,
|
| 587 |
+
"grad_norm": 0.4329131245613098,
|
| 588 |
+
"learning_rate": 8.166739753288954e-05,
|
| 589 |
+
"loss": 0.7889,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6939799331103679,
|
| 594 |
+
"grad_norm": 0.6933662295341492,
|
| 595 |
+
"learning_rate": 7.77983619413708e-05,
|
| 596 |
+
"loss": 0.7903,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7023411371237458,
|
| 601 |
+
"grad_norm": 0.7759296298027039,
|
| 602 |
+
"learning_rate": 7.399087115506633e-05,
|
| 603 |
+
"loss": 0.7835,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.7107023411371237,
|
| 608 |
+
"grad_norm": 0.7649604082107544,
|
| 609 |
+
"learning_rate": 7.024817068592166e-05,
|
| 610 |
+
"loss": 0.7865,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7190635451505016,
|
| 615 |
+
"grad_norm": 0.4624633193016052,
|
| 616 |
+
"learning_rate": 6.657345081850015e-05,
|
| 617 |
+
"loss": 0.788,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.7274247491638796,
|
| 622 |
+
"grad_norm": 1.3198479413986206,
|
| 623 |
+
"learning_rate": 6.296984389057886e-05,
|
| 624 |
+
"loss": 0.7813,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7357859531772575,
|
| 629 |
+
"grad_norm": 0.5763963460922241,
|
| 630 |
+
"learning_rate": 5.944042162313818e-05,
|
| 631 |
+
"loss": 0.7887,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7441471571906354,
|
| 636 |
+
"grad_norm": 0.595403254032135,
|
| 637 |
+
"learning_rate": 5.59881925020216e-05,
|
| 638 |
+
"loss": 0.7767,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7525083612040134,
|
| 643 |
+
"grad_norm": 0.9068358540534973,
|
| 644 |
+
"learning_rate": 5.2616099213496704e-05,
|
| 645 |
+
"loss": 0.7774,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.7608695652173914,
|
| 650 |
+
"grad_norm": 0.6962704658508301,
|
| 651 |
+
"learning_rate": 4.93270161359043e-05,
|
| 652 |
+
"loss": 0.7844,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.7692307692307693,
|
| 657 |
+
"grad_norm": 0.6204519271850586,
|
| 658 |
+
"learning_rate": 4.612374688953315e-05,
|
| 659 |
+
"loss": 0.7835,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.7775919732441472,
|
| 664 |
+
"grad_norm": 0.4705691635608673,
|
| 665 |
+
"learning_rate": 4.300902194680902e-05,
|
| 666 |
+
"loss": 0.7796,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.7859531772575251,
|
| 671 |
+
"grad_norm": 0.7778177857398987,
|
| 672 |
+
"learning_rate": 3.998549630483525e-05,
|
| 673 |
+
"loss": 0.7864,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.794314381270903,
|
| 678 |
+
"grad_norm": 0.7931321859359741,
|
| 679 |
+
"learning_rate": 3.7055747222268256e-05,
|
| 680 |
+
"loss": 0.7733,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.802675585284281,
|
| 685 |
+
"grad_norm": 0.5870620012283325,
|
| 686 |
+
"learning_rate": 3.422227202245778e-05,
|
| 687 |
+
"loss": 0.7615,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8110367892976589,
|
| 692 |
+
"grad_norm": 0.9947313666343689,
|
| 693 |
+
"learning_rate": 3.1487485964723966e-05,
|
| 694 |
+
"loss": 0.7693,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.8193979933110368,
|
| 699 |
+
"grad_norm": 0.5786251425743103,
|
| 700 |
+
"learning_rate": 2.885372018558604e-05,
|
| 701 |
+
"loss": 0.7859,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.8277591973244147,
|
| 706 |
+
"grad_norm": 0.5991637110710144,
|
| 707 |
+
"learning_rate": 2.6323219711697368e-05,
|
| 708 |
+
"loss": 0.7781,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.8361204013377926,
|
| 713 |
+
"grad_norm": 0.7340580821037292,
|
| 714 |
+
"learning_rate": 2.3898141546180678e-05,
|
| 715 |
+
"loss": 0.7689,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.8444816053511706,
|
| 720 |
+
"grad_norm": 0.4942578971385956,
|
| 721 |
+
"learning_rate": 2.1580552829994785e-05,
|
| 722 |
+
"loss": 0.7829,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.8528428093645485,
|
| 727 |
+
"grad_norm": 0.4644772708415985,
|
| 728 |
+
"learning_rate": 1.9372429079900052e-05,
|
| 729 |
+
"loss": 0.7672,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.8612040133779264,
|
| 734 |
+
"grad_norm": 0.36809882521629333,
|
| 735 |
+
"learning_rate": 1.727565250452414e-05,
|
| 736 |
+
"loss": 0.754,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.8695652173913043,
|
| 741 |
+
