Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- runs/Feb17_00-03-01_t25033090/events.out.tfevents.1739721843.t25033090.109000.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1569 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: zephyr-7b-sft-qlora
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# zephyr-7b-sft-qlora
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.9562
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- gradient_accumulation_steps: 64
|
| 48 |
+
- total_train_batch_size: 128
|
| 49 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.9468 | 0.9995 | 1083 | 0.9562 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- PEFT 0.14.0
|
| 64 |
+
- Transformers 4.48.3
|
| 65 |
+
- Pytorch 2.6.0+cu124
|
| 66 |
+
- Datasets 3.3.0
|
| 67 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995385325334564,
|
| 3 |
+
"total_flos": 1.2183828414859313e+19,
|
| 4 |
+
"train_loss": 0.9649847933019847,
|
| 5 |
+
"train_runtime": 330634.4933,
|
| 6 |
+
"train_samples": 207864,
|
| 7 |
+
"train_samples_per_second": 0.419,
|
| 8 |
+
"train_steps_per_second": 0.003
|
| 9 |
+
}
|
runs/Feb17_00-03-01_t25033090/events.out.tfevents.1739721843.t25033090.109000.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ffdf755459794452d7b45bef8439b93f1edd24c9623e9bb4cc7fef7a3c0e7c6
|
| 3 |
+
size 52927
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995385325334564,
|
| 3 |
+
"total_flos": 1.2183828414859313e+19,
|
| 4 |
+
"train_loss": 0.9649847933019847,
|
| 5 |
+
"train_runtime": 330634.4933,
|
| 6 |
+
"train_samples": 207864,
|
| 7 |
+
"train_samples_per_second": 0.419,
|
| 8 |
+
"train_steps_per_second": 0.003
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1569 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995385325334564,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1083,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0009229349330872173,
|
| 13 |
+
"grad_norm": 0.3153176009654999,
|
| 14 |
+
"learning_rate": 1.8348623853211011e-06,
|
| 15 |
+
"loss": 1.16,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0046146746654360865,
|
| 20 |
+
"grad_norm": 0.30069586634635925,
|
| 21 |
+
"learning_rate": 9.174311926605506e-06,
|
| 22 |
+
"loss": 1.157,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.009229349330872173,
|
| 27 |
+
"grad_norm": 0.24939967691898346,
|
| 28 |
+
"learning_rate": 1.834862385321101e-05,
|
| 29 |
+
"loss": 1.1423,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01384402399630826,
|
| 34 |
+
"grad_norm": 0.1986856758594513,
|
| 35 |
+
"learning_rate": 2.7522935779816515e-05,
|
| 36 |
+
"loss": 1.1082,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.018458698661744346,
|
| 41 |
+
"grad_norm": 0.16805031895637512,
|
| 42 |
+
"learning_rate": 3.669724770642202e-05,
|
| 43 |
+
"loss": 1.0915,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.023073373327180433,
|
| 48 |
+
"grad_norm": 0.16181856393814087,
|
| 49 |
+
"learning_rate": 4.587155963302753e-05,
|
| 50 |
+
"loss": 1.0639,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02768804799261652,
|
| 55 |
+
"grad_norm": 0.13395144045352936,
|
| 56 |
+
"learning_rate": 5.504587155963303e-05,
|
| 57 |
+
"loss": 1.021,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032302722658052604,
|
| 62 |
+
"grad_norm": 0.09093035757541656,
|
| 63 |
+
"learning_rate": 6.422018348623854e-05,
|
| 64 |
+
"loss": 1.0403,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03691739732348869,
|
| 69 |
+
"grad_norm": 0.08925778418779373,
|
| 70 |
+
"learning_rate": 7.339449541284404e-05,
|
| 71 |
+
"loss": 1.0398,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04153207198892478,
|
| 76 |
+
"grad_norm": 0.10212849825620651,
|
| 77 |
+
"learning_rate": 8.256880733944955e-05,
|
| 78 |
+
"loss": 1.0122,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.046146746654360866,
|
| 83 |
+
"grad_norm": 0.0883544310927391,
|
| 84 |
+
"learning_rate": 9.174311926605506e-05,
|
| 85 |
+
"loss": 1.003,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.050761421319796954,
|
| 90 |
+
"grad_norm": 0.09017772227525711,
|
| 91 |
+
"learning_rate": 0.00010091743119266055,
|
| 92 |
+
"loss": 0.9996,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05537609598523304,
|
| 97 |
+
"grad_norm": 0.08947195112705231,
|
| 98 |
+
"learning_rate": 0.00011009174311926606,
|
| 99 |
+
"loss": 1.0092,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.05999077065066913,
|
| 104 |
+
"grad_norm": 0.09361358731985092,
|
| 105 |
+
"learning_rate": 0.00011926605504587157,
|
| 106 |
+
"loss": 1.0053,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06460544531610521,
|
| 111 |
+
"grad_norm": 0.08942877501249313,
|
| 112 |
+
"learning_rate": 0.00012844036697247707,
|
| 113 |
+
"loss": 0.979,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0692201199815413,
|
| 118 |
+
"grad_norm": 0.08816999942064285,
|
| 119 |
+
"learning_rate": 0.00013761467889908258,
|
| 120 |
+
"loss": 0.9817,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07383479464697738,
|
| 125 |
+
"grad_norm": 0.10292733460664749,
|
| 126 |
+
"learning_rate": 0.0001467889908256881,
|
| 127 |
+
"loss": 0.972,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07844946931241348,
|
| 132 |
+
"grad_norm": 0.08368176966905594,
|
| 133 |
+
"learning_rate": 0.0001559633027522936,
|
| 134 |
+
"loss": 0.9869,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08306414397784956,
|
| 139 |
+
"grad_norm": 0.08516489714384079,
|
| 140 |
+
"learning_rate": 0.0001651376146788991,
|
| 141 |
+
"loss": 0.9841,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08767881864328565,
|
| 146 |
+
"grad_norm": 0.08280258625745773,
|
| 147 |
+
"learning_rate": 0.00017431192660550458,
|
| 148 |
+
