Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep15_04-56-03_COE-CS-sv003/events.out.tfevents.1726376440.COE-CS-sv003.3473779.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2408 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: feedback_p0.1_seed42_level2_styledirtybatch16
|
| 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 |
+
# feedback_p0.1_seed42_level2_styledirtybatch16
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None 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: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- total_train_batch_size: 16
|
| 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 |
+
- Transformers 4.44.2
|
| 58 |
+
- Pytorch 2.3.1+cu121
|
| 59 |
+
- Datasets 2.19.1
|
| 60 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 176088290426880.0,
|
| 4 |
+
"train_loss": 0.5311898304931332,
|
| 5 |
+
"train_runtime": 14992.3235,
|
| 6 |
+
"train_samples": 89042,
|
| 7 |
+
"train_samples_per_second": 1.795,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.44.2"
|
| 6 |
+
}
|
runs/Sep15_04-56-03_COE-CS-sv003/events.out.tfevents.1726376440.COE-CS-sv003.3473779.0
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 sha256:9f7615349b5798ebb01b8afdc067b63c036a9d320a22b84bc2a693d774cddec8
|
| 3 |
+
size 76850
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 176088290426880.0,
|
| 4 |
+
"train_loss": 0.5311898304931332,
|
| 5 |
+
"train_runtime": 14992.3235,
|
| 6 |
+
"train_samples": 89042,
|
| 7 |
+
"train_samples_per_second": 1.795,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1682,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0005945303210463733,
|
| 13 |
+
"grad_norm": 23.17915866800298,
|
| 14 |
+
"learning_rate": 5.91715976331361e-08,
|
| 15 |
+
"loss": 1.3012,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002972651605231867,
|
| 20 |
+
"grad_norm": 23.37449539925455,
|
| 21 |
+
"learning_rate": 2.958579881656805e-07,
|
| 22 |
+
"loss": 1.3439,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.005945303210463734,
|
| 27 |
+
"grad_norm": 10.391844977150628,
|
| 28 |
+
"learning_rate": 5.91715976331361e-07,
|
| 29 |
+
"loss": 1.2902,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0089179548156956,
|
| 34 |
+
"grad_norm": 12.298658554924508,
|
| 35 |
+
"learning_rate": 8.875739644970415e-07,
|
| 36 |
+
"loss": 1.1528,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.011890606420927468,
|
| 41 |
+
"grad_norm": 5.836227197737131,
|
| 42 |
+
"learning_rate": 1.183431952662722e-06,
|
| 43 |
+
"loss": 1.0462,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.014863258026159334,
|
| 48 |
+
"grad_norm": 3.59897554922516,
|
| 49 |
+
"learning_rate": 1.4792899408284026e-06,
|
| 50 |
+
"loss": 0.9416,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0178359096313912,
|
| 55 |
+
"grad_norm": 3.2741630752466273,
|
| 56 |
+
"learning_rate": 1.775147928994083e-06,
|
| 57 |
+
"loss": 0.9146,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.020808561236623068,
|
| 62 |
+
"grad_norm": 2.905060653147668,
|
| 63 |
+
"learning_rate": 2.0710059171597635e-06,
|
| 64 |
+
"loss": 0.8965,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.023781212841854936,
|
| 69 |
+
"grad_norm": 2.9848388765396066,
|
| 70 |
+
"learning_rate": 2.366863905325444e-06,
|
| 71 |
+
"loss": 0.8532,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0267538644470868,
|
| 76 |
+
"grad_norm": 2.928858994497014,
|
| 77 |
+
"learning_rate": 2.6627218934911246e-06,
|
| 78 |
+
"loss": 0.8607,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.029726516052318668,
|
| 83 |
+
"grad_norm": 2.9699519304565105,
|
| 84 |
+
"learning_rate": 2.958579881656805e-06,
|
| 85 |
+
"loss": 0.8293,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.032699167657550536,
|
| 90 |
+
"grad_norm": 2.9924496822372846,
|
| 91 |
+
"learning_rate": 3.2544378698224853e-06,
|
| 92 |
+
"loss": 0.8376,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0356718192627824,
|
| 97 |
+
"grad_norm": 3.0189144878653127,
|
| 98 |
+
"learning_rate": 3.550295857988166e-06,
|
| 99 |
+
"loss": 0.8223,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03864447086801427,
|
| 104 |
+
"grad_norm": 3.022152891252942,
|
| 105 |
+
"learning_rate": 3.846153846153847e-06,
|
| 106 |
+
"loss": 0.808,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.041617122473246136,
