Qin Liu
commited on
Commit
•
811145d
1
Parent(s):
517b59b
Model save
Browse files- README.md +61 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +924 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama3-sudo-5epochs-tofu_full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# llama3-sudo-5epochs-tofu_full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 5
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.12.0
|
| 58 |
+
- Transformers 4.44.0
|
| 59 |
+
- Pytorch 2.1.2
|
| 60 |
+
- Datasets 3.0.0
|
| 61 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 158493649076224.0,
|
| 4 |
+
"train_loss": 0.9354254070281982,
|
| 5 |
+
"train_runtime": 1023.8732,
|
| 6 |
+
"train_samples": 4000,
|
| 7 |
+
"train_samples_per_second": 19.534,
|
| 8 |
+
"train_steps_per_second": 0.61
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 158493649076224.0,
|
| 4 |
+
"train_loss": 0.9354254070281982,
|
| 5 |
+
"train_runtime": 1023.8732,
|
| 6 |
+
"train_samples": 4000,
|
| 7 |
+
"train_samples_per_second": 19.534,
|
| 8 |
+
"train_steps_per_second": 0.61
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,924 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 625,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008,
|
| 13 |
+
"grad_norm": 0.0,
|
| 14 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 0.0,
|
| 21 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 22 |
+
"loss": 0.0,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 0.0,
|
| 28 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 29 |
+
"loss": 0.0,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12,
|
| 34 |
+
"grad_norm": 0.0,
|
| 35 |
+
"learning_rate": 4.761904761904762e-05,
|
| 36 |
+
"loss": 0.0,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16,
|
| 41 |
+
"grad_norm": 0.0,
|
| 42 |
+
"learning_rate": 6.349206349206349e-05,
|
| 43 |
+
"loss": 0.0,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"grad_norm": 0.0,
|
| 49 |
+
"learning_rate": 7.936507936507937e-05,
|
| 50 |
+
"loss": 0.0,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24,
|
| 55 |
+
"grad_norm": 0.0,
|
| 56 |
+
"learning_rate": 9.523809523809524e-05,
|
| 57 |
+
"loss": 0.0,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.28,
|
| 62 |
+
"grad_norm": 0.0,
|
| 63 |
+
"learning_rate": 0.00011111111111111112,
|
| 64 |
+
"loss": 0.0,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.32,
|
| 69 |
+
"grad_norm": 0.0,
|
| 70 |
+
"learning_rate": 0.00012698412698412698,
|
| 71 |
+
"loss": 0.0,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.36,
|
| 76 |
+
"grad_norm": 0.0,
|
| 77 |
+
"learning_rate": 0.00014285714285714287,
|
| 78 |
+
"loss": 0.0,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4,
|
| 83 |
+
"grad_norm": 0.0,
|
| 84 |
+
"learning_rate": 0.00015873015873015873,
|
| 85 |
+
"loss": 0.0,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.44,
|
| 90 |
+
"grad_norm": 0.0,
|
| 91 |
+
"learning_rate": 0.00017460317460317462,
|
| 92 |
+
"loss": 0.0,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.48,
|
| 97 |
+
"grad_norm": 0.0,
|
| 98 |
+
"learning_rate": 0.00019047619047619048,
|
| 99 |
+
"loss": 0.0,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.52,
|
| 104 |
+
"grad_norm": 0.0,
|
| 105 |
+
"learning_rate": 0.00019999375039475277,
|
| 106 |
+
"loss": 0.0,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.56,
|
| 111 |
+
"grad_norm": 0.0,
|
| 112 |
+
"learning_rate": 0.0001999234513064475,
|
| 113 |
+
"loss": 0.0,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6,