"loss": 0.9859,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.09229349330872173,
|
| 153 |
+
"grad_norm": 0.08506108820438385,
|
| 154 |
+
"learning_rate": 0.00018348623853211012,
|
| 155 |
+
"loss": 0.9913,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09690816797415783,
|
| 160 |
+
"grad_norm": 0.0873042568564415,
|
| 161 |
+
"learning_rate": 0.0001926605504587156,
|
| 162 |
+
"loss": 1.014,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.10152284263959391,
|
| 167 |
+
"grad_norm": 0.09446421265602112,
|
| 168 |
+
"learning_rate": 0.00019999947982262415,
|
| 169 |
+
"loss": 0.9959,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.10613751730503,
|
| 174 |
+
"grad_norm": 0.0792991891503334,
|
| 175 |
+
"learning_rate": 0.00019998127418269004,
|
| 176 |
+
"loss": 0.9976,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.11075219197046608,
|
| 181 |
+
"grad_norm": 0.08645275980234146,
|
| 182 |
+
"learning_rate": 0.00019993706508539968,
|
| 183 |
+
"loss": 0.9774,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.11536686663590216,
|
| 188 |
+
"grad_norm": 0.07994881272315979,
|
| 189 |
+
"learning_rate": 0.0001998668640288,
|
| 190 |
+
"loss": 0.9962,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.11998154130133826,
|
| 195 |
+
"grad_norm": 0.07281699776649475,
|
| 196 |
+
"learning_rate": 0.0001997706892710117,
|
| 197 |
+
"loss": 0.9682,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.12459621596677434,
|
| 202 |
+
"grad_norm": 0.0806204155087471,
|
| 203 |
+
"learning_rate": 0.00019964856582548092,
|
| 204 |
+
"loss": 0.9973,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.12921089063221042,
|
| 209 |
+
"grad_norm": 0.08152524381875992,
|
| 210 |
+
"learning_rate": 0.00019950052545447352,
|
| 211 |
+
"loss": 0.9926,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.13382556529764653,
|
| 216 |
+
"grad_norm": 0.07916297018527985,
|
| 217 |
+
"learning_rate": 0.0001993266066608142,
|
| 218 |
+
"loss": 0.9681,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1384402399630826,
|
| 223 |
+
"grad_norm": 0.07692616432905197,
|
| 224 |
+
"learning_rate": 0.00019912685467787257,
|
| 225 |
+
"loss": 0.9552,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1430549146285187,
|
| 230 |
+
"grad_norm": 0.07867322117090225,
|
| 231 |
+
"learning_rate": 0.00019890132145779885,
|
| 232 |
+
"loss": 1.0056,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.14766958929395477,
|
| 237 |
+
"grad_norm": 0.07720212638378143,
|
| 238 |
+
"learning_rate": 0.0001986500656580118,
|
| 239 |
+
"loss": 0.9603,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.15228426395939088,
|
| 244 |
+
"grad_norm": 0.0785161629319191,
|
| 245 |
+
"learning_rate": 0.00019837315262594306,
|
| 246 |
+
"loss": 0.9693,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.15689893862482696,
|
| 251 |
+
"grad_norm": 0.0887812152504921,
|
| 252 |
+
"learning_rate": 0.00019807065438204118,
|
| 253 |
+
"loss": 0.9713,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.16151361329026304,
|
| 258 |
+
"grad_norm": 0.07461399585008621,
|
| 259 |
+
"learning_rate": 0.00019774264960104057,
|
| 260 |
+
"loss": 0.9561,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.16612828795569912,
|
| 265 |
+
"grad_norm": 0.07251787185668945,
|
| 266 |
+
"learning_rate": 0.00019738922359149926,
|
| 267 |
+
"loss": 0.9701,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1707429626211352,
|
| 272 |
+
"grad_norm": 0.07772507518529892,
|
| 273 |
+
"learning_rate": 0.00019701046827361177,
|
| 274 |
+
"loss": 0.9775,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.1753576372865713,
|
| 279 |
+
"grad_norm": 0.07318438589572906,
|
| 280 |
+
"learning_rate": 0.00019660648215530206,
|
| 281 |
+
"loss": 0.9585,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.17997231195200739,
|
| 286 |
+
"grad_norm": 0.07861252874135971,
|
| 287 |
+
"learning_rate": 0.00019617737030660338,
|
| 288 |
+
"loss": 0.9642,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.18458698661744347,
|
| 293 |
+
"grad_norm": 0.07000173628330231,
|
| 294 |
+
"learning_rate": 0.0001957232443323312,
|
| 295 |
+
"loss": 0.9679,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.18920166128287955,
|
| 300 |
+
"grad_norm": 0.07377786934375763,
|
| 301 |
+
"learning_rate": 0.00019524422234305677,
|
| 302 |
+
"loss": 0.9579,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.19381633594831565,
|
| 307 |
+
"grad_norm": 0.07430287450551987,
|
| 308 |
+
"learning_rate": 0.0001947404289243885,
|
| 309 |
+
"loss": 0.9385,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.19843101061375173,
|
| 314 |
+
"grad_norm": 0.07597630470991135,
|
| 315 |
+
"learning_rate": 0.0001942119951045692,
|
| 316 |
+
"loss": 0.9522,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.20304568527918782,
|
| 321 |
+
"grad_norm": 0.07650153338909149,
|
| 322 |
+
"learning_rate": 0.00019365905832039815,
|
| 323 |
+
"loss": 0.9766,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2076603599446239,
|
| 328 |
+
"grad_norm": 0.07343017309904099,
|
| 329 |
+
"learning_rate": 0.00019308176238148564,
|
| 330 |
+
"loss": 0.979,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.21227503461006,
|
| 335 |
+
"grad_norm": 0.0811387151479721,
|
| 336 |
+
"learning_rate": 0.0001924802574328509,
|
| 337 |
+
"loss": 0.9575,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.21688970927549608,
|
| 342 |
+
"grad_norm": 0.0797664150595665,
|
| 343 |
+
"learning_rate": 0.00019185469991587166,
|
| 344 |
+
"loss": 0.9746,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.22150438394093216,
|
| 349 |
+
"grad_norm": 0.07318708300590515,
|
| 350 |
+
"learning_rate": 0.00019120525252759647,
|
| 351 |
+
"loss": 0.9659,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.22611905860636825,