|
| 111 |
+
"grad_norm": 3.0781659112469577,
|
| 112 |
+
"learning_rate": 4.142011834319527e-06,
|
| 113 |
+
"loss": 0.7936,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.044589774078478,
|
| 118 |
+
"grad_norm": 3.084476562677424,
|
| 119 |
+
"learning_rate": 4.437869822485207e-06,
|
| 120 |
+
"loss": 0.7752,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04756242568370987,
|
| 125 |
+
"grad_norm": 3.2098986890021237,
|
| 126 |
+
"learning_rate": 4.733727810650888e-06,
|
| 127 |
+
"loss": 0.7763,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.050535077288941736,
|
| 132 |
+
"grad_norm": 3.19384567951823,
|
| 133 |
+
"learning_rate": 5.029585798816569e-06,
|
| 134 |
+
"loss": 0.7746,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0535077288941736,
|
| 139 |
+
"grad_norm": 2.964927416048633,
|
| 140 |
+
"learning_rate": 5.325443786982249e-06,
|
| 141 |
+
"loss": 0.7682,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05648038049940547,
|
| 146 |
+
"grad_norm": 3.1019748122364277,
|
| 147 |
+
"learning_rate": 5.621301775147929e-06,
|
| 148 |
+
"loss": 0.7518,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.059453032104637336,
|
| 153 |
+
"grad_norm": 3.2201430089223386,
|
| 154 |
+
"learning_rate": 5.91715976331361e-06,
|
| 155 |
+
"loss": 0.7436,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0624256837098692,
|
| 160 |
+
"grad_norm": 2.927109670294165,
|
| 161 |
+
"learning_rate": 6.21301775147929e-06,
|
| 162 |
+
"loss": 0.7426,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06539833531510107,
|
| 167 |
+
"grad_norm": 2.8885844881352742,
|
| 168 |
+
"learning_rate": 6.5088757396449705e-06,
|
| 169 |
+
"loss": 0.74,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06837098692033294,
|
| 174 |
+
"grad_norm": 3.172326235032539,
|
| 175 |
+
"learning_rate": 6.8047337278106515e-06,
|
| 176 |
+
"loss": 0.7647,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0713436385255648,
|
| 181 |
+
"grad_norm": 2.8788604196009047,
|
| 182 |
+
"learning_rate": 7.100591715976332e-06,
|
| 183 |
+
"loss": 0.7341,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.07431629013079667,
|
| 188 |
+
"grad_norm": 2.7082199945019956,
|
| 189 |
+
"learning_rate": 7.396449704142013e-06,
|
| 190 |
+
"loss": 0.7347,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07728894173602854,
|
| 195 |
+
"grad_norm": 2.877616745493528,
|
| 196 |
+
"learning_rate": 7.692307692307694e-06,
|
| 197 |
+
"loss": 0.7266,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0802615933412604,
|
| 202 |
+
"grad_norm": 2.873705604654048,
|
| 203 |
+
"learning_rate": 7.988165680473373e-06,
|
| 204 |
+
"loss": 0.7461,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.08323424494649227,
|
| 209 |
+
"grad_norm": 3.188866051330491,
|
| 210 |
+
"learning_rate": 8.284023668639054e-06,
|
| 211 |
+
"loss": 0.7267,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.08620689655172414,
|
| 216 |
+
"grad_norm": 2.7709923287552787,
|
| 217 |
+
"learning_rate": 8.579881656804735e-06,
|
| 218 |
+
"loss": 0.7183,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.089179548156956,
|
| 223 |
+
"grad_norm": 2.8980920523843032,
|
| 224 |
+
"learning_rate": 8.875739644970414e-06,
|
| 225 |
+
"loss": 0.7204,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.09215219976218787,
|
| 230 |
+
"grad_norm": 2.8127651120484893,
|
| 231 |
+
"learning_rate": 9.171597633136095e-06,
|
| 232 |
+
"loss": 0.7263,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09512485136741974,
|
| 237 |
+
"grad_norm": 3.099526975800466,
|
| 238 |
+
"learning_rate": 9.467455621301776e-06,
|
| 239 |
+
"loss": 0.7266,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0980975029726516,
|
| 244 |
+
"grad_norm": 2.847472407806089,
|
| 245 |
+
"learning_rate": 9.763313609467457e-06,
|
| 246 |
+
"loss": 0.7148,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.10107015457788347,
|
| 251 |
+
"grad_norm": 3.1542218699949243,
|
| 252 |
+
"learning_rate": 9.999989221415223e-06,
|
| 253 |
+
"loss": 0.73,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.10404280618311534,
|
| 258 |
+
"grad_norm": 2.7886695417326197,
|
| 259 |
+
"learning_rate": 9.999611975827441e-06,
|
| 260 |
+
"loss": 0.7205,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1070154577883472,
|
| 265 |
+