"grad_norm": 0.4026561379432678,
|
| 742 |
+
"learning_rate": 1.52920103999642e-05,
|
| 743 |
+
"loss": 0.7628,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.8779264214046822,
|
| 748 |
+
"grad_norm": 0.45631930232048035,
|
| 749 |
+
"learning_rate": 1.3423193626292405e-05,
|
| 750 |
+
"loss": 0.7838,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.8862876254180602,
|
| 755 |
+
"grad_norm": 0.4896789789199829,
|
| 756 |
+
"learning_rate": 1.1670795166263846e-05,
|
| 757 |
+
"loss": 0.7797,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.8946488294314381,
|
| 762 |
+
"grad_norm": 0.4223991334438324,
|
| 763 |
+
"learning_rate": 1.003630876745522e-05,
|
| 764 |
+
"loss": 0.7747,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.903010033444816,
|
| 769 |
+
"grad_norm": 0.4364998936653137,
|
| 770 |
+
"learning_rate": 8.521127668991612e-06,
|
| 771 |
+
"loss": 0.7628,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.9113712374581939,
|
| 776 |
+
"grad_norm": 0.4812104403972626,
|
| 777 |
+
"learning_rate": 7.126543413947045e-06,
|
| 778 |
+
"loss": 0.7615,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.919732441471572,
|
| 783 |
+
"grad_norm": 0.4221721291542053,
|
| 784 |
+
"learning_rate": 5.853744748430883e-06,
|
| 785 |
+
"loss": 0.7692,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.9280936454849499,
|
| 790 |
+
"grad_norm": 0.42621150612831116,
|
| 791 |
+
"learning_rate": 4.703816608298533e-06,
|
| 792 |
+
"loss": 0.7862,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.9364548494983278,
|
| 797 |
+
"grad_norm": 0.3731984794139862,
|
| 798 |
+
"learning_rate": 3.6777391943500877e-06,
|
| 799 |
+
"loss": 0.7716,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.9448160535117057,
|
| 804 |
+
"grad_norm": 0.409588485956192,
|
| 805 |
+
"learning_rate": 2.7763871368055137e-06,
|
| 806 |
+
"loss": 0.7705,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.9531772575250836,
|
| 811 |
+
"grad_norm": 0.45919135212898254,
|
| 812 |
+
"learning_rate": 2.000528749768199e-06,
|
| 813 |
+
"loss": 0.7648,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.9615384615384616,
|
| 818 |
+
"grad_norm": 0.4654495120048523,
|
| 819 |
+
"learning_rate": 1.3508253763127974e-06,
|
| 820 |
+
"loss": 0.7715,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.9698996655518395,
|
| 825 |
+
"grad_norm": 0.37038466334342957,
|
| 826 |
+
"learning_rate": 8.278308247549992e-07,
|
| 827 |
+
"loss": 0.7731,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.9782608695652174,
|
| 832 |
+
"grad_norm": 0.40466973185539246,
|
| 833 |
+
"learning_rate": 4.3199089658449425e-07,
|
| 834 |
+
"loss": 0.7629,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.9866220735785953,
|
| 839 |
+
"grad_norm": 0.4049622118473053,
|
| 840 |
+
"learning_rate": 1.6364300646291018e-07,
|
| 841 |
+
"loss": 0.7578,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.9949832775919732,
|
| 846 |
+
"grad_norm": 0.37162256240844727,
|
| 847 |
+
"learning_rate": 2.30158946110115e-08,
|
| 848 |
+
"loss": 0.7674,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.0,
|
| 853 |
+
"eval_loss": 1.468013048171997,
|
| 854 |
+
"eval_runtime": 1.3394,
|
| 855 |
+
"eval_samples_per_second": 3.733,
|
| 856 |
+
"eval_steps_per_second": 0.747,
|
| 857 |
+
"step": 598
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0,
|
| 861 |
+
"step": 598,
|
| 862 |
+
"total_flos": 9.117045735743816e+17,
|
| 863 |
+
"train_loss": 1.9824217689475885,
|
| 864 |
+
"train_runtime": 7933.7629,
|
| 865 |
+
"train_samples_per_second": 2.411,
|
| 866 |
+
"train_steps_per_second": 0.075
|
| 867 |
+
}
|
| 868 |
+
],
|
| 869 |
+
"logging_steps": 5,
|
| 870 |
+
"max_steps": 598,
|
| 871 |
+
"num_input_tokens_seen": 0,
|
| 872 |
+
"num_train_epochs": 1,
|
| 873 |
+
"save_steps": 100,
|
| 874 |
+
"stateful_callbacks": {
|
| 875 |
+
"TrainerControl": {
|
| 876 |
+
"args": {
|
| 877 |
+
"should_epoch_stop": false,
|
| 878 |
+
"should_evaluate": false,
|
| 879 |
+
"should_log": false,
|
| 880 |
+
"should_save": true,
|
| 881 |
+
"should_training_stop": true
|
| 882 |
+
},
|
| 883 |
+
"attributes": {}
|
| 884 |
+
}
|
| 885 |
+
},
|
| 886 |
+
"total_flos": 9.117045735743816e+17,
|
| 887 |
+
"train_batch_size": 4,
|
| 888 |
+
"trial_name": null,
|
| 889 |
+
"trial_params": null
|
| 890 |
+
}
|