|
| 356 |
+
"grad_norm": 0.07425623387098312,
|
| 357 |
+
"learning_rate": 0.00019053208417842978,
|
| 358 |
+
"loss": 0.9644,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.23073373327180433,
|
| 363 |
+
"grad_norm": 0.07410068064928055,
|
| 364 |
+
"learning_rate": 0.0001898353699482014,
|
| 365 |
+
"loss": 0.9652,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.23534840793724043,
|
| 370 |
+
"grad_norm": 0.07423646003007889,
|
| 371 |
+
"learning_rate": 0.0001891152910406309,
|
| 372 |
+
"loss": 0.9691,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.23996308260267651,
|
| 377 |
+
"grad_norm": 0.06945409625768661,
|
| 378 |
+
"learning_rate": 0.00018837203473619978,
|
| 379 |
+
"loss": 0.9739,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2445777572681126,
|
| 384 |
+
"grad_norm": 0.0697169378399849,
|
| 385 |
+
"learning_rate": 0.0001876057943434428,
|
| 386 |
+
"loss": 0.9772,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.24919243193354867,
|
| 391 |
+
"grad_norm": 0.07200105488300323,
|
| 392 |
+
"learning_rate": 0.00018681676914867175,
|
| 393 |
+
"loss": 0.9742,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.25380710659898476,
|
| 398 |
+
"grad_norm": 0.0744839757680893,
|
| 399 |
+
"learning_rate": 0.0001860051643641443,
|
| 400 |
+
"loss": 0.9613,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.25842178126442084,
|
| 405 |
+
"grad_norm": 0.08401075750589371,
|
| 406 |
+
"learning_rate": 0.0001851711910746919,
|
| 407 |
+
"loss": 0.9721,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.26303645592985697,
|
| 412 |
+
"grad_norm": 0.06904800236225128,
|
| 413 |
+
"learning_rate": 0.00018431506618282,
|
| 414 |
+
"loss": 0.9572,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.26765113059529305,
|
| 419 |
+
"grad_norm": 0.07013043761253357,
|
| 420 |
+
"learning_rate": 0.0001834370123522954,
|
| 421 |
+
"loss": 0.9706,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.27226580526072913,
|
| 426 |
+
"grad_norm": 0.07055062055587769,
|
| 427 |
+
"learning_rate": 0.00018253725795023504,
|
| 428 |
+
"loss": 0.9612,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2768804799261652,
|
| 433 |
+
"grad_norm": 0.07045809924602509,
|
| 434 |
+
"learning_rate": 0.0001816160369877117,
|
| 435 |
+
"loss": 0.9707,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2814951545916013,
|
| 440 |
+
"grad_norm": 0.06949017941951752,
|
| 441 |
+
"learning_rate": 0.00018067358905889146,
|
| 442 |
+
"loss": 0.9405,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2861098292570374,
|
| 447 |
+
"grad_norm": 0.06768112629652023,
|
| 448 |
+
"learning_rate": 0.00017971015927871942,
|
| 449 |
+
"loss": 0.97,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.29072450392247345,
|
| 454 |
+
"grad_norm": 0.06964079290628433,
|
| 455 |
+
"learning_rate": 0.0001787259982191692,
|
| 456 |
+
"loss": 0.9581,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.29533917858790953,
|
| 461 |
+
"grad_norm": 0.07223650813102722,
|
| 462 |
+
"learning_rate": 0.00017772136184407365,
|
| 463 |
+
"loss": 0.9611,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.2999538532533456,
|
| 468 |
+
"grad_norm": 0.06840556859970093,
|
| 469 |
+
"learning_rate": 0.00017669651144255265,
|
| 470 |
+
"loss": 0.9631,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.30456852791878175,
|
| 475 |
+
"grad_norm": 0.07011925429105759,
|
| 476 |
+
"learning_rate": 0.00017565171356105627,
|
| 477 |
+
"loss": 0.9817,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.30918320258421783,
|
| 482 |
+
"grad_norm": 0.06768331676721573,
|
| 483 |
+
"learning_rate": 0.00017458723993404065,
|
| 484 |
+
"loss": 0.9796,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3137978772496539,
|
| 489 |
+
"grad_norm": 0.06805837899446487,
|
| 490 |
+
"learning_rate": 0.00017350336741329413,
|
| 491 |
+
"loss": 0.9683,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.31841255191509,
|
| 496 |
+
"grad_norm": 0.07038763910531998,
|
| 497 |
+
"learning_rate": 0.00017240037789593307,
|
| 498 |
+
"loss": 0.9762,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3230272265805261,
|
| 503 |
+
"grad_norm": 0.0689588338136673,
|
| 504 |
+
"learning_rate": 0.0001712785582510848,
|
| 505 |
+
"loss": 0.9537,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.32764190124596215,
|
| 510 |
+
"grad_norm": 0.06688909232616425,
|
| 511 |
+
"learning_rate": 0.00017013820024527798,
|
| 512 |
+
"loss": 0.9643,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.33225657591139823,
|
| 517 |
+
"grad_norm": 0.073676697909832,
|
| 518 |
+
"learning_rate": 0.00016897960046655886,
|
| 519 |
+
"loss": 0.9611,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3368712505768343,
|
| 524 |
+
"grad_norm": 0.07165560126304626,
|
| 525 |
+
"learning_rate": 0.00016780306024735382,
|
| 526 |
+
"loss": 0.957,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3414859252422704,
|
| 531 |
+
"grad_norm": 0.07094935327768326,
|
| 532 |
+
"learning_rate": 0.00016660888558609773,
|
| 533 |
+
"loss": 0.9854,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.34610059990770653,
|
| 538 |
+
"grad_norm": 0.06721330434083939,
|
| 539 |
+
"learning_rate": 0.00016539738706764894,
|
| 540 |
+
"loss": 0.9648,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3507152745731426,
|
| 545 |
+
"grad_norm": 0.0699782595038414,
|
| 546 |
+
"learning_rate": 0.00016416887978251135,
|
| 547 |
+
"loss": 0.9587,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3553299492385787,
|
| 552 |
+
"grad_norm": 0.06915416568517685,
|
| 553 |
+
"learning_rate": 0.00016292368324488462,
|
| 554 |
+
"loss": 0.9395,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.35994462390401477,
|
| 559 |
+