"grad_norm": 2.863907914649196,
|
| 266 |
+
"learning_rate": 9.998695847471015e-06,
|
| 267 |
+
"loss": 0.7291,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.10998810939357907,
|
| 272 |
+
"grad_norm": 2.682699306725325,
|
| 273 |
+
"learning_rate": 9.997240935090764e-06,
|
| 274 |
+
"loss": 0.7179,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.11296076099881094,
|
| 279 |
+
"grad_norm": 2.6714047020353893,
|
| 280 |
+
"learning_rate": 9.9952473955043e-06,
|
| 281 |
+
"loss": 0.7095,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1159334126040428,
|
| 286 |
+
"grad_norm": 2.919385127037625,
|
| 287 |
+
"learning_rate": 9.992715443585123e-06,
|
| 288 |
+
"loss": 0.7183,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.11890606420927467,
|
| 293 |
+
"grad_norm": 2.758146983625847,
|
| 294 |
+
"learning_rate": 9.989645352239467e-06,
|
| 295 |
+
"loss": 0.7097,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.12187871581450654,
|
| 300 |
+
"grad_norm": 2.478949177408348,
|
| 301 |
+
"learning_rate": 9.986037452376875e-06,
|
| 302 |
+
"loss": 0.7053,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1248513674197384,
|
| 307 |
+
"grad_norm": 2.7139657440292004,
|
| 308 |
+
"learning_rate": 9.98189213287454e-06,
|
| 309 |
+
"loss": 0.7141,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.1278240190249703,
|
| 314 |
+
"grad_norm": 2.525450968321056,
|
| 315 |
+
"learning_rate": 9.977209840535388e-06,
|
| 316 |
+
"loss": 0.712,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.13079667063020214,
|
| 321 |
+
"grad_norm": 2.5660210355660085,
|
| 322 |
+
"learning_rate": 9.971991080039912e-06,
|
| 323 |
+
"loss": 0.7029,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.133769322235434,
|
| 328 |
+
"grad_norm": 2.719791305848057,
|
| 329 |
+
"learning_rate": 9.966236413891787e-06,
|
| 330 |
+
"loss": 0.6874,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1367419738406659,
|
| 335 |
+
"grad_norm": 2.7013784687029174,
|
| 336 |
+
"learning_rate": 9.959946462357237e-06,
|
| 337 |
+
"loss": 0.7053,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.13971462544589774,
|
| 342 |
+
"grad_norm": 2.4163450862939273,
|
| 343 |
+
"learning_rate": 9.953121903398172e-06,
|
| 344 |
+
"loss": 0.69,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1426872770511296,
|
| 349 |
+
"grad_norm": 2.6651187768588884,
|
| 350 |
+
"learning_rate": 9.945763472599125e-06,
|
| 351 |
+
"loss": 0.6974,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.1456599286563615,
|
| 356 |
+
"grad_norm": 2.61783925406702,
|
| 357 |
+
"learning_rate": 9.937871963087958e-06,
|
| 358 |
+
"loss": 0.6964,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.14863258026159334,
|
| 363 |
+
"grad_norm": 2.6420632329467826,
|
| 364 |
+
"learning_rate": 9.929448225450375e-06,
|
| 365 |
+
"loss": 0.6814,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.1516052318668252,
|
| 370 |
+
"grad_norm": 2.585841442008173,
|
| 371 |
+
"learning_rate": 9.920493167638256e-06,
|
| 372 |
+
"loss": 0.6904,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1545778834720571,
|
| 377 |
+
"grad_norm": 2.772149995259441,
|
| 378 |
+
"learning_rate": 9.911007754871773e-06,
|
| 379 |
+
"loss": 0.6998,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.15755053507728894,
|
| 384 |
+
"grad_norm": 2.633310745015164,
|
| 385 |
+
"learning_rate": 9.900993009535365e-06,
|
| 386 |
+
"loss": 0.6936,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1605231866825208,
|
| 391 |
+
"grad_norm": 2.5624767016075016,
|
| 392 |
+
"learning_rate": 9.890450011067544e-06,
|
| 393 |
+
"loss": 0.6901,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1634958382877527,
|
| 398 |
+
"grad_norm": 2.4863789713476803,
|
| 399 |
+
"learning_rate": 9.879379895844537e-06,
|
| 400 |
+
"loss": 0.7005,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.16646848989298454,
|
| 405 |
+
"grad_norm": 2.6081863153211535,
|
| 406 |
+
"learning_rate": 9.867783857057808e-06,
|
| 407 |
+
"loss": 0.6739,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.1694411414982164,
|
| 412 |
+
"grad_norm": 2.5731120093742854,
|
| 413 |
+
"learning_rate": 9.855663144585456e-06,
|
| 414 |
+
"loss": 0.6788,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.1724137931034483,
|
| 419 |
+
"grad_norm": 2.4603786025187375,
|
| 420 |
+
