Model save
Browse files- README.md +61 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1512 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: negative_sent
|
| 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 |
+
# negative_sent
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 1e-05
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- total_eval_batch_size: 4
|
| 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: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.13.0
|
| 58 |
+
- Transformers 4.45.1
|
| 59 |
+
- Pytorch 2.4.1+cu121
|
| 60 |
+
- Datasets 3.0.1
|
| 61 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1940427569627136.0,
|
| 4 |
+
"train_loss": 1.0122476654034465,
|
| 5 |
+
"train_runtime": 20247.7008,
|
| 6 |
+
"train_samples": 100000,
|
| 7 |
+
"train_samples_per_second": 3.298,
|
| 8 |
+
"train_steps_per_second": 0.052
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1940427569627136.0,
|
| 4 |
+
"train_loss": 1.0122476654034465,
|
| 5 |
+
"train_runtime": 20247.7008,
|
| 6 |
+
"train_samples": 100000,
|
| 7 |
+
"train_samples_per_second": 3.298,
|
| 8 |
+
"train_steps_per_second": 0.052
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1512 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1044,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0009578544061302681,
|
| 13 |
+
"grad_norm": 0.6597593171619324,
|
| 14 |
+
"learning_rate": 9.523809523809525e-08,
|
| 15 |
+
"loss": 1.1525,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004789272030651341,
|
| 20 |
+
"grad_norm": 0.6607550915738474,
|
| 21 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 22 |
+
"loss": 1.1632,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.009578544061302681,
|
| 27 |
+
"grad_norm": 0.6985874969645404,
|
| 28 |
+
"learning_rate": 9.523809523809525e-07,
|
| 29 |
+
"loss": 1.1753,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.014367816091954023,
|
| 34 |
+
"grad_norm": 0.6553768135986224,
|
| 35 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 36 |
+
"loss": 1.1488,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.019157088122605363,
|
| 41 |
+
"grad_norm": 0.6087816631352209,
|
| 42 |
+
"learning_rate": 1.904761904761905e-06,
|
| 43 |
+
"loss": 1.1384,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.023946360153256706,
|
| 48 |
+
"grad_norm": 0.5225466109798246,
|
| 49 |
+
"learning_rate": 2.380952380952381e-06,
|
| 50 |
+
"loss": 1.122,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.028735632183908046,
|
| 55 |
+
"grad_norm": 0.5080052683286845,
|
| 56 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 57 |
+
"loss": 1.1505,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.033524904214559385,
|
| 62 |
+
"grad_norm": 0.4341207873557241,
|
| 63 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 64 |
+
"loss": 1.1339,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.038314176245210725,
|
| 69 |
+
"grad_norm": 0.3985137882747194,
|
| 70 |
+
"learning_rate": 3.80952380952381e-06,
|
| 71 |
+
"loss": 1.1282,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04310344827586207,
|
| 76 |
+
"grad_norm": 0.36938748261120696,
|
| 77 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 78 |
+
"loss": 1.1141,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04789272030651341,
|
| 83 |
+
"grad_norm": 0.31186688358132403,
|
| 84 |
+
"learning_rate": 4.761904761904762e-06,
|
| 85 |
+
"loss": 1.0914,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05268199233716475,
|
| 90 |
+
"grad_norm": 0.3279958963323018,
|
| 91 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 92 |
+
"loss": 1.1115,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05747126436781609,
|
| 97 |
+
"grad_norm": 0.3107640896000187,
|
| 98 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 99 |
+
"loss": 1.0897,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06226053639846743,
|
| 104 |
+
"grad_norm": 0.3071723661825106,
|
| 105 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 106 |
+
"loss": 1.1045,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06704980842911877,
|
| 111 |
+
"grad_norm": 0.2936092764163838,
|
| 112 |
+
"learning_rate": 6.666666666666667e-06,
|
| 113 |
+
"loss": 1.0661,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.07183908045977011,
|
| 118 |
+
"grad_norm": 0.28053978486957076,
|
| 119 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 120 |
+
"loss": 1.0887,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07662835249042145,
|
| 125 |
+
"grad_norm": 0.2891456438800518,
|
| 126 |
+
"learning_rate": 7.61904761904762e-06,
|
| 127 |
+
"loss": 1.0756,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.08141762452107279,
|
| 132 |
+
"grad_norm": 0.24950135731624706,
|
| 133 |
+
"learning_rate": 8.095238095238097e-06,
|
| 134 |
+
"loss": 1.0478,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08620689655172414,
|
| 139 |
+
"grad_norm": 0.23670461068088686,
|
| 140 |
+
"learning_rate": 8.571428571428571e-06,
|
| 141 |
+
"loss": 1.0389,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.09099616858237548,
|
| 146 |
+
"grad_norm": 0.2507461508986584,
|
| 147 |
+
"learning_rate": 9.047619047619049e-06,
|
| 148 |
+
"loss": 1.0509,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09578544061302682,
|
| 153 |
+
"grad_norm": 0.22930855800514297,
|
| 154 |
+
"learning_rate": 9.523809523809525e-06,
|
| 155 |
+
"loss": 1.0377,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.10057471264367816,