"grad_norm": 0.06952769309282303,
|
| 560 |
+
"learning_rate": 0.00016166212130956382,
|
| 561 |
+
"loss": 0.9476,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.36455929856945085,
|
| 566 |
+
"grad_norm": 0.06895878911018372,
|
| 567 |
+
"learning_rate": 0.00016038452208771037,
|
| 568 |
+
"loss": 0.9725,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.36917397323488693,
|
| 573 |
+
"grad_norm": 0.06924083083868027,
|
| 574 |
+
"learning_rate": 0.00015909121786151568,
|
| 575 |
+
"loss": 0.9541,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.373788647900323,
|
| 580 |
+
"grad_norm": 0.06652365624904633,
|
| 581 |
+
"learning_rate": 0.00015778254499778006,
|
| 582 |
+
"loss": 0.9592,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3784033225657591,
|
| 587 |
+
"grad_norm": 0.06965645402669907,
|
| 588 |
+
"learning_rate": 0.00015645884386042958,
|
| 589 |
+
"loss": 0.9484,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.3830179972311952,
|
| 594 |
+
"grad_norm": 0.0711289793252945,
|
| 595 |
+
"learning_rate": 0.00015512045872199276,
|
| 596 |
+
"loss": 0.9395,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.3876326718966313,
|
| 601 |
+
"grad_norm": 0.0690288171172142,
|
| 602 |
+
"learning_rate": 0.00015376773767406142,
|
| 603 |
+
"loss": 0.983,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3922473465620674,
|
| 608 |
+
"grad_norm": 0.0725955069065094,
|
| 609 |
+
"learning_rate": 0.00015240103253675756,
|
| 610 |
+
"loss": 0.956,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.39686202122750347,
|
| 615 |
+
"grad_norm": 0.07096763700246811,
|
| 616 |
+
"learning_rate": 0.00015102069876723098,
|
| 617 |
+
"loss": 0.9638,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.40147669589293955,
|
| 622 |
+
"grad_norm": 0.06781638413667679,
|
| 623 |
+
"learning_rate": 0.00014962709536721087,
|
| 624 |
+
"loss": 0.9413,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.40609137055837563,
|
| 629 |
+
"grad_norm": 0.06911034137010574,
|
| 630 |
+
"learning_rate": 0.00014822058478963532,
|
| 631 |
+
"loss": 0.9576,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4107060452238117,
|
| 636 |
+
"grad_norm": 0.07025574147701263,
|
| 637 |
+
"learning_rate": 0.00014680153284438345,
|
| 638 |
+
"loss": 0.961,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4153207198892478,
|
| 643 |
+
"grad_norm": 0.07122451812028885,
|
| 644 |
+
"learning_rate": 0.00014537030860313442,
|
| 645 |
+
"loss": 0.9678,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.41993539455468387,
|
| 650 |
+
"grad_norm": 0.06810062378644943,
|
| 651 |
+
"learning_rate": 0.000143927284303378,
|
| 652 |
+
"loss": 0.9497,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.42455006922012,
|
| 657 |
+
"grad_norm": 0.06889387220144272,
|
| 658 |
+
"learning_rate": 0.00014247283525160178,
|
| 659 |
+
"loss": 0.9461,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.4291647438855561,
|
| 664 |
+
"grad_norm": 0.06921575218439102,
|
| 665 |
+
"learning_rate": 0.00014100733972568038,
|
| 666 |
+
"loss": 0.9625,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.43377941855099217,
|
| 671 |
+
"grad_norm": 0.06750404834747314,
|
| 672 |
+
"learning_rate": 0.00013953117887649153,
|
| 673 |
+
"loss": 0.9678,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.43839409321642825,
|
| 678 |
+
"grad_norm": 0.07006347179412842,
|
| 679 |
+
"learning_rate": 0.00013804473662878519,
|
| 680 |
+
"loss": 0.9646,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.44300876788186433,
|
| 685 |
+
"grad_norm": 0.06842590123414993,
|
| 686 |
+
"learning_rate": 0.00013654839958133117,
|
| 687 |
+
"loss": 0.956,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4476234425473004,
|
| 692 |
+
"grad_norm": 0.07282765209674835,
|
| 693 |
+
"learning_rate": 0.0001350425569063712,
|
| 694 |
+
"loss": 0.9787,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4522381172127365,
|
| 699 |
+
"grad_norm": 0.06680766493082047,
|
| 700 |
+
"learning_rate": 0.00013352760024840175,
|
| 701 |
+
"loss": 0.9544,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.45685279187817257,
|
| 706 |
+
"grad_norm": 0.0665644034743309,
|
| 707 |
+
"learning_rate": 0.00013200392362231383,
|
| 708 |
+
"loss": 0.9397,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.46146746654360865,
|
| 713 |
+
"grad_norm": 0.06751461327075958,
|
| 714 |
+
"learning_rate": 0.00013047192331091636,
|
| 715 |
+
"loss": 0.974,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4660821412090448,
|
| 720 |
+
"grad_norm": 0.06943210959434509,
|
| 721 |
+
"learning_rate": 0.00012893199776186956,
|
| 722 |
+
"loss": 0.9487,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.47069681587448087,
|
| 727 |
+
"grad_norm": 0.06830769777297974,
|
| 728 |
+
"learning_rate": 0.0001273845474840555,
|
| 729 |
+
"loss": 0.9614,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.47531149053991695,
|
| 734 |
+
"grad_norm": 0.06783465296030045,
|
| 735 |
+
"learning_rate": 0.0001258299749434123,
|
| 736 |
+
"loss": 0.9716,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.47992616520535303,
|
| 741 |
+
"grad_norm": 0.07035640627145767,
|
| 742 |
+
"learning_rate": 0.00012426868445825954,
|
| 743 |
+
"loss": 0.9639,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.4845408398707891,
|
| 748 |
+
"grad_norm": 0.06989864259958267,
|
| 749 |
+
"learning_rate": 0.00012270108209414186,
|
| 750 |
+
"loss": 0.9483,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.4891555145362252,
|
| 755 |
+
"grad_norm": 0.06680671125650406,
|
| 756 |
+
"learning_rate": 0.00012112757555821797,
|
| 757 |
+
"loss": 0.9596,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.49377018920166127,
|
| 762 |
+
"grad_norm": 0.07067760825157166,
|