"learning_rate": 9.843019064857481e-06,
|
| 421 |
+
"loss": 0.682,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.17538644470868014,
|
| 426 |
+
"grad_norm": 2.5203036804775083,
|
| 427 |
+
"learning_rate": 9.829852980714986e-06,
|
| 428 |
+
"loss": 0.6592,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.178359096313912,
|
| 433 |
+
"grad_norm": 2.4982207442211846,
|
| 434 |
+
"learning_rate": 9.816166311263276e-06,
|
| 435 |
+
"loss": 0.6678,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1813317479191439,
|
| 440 |
+
"grad_norm": 2.7749883913033395,
|
| 441 |
+
"learning_rate": 9.801960531718898e-06,
|
| 442 |
+
"loss": 0.6906,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.18430439952437574,
|
| 447 |
+
"grad_norm": 2.604444101827745,
|
| 448 |
+
"learning_rate": 9.787237173250641e-06,
|
| 449 |
+
"loss": 0.6591,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1872770511296076,
|
| 454 |
+
"grad_norm": 2.4391472456168812,
|
| 455 |
+
"learning_rate": 9.771997822814496e-06,
|
| 456 |
+
"loss": 0.6697,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.1902497027348395,
|
| 461 |
+
"grad_norm": 2.4616817852361366,
|
| 462 |
+
"learning_rate": 9.756244122982608e-06,
|
| 463 |
+
"loss": 0.6734,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.19322235434007135,
|
| 468 |
+
"grad_norm": 2.5774348327106984,
|
| 469 |
+
"learning_rate": 9.739977771766225e-06,
|
| 470 |
+
"loss": 0.6588,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.1961950059453032,
|
| 475 |
+
"grad_norm": 2.5087234779825116,
|
| 476 |
+
"learning_rate": 9.723200522432683e-06,
|
| 477 |
+
"loss": 0.6664,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1991676575505351,
|
| 482 |
+
"grad_norm": 2.3989927240738607,
|
| 483 |
+
"learning_rate": 9.705914183316435e-06,
|
| 484 |
+
"loss": 0.6803,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.20214030915576695,
|
| 489 |
+
"grad_norm": 2.401172984855569,
|
| 490 |
+
"learning_rate": 9.68812061762413e-06,
|
| 491 |
+
"loss": 0.6636,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.2051129607609988,
|
| 496 |
+
"grad_norm": 2.4421036295734426,
|
| 497 |
+
"learning_rate": 9.669821743233794e-06,
|
| 498 |
+
"loss": 0.6389,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.2080856123662307,
|
| 503 |
+
"grad_norm": 2.577840676624431,
|
| 504 |
+
"learning_rate": 9.65101953248811e-06,
|
| 505 |
+
"loss": 0.6586,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.21105826397146255,
|
| 510 |
+
"grad_norm": 2.3940226323264917,
|
| 511 |
+
"learning_rate": 9.631716011981823e-06,
|
| 512 |
+
"loss": 0.6479,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2140309155766944,
|
| 517 |
+
"grad_norm": 2.5250690081911786,
|
| 518 |
+
"learning_rate": 9.611913262343321e-06,
|
| 519 |
+
"loss": 0.6506,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.2170035671819263,
|
| 524 |
+
"grad_norm": 2.4264301363563545,
|
| 525 |
+
"learning_rate": 9.591613418010355e-06,
|
| 526 |
+
"loss": 0.6357,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.21997621878715815,
|
| 531 |
+
"grad_norm": 2.751369457099525,
|
| 532 |
+
"learning_rate": 9.57081866699999e-06,
|
| 533 |
+
"loss": 0.6551,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.22294887039239,
|
| 538 |
+
"grad_norm": 2.7219604193356672,
|
| 539 |
+
"learning_rate": 9.549531250672764e-06,
|
| 540 |
+
"loss": 0.6463,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.2259215219976219,
|
| 545 |
+
"grad_norm": 2.45624731672107,
|
| 546 |
+
"learning_rate": 9.52775346349111e-06,
|
| 547 |
+
"loss": 0.646,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.22889417360285375,
|
| 552 |
+
"grad_norm": 2.544975764712231,
|
| 553 |
+
"learning_rate": 9.505487652772038e-06,
|
| 554 |
+
"loss": 0.6354,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2318668252080856,
|
| 559 |
+
"grad_norm": 2.374830073694884,
|
| 560 |
+
"learning_rate": 9.482736218434144e-06,
|
| 561 |
+
"loss": 0.6502,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2348394768133175,
|
| 566 |
+
"grad_norm": 2.422663231385471,
|
| 567 |
+
"learning_rate": 9.459501612738915e-06,
|
| 568 |
+
"loss": 0.6502,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.23781212841854935,
|
| 573 |
+
"grad_norm": 2.490293745714411,
|
| 574 |
+
"learning_rate": 9.435786340026434e-06,
|
| 575 |