|
| 118 |
+
"grad_norm": 0.0,
|
| 119 |
+
"learning_rate": 0.00019977509622105233,
|
| 120 |
+
"loss": 0.0,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.64,
|
| 125 |
+
"grad_norm": 0.0,
|
| 126 |
+
"learning_rate": 0.0001995488010273198,
|
| 127 |
+
"loss": 0.0,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.68,
|
| 132 |
+
"grad_norm": 0.0,
|
| 133 |
+
"learning_rate": 0.00019924474249753655,
|
| 134 |
+
"loss": 0.0,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.72,
|
| 139 |
+
"grad_norm": 0.0,
|
| 140 |
+
"learning_rate": 0.00019886315814943647,
|
| 141 |
+
"loss": 0.0,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.76,
|
| 146 |
+
"grad_norm": 0.0,
|
| 147 |
+
"learning_rate": 0.0001984043460606618,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8,
|
| 153 |
+
"grad_norm": 0.0,
|
| 154 |
+
"learning_rate": 0.0001978686646359173,
|
| 155 |
+
"loss": 0.0,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.84,
|
| 160 |
+
"grad_norm": 4.8843664841655485,
|
| 161 |
+
"learning_rate": 0.0001972565323269996,
|
| 162 |
+
"loss": 3.5275,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.88,
|
| 167 |
+
"grad_norm": 1.9367197537847722,
|
| 168 |
+
"learning_rate": 0.00019656842730592046,
|
| 169 |
+
"loss": 2.4617,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.92,
|
| 174 |
+
"grad_norm": 1.6692050704025108,
|
| 175 |
+
"learning_rate": 0.0001958048870913786,
|
| 176 |
+
"loss": 2.0719,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.96,
|
| 181 |
+
"grad_norm": 1.0484984779217945,
|
| 182 |
+
"learning_rate": 0.0001949665081288729,
|
| 183 |
+
"loss": 1.9191,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"grad_norm": 2.084657145540847,
|
| 189 |
+
"learning_rate": 0.00019405394532478424,
|
| 190 |
+
"loss": 1.7622,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.04,
|
| 195 |
+
"grad_norm": 0.8826541418665111,
|
| 196 |
+
"learning_rate": 0.00019306791153479006,
|
| 197 |
+
"loss": 1.5793,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.08,
|
| 202 |
+
"grad_norm": 0.8402855604097518,
|
| 203 |
+
"learning_rate": 0.00019200917700701176,
|
| 204 |
+
"loss": 1.5816,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.12,
|
| 209 |
+
"grad_norm": 0.8971788963916263,
|
| 210 |
+
"learning_rate": 0.0001908785687803289,
|
| 211 |
+
"loss": 1.4692,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.16,
|
| 216 |
+
"grad_norm": 0.5837535747952808,
|
| 217 |
+
"learning_rate": 0.00018967697003833157,
|
| 218 |
+
"loss": 1.4171,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2,
|
| 223 |
+
"grad_norm": 0.6080532043018163,
|
| 224 |
+
"learning_rate": 0.0001884053194194142,
|
| 225 |
+
"loss": 1.3879,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.24,
|
| 230 |
+
"grad_norm": 0.5424236872385151,
|
| 231 |
+
"learning_rate": 0.00018706461028355104,
|
| 232 |
+
"loss": 1.3751,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.28,
|
| 237 |
+
"grad_norm": 0.521156712371918,
|
| 238 |
+
"learning_rate": 0.00018565588993632487,
|
| 239 |
+
"loss": 1.353,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.32,
|
| 244 |
+
"grad_norm": 0.5630616486472927,
|
| 245 |
+
"learning_rate": 0.0001841802588108161,
|
| 246 |
+
"loss": 1.3693,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3599999999999999,
|
| 251 |
+
"grad_norm": 0.5762860311050592,
|
| 252 |
+
"learning_rate": 0.00018263886960799062,
|
| 253 |
+
"loss": 1.3361,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.4,