| 763 |
+
"learning_rate": 0.00011954857409322302,
|
| 764 |
+
"loss": 0.9449,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.49838486386709735,
|
| 769 |
+
"grad_norm": 0.06822020560503006,
|
| 770 |
+
"learning_rate": 0.00011796448837103129,
|
| 771 |
+
"loss": 0.9558,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5029995385325334,
|
| 776 |
+
"grad_norm": 0.06769659370183945,
|
| 777 |
+
"learning_rate": 0.00011637573038584729,
|
| 778 |
+
"loss": 0.9458,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5076142131979695,
|
| 783 |
+
"grad_norm": 0.06936723738908768,
|
| 784 |
+
"learning_rate": 0.00011478271334705302,
|
| 785 |
+
"loss": 0.9504,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5122288878634056,
|
| 790 |
+
"grad_norm": 0.07083772867918015,
|
| 791 |
+
"learning_rate": 0.00011318585157173913,
|
| 792 |
+
"loss": 0.9628,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.5168435625288417,
|
| 797 |
+
"grad_norm": 0.07207299768924713,
|
| 798 |
+
"learning_rate": 0.0001115855603769479,
|
| 799 |
+
"loss": 0.9492,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.5214582371942778,
|
| 804 |
+
"grad_norm": 0.06986602395772934,
|
| 805 |
+
"learning_rate": 0.00010998225597165628,
|
| 806 |
+
"loss": 0.9507,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5260729118597139,
|
| 811 |
+
"grad_norm": 0.07052252441644669,
|
| 812 |
+
"learning_rate": 0.00010837635534852686,
|
| 813 |
+
"loss": 0.9497,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.53068758652515,
|
| 818 |
+
"grad_norm": 0.07066074013710022,
|
| 819 |
+
"learning_rate": 0.00010676827617545511,
|
| 820 |
+
"loss": 0.9506,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5353022611905861,
|
| 825 |
+
"grad_norm": 0.07176294177770615,
|
| 826 |
+
"learning_rate": 0.00010515843668694085,
|
| 827 |
+
"loss": 0.9501,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5399169358560222,
|
| 832 |
+
"grad_norm": 0.07183931022882462,
|
| 833 |
+
"learning_rate": 0.00010354725557531257,
|
| 834 |
+
"loss": 0.9514,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5445316105214583,
|
| 839 |
+
"grad_norm": 0.06932860612869263,
|
| 840 |
+
"learning_rate": 0.00010193515188183245,
|
| 841 |
+
"loss": 0.9452,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5491462851868943,
|
| 846 |
+
"grad_norm": 0.06957747042179108,
|
| 847 |
+
"learning_rate": 0.0001003225448877108,
|
| 848 |
+
"loss": 0.9649,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5537609598523304,
|
| 853 |
+
"grad_norm": 0.06706763803958893,
|
| 854 |
+
"learning_rate": 9.870985400505804e-05,
|
| 855 |
+
"loss": 0.9468,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5583756345177665,
|
| 860 |
+
"grad_norm": 0.06936302781105042,
|
| 861 |
+
"learning_rate": 9.709749866780248e-05,
|
| 862 |
+
"loss": 0.9569,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5629903091832026,
|
| 867 |
+
"grad_norm": 0.06822703033685684,
|
| 868 |
+
"learning_rate": 9.548589822260281e-05,
|
| 869 |
+
"loss": 0.9672,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5676049838486387,
|
| 874 |
+
"grad_norm": 0.06881389766931534,
|
| 875 |
+
"learning_rate": 9.387547181978291e-05,
|
| 876 |
+
"loss": 0.9493,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5722196585140747,
|
| 881 |
+
"grad_norm": 0.06797238439321518,
|
| 882 |
+
"learning_rate": 9.226663830431777e-05,
|
| 883 |
+
"loss": 0.9658,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5768343331795108,
|
| 888 |
+
"grad_norm": 0.06790480017662048,
|
| 889 |
+
"learning_rate": 9.065981610689914e-05,
|
| 890 |
+
"loss": 0.9506,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5814490078449469,
|
| 895 |
+
"grad_norm": 0.06801264733076096,
|
| 896 |
+
"learning_rate": 8.905542313510846e-05,
|
| 897 |
+
"loss": 0.9552,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.586063682510383,
|
| 902 |
+
"grad_norm": 0.07247908413410187,
|
| 903 |
+
"learning_rate": 8.745387666472637e-05,
|
| 904 |
+
"loss": 0.9632,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5906783571758191,
|
| 909 |
+
"grad_norm": 0.06877297908067703,
|
| 910 |
+
"learning_rate": 8.58555932312059e-05,
|
| 911 |
+
"loss": 0.9652,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5952930318412551,
|
| 916 |
+
"grad_norm": 0.06959784030914307,
|
| 917 |
+
"learning_rate": 8.426098852133892e-05,
|
| 918 |
+
"loss": 0.9436,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5999077065066912,
|
| 923 |
+
"grad_norm": 0.06700550764799118,
|
| 924 |
+
"learning_rate": 8.267047726514278e-05,
|
| 925 |
+
"loss": 0.9644,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.6045223811721273,
|
| 930 |
+
"grad_norm": 0.06979133933782578,
|
| 931 |
+
"learning_rate": 8.108447312799587e-05,
|
| 932 |
+
"loss": 0.9603,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.6091370558375635,
|
| 937 |
+
"grad_norm": 0.06916554272174835,
|
| 938 |
+
"learning_rate": 7.950338860305048e-05,
|
| 939 |
+
"loss": 0.9479,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.6137517305029996,
|
| 944 |
+
"grad_norm": 0.0692073404788971,
|
| 945 |
+
"learning_rate": 7.792763490394984e-05,
|
| 946 |
+
"loss": 0.9583,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.6183664051684357,
|
| 951 |
+
"grad_norm": 0.06973334401845932,
|
| 952 |
+
"learning_rate": 7.635762185787868e-05,
|
| 953 |
+
"loss": 0.9598,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6229810798338717,
|
| 958 |
+
"grad_norm": 0.069077268242836,
|
| 959 |
+
"learning_rate": 7.479375779897379e-05,
|
| 960 |
+
"loss": 0.9508,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.6275957544993078,
|
| 965 |
+
"grad_norm": 0.06755080074071884,
|
| 966 |
+
"learning_rate": 7.323644946212331e-05,
|
| 967 |
+