+
"loss": 0.6303,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2407847800237812,
|
| 580 |
+
"grad_norm": 2.6066004181742124,
|
| 581 |
+
"learning_rate": 9.41159295644543e-06,
|
| 582 |
+
"loss": 0.6486,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.2437574316290131,
|
| 587 |
+
"grad_norm": 2.5218752196441434,
|
| 588 |
+
"learning_rate": 9.38692406967778e-06,
|
| 589 |
+
"loss": 0.6209,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.24673008323424495,
|
| 594 |
+
"grad_norm": 2.389380886868179,
|
| 595 |
+
"learning_rate": 9.36178233865743e-06,
|
| 596 |
+
"loss": 0.6168,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.2497027348394768,
|
| 601 |
+
"grad_norm": 2.5150661226784794,
|
| 602 |
+
"learning_rate": 9.336170473283803e-06,
|
| 603 |
+
"loss": 0.6171,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.25267538644470866,
|
| 608 |
+
"grad_norm": 2.435724631506405,
|
| 609 |
+
"learning_rate": 9.310091234129718e-06,
|
| 610 |
+
"loss": 0.6299,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2556480380499406,
|
| 615 |
+
"grad_norm": 2.394787101037759,
|
| 616 |
+
"learning_rate": 9.283547432143842e-06,
|
| 617 |
+
"loss": 0.6051,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.25862068965517243,
|
| 622 |
+
"grad_norm": 2.3112769318054602,
|
| 623 |
+
"learning_rate": 9.256541928347701e-06,
|
| 624 |
+
"loss": 0.6332,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2615933412604043,
|
| 629 |
+
"grad_norm": 2.395884463823803,
|
| 630 |
+
"learning_rate": 9.229077633527317e-06,
|
| 631 |
+
"loss": 0.6363,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.26456599286563615,
|
| 636 |
+
"grad_norm": 2.5353977000342245,
|
| 637 |
+
"learning_rate": 9.201157507919466e-06,
|
| 638 |
+
"loss": 0.6096,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.267538644470868,
|
| 643 |
+
"grad_norm": 2.4062321379781957,
|
| 644 |
+
"learning_rate": 9.17278456089261e-06,
|
| 645 |
+
"loss": 0.6214,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.27051129607609986,
|
| 650 |
+
"grad_norm": 2.3853947296491254,
|
| 651 |
+
"learning_rate": 9.143961850622523e-06,
|
| 652 |
+
"loss": 0.6357,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.2734839476813318,
|
| 657 |
+
"grad_norm": 2.3411923936500587,
|
| 658 |
+
"learning_rate": 9.114692483762682e-06,
|
| 659 |
+
"loss": 0.6111,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.27645659928656363,
|
| 664 |
+
"grad_norm": 2.805658532417448,
|
| 665 |
+
"learning_rate": 9.084979615109402e-06,
|
| 666 |
+
"loss": 0.6338,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.2794292508917955,
|
| 671 |
+
"grad_norm": 2.519691039204996,
|
| 672 |
+
"learning_rate": 9.054826447261807e-06,
|
| 673 |
+
"loss": 0.616,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.28240190249702735,
|
| 678 |
+
"grad_norm": 2.5502443998981295,
|
| 679 |
+
"learning_rate": 9.02423623027663e-06,
|
| 680 |
+
"loss": 0.6215,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.2853745541022592,
|
| 685 |
+
"grad_norm": 2.3581542332305374,
|
| 686 |
+
"learning_rate": 8.993212261317911e-06,
|
| 687 |
+
"loss": 0.6143,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.28834720570749106,
|
| 692 |
+
"grad_norm": 2.2185371096529267,
|
| 693 |
+
"learning_rate": 8.961757884301614e-06,
|
| 694 |
+
"loss": 0.6103,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.291319857312723,
|
| 699 |
+
"grad_norm": 2.388161926408038,
|
| 700 |
+
"learning_rate": 8.929876489535196e-06,
|
| 701 |
+
"loss": 0.6165,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.29429250891795483,
|
| 706 |
+
"grad_norm": 2.3962973629889466,
|
| 707 |
+
"learning_rate": 8.89757151335219e-06,
|
| 708 |
+
"loss": 0.6124,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2972651605231867,
|
| 713 |
+
"grad_norm": 2.3456101381645746,
|
| 714 |
+
"learning_rate": 8.864846437741817e-06,
|
| 715 |
+
"loss": 0.6168,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.30023781212841855,
|
| 720 |
+
"grad_norm": 2.857739205060792,
|
| 721 |
+
"learning_rate": 8.831704789973677e-06,
|
| 722 |
+
"loss": 0.601,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.3032104637336504,
|
| 727 |
+
"grad_norm": 2.404200391558541,
|
| 728 |
+
"learning_rate": 8.79815014221757e-06,
|
| 729 |
+