|
| 160 |
+
"grad_norm": 0.24445927836597864,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 1.0506,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1053639846743295,
|
| 167 |
+
"grad_norm": 0.22388714842997454,
|
| 168 |
+
"learning_rate": 9.999300418283908e-06,
|
| 169 |
+
"loss": 1.0377,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11015325670498084,
|
| 174 |
+
"grad_norm": 0.2406057364217601,
|
| 175 |
+
"learning_rate": 9.997201868901463e-06,
|
| 176 |
+
"loss": 1.0374,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11494252873563218,
|
| 181 |
+
"grad_norm": 0.2275701466092952,
|
| 182 |
+
"learning_rate": 9.993704939095376e-06,
|
| 183 |
+
"loss": 1.0663,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.11973180076628352,
|
| 188 |
+
"grad_norm": 0.22200651495287974,
|
| 189 |
+
"learning_rate": 9.988810607420912e-06,
|
| 190 |
+
"loss": 1.0448,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.12452107279693486,
|
| 195 |
+
"grad_norm": 0.22051254365376602,
|
| 196 |
+
"learning_rate": 9.982520243472044e-06,
|
| 197 |
+
"loss": 1.0099,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12931034482758622,
|
| 202 |
+
"grad_norm": 0.23279527845715264,
|
| 203 |
+
"learning_rate": 9.974835607498224e-06,
|
| 204 |
+
"loss": 1.0212,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.13409961685823754,
|
| 209 |
+
"grad_norm": 0.22813702069156522,
|
| 210 |
+
"learning_rate": 9.965758849911774e-06,
|
| 211 |
+
"loss": 1.023,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1388888888888889,
|
| 216 |
+
"grad_norm": 0.23555996785615885,
|
| 217 |
+
"learning_rate": 9.955292510686156e-06,
|
| 218 |
+
"loss": 0.9997,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.14367816091954022,
|
| 223 |
+
"grad_norm": 0.2560040654609538,
|
| 224 |
+
"learning_rate": 9.943439518645193e-06,
|
| 225 |
+
"loss": 1.0172,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.14846743295019157,
|
| 230 |
+
"grad_norm": 0.24096780952464245,
|
| 231 |
+
"learning_rate": 9.930203190643491e-06,
|
| 232 |
+
"loss": 0.9876,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1532567049808429,
|
| 237 |
+
"grad_norm": 0.24193989881098193,
|
| 238 |
+
"learning_rate": 9.915587230638269e-06,
|
| 239 |
+
"loss": 1.0417,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15804597701149425,
|
| 244 |
+
"grad_norm": 0.24788380685714667,
|
| 245 |
+
"learning_rate": 9.899595728652883e-06,
|
| 246 |
+
"loss": 1.0332,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.16283524904214558,
|
| 251 |
+
"grad_norm": 0.2570877531631883,
|
| 252 |
+
"learning_rate": 9.882233159632297e-06,
|
| 253 |
+
"loss": 1.0129,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16762452107279693,
|
| 258 |
+
"grad_norm": 0.26735645578353723,
|
| 259 |
+
"learning_rate": 9.863504382190838e-06,
|
| 260 |
+
"loss": 1.0255,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1724137931034483,
|
| 265 |
+
"grad_norm": 0.24596191852493296,
|
| 266 |
+
"learning_rate": 9.843414637252615e-06,
|
| 267 |
+
"loss": 1.0125,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1772030651340996,
|
| 272 |
+
"grad_norm": 0.2510254446995529,
|
| 273 |
+
"learning_rate": 9.821969546584922e-06,
|
| 274 |
+
"loss": 1.022,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.18199233716475097,
|
| 279 |
+
"grad_norm": 0.2626288820781652,
|
| 280 |
+
"learning_rate": 9.79917511122509e-06,
|
| 281 |
+
"loss": 1.0016,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1867816091954023,
|
| 286 |
+
"grad_norm": 0.2588872211996587,
|
| 287 |
+
"learning_rate": 9.775037709801206e-06,
|
| 288 |
+
"loss": 1.0292,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.19157088122605365,
|
| 293 |
+
"grad_norm": 0.28272889728543066,
|
| 294 |
+
"learning_rate": 9.749564096747148e-06,
|
| 295 |
+
"loss": 1.0255,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.19636015325670497,
|
| 300 |
+
"grad_norm": 0.25691560926098406,
|
| 301 |
+
"learning_rate": 9.722761400412496e-06,
|
| 302 |
+
"loss": 1.0205,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.20114942528735633,
|
| 307 |
+
"grad_norm": 0.31206698507075104,
|
| 308 |
+
"learning_rate": 9.694637121067764e-06,
|
| 309 |
+
"loss": 1.0018,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.20593869731800765,
|
| 314 |
+
"grad_norm": 0.24725309050346184,
|
| 315 |
+
"learning_rate": 9.6651991288056e-06,
|
| 316 |
+
"loss": 1.013,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.210727969348659,
|
| 321 |
+
"grad_norm": 0.2530356632425841,
|
| 322 |
+
"learning_rate": 9.63445566133846e-06,
|
| 323 |
+
"loss": 0.9921,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.21551724137931033,
|
| 328 |
+
"grad_norm": 0.2784122469884546,
|
| 329 |
+
"learning_rate": 9.602415321693434e-06,
|
| 330 |
+
"loss": 1.0066,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.22030651340996169,
|
| 335 |
+
"grad_norm": 0.3098632552557301,
|
| 336 |
+
"learning_rate": 9.569087075804842e-06,
|
| 337 |
+
"loss": 1.0062,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22509578544061304,
|
| 342 |
+
"grad_norm": 0.26451308039501314,
|
| 343 |
+
"learning_rate": 9.534480250005263e-06,
|
| 344 |
+
"loss": 0.9951,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22988505747126436,
|
| 349 |
+
"grad_norm": 0.27301629134605937,
|
| 350 |
+
"learning_rate": 9.498604528415731e-06,
|
| 351 |
+