"loss": 0.9538,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.6322104291647439,
|
| 972 |
+
"grad_norm": 0.06810387223958969,
|
| 973 |
+
"learning_rate": 7.168610187718164e-05,
|
| 974 |
+
"loss": 0.9563,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.63682510383018,
|
| 979 |
+
"grad_norm": 0.06826294958591461,
|
| 980 |
+
"learning_rate": 7.014311826362804e-05,
|
| 981 |
+
"loss": 0.951,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.6414397784956161,
|
| 986 |
+
"grad_norm": 0.07014641910791397,
|
| 987 |
+
"learning_rate": 6.8607899925696e-05,
|
| 988 |
+
"loss": 0.9669,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.6460544531610521,
|
| 993 |
+
"grad_norm": 0.0688079446554184,
|
| 994 |
+
"learning_rate": 6.708084614800064e-05,
|
| 995 |
+
"loss": 0.9361,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.6506691278264882,
|
| 1000 |
+
"grad_norm": 0.07005127519369125,
|
| 1001 |
+
"learning_rate": 6.556235409169154e-05,
|
| 1002 |
+
"loss": 0.9337,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.6552838024919243,
|
| 1007 |
+
"grad_norm": 0.06724046170711517,
|
| 1008 |
+
"learning_rate": 6.405281869115768e-05,
|
| 1009 |
+
"loss": 0.9404,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6598984771573604,
|
| 1014 |
+
"grad_norm": 0.07361240684986115,
|
| 1015 |
+
"learning_rate": 6.255263255131172e-05,
|
| 1016 |
+
"loss": 0.9527,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.6645131518227965,
|
| 1021 |
+
"grad_norm": 0.06800534576177597,
|
| 1022 |
+
"learning_rate": 6.106218584547991e-05,
|
| 1023 |
+
"loss": 0.9531,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6691278264882325,
|
| 1028 |
+
"grad_norm": 0.0687314122915268,
|
| 1029 |
+
"learning_rate": 5.9581866213924656e-05,
|
| 1030 |
+
"loss": 0.9421,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6737425011536686,
|
| 1035 |
+
"grad_norm": 0.06845971941947937,
|
| 1036 |
+
"learning_rate": 5.8112058663025706e-05,
|
| 1037 |
+
"loss": 0.9455,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6783571758191047,
|
| 1042 |
+
"grad_norm": 0.06654047966003418,
|
| 1043 |
+
"learning_rate": 5.665314546514633e-05,
|
| 1044 |
+
"loss": 0.9514,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6829718504845408,
|
| 1049 |
+
"grad_norm": 0.069442018866539,
|
| 1050 |
+
"learning_rate": 5.520550605921091e-05,
|
| 1051 |
+
"loss": 0.9537,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.687586525149977,
|
| 1056 |
+
"grad_norm": 0.0674603134393692,
|
| 1057 |
+
"learning_rate": 5.376951695201894e-05,
|
| 1058 |
+
"loss": 0.9536,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6922011998154131,
|
| 1063 |
+
"grad_norm": 0.06752391904592514,
|
| 1064 |
+
"learning_rate": 5.234555162032221e-05,
|
| 1065 |
+
"loss": 0.9477,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6968158744808491,
|
| 1070 |
+
"grad_norm": 0.07034114748239517,
|
| 1071 |
+
"learning_rate": 5.093398041368942e-05,
|
| 1072 |
+
"loss": 0.9637,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.7014305491462852,
|
| 1077 |
+
"grad_norm": 0.06883241981267929,
|
| 1078 |
+
"learning_rate": 4.953517045818473e-05,
|
| 1079 |
+
"loss": 0.9556,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.7060452238117213,
|
| 1084 |
+
"grad_norm": 0.06869496405124664,
|
| 1085 |
+
"learning_rate": 4.81494855608843e-05,
|
| 1086 |
+
"loss": 0.9581,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7106598984771574,
|
| 1091 |
+
"grad_norm": 0.07270540297031403,
|
| 1092 |
+
"learning_rate": 4.677728611525605e-05,
|
| 1093 |
+
"loss": 0.9503,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7152745731425935,
|
| 1098 |
+
"grad_norm": 0.06813713908195496,
|
| 1099 |
+
"learning_rate": 4.541892900742757e-05,
|
| 1100 |
+
"loss": 0.9428,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.7198892478080295,
|
| 1105 |
+
"grad_norm": 0.06918053328990936,
|
| 1106 |
+
"learning_rate": 4.407476752336576e-05,
|
| 1107 |
+
"loss": 0.9433,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.7245039224734656,
|
| 1112 |
+
"grad_norm": 0.06645094603300095,
|
| 1113 |
+
"learning_rate": 4.274515125699332e-05,
|
| 1114 |
+
"loss": 0.9444,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7291185971389017,
|
| 1119 |
+
"grad_norm": 0.06784369051456451,
|
| 1120 |
+
"learning_rate": 4.1430426019264924e-05,
|
| 1121 |
+
"loss": 0.9558,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7337332718043378,
|
| 1126 |
+
"grad_norm": 0.0678802952170372,
|
| 1127 |
+
"learning_rate": 4.0130933748227885e-05,
|
| 1128 |
+
"loss": 0.938,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7383479464697739,
|
| 1133 |
+
"grad_norm": 0.06705697625875473,
|
| 1134 |
+
"learning_rate": 3.884701242008949e-05,
|
| 1135 |
+
"loss": 0.9309,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.7429626211352099,
|
| 1140 |
+
"grad_norm": 0.06846518814563751,
|
| 1141 |
+
"learning_rate": 3.757899596131529e-05,
|
| 1142 |
+
"loss": 0.9602,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.747577295800646,
|
| 1147 |
+
"grad_norm": 0.07015591859817505,
|
| 1148 |
+
"learning_rate": 3.632721416178029e-05,
|
| 1149 |
+
"loss": 0.9831,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.7521919704660821,
|
| 1154 |
+
"grad_norm": 0.06770645827054977,
|
| 1155 |
+
"learning_rate": 3.509199258899603e-05,
|
| 1156 |
+
"loss": 0.9638,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7568066451315182,
|
| 1161 |
+
"grad_norm": 0.07250072807073593,
|
| 1162 |
+
"learning_rate": 3.387365250343615e-05,
|
| 1163 |
+
"loss": 0.9607,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7614213197969543,
|
| 1168 |
+
"grad_norm": 0.06818177551031113,
|
| 1169 |
+
"learning_rate": 3.267251077498169e-05,
|
| 1170 |
+