"loss": 0.6159,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.30618311533888226,
|
| 734 |
+
"grad_norm": 2.5066882094814185,
|
| 735 |
+
"learning_rate": 8.764186111158468e-06,
|
| 736 |
+
"loss": 0.6107,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.3091557669441142,
|
| 741 |
+
"grad_norm": 2.439281663409053,
|
| 742 |
+
"learning_rate": 8.729816357606683e-06,
|
| 743 |
+
"loss": 0.6082,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.31212841854934603,
|
| 748 |
+
"grad_norm": 2.434841960288868,
|
| 749 |
+
"learning_rate": 8.695044586103297e-06,
|
| 750 |
+
"loss": 0.6085,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.3151010701545779,
|
| 755 |
+
"grad_norm": 2.3045925871070394,
|
| 756 |
+
"learning_rate": 8.659874544520862e-06,
|
| 757 |
+
"loss": 0.5752,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.31807372175980975,
|
| 762 |
+
"grad_norm": 2.515840298273436,
|
| 763 |
+
"learning_rate": 8.624310023659437e-06,
|
| 764 |
+
"loss": 0.5954,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.3210463733650416,
|
| 769 |
+
"grad_norm": 2.514641603087097,
|
| 770 |
+
"learning_rate": 8.588354856838002e-06,
|
| 771 |
+
"loss": 0.5923,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.32401902497027346,
|
| 776 |
+
"grad_norm": 2.353964195966498,
|
| 777 |
+
"learning_rate": 8.552012919481278e-06,
|
| 778 |
+
"loss": 0.5785,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.3269916765755054,
|
| 783 |
+
"grad_norm": 2.3620191543194657,
|
| 784 |
+
"learning_rate": 8.515288128702015e-06,
|
| 785 |
+
"loss": 0.5942,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.32996432818073723,
|
| 790 |
+
"grad_norm": 2.5008196020127964,
|
| 791 |
+
"learning_rate": 8.478184442878787e-06,
|
| 792 |
+
"loss": 0.6116,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3329369797859691,
|
| 797 |
+
"grad_norm": 2.3614970118631833,
|
| 798 |
+
"learning_rate": 8.440705861229344e-06,
|
| 799 |
+
"loss": 0.5838,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.33590963139120095,
|
| 804 |
+
"grad_norm": 2.3019970993481813,
|
| 805 |
+
"learning_rate": 8.40285642337955e-06,
|
| 806 |
+
"loss": 0.5979,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.3388822829964328,
|
| 811 |
+
"grad_norm": 2.437131942480355,
|
| 812 |
+
"learning_rate": 8.36464020892797e-06,
|
| 813 |
+
"loss": 0.5583,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.34185493460166466,
|
| 818 |
+
"grad_norm": 2.326966178552118,
|
| 819 |
+
"learning_rate": 8.326061337006161e-06,
|
| 820 |
+
"loss": 0.5877,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3448275862068966,
|
| 825 |
+
"grad_norm": 2.5231196817030455,
|
| 826 |
+
"learning_rate": 8.287123965834682e-06,
|
| 827 |
+
"loss": 0.5774,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.34780023781212843,
|
| 832 |
+
"grad_norm": 2.445974147547591,
|
| 833 |
+
"learning_rate": 8.247832292274909e-06,
|
| 834 |
+
"loss": 0.5957,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.3507728894173603,
|
| 839 |
+
"grad_norm": 2.30995967302817,
|
| 840 |
+
"learning_rate": 8.208190551376668e-06,
|
| 841 |
+
"loss": 0.5913,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.35374554102259215,
|
| 846 |
+
"grad_norm": 2.304615444057916,
|
| 847 |
+
"learning_rate": 8.16820301592176e-06,
|
| 848 |
+
"loss": 0.5951,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.356718192627824,
|
| 853 |
+
"grad_norm": 2.2337712440097466,
|
| 854 |
+
"learning_rate": 8.127873995963439e-06,
|
| 855 |
+
"loss": 0.5717,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.35969084423305586,
|
| 860 |
+
"grad_norm": 2.352192550598562,
|
| 861 |
+
"learning_rate": 8.087207838361819e-06,
|
| 862 |
+
"loss": 0.5559,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3626634958382878,
|
| 867 |
+
"grad_norm": 2.4383288854885086,
|
| 868 |
+
"learning_rate": 8.046208926315381e-06,
|
| 869 |
+
"loss": 0.5621,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.36563614744351963,
|
| 874 |
+
"grad_norm": 2.4669126509592982,
|
| 875 |
+
"learning_rate": 8.004881678888518e-06,
|
| 876 |
+
"loss": 0.5822,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.3686087990487515,
|
| 881 |
+
"grad_norm": 2.350359506686674,
|
| 882 |
+
"learning_rate": 7.963230550535212e-06,
|
| 883 |
+
"loss": 0.5726,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.37158145065398335,