"loss": 1.0347,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.23467432950191572,
|
| 356 |
+
"grad_norm": 0.2891326880180606,
|
| 357 |
+
"learning_rate": 9.461469950235795e-06,
|
| 358 |
+
"loss": 1.0114,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23946360153256704,
|
| 363 |
+
"grad_norm": 0.26574747916476,
|
| 364 |
+
"learning_rate": 9.423086906934228e-06,
|
| 365 |
+
"loss": 1.0272,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2442528735632184,
|
| 370 |
+
"grad_norm": 0.26114773270931335,
|
| 371 |
+
"learning_rate": 9.38346613934115e-06,
|
| 372 |
+
"loss": 1.0039,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.24904214559386972,
|
| 377 |
+
"grad_norm": 0.28383740993290196,
|
| 378 |
+
"learning_rate": 9.342618734642395e-06,
|
| 379 |
+
"loss": 1.0077,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.25383141762452105,
|
| 384 |
+
"grad_norm": 0.28127484887890697,
|
| 385 |
+
"learning_rate": 9.300556123276955e-06,
|
| 386 |
+
"loss": 1.0306,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.25862068965517243,
|
| 391 |
+
"grad_norm": 0.2702807344360773,
|
| 392 |
+
"learning_rate": 9.257290075738365e-06,
|
| 393 |
+
"loss": 0.9924,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26340996168582376,
|
| 398 |
+
"grad_norm": 0.2912366855364206,
|
| 399 |
+
"learning_rate": 9.212832699280942e-06,
|
| 400 |
+
"loss": 1.026,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2681992337164751,
|
| 405 |
+
"grad_norm": 0.30617702200806085,
|
| 406 |
+
"learning_rate": 9.16719643453177e-06,
|
| 407 |
+
"loss": 1.0247,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.27298850574712646,
|
| 412 |
+
"grad_norm": 0.2590934020046758,
|
| 413 |
+
"learning_rate": 9.120394052009412e-06,
|
| 414 |
+
"loss": 1.0211,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.2777777777777778,
|
| 419 |
+
"grad_norm": 0.27434400868197933,
|
| 420 |
+
"learning_rate": 9.072438648550304e-06,
|
| 421 |
+
"loss": 1.0243,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2825670498084291,
|
| 426 |
+
"grad_norm": 0.2813695079919259,
|
| 427 |
+
"learning_rate": 9.023343643643821e-06,
|
| 428 |
+
"loss": 1.0008,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.28735632183908044,
|
| 433 |
+
"grad_norm": 0.2764043745947579,
|
| 434 |
+
"learning_rate": 8.973122775677078e-06,
|
| 435 |
+
"loss": 1.0066,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2921455938697318,
|
| 440 |
+
"grad_norm": 0.2993769190948342,
|
| 441 |
+
"learning_rate": 8.921790098090477e-06,
|
| 442 |
+
"loss": 1.015,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.29693486590038315,
|
| 447 |
+
"grad_norm": 0.28718834695385625,
|
| 448 |
+
"learning_rate": 8.869359975445085e-06,
|
| 449 |
+
"loss": 1.0212,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3017241379310345,
|
| 454 |
+
"grad_norm": 0.3787907086651271,
|
| 455 |
+
"learning_rate": 8.815847079402972e-06,
|
| 456 |
+
"loss": 1.0079,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.3065134099616858,
|
| 461 |
+
"grad_norm": 0.3012426621088511,
|
| 462 |
+
"learning_rate": 8.761266384621599e-06,
|
| 463 |
+
"loss": 1.0245,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3113026819923372,
|
| 468 |
+
"grad_norm": 0.545229044151294,
|
| 469 |
+
"learning_rate": 8.705633164563413e-06,
|
| 470 |
+
"loss": 1.0014,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3160919540229885,
|
| 475 |
+
"grad_norm": 0.3018913245413703,
|
| 476 |
+
"learning_rate": 8.648962987221837e-06,
|
| 477 |
+
"loss": 1.0035,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.32088122605363983,
|
| 482 |
+
"grad_norm": 0.2937330943277994,
|
| 483 |
+
"learning_rate": 8.591271710764839e-06,
|
| 484 |
+
"loss": 0.9932,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.32567049808429116,
|
| 489 |
+
"grad_norm": 0.30415781861083496,
|
| 490 |
+
"learning_rate": 8.532575479097294e-06,
|
| 491 |
+
"loss": 0.982,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.33045977011494254,
|
| 496 |
+
"grad_norm": 0.2726446228184506,
|
| 497 |
+
"learning_rate": 8.472890717343391e-06,
|
| 498 |
+
"loss": 0.9992,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.33524904214559387,
|
| 503 |
+
"grad_norm": 0.2841460417699516,
|
| 504 |
+
"learning_rate": 8.412234127250353e-06,
|
| 505 |
+
"loss": 1.0007,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3400383141762452,
|
| 510 |
+
"grad_norm": 0.313253280455998,
|
| 511 |
+
"learning_rate": 8.350622682514735e-06,
|
| 512 |
+
"loss": 0.9951,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.3448275862068966,
|
| 517 |
+
"grad_norm": 0.33772538052784323,
|
| 518 |
+
"learning_rate": 8.288073624032634e-06,
|
| 519 |
+
"loss": 1.0169,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3496168582375479,
|
| 524 |
+
"grad_norm": 0.2810004404857808,
|
| 525 |
+
"learning_rate": 8.224604455075115e-06,
|
| 526 |
+
"loss": 1.0086,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3544061302681992,
|
| 531 |
+
"grad_norm": 0.2817546952474833,
|
| 532 |
+
"learning_rate": 8.160232936390239e-06,
|
| 533 |
+
"loss": 0.9888,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.35919540229885055,
|
| 538 |
+
"grad_norm": 0.32316453097441,
|
| 539 |
+
"learning_rate": 8.094977081233006e-06,
|
| 540 |
+
"loss": 0.997,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.36398467432950193,
|
| 545 |
+
"grad_norm": 0.2920029553424864,
|
| 546 |
+
"learning_rate": 8.02885515032467e-06,
|
| 547 |
+