|
| 258 |
+
"grad_norm": 0.5670131315191044,
|
| 259 |
+
"learning_rate": 0.00018103292639625837,
|
| 260 |
+
"loss": 1.3246,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.44,
|
| 265 |
+
"grad_norm": 0.5872553271388077,
|
| 266 |
+
"learning_rate": 0.0001793636836709057,
|
| 267 |
+
"loss": 1.3378,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.48,
|
| 272 |
+
"grad_norm": 0.47848829808272364,
|
| 273 |
+
"learning_rate": 0.0001776324453741365,
|
| 274 |
+
"loss": 1.3614,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.52,
|
| 279 |
+
"grad_norm": 0.49455580287303413,
|
| 280 |
+
"learning_rate": 0.00017584056387648727,
|
| 281 |
+
"loss": 1.2795,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.56,
|
| 286 |
+
"grad_norm": 0.5545081477783124,
|
| 287 |
+
"learning_rate": 0.0001739894389204122,
|
| 288 |
+
"loss": 1.3505,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6,
|
| 293 |
+
"grad_norm": 0.5273540066664081,
|
| 294 |
+
"learning_rate": 0.00017208051652686335,
|
| 295 |
+
"loss": 1.304,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6400000000000001,
|
| 300 |
+
"grad_norm": 0.5236332903582206,
|
| 301 |
+
"learning_rate": 0.00017011528786571969,
|
| 302 |
+
"loss": 1.2964,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6800000000000002,
|
| 307 |
+
"grad_norm": 0.522859471024846,
|
| 308 |
+
"learning_rate": 0.00016809528809094807,
|
| 309 |
+
"loss": 1.3191,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.72,
|
| 314 |
+
"grad_norm": 0.5325159438088393,
|
| 315 |
+
"learning_rate": 0.0001660220951414055,
|
| 316 |
+
"loss": 1.3365,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.76,
|
| 321 |
+
"grad_norm": 0.5932904452055382,
|
| 322 |
+
"learning_rate": 0.00016389732850821966,
|
| 323 |
+
"loss": 1.3065,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8,
|
| 328 |
+
"grad_norm": 0.5753490852273148,
|
| 329 |
+
"learning_rate": 0.0001617226479697105,
|
| 330 |
+
"loss": 1.2923,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8399999999999999,
|
| 335 |
+
"grad_norm": 0.7099770456528512,
|
| 336 |
+
"learning_rate": 0.00015949975229484134,
|
| 337 |
+
"loss": 1.3006,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.88,
|
| 342 |
+
"grad_norm": 0.5445882124083564,
|
| 343 |
+
"learning_rate": 0.00015723037791621193,
|
| 344 |
+
"loss": 1.2631,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.92,
|
| 349 |
+
"grad_norm": 0.5508092626640723,
|
| 350 |
+
"learning_rate": 0.00015491629757363032,
|
| 351 |
+
"loss": 1.2956,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.96,
|
| 356 |
+
"grad_norm": 0.5700022934921076,
|
| 357 |
+
"learning_rate": 0.00015255931892932333,
|
| 358 |
+
"loss": 1.3077,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0,
|
| 363 |
+
"grad_norm": 0.6420724844011209,
|
| 364 |
+
"learning_rate": 0.0001501612831558664,
|
| 365 |
+
"loss": 1.2865,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.04,
|
| 370 |
+
"grad_norm": 0.5185087077026251,
|
| 371 |
+
"learning_rate": 0.00014772406349793744,
|
| 372 |
+
"loss": 1.0933,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.08,
|
| 377 |
+
"grad_norm": 0.6939023149806638,
|
| 378 |
+
"learning_rate": 0.0001452495638090167,
|
| 379 |
+
"loss": 1.1302,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.12,
|
| 384 |
+
"grad_norm": 0.67218828804889,
|
| 385 |
+
"learning_rate": 0.00014273971706417647,
|
| 386 |
+
"loss": 1.1181,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.16,
|
| 391 |
+