"loss": 0.9445,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7660359944623903,
|
| 1175 |
+
"grad_norm": 0.06822264194488525,
|
| 1176 |
+
"learning_rate": 3.148887980050872e-05,
|
| 1177 |
+
"loss": 0.9521,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7706506691278265,
|
| 1182 |
+
"grad_norm": 0.06892835348844528,
|
| 1183 |
+
"learning_rate": 3.0323067422638908e-05,
|
| 1184 |
+
"loss": 0.9624,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7752653437932626,
|
| 1189 |
+
"grad_norm": 0.06881006807088852,
|
| 1190 |
+
"learning_rate": 2.9175376849675073e-05,
|
| 1191 |
+
"loss": 0.9773,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7798800184586987,
|
| 1196 |
+
"grad_norm": 0.06809905171394348,
|
| 1197 |
+
"learning_rate": 2.8046106576741605e-05,
|
| 1198 |
+
"loss": 0.9462,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7844946931241348,
|
| 1203 |
+
"grad_norm": 0.06759600341320038,
|
| 1204 |
+
"learning_rate": 2.6935550308150847e-05,
|
| 1205 |
+
"loss": 0.9488,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7891093677895709,
|
| 1210 |
+
"grad_norm": 0.06885316222906113,
|
| 1211 |
+
"learning_rate": 2.5843996881015676e-05,
|
| 1212 |
+
"loss": 0.9526,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7937240424550069,
|
| 1217 |
+
"grad_norm": 0.06799903512001038,
|
| 1218 |
+
"learning_rate": 2.4771730190127618e-05,
|
| 1219 |
+
"loss": 0.9446,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.798338717120443,
|
| 1224 |
+
"grad_norm": 0.06789611279964447,
|
| 1225 |
+
"learning_rate": 2.3719029114120716e-05,
|
| 1226 |
+
"loss": 0.949,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8029533917858791,
|
| 1231 |
+
"grad_norm": 0.06740868836641312,
|
| 1232 |
+
"learning_rate": 2.268616744293973e-05,
|
| 1233 |
+
"loss": 0.9531,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8075680664513152,
|
| 1238 |
+
"grad_norm": 0.06866241991519928,
|
| 1239 |
+
"learning_rate": 2.1673413806632102e-05,
|
| 1240 |
+
"loss": 0.9534,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.8121827411167513,
|
| 1245 |
+
"grad_norm": 0.06787573546171188,
|
| 1246 |
+
"learning_rate": 2.068103160548156e-05,
|
| 1247 |
+
"loss": 0.9473,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8167974157821873,
|
| 1252 |
+
"grad_norm": 0.07063360512256622,
|
| 1253 |
+
"learning_rate": 1.9709278941502363e-05,
|
| 1254 |
+
"loss": 0.9486,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8214120904476234,
|
| 1259 |
+
"grad_norm": 0.07002748548984528,
|
| 1260 |
+
"learning_rate": 1.8758408551311047e-05,
|
| 1261 |
+
"loss": 0.943,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.8260267651130595,
|
| 1266 |
+
"grad_norm": 0.07106012105941772,
|
| 1267 |
+
"learning_rate": 1.7828667740394044e-05,
|
| 1268 |
+
"loss": 0.9662,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8306414397784956,
|
| 1273 |
+
"grad_norm": 0.06852705031633377,
|
| 1274 |
+
"learning_rate": 1.692029831878753e-05,
|
| 1275 |
+
"loss": 0.9505,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.8352561144439317,
|
| 1280 |
+
"grad_norm": 0.07118076831102371,
|
| 1281 |
+
"learning_rate": 1.6033536538186778e-05,
|
| 1282 |
+
"loss": 0.9553,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.8398707891093677,
|
| 1287 |
+
"grad_norm": 0.06763019412755966,
|
| 1288 |
+
"learning_rate": 1.5168613030500923e-05,
|
| 1289 |
+
"loss": 0.9445,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8444854637748038,
|
| 1294 |
+
"grad_norm": 0.06864377856254578,
|
| 1295 |
+
"learning_rate": 1.4325752747869626e-05,
|
| 1296 |
+
"loss": 0.9553,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.84910013844024,
|
| 1301 |
+
"grad_norm": 0.06862477213144302,
|
| 1302 |
+
"learning_rate": 1.3505174904156593e-05,
|
| 1303 |
+
"loss": 0.948,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.8537148131056761,
|
| 1308 |
+
"grad_norm": 0.06800781190395355,
|
| 1309 |
+
"learning_rate": 1.2707092917935914e-05,
|
| 1310 |
+
"loss": 0.9604,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.8583294877711122,
|
| 1315 |
+
"grad_norm": 0.06934888660907745,
|
| 1316 |
+
"learning_rate": 1.1931714356985257e-05,
|
| 1317 |
+
"loss": 0.9487,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.8629441624365483,
|
| 1322 |
+
"grad_norm": 0.06795363873243332,
|
| 1323 |
+
"learning_rate": 1.1179240884301156e-05,
|
| 1324 |
+
"loss": 0.94,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.8675588371019843,
|
| 1329 |
+
"grad_norm": 0.06862738728523254,
|
| 1330 |
+
"learning_rate": 1.0449868205649649e-05,
|
| 1331 |
+
"loss": 0.9314,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.8721735117674204,
|
| 1336 |
+
"grad_norm": 0.06817808747291565,
|
| 1337 |
+
"learning_rate": 9.74378601866669e-06,
|
| 1338 |
+
"loss": 0.9552,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.8767881864328565,
|
| 1343 |
+
"grad_norm": 0.06724893301725388,
|
| 1344 |
+
"learning_rate": 9.061177963520751e-06,
|
| 1345 |
+
"loss": 0.9624,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.8814028610982926,
|
| 1350 |
+
"grad_norm": 0.06659146398305893,
|
| 1351 |
+
"learning_rate": 8.402221575151238e-06,
|
| 1352 |
+
"loss": 0.9275,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.8860175357637287,
|
| 1357 |
+
"grad_norm": 0.06741462647914886,
|
| 1358 |
+
"learning_rate": 7.767088237094577e-06,
|
| 1359 |
+
"loss": 0.9576,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.8906322104291647,
|
| 1364 |
+
"grad_norm": 0.06838846951723099,
|
| 1365 |
+
"learning_rate": 7.155943136910193e-06,
|
| 1366 |
+
"loss": 0.9583,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8952468850946008,
|
| 1371 |
+
"grad_norm": 0.06980287283658981,
|
| 1372 |
+
"learning_rate": 6.5689452232180485e-06,