"loss": 1.0172,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.36877394636015326,
|
| 552 |
+
"grad_norm": 0.28736749227532504,
|
| 553 |
+
"learning_rate": 7.961885646742793e-06,
|
| 554 |
+
"loss": 1.0092,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3735632183908046,
|
| 559 |
+
"grad_norm": 0.29552008976856375,
|
| 560 |
+
"learning_rate": 7.894087310743468e-06,
|
| 561 |
+
"loss": 0.9952,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3783524904214559,
|
| 566 |
+
"grad_norm": 0.28037261402408636,
|
| 567 |
+
"learning_rate": 7.825479114517197e-06,
|
| 568 |
+
"loss": 1.0148,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.3831417624521073,
|
| 573 |
+
"grad_norm": 0.3259544387907705,
|
| 574 |
+
"learning_rate": 7.756080256879837e-06,
|
| 575 |
+
"loss": 1.0172,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3879310344827586,
|
| 580 |
+
"grad_norm": 0.2866306787997861,
|
| 581 |
+
"learning_rate": 7.685910157900158e-06,
|
| 582 |
+
"loss": 0.9969,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.39272030651340994,
|
| 587 |
+
"grad_norm": 0.27836252924957877,
|
| 588 |
+
"learning_rate": 7.614988453465469e-06,
|
| 589 |
+
"loss": 0.9981,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3975095785440613,
|
| 594 |
+
"grad_norm": 0.2881265537652179,
|
| 595 |
+
"learning_rate": 7.5433349897868445e-06,
|
| 596 |
+
"loss": 1.0075,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.40229885057471265,
|
| 601 |
+
"grad_norm": 0.286210264814618,
|
| 602 |
+
"learning_rate": 7.470969817845518e-06,
|
| 603 |
+
"loss": 1.0025,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.407088122605364,
|
| 608 |
+
"grad_norm": 0.28784515054514276,
|
| 609 |
+
"learning_rate": 7.397913187781962e-06,
|
| 610 |
+
"loss": 0.9918,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4118773946360153,
|
| 615 |
+
"grad_norm": 0.28225636678596183,
|
| 616 |
+
"learning_rate": 7.324185543229226e-06,
|
| 617 |
+
"loss": 1.0164,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4166666666666667,
|
| 622 |
+
"grad_norm": 0.30273570716493303,
|
| 623 |
+
"learning_rate": 7.249807515592149e-06,
|
| 624 |
+
"loss": 0.991,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.421455938697318,
|
| 629 |
+
"grad_norm": 0.29638416230646264,
|
| 630 |
+
"learning_rate": 7.174799918274018e-06,
|
| 631 |
+
"loss": 1.0103,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.42624521072796934,
|
| 636 |
+
"grad_norm": 0.27796285045314706,
|
| 637 |
+
"learning_rate": 7.099183740852296e-06,
|
| 638 |
+
"loss": 0.9929,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.43103448275862066,
|
| 643 |
+
"grad_norm": 0.3024800017009751,
|
| 644 |
+
"learning_rate": 7.022980143205046e-06,
|
| 645 |
+
"loss": 0.9945,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.43582375478927204,
|
| 650 |
+
"grad_norm": 0.308729839004599,
|
| 651 |
+
"learning_rate": 6.946210449589714e-06,
|
| 652 |
+
"loss": 1.0131,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.44061302681992337,
|
| 657 |
+
"grad_norm": 0.29787252415350113,
|
| 658 |
+
"learning_rate": 6.868896142675903e-06,
|
| 659 |
+
"loss": 1.0053,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4454022988505747,
|
| 664 |
+
"grad_norm": 0.28555796101935293,
|
| 665 |
+
"learning_rate": 6.791058857533814e-06,
|
| 666 |
+
"loss": 1.0106,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4501915708812261,
|
| 671 |
+
"grad_norm": 0.27754653040108523,
|
| 672 |
+
"learning_rate": 6.712720375580057e-06,
|
| 673 |
+
"loss": 1.0127,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.4549808429118774,
|
| 678 |
+
"grad_norm": 0.3064883256256046,
|
| 679 |
+
"learning_rate": 6.633902618482484e-06,
|
| 680 |
+
"loss": 1.0137,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.45977011494252873,
|
| 685 |
+
"grad_norm": 0.2871757827962217,
|
| 686 |
+
"learning_rate": 6.554627642025807e-06,
|
| 687 |
+
"loss": 0.9808,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.46455938697318006,
|
| 692 |
+
"grad_norm": 0.32016740057261645,
|
| 693 |
+
"learning_rate": 6.474917629939652e-06,
|
| 694 |
+
"loss": 1.0154,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.46934865900383144,
|
| 699 |
+
"grad_norm": 0.28945157272232624,
|
| 700 |
+
"learning_rate": 6.394794887690838e-06,
|
| 701 |
+
"loss": 0.987,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.47413793103448276,
|
| 706 |
+
"grad_norm": 0.45234637623400176,
|
| 707 |
+
"learning_rate": 6.314281836241573e-06,
|
| 708 |
+
"loss": 1.0072,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4789272030651341,
|
| 713 |
+
"grad_norm": 0.3043561526142259,
|
| 714 |
+
"learning_rate": 6.233401005775339e-06,
|
| 715 |
+
"loss": 0.9947,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4837164750957854,
|
| 720 |
+
"grad_norm": 0.3021339898048032,
|
| 721 |
+
"learning_rate": 6.1521750293922035e-06,
|
| 722 |
+
"loss": 1.0168,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4885057471264368,
|
| 727 |
+
"grad_norm": 0.262840671697266,
|
| 728 |
+
"learning_rate": 6.070626636775349e-06,
|
| 729 |
+
"loss": 0.9854,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4932950191570881,
|
| 734 |
+
"grad_norm": 0.2717384304425024,
|
| 735 |
+
"learning_rate": 5.988778647830554e-06,
|
| 736 |
+
"loss": 0.9847,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.49808429118773945,
|
| 741 |
+
"grad_norm": 0.3005959006799932,
|
| 742 |
+
"learning_rate": 5.906653966300444e-06,