|
| 888 |
+
"grad_norm": 2.3573597155480965,
|
| 889 |
+
"learning_rate": 7.921260030618935e-06,
|
| 890 |
+
"loss": 0.5615,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.3745541022592152,
|
| 895 |
+
"grad_norm": 2.768754472930866,
|
| 896 |
+
"learning_rate": 7.878974642928752e-06,
|
| 897 |
+
"loss": 0.566,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.37752675386444706,
|
| 902 |
+
"grad_norm": 2.460878358484002,
|
| 903 |
+
"learning_rate": 7.836378945191718e-06,
|
| 904 |
+
"loss": 0.5534,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.380499405469679,
|
| 909 |
+
"grad_norm": 2.280914113206368,
|
| 910 |
+
"learning_rate": 7.793477528581642e-06,
|
| 911 |
+
"loss": 0.5655,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.38347205707491083,
|
| 916 |
+
"grad_norm": 2.481778359904293,
|
| 917 |
+
"learning_rate": 7.750275017224208e-06,
|
| 918 |
+
"loss": 0.5676,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3864447086801427,
|
| 923 |
+
"grad_norm": 2.616616432524906,
|
| 924 |
+
"learning_rate": 7.706776067698574e-06,
|
| 925 |
+
"loss": 0.564,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.38941736028537455,
|
| 930 |
+
"grad_norm": 2.371851297853059,
|
| 931 |
+
"learning_rate": 7.662985368535465e-06,
|
| 932 |
+
"loss": 0.5633,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.3923900118906064,
|
| 937 |
+
"grad_norm": 2.3788259328454413,
|
| 938 |
+
"learning_rate": 7.618907639711816e-06,
|
| 939 |
+
"loss": 0.5478,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.39536266349583826,
|
| 944 |
+
"grad_norm": 2.329685605293642,
|
| 945 |
+
"learning_rate": 7.574547632142029e-06,
|
| 946 |
+
"loss": 0.5496,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3983353151010702,
|
| 951 |
+
"grad_norm": 2.3986113985448867,
|
| 952 |
+
"learning_rate": 7.529910127165897e-06,
|
| 953 |
+
"loss": 0.5488,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.40130796670630203,
|
| 958 |
+
"grad_norm": 2.314354656341197,
|
| 959 |
+
"learning_rate": 7.48499993603325e-06,
|
| 960 |
+
"loss": 0.5564,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.4042806183115339,
|
| 965 |
+
"grad_norm": 2.301009486833614,
|
| 966 |
+
"learning_rate": 7.4398218993853765e-06,
|
| 967 |
+
"loss": 0.5579,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.40725326991676575,
|
| 972 |
+
"grad_norm": 2.529267389965807,
|
| 973 |
+
"learning_rate": 7.394380886733263e-06,
|
| 974 |
+
"loss": 0.5418,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.4102259215219976,
|
| 979 |
+
"grad_norm": 2.273496393101965,
|
| 980 |
+
"learning_rate": 7.3486817959327524e-06,
|
| 981 |
+
"loss": 0.5486,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.41319857312722946,
|
| 986 |
+
"grad_norm": 2.362055285648788,
|
| 987 |
+
"learning_rate": 7.302729552656613e-06,
|
| 988 |
+
"loss": 0.5473,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.4161712247324614,
|
| 993 |
+
"grad_norm": 2.568398004847708,
|
| 994 |
+
"learning_rate": 7.256529109863637e-06,
|
| 995 |
+
"loss": 0.5635,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.41914387633769323,
|
| 1000 |
+
"grad_norm": 2.334007582897662,
|
| 1001 |
+
"learning_rate": 7.210085447264777e-06,
|
| 1002 |
+
"loss": 0.5569,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.4221165279429251,
|
| 1007 |
+
"grad_norm": 2.27944109416587,
|
| 1008 |
+
"learning_rate": 7.163403570786416e-06,
|
| 1009 |
+
"loss": 0.5314,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.42508917954815695,
|
| 1014 |
+
"grad_norm": 2.439475832033061,
|
| 1015 |
+
"learning_rate": 7.116488512030798e-06,
|
| 1016 |
+
"loss": 0.5511,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.4280618311533888,
|
| 1021 |
+
"grad_norm": 2.3531415117791354,
|
| 1022 |
+
"learning_rate": 7.069345327733701e-06,
|
| 1023 |
+
"loss": 0.5457,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.43103448275862066,
|
| 1028 |
+
"grad_norm": 2.3295198969589035,
|
| 1029 |
+
"learning_rate": 7.021979099219396e-06,
|
| 1030 |
+
"loss": 0.5239,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.4340071343638526,
|
| 1035 |
+
"grad_norm": 2.5063503569942385,
|
| 1036 |
+
"learning_rate": 6.974394931852957e-06,
|
| 1037 |
+
"loss": 0.5384,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.43697978596908443,
|
| 1042 |