"grad_norm": 0.6679846698249866,
|
| 392 |
+
"learning_rate": 0.00014019648385012244,
|
| 393 |
+
"loss": 1.1407,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.2,
|
| 398 |
+
"grad_norm": 0.6857639874881996,
|
| 399 |
+
"learning_rate": 0.00013762185083366556,
|
| 400 |
+
"loss": 1.1191,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.24,
|
| 405 |
+
"grad_norm": 0.6584817159906468,
|
| 406 |
+
"learning_rate": 0.00013501782920982184,
|
| 407 |
+
"loss": 1.1132,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.2800000000000002,
|
| 412 |
+
"grad_norm": 0.6587937675440276,
|
| 413 |
+
"learning_rate": 0.00013238645313075104,
|
| 414 |
+
"loss": 1.1154,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.32,
|
| 419 |
+
"grad_norm": 0.7108364768563155,
|
| 420 |
+
"learning_rate": 0.00012972977811676287,
|
| 421 |
+
"loss": 1.0738,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.36,
|
| 426 |
+
"grad_norm": 0.7654695954348383,
|
| 427 |
+
"learning_rate": 0.00012704987945063068,
|
| 428 |
+
"loss": 1.1112,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.4,
|
| 433 |
+
"grad_norm": 0.6510685094630188,
|
| 434 |
+
"learning_rate": 0.00012434885055646823,
|
| 435 |
+
"loss": 1.076,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.44,
|
| 440 |
+
"grad_norm": 0.6513602137372655,
|
| 441 |
+
"learning_rate": 0.00012162880136443447,
|
| 442 |
+
"loss": 1.0938,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.48,
|
| 447 |
+
"grad_norm": 0.6518580265652315,
|
| 448 |
+
"learning_rate": 0.00011889185666254506,
|
| 449 |
+
"loss": 1.1091,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.52,
|
| 454 |
+
"grad_norm": 0.700791005032011,
|
| 455 |
+
"learning_rate": 0.00011614015443687722,
|
| 456 |
+
"loss": 1.0928,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.56,
|
| 461 |
+
"grad_norm": 0.7137299516787894,
|
| 462 |
+
"learning_rate": 0.0001133758442014651,
|
| 463 |
+
"loss": 1.0975,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.6,
|
| 468 |
+
"grad_norm": 0.7096635920365164,
|
| 469 |
+
"learning_rate": 0.00011060108531918971,
|
| 470 |
+
"loss": 1.0866,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.64,
|
| 475 |
+
"grad_norm": 0.7329519901448388,
|
| 476 |
+
"learning_rate": 0.0001078180453149754,
|
| 477 |
+
"loss": 1.1202,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.68,
|
| 482 |
+
"grad_norm": 0.6956042484637527,
|
| 483 |
+
"learning_rate": 0.00010502889818261075,
|
| 484 |
+
"loss": 1.0804,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.7199999999999998,
|
| 489 |
+
"grad_norm": 0.708989418947315,
|
| 490 |
+
"learning_rate": 0.00010223582268651586,
|
| 491 |
+
"loss": 1.0851,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.76,
|
| 496 |
+
"grad_norm": 0.8321704062723837,
|
| 497 |
+
"learning_rate": 9.94410006597835e-05,
|
| 498 |
+
"loss": 1.0877,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.8,
|
| 503 |
+
"grad_norm": 0.774733895652043,
|
| 504 |
+
"learning_rate": 9.66466152998226e-05,
|
| 505 |
+
"loss": 1.0717,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.84,
|
| 510 |
+
"grad_norm": 0.7903318932347777,
|
| 511 |
+
"learning_rate": 9.385484946293637e-05,
|
| 512 |
+
"loss": 1.1324,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.88,
|
| 517 |
+
"grad_norm": 0.7341720746069825,
|
| 518 |
+
"learning_rate": 9.106788395916678e-05,
|
| 519 |
+
"loss": 1.1025,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.92,
|
| 524 |
+
"grad_norm": 0.7846739828245529,
|