|
| 1373 |
+
"loss": 0.9594,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8998615597600369,
|
| 1378 |
+
"grad_norm": 0.0681188777089119,
|
| 1379 |
+
"learning_rate": 6.00624716435868e-06,
|
| 1380 |
+
"loss": 0.9361,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.904476234425473,
|
| 1385 |
+
"grad_norm": 0.06910879909992218,
|
| 1386 |
+
"learning_rate": 5.467995308686813e-06,
|
| 1387 |
+
"loss": 0.9675,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.9090909090909091,
|
| 1392 |
+
"grad_norm": 0.07297144830226898,
|
| 1393 |
+
"learning_rate": 4.954329646508505e-06,
|
| 1394 |
+
"loss": 0.9525,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.9137055837563451,
|
| 1399 |
+
"grad_norm": 0.06912152469158173,
|
| 1400 |
+
"learning_rate": 4.465383773672127e-06,
|
| 1401 |
+
"loss": 0.9597,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.9183202584217812,
|
| 1406 |
+
"grad_norm": 0.06780077517032623,
|
| 1407 |
+
"learning_rate": 4.001284856822174e-06,
|
| 1408 |
+
"loss": 0.9572,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.9229349330872173,
|
| 1413 |
+
"grad_norm": 0.0673639103770256,
|
| 1414 |
+
"learning_rate": 3.562153600325491e-06,
|
| 1415 |
+
"loss": 0.9394,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.9275496077526535,
|
| 1420 |
+
"grad_norm": 0.06862404197454453,
|
| 1421 |
+
"learning_rate": 3.1481042148779672e-06,
|
| 1422 |
+
"loss": 0.9654,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.9321642824180896,
|
| 1427 |
+
"grad_norm": 0.06896745413541794,
|
| 1428 |
+
"learning_rate": 2.7592443878003195e-06,
|
| 1429 |
+
"loss": 0.963,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.9367789570835257,
|
| 1434 |
+
"grad_norm": 0.06962341070175171,
|
| 1435 |
+
"learning_rate": 2.395675255030383e-06,
|
| 1436 |
+
"loss": 0.9473,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.9413936317489617,
|
| 1441 |
+
"grad_norm": 0.06696717441082001,
|
| 1442 |
+
"learning_rate": 2.0574913748193647e-06,
|
| 1443 |
+
"loss": 0.9493,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.9460083064143978,
|
| 1448 |
+
"grad_norm": 0.06831862032413483,
|
| 1449 |
+
"learning_rate": 1.7447807031388264e-06,
|
| 1450 |
+
"loss": 0.9504,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.9506229810798339,
|
| 1455 |
+
"grad_norm": 0.07115928083658218,
|
| 1456 |
+
"learning_rate": 1.457624570804772e-06,
|
| 1457 |
+
"loss": 0.943,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.95523765574527,
|
| 1462 |
+
"grad_norm": 0.06887007504701614,
|
| 1463 |
+
"learning_rate": 1.196097662324902e-06,
|
| 1464 |
+
"loss": 0.9679,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.9598523304107061,
|
| 1469 |
+
"grad_norm": 0.06956353038549423,
|
| 1470 |
+
"learning_rate": 9.602679964744288e-07,
|
| 1471 |
+
"loss": 0.9413,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.9644670050761421,
|
| 1476 |
+
"grad_norm": 0.06954739987850189,
|
| 1477 |
+
"learning_rate": 7.501969086054717e-07,
|
| 1478 |
+
"loss": 0.9497,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.9690816797415782,
|
| 1483 |
+
"grad_norm": 0.06847439706325531,
|
| 1484 |
+
"learning_rate": 5.659390346948179e-07,
|
| 1485 |
+
"loss": 0.9641,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.9736963544070143,
|
| 1490 |
+
"grad_norm": 0.06772764027118683,
|
| 1491 |
+
"learning_rate": 4.075422971340115e-07,
|
| 1492 |
+
"loss": 0.9616,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.9783110290724504,
|
| 1497 |
+
"grad_norm": 0.06802436709403992,
|
| 1498 |
+
"learning_rate": 2.7504789226548977e-07,
|
| 1499 |
+
"loss": 0.953,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.9829257037378865,
|
| 1504 |
+
"grad_norm": 0.06744276732206345,
|
| 1505 |
+
"learning_rate": 1.6849027966816532e-07,
|
| 1506 |
+
"loss": 0.9489,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.9875403784033225,
|
| 1511 |
+
"grad_norm": 0.06742815673351288,
|
| 1512 |
+
"learning_rate": 8.789717319505065e-08,
|
| 1513 |
+
"loss": 0.9593,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.9921550530687586,
|
| 1518 |
+
"grad_norm": 0.07070456445217133,
|
| 1519 |
+
"learning_rate": 3.328953376530164e-08,
|
| 1520 |
+
"loss": 0.9528,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.9967697277341947,
|
| 1525 |
+
"grad_norm": 0.06779249012470245,
|
| 1526 |
+
"learning_rate": 4.6815639127006925e-09,
|
| 1527 |
+
"loss": 0.9468,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.9995385325334564,
|
| 1532 |
+
"eval_loss": 0.9562498331069946,
|
| 1533 |
+
"eval_runtime": 12105.6627,
|
| 1534 |
+
"eval_samples_per_second": 1.268,
|
| 1535 |
+
"eval_steps_per_second": 1.268,
|
| 1536 |
+
"step": 1083
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9995385325334564,
|
| 1540 |
+
"step": 1083,
|
| 1541 |
+
"total_flos": 1.2183828414859313e+19,
|
| 1542 |
+
"train_loss": 0.9649847933019847,
|
| 1543 |
+
"train_runtime": 330634.4933,
|
| 1544 |
+
"train_samples_per_second": 0.419,
|
| 1545 |
+
"train_steps_per_second": 0.003
|
| 1546 |
+
}
|
| 1547 |
+
],
|
| 1548 |
+
"logging_steps": 5,
|
| 1549 |
+
"max_steps": 1083,
|
| 1550 |
+
"num_input_tokens_seen": 0,
|
| 1551 |
+
"num_train_epochs": 1,
|
| 1552 |
+
"save_steps": 100,
|
| 1553 |
+
"stateful_callbacks": {
|
| 1554 |
+
"TrainerControl": {
|
| 1555 |
+
"args": {
|
| 1556 |
+
"should_epoch_stop": false,
|
| 1557 |
+
"should_evaluate": false,
|
| 1558 |
+
"should_log": false,
|
| 1559 |
+
"should_save": true,
|
| 1560 |
+
"should_training_stop": true
|
| 1561 |
+
},
|
| 1562 |
+
"attributes": {}
|
| 1563 |
+
}
|
| 1564 |
+
},
|
| 1565 |
+
"total_flos": 1.2183828414859313e+19,
|
| 1566 |
+
"train_batch_size": 2,
|
| 1567 |
+
"trial_name": null,
|
| 1568 |
+
"trial_params": null
|
| 1569 |
+
}
|