|
| 743 |
+
"loss": 1.0007,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5028735632183908,
|
| 748 |
+
"grad_norm": 0.2810709946318669,
|
| 749 |
+
"learning_rate": 5.824275573355278e-06,
|
| 750 |
+
"loss": 0.9891,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5076628352490421,
|
| 755 |
+
"grad_norm": 0.31324328313914135,
|
| 756 |
+
"learning_rate": 5.741666521162055e-06,
|
| 757 |
+
"loss": 1.0049,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5124521072796935,
|
| 762 |
+
"grad_norm": 0.29241234641844166,
|
| 763 |
+
"learning_rate": 5.658849926433774e-06,
|
| 764 |
+
"loss": 1.0019,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5172413793103449,
|
| 769 |
+
"grad_norm": 0.29226941844525284,
|
| 770 |
+
"learning_rate": 5.575848963960621e-06,
|
| 771 |
+
"loss": 0.9964,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5220306513409961,
|
| 776 |
+
"grad_norm": 0.2869562590824223,
|
| 777 |
+
"learning_rate": 5.4926868601249e-06,
|
| 778 |
+
"loss": 1.003,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5268199233716475,
|
| 783 |
+
"grad_norm": 0.2887086296052449,
|
| 784 |
+
"learning_rate": 5.4093868864015405e-06,
|
| 785 |
+
"loss": 0.9911,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5316091954022989,
|
| 790 |
+
"grad_norm": 0.2990975733324071,
|
| 791 |
+
"learning_rate": 5.325972352845965e-06,
|
| 792 |
+
"loss": 0.9961,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5363984674329502,
|
| 797 |
+
"grad_norm": 0.2964344269886325,
|
| 798 |
+
"learning_rate": 5.24246660157119e-06,
|
| 799 |
+
"loss": 1.0045,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5411877394636015,
|
| 804 |
+
"grad_norm": 0.3080697315686108,
|
| 805 |
+
"learning_rate": 5.1588930002159255e-06,
|
| 806 |
+
"loss": 0.9897,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5459770114942529,
|
| 811 |
+
"grad_norm": 0.3217970889035437,
|
| 812 |
+
"learning_rate": 5.075274935405554e-06,
|
| 813 |
+
"loss": 1.0022,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5507662835249042,
|
| 818 |
+
"grad_norm": 0.32311237689799727,
|
| 819 |
+
"learning_rate": 4.991635806207788e-06,
|
| 820 |
+
"loss": 0.9918,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5555555555555556,
|
| 825 |
+
"grad_norm": 0.3076150767243147,
|
| 826 |
+
"learning_rate": 4.90799901758484e-06,
|
| 827 |
+
"loss": 1.0156,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5603448275862069,
|
| 832 |
+
"grad_norm": 0.29579117268352634,
|
| 833 |
+
"learning_rate": 4.824387973843957e-06,
|
| 834 |
+
"loss": 0.9859,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5651340996168582,
|
| 839 |
+
"grad_norm": 0.27808702972070926,
|
| 840 |
+
"learning_rate": 4.74082607208812e-06,
|
| 841 |
+
"loss": 0.988,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5699233716475096,
|
| 846 |
+
"grad_norm": 0.2772865889207572,
|
| 847 |
+
"learning_rate": 4.6573366956687885e-06,
|
| 848 |
+
"loss": 1.0042,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5747126436781609,
|
| 853 |
+
"grad_norm": 0.2741988412251713,
|
| 854 |
+
"learning_rate": 4.573943207642452e-06,
|
| 855 |
+
"loss": 1.018,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5795019157088123,
|
| 860 |
+
"grad_norm": 0.3041843000888798,
|
| 861 |
+
"learning_rate": 4.4906689442328935e-06,
|
| 862 |
+
"loss": 1.0095,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5842911877394636,
|
| 867 |
+
"grad_norm": 0.3234627396285633,
|
| 868 |
+
"learning_rate": 4.407537208300957e-06,
|
| 869 |
+
"loss": 0.9981,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5890804597701149,
|
| 874 |
+
"grad_norm": 0.30361837699199173,
|
| 875 |
+
"learning_rate": 4.3245712628236356e-06,
|
| 876 |
+
"loss": 0.9945,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5938697318007663,
|
| 881 |
+
"grad_norm": 0.3068819956047309,
|
| 882 |
+
"learning_rate": 4.241794324384334e-06,
|
| 883 |
+
"loss": 0.9829,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5986590038314177,
|
| 888 |
+
"grad_norm": 0.3010857723276443,
|
| 889 |
+
"learning_rate": 4.159229556676111e-06,
|
| 890 |
+
"loss": 0.9778,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.603448275862069,
|
| 895 |
+
"grad_norm": 0.3212249651416007,
|
| 896 |
+
"learning_rate": 4.076900064019721e-06,
|
| 897 |
+
"loss": 1.007,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6082375478927203,
|
| 902 |
+
"grad_norm": 0.2842660737481042,
|
| 903 |
+
"learning_rate": 3.994828884898267e-06,
|
| 904 |
+
"loss": 1.0056,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6130268199233716,
|
| 909 |
+
"grad_norm": 0.2887728882458368,
|
| 910 |
+
"learning_rate": 3.91303898551028e-06,
|
| 911 |
+
"loss": 1.0131,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.617816091954023,
|
| 916 |
+
"grad_norm": 0.31374850764975326,
|
| 917 |
+
"learning_rate": 3.8315532533430285e-06,
|
| 918 |
+
"loss": 0.9979,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6226053639846744,
|
| 923 |
+
"grad_norm": 0.2990812859204113,
|
| 924 |
+
"learning_rate": 3.7503944907678543e-06,
|
| 925 |
+
"loss": 0.9979,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6273946360153256,
|
| 930 |
+
"grad_norm": 0.31174935012060845,
|
| 931 |
+
"learning_rate": 3.6695854086593126e-06,
|
| 932 |
+
"loss": 0.9907,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.632183908045977,
|
| 937 |
+
"grad_norm": 0.30150077718156976,
|
| 938 |
+
"learning_rate": 3.5891486200399413e-06,