| 525 |
+
"learning_rate": 8.828789584873754e-05,
|
| 526 |
+
"loss": 1.1411,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.96,
|
| 531 |
+
"grad_norm": 0.7345758394982582,
|
| 532 |
+
"learning_rate": 8.551705674142617e-05,
|
| 533 |
+
"loss": 1.103,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.0,
|
| 538 |
+
"grad_norm": 0.7564552144611311,
|
| 539 |
+
"learning_rate": 8.275753110019367e-05,
|
| 540 |
+
"loss": 1.07,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.04,
|
| 545 |
+
"grad_norm": 0.7129645924023327,
|
| 546 |
+
"learning_rate": 8.001147455039735e-05,
|
| 547 |
+
"loss": 0.98,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.08,
|
| 552 |
+
"grad_norm": 0.7646350891088591,
|
| 553 |
+
"learning_rate": 7.728103219590681e-05,
|
| 554 |
+
"loss": 0.927,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.12,
|
| 559 |
+
"grad_norm": 1.0269234227263822,
|
| 560 |
+
"learning_rate": 7.456833694343906e-05,
|
| 561 |
+
"loss": 0.9207,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.16,
|
| 566 |
+
"grad_norm": 0.8773416480143502,
|
| 567 |
+
"learning_rate": 7.18755078364214e-05,
|
| 568 |
+
"loss": 0.943,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.2,
|
| 573 |
+
"grad_norm": 0.8734652261717027,
|
| 574 |
+
"learning_rate": 6.920464839968405e-05,
|
| 575 |
+
"loss": 0.9383,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.24,
|
| 580 |
+
"grad_norm": 0.9047400612085651,
|
| 581 |
+
"learning_rate": 6.65578449962749e-05,
|
| 582 |
+
"loss": 0.9265,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.2800000000000002,
|
| 587 |
+
"grad_norm": 0.9563261274281473,
|
| 588 |
+
"learning_rate": 6.393716519768047e-05,
|
| 589 |
+
"loss": 0.9405,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.32,
|
| 594 |
+
"grad_norm": 0.8697172121076815,
|
| 595 |
+
"learning_rate": 6.134465616872598e-05,
|
| 596 |
+
"loss": 0.9677,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.36,
|
| 601 |
+
"grad_norm": 0.8811910025949315,
|
| 602 |
+
"learning_rate": 5.878234306841637e-05,
|
| 603 |
+
"loss": 0.9201,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.4,
|
| 608 |
+
"grad_norm": 0.91464519619479,
|
| 609 |
+
"learning_rate": 5.62522274679673e-05,
|
| 610 |
+
"loss": 0.9695,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.44,
|
| 615 |
+
"grad_norm": 0.8875127022364347,
|
| 616 |
+
"learning_rate": 5.375628578726181e-05,
|
| 617 |
+
"loss": 0.9259,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.48,
|
| 622 |
+
"grad_norm": 0.9140384002718888,
|
| 623 |
+
"learning_rate": 5.1296467750954314e-05,
|
| 624 |
+
"loss": 0.9382,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.52,
|
| 629 |
+
"grad_norm": 0.9130113252787699,
|
| 630 |
+
"learning_rate": 4.8874694865427676e-05,
|
| 631 |
+
"loss": 0.9578,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.56,
|
| 636 |
+
"grad_norm": 0.9169457361937253,
|
| 637 |
+
"learning_rate": 4.649285891779327e-05,
|
| 638 |
+
"loss": 0.9179,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.6,
|
| 643 |
+
"grad_norm": 0.9424562700953132,
|
| 644 |
+
"learning_rate": 4.415282049810644e-05,
|
| 645 |
+
"loss": 0.9191,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.64,
|
| 650 |
+
"grad_norm": 0.9245761957614527,
|
| 651 |
+
"learning_rate": 4.1856407545951834e-05,
|
| 652 |
+
"loss": 0.9242,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.68,
|
| 657 |
+
"grad_norm": 0.9672178741357245,
|
| 658 |
+
"learning_rate": 3.9605413922533874e-05,
|
| 659 |
+