|
| 939 |
+
"loss": 0.9937,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6369731800766284,
|
| 944 |
+
"grad_norm": 0.304753149818871,
|
| 945 |
+
"learning_rate": 3.509106633752387e-06,
|
| 946 |
+
"loss": 1.0164,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6417624521072797,
|
| 951 |
+
"grad_norm": 0.2993950641947178,
|
| 952 |
+
"learning_rate": 3.429481848160702e-06,
|
| 953 |
+
"loss": 1.0093,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.646551724137931,
|
| 958 |
+
"grad_norm": 0.3102107207132909,
|
| 959 |
+
"learning_rate": 3.350296544882543e-06,
|
| 960 |
+
"loss": 0.969,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6513409961685823,
|
| 965 |
+
"grad_norm": 0.27647028696280174,
|
| 966 |
+
"learning_rate": 3.2715728825540525e-06,
|
| 967 |
+
"loss": 1.0102,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6561302681992337,
|
| 972 |
+
"grad_norm": 0.30329159137172645,
|
| 973 |
+
"learning_rate": 3.19333289062915e-06,
|
| 974 |
+
"loss": 0.9992,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.6609195402298851,
|
| 979 |
+
"grad_norm": 0.3233989260192753,
|
| 980 |
+
"learning_rate": 3.1155984632149565e-06,
|
| 981 |
+
"loss": 0.9984,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6657088122605364,
|
| 986 |
+
"grad_norm": 0.284592333087901,
|
| 987 |
+
"learning_rate": 3.0383913529451286e-06,
|
| 988 |
+
"loss": 1.0097,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6704980842911877,
|
| 993 |
+
"grad_norm": 0.284014773245373,
|
| 994 |
+
"learning_rate": 2.961733164892744e-06,
|
| 995 |
+
"loss": 1.0048,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6752873563218391,
|
| 1000 |
+
"grad_norm": 0.29864923395210635,
|
| 1001 |
+
"learning_rate": 2.8856453505245018e-06,
|
| 1002 |
+
"loss": 1.008,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6800766283524904,
|
| 1007 |
+
"grad_norm": 0.28455877244795186,
|
| 1008 |
+
"learning_rate": 2.8101492016979027e-06,
|
| 1009 |
+
"loss": 1.0082,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6848659003831418,
|
| 1014 |
+
"grad_norm": 0.29297293441472344,
|
| 1015 |
+
"learning_rate": 2.7352658447030882e-06,
|
| 1016 |
+
"loss": 1.0137,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6896551724137931,
|
| 1021 |
+
"grad_norm": 0.29774107321754356,
|
| 1022 |
+
"learning_rate": 2.6610162343510183e-06,
|
| 1023 |
+
"loss": 0.9878,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6944444444444444,
|
| 1028 |
+
"grad_norm": 0.2886426546973218,
|
| 1029 |
+
"learning_rate": 2.587421148109619e-06,
|
| 1030 |
+
"loss": 0.9855,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6992337164750958,
|
| 1035 |
+
"grad_norm": 0.30340545161406907,
|
| 1036 |
+
"learning_rate": 2.5145011802895835e-06,
|
| 1037 |
+
"loss": 1.004,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7040229885057471,
|
| 1042 |
+
"grad_norm": 0.28629744556011416,
|
| 1043 |
+
"learning_rate": 2.4422767362814045e-06,
|
| 1044 |
+
"loss": 0.9935,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7088122605363985,
|
| 1049 |
+
"grad_norm": 0.29480150488982737,
|
| 1050 |
+
"learning_rate": 2.370768026845276e-06,
|
| 1051 |
+
"loss": 1.0013,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.7136015325670498,
|
| 1056 |
+
"grad_norm": 0.30424158130358797,
|
| 1057 |
+
"learning_rate": 2.299995062455459e-06,
|
| 1058 |
+
"loss": 0.9932,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7183908045977011,
|
| 1063 |
+
"grad_norm": 0.3179663498265742,
|
| 1064 |
+
"learning_rate": 2.2299776477007073e-06,
|
| 1065 |
+
"loss": 1.007,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7231800766283525,
|
| 1070 |
+
"grad_norm": 0.303515618658323,
|
| 1071 |
+
"learning_rate": 2.16073537574229e-06,
|
| 1072 |
+
"loss": 0.9963,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7279693486590039,
|
| 1077 |
+
"grad_norm": 0.30307569076630475,
|
| 1078 |
+
"learning_rate": 2.0922876228311833e-06,
|
| 1079 |
+
"loss": 0.9772,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7327586206896551,
|
| 1084 |
+
"grad_norm": 0.3143565291039063,
|
| 1085 |
+
"learning_rate": 2.0246535428859652e-06,
|
| 1086 |
+
"loss": 0.9899,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7375478927203065,
|
| 1091 |
+
"grad_norm": 0.28738666111079514,
|
| 1092 |
+
"learning_rate": 1.957852062132924e-06,
|
| 1093 |
+
"loss": 0.9848,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7423371647509579,
|
| 1098 |
+
"grad_norm": 0.2850271965375348,
|
| 1099 |
+
"learning_rate": 1.8919018738098704e-06,
|
| 1100 |
+
"loss": 1.0076,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7471264367816092,
|
| 1105 |
+
"grad_norm": 0.29940367717031596,
|
| 1106 |
+
"learning_rate": 1.8268214329351797e-06,
|
| 1107 |
+
"loss": 0.9864,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7519157088122606,
|
| 1112 |
+
"grad_norm": 0.2957695153675884,
|
| 1113 |
+
"learning_rate": 1.762628951143454e-06,
|
| 1114 |
+
"loss": 0.9972,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7567049808429118,
|
| 1119 |
+
"grad_norm": 0.2884019240313734,
|
| 1120 |
+
"learning_rate": 1.6993423915893241e-06,
|
| 1121 |
+
"loss": 0.9969,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7614942528735632,
|
| 1126 |
+
"grad_norm": 0.30882836660635715,
|
| 1127 |
+
"learning_rate": 1.6369794639207626e-06,
|
| 1128 |
+
"loss": 1.0005,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7662835249042146,
|
| 1133 |
+