"loss": 0.9503,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.7199999999999998,
|
| 664 |
+
"grad_norm": 0.952034748851393,
|
| 665 |
+
"learning_rate": 3.740159800938784e-05,
|
| 666 |
+
"loss": 0.9319,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.76,
|
| 671 |
+
"grad_norm": 0.9200447825604482,
|
| 672 |
+
"learning_rate": 3.5246681334806175e-05,
|
| 673 |
+
"loss": 0.9378,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.8,
|
| 678 |
+
"grad_norm": 0.9213126186210203,
|
| 679 |
+
"learning_rate": 3.3142347229053015e-05,
|
| 680 |
+
"loss": 0.891,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.84,
|
| 685 |
+
"grad_norm": 1.0516175908801786,
|
| 686 |
+
"learning_rate": 3.109023950941736e-05,
|
| 687 |
+
"loss": 0.9619,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.88,
|
| 692 |
+
"grad_norm": 0.9277117122712767,
|
| 693 |
+
"learning_rate": 2.909196119613218e-05,
|
| 694 |
+
"loss": 0.9036,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.92,
|
| 699 |
+
"grad_norm": 0.9156379739401684,
|
| 700 |
+
"learning_rate": 2.7149073260162416e-05,
|
| 701 |
+
"loss": 0.9272,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.96,
|
| 706 |
+
"grad_norm": 0.9956486640584029,
|
| 707 |
+
"learning_rate": 2.5263093403840142e-05,
|
| 708 |
+
"loss": 0.9244,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.0,
|
| 713 |
+
"grad_norm": 0.911041002840735,
|
| 714 |
+
"learning_rate": 2.3435494875299314e-05,
|
| 715 |
+
"loss": 0.8899,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.04,
|
| 720 |
+
"grad_norm": 0.9135972762786166,
|
| 721 |
+
"learning_rate": 2.166770531763633e-05,
|
| 722 |
+
"loss": 0.8285,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.08,
|
| 727 |
+
"grad_norm": 0.9273774203812593,
|
| 728 |
+
"learning_rate": 1.9961105653695266e-05,
|
| 729 |
+
"loss": 0.8119,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.12,
|
| 734 |
+
"grad_norm": 1.0596081187704738,
|
| 735 |
+
"learning_rate": 1.8317029007349085e-05,
|
| 736 |
+
"loss": 0.8444,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.16,
|
| 741 |
+
"grad_norm": 1.1322325016109431,
|
| 742 |
+
"learning_rate": 1.6736759662119183e-05,
|
| 743 |
+
"loss": 0.8257,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.2,
|
| 748 |
+
"grad_norm": 1.0759195776028518,
|
| 749 |
+
"learning_rate": 1.5221532057947419e-05,
|
| 750 |
+
"loss": 0.8464,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.24,
|
| 755 |
+
"grad_norm": 1.1095362756261793,
|
| 756 |
+
"learning_rate": 1.3772529826903269e-05,
|
| 757 |
+
"loss": 0.8389,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.28,
|
| 762 |
+
"grad_norm": 1.2253346667978913,
|
| 763 |
+
"learning_rate": 1.23908848685804e-05,
|
| 764 |
+
"loss": 0.8397,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.32,
|
| 769 |
+
"grad_norm": 1.1019952367500718,
|
| 770 |
+
"learning_rate": 1.1077676465904208e-05,
|
| 771 |
+
"loss": 0.7909,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.36,
|
| 776 |
+
"grad_norm": 1.1104082298724263,
|
| 777 |
+
"learning_rate": 9.833930442041506e-06,
|
| 778 |
+
"loss": 0.8177,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.4,
|
| 783 |
+
"grad_norm": 1.1198369280329472,
|
| 784 |
+
"learning_rate": 8.660618359070604e-06,
|
| 785 |
+
"loss": 0.8027,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.44,
|
| 790 |
+
"grad_norm": 1.1477607984789764,
|
| 791 |
+
"learning_rate": 7.558656759037797e-06,
|
| 792 |
+
"loss": 0.819,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.48,
|
| 797 |
+
"grad_norm": 1.1041070390660572,
|
| 798 |
+
"learning_rate": 6.528906447993288e-06,
|
| 799 |
+
"loss": 0.8273,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.52,
|
| 804 |
+
"grad_norm": 1.097202307726145,
|
| 805 |
+
"learning_rate": 5.572171823565797e-06,
|
| 806 |
+
"loss": 0.8386,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.5600000000000005,
|
| 811 |
+
"grad_norm": 1.0733098668282173,
|
| 812 |
+
"learning_rate": 4.689200246600867e-06,
|
| 813 |
+
"loss": 0.7639,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.6,
|
| 818 |
+
"grad_norm": 1.1855618601043227,
|
| 819 |
+
"learning_rate": 3.880681457354118e-06,
|
| 820 |
+
"loss": 0.8059,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.64,
|
| 825 |
+
"grad_norm": 1.0801503593334882,
|
| 826 |
+
"learning_rate": 3.1472470366950334e-06,
|
| 827 |
+
"loss": 0.8106,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.68,
|
| 832 |
+
"grad_norm": 1.0698196762898835,
|
| 833 |
+
"learning_rate": 2.4894699127426367e-06,
|
| 834 |
+
"loss": 0.8094,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.72,
|
| 839 |
+
"grad_norm": 1.1338177263997045,
|
| 840 |
+
"learning_rate": 1.907863913318153e-06,
|
| 841 |
+
"loss": 0.8446,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.76,
|
| 846 |
+
"grad_norm": 1.0725846404716162,
|
| 847 |
+
"learning_rate": 1.4028833645643113e-06,
|
| 848 |
+
"loss": 0.8192,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.8,
|
| 853 |
+
"grad_norm": 1.1178750406023408,
|
| 854 |
+
"learning_rate": 9.749227360448143e-07,
|
| 855 |
+
"loss": 0.8228,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.84,
|
| 860 |
+
"grad_norm": 1.1186187264597325,
|
| 861 |
+
"learning_rate": 6.243163326014267e-07,
|
| 862 |
+
"loss": 0.8227,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.88,
|
| 867 |
+
"grad_norm": 1.0422142146950775,
|
| 868 |
+
"learning_rate": 3.5133803320896994e-07,
|
| 869 |
+
"loss": 0.8152,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.92,
|
| 874 |
+
"grad_norm": 1.0424393555941693,
|
| 875 |
+
"learning_rate": 1.562010770326916e-07,
|
| 876 |
+
"loss": 0.7819,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 4.96,
|
| 881 |
+
"grad_norm": 1.1517583346783666,
|
| 882 |
+
"learning_rate": 3.905789685471062e-08,
|
| 883 |
+
"loss": 0.8124,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.0,
|
| 888 |
+
"grad_norm": 1.0989408579221684,
|
| 889 |
+
"learning_rate": 0.0,
|
| 890 |
+
"loss": 0.8157,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.0,
|
| 895 |
+
"step": 625,
|
| 896 |
+
"total_flos": 158493649076224.0,
|
| 897 |
+
"train_loss": 0.9354254070281982,
|
| 898 |
+
"train_runtime": 1023.8732,
|
| 899 |
+
"train_samples_per_second": 19.534,
|
| 900 |
+
"train_steps_per_second": 0.61
|
| 901 |
+
}
|
| 902 |
+
],
|
| 903 |
+
"logging_steps": 5,
|
| 904 |
+
"max_steps": 625,
|
| 905 |
+
"num_input_tokens_seen": 0,
|
| 906 |
+
"num_train_epochs": 5,
|
| 907 |
+
"save_steps": 100,
|
| 908 |
+
"stateful_callbacks": {
|
| 909 |
+
"TrainerControl": {
|
| 910 |
+
"args": {
|
| 911 |
+
"should_epoch_stop": false,
|
| 912 |
+
"should_evaluate": false,
|
| 913 |
+
"should_log": false,
|
| 914 |
+
"should_save": true,
|
| 915 |
+
"should_training_stop": true
|
| 916 |
+
},
|
| 917 |
+
"attributes": {}
|
| 918 |
+
}
|
| 919 |
+
},
|
| 920 |
+
"total_flos": 158493649076224.0,
|
| 921 |
+
"train_batch_size": 8,
|
| 922 |
+
"trial_name": null,
|
| 923 |
+
"trial_params": null
|
| 924 |
+
}
|