"grad_norm": 0.2880996272538283,
|
| 1134 |
+
"learning_rate": 1.575557619323353e-06,
|
| 1135 |
+
"loss": 0.9853,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7710727969348659,
|
| 1140 |
+
"grad_norm": 0.28083999464104503,
|
| 1141 |
+
"learning_rate": 1.5150940456368784e-06,
|
| 1142 |
+
"loss": 0.9579,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7758620689655172,
|
| 1147 |
+
"grad_norm": 0.2977795145319976,
|
| 1148 |
+
"learning_rate": 1.4556056625455922e-06,
|
| 1149 |
+
"loss": 0.9944,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7806513409961686,
|
| 1154 |
+
"grad_norm": 0.3044689990672244,
|
| 1155 |
+
"learning_rate": 1.3971091168435463e-06,
|
| 1156 |
+
"loss": 0.997,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7854406130268199,
|
| 1161 |
+
"grad_norm": 0.2951506289424605,
|
| 1162 |
+
"learning_rate": 1.3396207777762732e-06,
|
| 1163 |
+
"loss": 1.0116,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7902298850574713,
|
| 1168 |
+
"grad_norm": 0.284297818009739,
|
| 1169 |
+
"learning_rate": 1.2831567324601325e-06,
|
| 1170 |
+
"loss": 0.9792,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7950191570881227,
|
| 1175 |
+
"grad_norm": 0.31450502170794314,
|
| 1176 |
+
"learning_rate": 1.2277327813806123e-06,
|
| 1177 |
+
"loss": 0.9927,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7998084291187739,
|
| 1182 |
+
"grad_norm": 0.2896076523698672,
|
| 1183 |
+
"learning_rate": 1.173364433970835e-06,
|
| 1184 |
+
"loss": 0.9795,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.8045977011494253,
|
| 1189 |
+
"grad_norm": 0.2834770010415917,
|
| 1190 |
+
"learning_rate": 1.1200669042715163e-06,
|
| 1191 |
+
"loss": 0.9966,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.8093869731800766,
|
| 1196 |
+
"grad_norm": 0.34009482243032485,
|
| 1197 |
+
"learning_rate": 1.0678551066735671e-06,
|
| 1198 |
+
"loss": 0.9767,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.814176245210728,
|
| 1203 |
+
"grad_norm": 0.29936688994813515,
|
| 1204 |
+
"learning_rate": 1.0167436517445777e-06,
|
| 1205 |
+
"loss": 1.003,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8189655172413793,
|
| 1210 |
+
"grad_norm": 0.29389391810900556,
|
| 1211 |
+
"learning_rate": 9.66746842140287e-07,
|
| 1212 |
+
"loss": 0.9888,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8237547892720306,
|
| 1217 |
+
"grad_norm": 0.29840441886793445,
|
| 1218 |
+
"learning_rate": 9.178786686022417e-07,
|
| 1219 |
+
"loss": 1.0011,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.828544061302682,
|
| 1224 |
+
"grad_norm": 0.3050673773124508,
|
| 1225 |
+
"learning_rate": 8.701528060427194e-07,
|
| 1226 |
+
"loss": 0.9867,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8333333333333334,
|
| 1231 |
+
"grad_norm": 0.2809885669064277,
|
| 1232 |
+
"learning_rate": 8.235826097180566e-07,
|
| 1233 |
+
"loss": 0.9802,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8381226053639846,
|
| 1238 |
+
"grad_norm": 0.29288746432276136,
|
| 1239 |
+
"learning_rate": 7.781811114913995e-07,
|
| 1240 |
+
"loss": 0.9965,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.842911877394636,
|
| 1245 |
+
"grad_norm": 0.29110203494522685,
|
| 1246 |
+
"learning_rate": 7.339610161859618e-07,
|
| 1247 |
+
"loss": 0.9809,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8477011494252874,
|
| 1252 |
+
"grad_norm": 0.30532295542101273,
|
| 1253 |
+
"learning_rate": 6.909346980298093e-07,
|
| 1254 |
+
"loss": 1.0039,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8524904214559387,
|
| 1259 |
+
"grad_norm": 0.3178843529727934,
|
| 1260 |
+
"learning_rate": 6.49114197193137e-07,
|
| 1261 |
+
"loss": 0.9992,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.85727969348659,
|
| 1266 |
+
"grad_norm": 0.30030807864509074,
|
| 1267 |
+
"learning_rate": 6.085112164190466e-07,
|
| 1268 |
+
"loss": 0.9967,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8620689655172413,
|
| 1273 |
+
"grad_norm": 0.283276426877559,
|
| 1274 |
+
"learning_rate": 5.691371177487215e-07,
|
| 1275 |
+
"loss": 0.9951,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8668582375478927,
|
| 1280 |
+
"grad_norm": 0.2771047728402987,
|
| 1281 |
+
"learning_rate": 5.310029193419697e-07,
|
| 1282 |
+
"loss": 0.9823,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8716475095785441,
|
| 1287 |
+
"grad_norm": 0.30200927801260424,
|
| 1288 |
+
"learning_rate": 4.941192923939769e-07,
|
| 1289 |
+
"loss": 0.9944,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8764367816091954,
|
| 1294 |
+
"grad_norm": 0.29243200143497705,
|
| 1295 |
+
"learning_rate": 4.5849655814915683e-07,
|
| 1296 |
+
"loss": 0.9923,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.8812260536398467,
|
| 1301 |
+
"grad_norm": 0.38073762499381975,
|
| 1302 |
+
"learning_rate": 4.2414468501293217e-07,
|
| 1303 |
+
"loss": 0.9931,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8860153256704981,
|
| 1308 |
+
"grad_norm": 0.28457589633356245,
|
| 1309 |
+
"learning_rate": 3.9107328576224736e-07,
|
| 1310 |
+
"loss": 0.9879,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8908045977011494,
|
| 1315 |
+
"grad_norm": 0.29913915061920765,
|
| 1316 |
+
"learning_rate": 3.5929161485559694e-07,
|
| 1317 |
+
"loss": 1.0269,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8955938697318008,
|
| 1322 |
+
"grad_norm": 0.28795408054019833,
|
| 1323 |
+
"learning_rate": 3.2880856584333043e-07,
|
| 1324 |
+
"loss": 0.984,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.9003831417624522,
|
| 1329 |
+
"grad_norm": 0.28456219117461123,
|
| 1330 |
+
"learning_rate": 2.9963266887894526e-07,
|
| 1331 |
+
"loss": 1.0007,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.9051724137931034,
|
| 1336 |
+
"grad_norm": 0.30655155945282825,
|
| 1337 |
+
"learning_rate": 2.717720883320685e-07,
|
| 1338 |
+
"loss": 1.0093,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.9099616858237548,
|
| 1343 |
+
"grad_norm": 0.28653578966574017,
|
| 1344 |
+
"learning_rate": 2.4523462050379864e-07,
|
| 1345 |
+
"loss": 0.9861,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.9147509578544061,
|
| 1350 |
+
"grad_norm": 0.30075605446410747,
|
| 1351 |
+
"learning_rate": 2.2002769144504943e-07,
|
| 1352 |
+
"loss": 0.997,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.9195402298850575,
|
| 1357 |
+
"grad_norm": 0.28984184857418177,
|
| 1358 |
+
"learning_rate": 1.9615835487849677e-07,
|
| 1359 |
+
"loss": 0.9772,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.9243295019157088,
|
| 1364 |
+
"grad_norm": 0.2971882152661699,
|
| 1365 |
+
"learning_rate": 1.7363329022471564e-07,
|
| 1366 |
+
"loss": 1.0125,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.9291187739463601,
|
| 1371 |
+
"grad_norm": 0.30026576782404996,
|
| 1372 |
+
"learning_rate": 1.5245880073305963e-07,
|
| 1373 |
+
"loss": 1.0128,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.9339080459770115,
|
| 1378 |
+
"grad_norm": 0.2971224564720333,
|
| 1379 |
+
"learning_rate": 1.3264081171780797e-07,
|
| 1380 |
+
"loss": 1.0114,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.9386973180076629,
|
| 1385 |
+
"grad_norm": 0.278422035094591,
|
| 1386 |
+
"learning_rate": 1.1418486890006574e-07,
|
| 1387 |
+
"loss": 0.982,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9434865900383141,
|
| 1392 |
+
"grad_norm": 0.29059990973676236,
|
| 1393 |
+
"learning_rate": 9.709613685589314e-08,
|
| 1394 |
+
"loss": 0.998,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9482758620689655,
|
| 1399 |
+
"grad_norm": 0.29092073403074437,
|
| 1400 |
+
"learning_rate": 8.137939757108526e-08,
|
| 1401 |
+
"loss": 1.011,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9530651340996169,
|
| 1406 |
+
"grad_norm": 0.2923297366913393,
|
| 1407 |
+
"learning_rate": 6.703904910301929e-08,
|
| 1408 |
+
"loss": 0.9656,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.9578544061302682,
|
| 1413 |
+
"grad_norm": 0.2931478943843858,
|
| 1414 |
+
"learning_rate": 5.4079104349929465e-08,
|
| 1415 |
+
"loss": 1.0036,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9626436781609196,
|
| 1420 |
+
"grad_norm": 0.2923376776086664,
|
| 1421 |
+
"learning_rate": 4.250318992797375e-08,
|
| 1422 |
+
"loss": 1.0083,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9674329501915708,
|
| 1427 |
+
"grad_norm": 0.2863912260830555,
|
| 1428 |
+
"learning_rate": 3.231454515638221e-08,
|
| 1429 |
+
"loss": 0.9955,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9722222222222222,
|
| 1434 |
+
"grad_norm": 0.2974177186982834,
|
| 1435 |
+
"learning_rate": 2.351602115099272e-08,
|
| 1436 |
+
"loss": 0.9865,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9770114942528736,
|
| 1441 |
+
"grad_norm": 0.29561321400349233,
|
| 1442 |
+
"learning_rate": 1.6110080026414123e-08,
|
| 1443 |
+
"loss": 1.0083,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9818007662835249,
|
| 1448 |
+
"grad_norm": 0.29932685669861786,
|
| 1449 |
+
"learning_rate": 1.0098794207047402e-08,
|
| 1450 |
+
"loss": 1.0118,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9865900383141762,
|
| 1455 |
+
"grad_norm": 0.29155813115628504,
|
| 1456 |
+
"learning_rate": 5.483845847151226e-09,
|
| 1457 |
+
"loss": 0.9846,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.9913793103448276,
|
| 1462 |
+
"grad_norm": 0.2910040393119768,
|
| 1463 |
+
"learning_rate": 2.2665263601240328e-09,
|
| 1464 |
+
"loss": 0.9812,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9961685823754789,
|
| 1469 |
+
"grad_norm": 0.28919827046140006,
|
| 1470 |
+
"learning_rate": 4.4773605712089554e-10,
|
| 1471 |
+
"loss": 1.0115,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.0,
|
| 1476 |
+
"eval_runtime": 6595.9355,
|
| 1477 |
+
"eval_samples_per_second": 3.504,
|
| 1478 |
+
"eval_steps_per_second": 0.876,
|
| 1479 |
+
"step": 1044
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.0,
|
| 1483 |
+
"step": 1044,
|
| 1484 |
+
"total_flos": 1940427569627136.0,
|
| 1485 |
+
"train_loss": 1.0122476654034465,
|
| 1486 |
+
"train_runtime": 20247.7008,
|
| 1487 |
+
"train_samples_per_second": 3.298,
|
| 1488 |
+
"train_steps_per_second": 0.052
|
| 1489 |
+
}
|
| 1490 |
+
],
|
| 1491 |
+
"logging_steps": 5,
|
| 1492 |
+
"max_steps": 1044,
|
| 1493 |
+
"num_input_tokens_seen": 0,
|
| 1494 |
+
"num_train_epochs": 1,
|
| 1495 |
+
"save_steps": 100,
|
| 1496 |
+
"stateful_callbacks": {
|
| 1497 |
+
"TrainerControl": {
|
| 1498 |
+
"args": {
|
| 1499 |
+
"should_epoch_stop": false,
|
| 1500 |
+
"should_evaluate": false,
|
| 1501 |
+
"should_log": false,
|
| 1502 |
+
"should_save": true,
|
| 1503 |
+
"should_training_stop": true
|
| 1504 |
+
},
|
| 1505 |
+
"attributes": {}
|
| 1506 |
+
}
|
| 1507 |
+
},
|
| 1508 |
+
"total_flos": 1940427569627136.0,
|
| 1509 |
+
"train_batch_size": 16,
|
| 1510 |
+
"trial_name": null,
|
| 1511 |
+
"trial_params": null
|
| 1512 |
+
}
|