+
"grad_norm": 2.355478191724581,
|
| 1043 |
+
"learning_rate": 6.926597954489979e-06,
|
| 1044 |
+
"loss": 0.5098,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.4399524375743163,
|
| 1049 |
+
"grad_norm": 2.4091145093686372,
|
| 1050 |
+
"learning_rate": 6.878593318923763e-06,
|
| 1051 |
+
"loss": 0.5146,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.44292508917954815,
|
| 1056 |
+
"grad_norm": 2.3684497417326913,
|
| 1057 |
+
"learning_rate": 6.830386199330036e-06,
|
| 1058 |
+
"loss": 0.5146,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.44589774078478,
|
| 1063 |
+
"grad_norm": 2.4513900163292113,
|
| 1064 |
+
"learning_rate": 6.781981791709247e-06,
|
| 1065 |
+
"loss": 0.5152,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.44887039239001186,
|
| 1070 |
+
"grad_norm": 2.453629962173857,
|
| 1071 |
+
"learning_rate": 6.73338531332652e-06,
|
| 1072 |
+
"loss": 0.536,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.4518430439952438,
|
| 1077 |
+
"grad_norm": 2.474092048043491,
|
| 1078 |
+
"learning_rate": 6.6846020021493105e-06,
|
| 1079 |
+
"loss": 0.5236,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.45481569560047563,
|
| 1084 |
+
"grad_norm": 2.4532902284126523,
|
| 1085 |
+
"learning_rate": 6.63563711628283e-06,
|
| 1086 |
+
"loss": 0.518,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.4577883472057075,
|
| 1091 |
+
"grad_norm": 2.4470168591075163,
|
| 1092 |
+
"learning_rate": 6.586495933403306e-06,
|
| 1093 |
+
"loss": 0.5192,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.46076099881093935,
|
| 1098 |
+
"grad_norm": 2.483107107350786,
|
| 1099 |
+
"learning_rate": 6.53718375018912e-06,
|
| 1100 |
+
"loss": 0.5217,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.4637336504161712,
|
| 1105 |
+
"grad_norm": 2.433139401600069,
|
| 1106 |
+
"learning_rate": 6.4877058817499174e-06,
|
| 1107 |
+
"loss": 0.4948,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.4667063020214031,
|
| 1112 |
+
"grad_norm": 2.3018625992746684,
|
| 1113 |
+
"learning_rate": 6.4380676610537075e-06,
|
| 1114 |
+
"loss": 0.5156,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.469678953626635,
|
| 1119 |
+
"grad_norm": 2.425100167363479,
|
| 1120 |
+
"learning_rate": 6.388274438352053e-06,
|
| 1121 |
+
"loss": 0.5186,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.47265160523186683,
|
| 1126 |
+
"grad_norm": 2.4243934526405493,
|
| 1127 |
+
"learning_rate": 6.3383315806034014e-06,
|
| 1128 |
+
"loss": 0.5123,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.4756242568370987,
|
| 1133 |
+
"grad_norm": 2.3005885180264545,
|
| 1134 |
+
"learning_rate": 6.288244470894596e-06,
|
| 1135 |
+
"loss": 0.5147,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.47859690844233055,
|
| 1140 |
+
"grad_norm": 2.461720715630345,
|
| 1141 |
+
"learning_rate": 6.238018507860667e-06,
|
| 1142 |
+
"loss": 0.5192,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4815695600475624,
|
| 1147 |
+
"grad_norm": 2.391513806976481,
|
| 1148 |
+
"learning_rate": 6.187659105102941e-06,
|
| 1149 |
+
"loss": 0.5114,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.4845422116527943,
|
| 1154 |
+
"grad_norm": 2.2043491836548363,
|
| 1155 |
+
"learning_rate": 6.1371716906055336e-06,
|
| 1156 |
+
"loss": 0.5277,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4875148632580262,
|
| 1161 |
+
"grad_norm": 2.4124196938652074,
|
| 1162 |
+
"learning_rate": 6.086561706150292e-06,
|
| 1163 |
+
"loss": 0.5271,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.49048751486325803,
|
| 1168 |
+
"grad_norm": 2.365747909189894,
|
| 1169 |
+
"learning_rate": 6.035834606730258e-06,
|
| 1170 |
+
"loss": 0.4949,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4934601664684899,
|
| 1175 |
+
"grad_norm": 2.4935417512792273,
|
| 1176 |
+
"learning_rate": 5.984995859961707e-06,
|
| 1177 |
+
"loss": 0.4807,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.49643281807372175,
|
| 1182 |
+
"grad_norm": 2.23752471394695,
|
| 1183 |
+
"learning_rate": 5.934050945494803e-06,
|
| 1184 |
+
"loss": 0.5053,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.4994054696789536,
|
| 1189 |
+
"grad_norm": 2.3920061376574187,
|
| 1190 |
+
"learning_rate": 5.883005354422995e-06,
|
| 1191 |
+
"loss": 0.5087,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.5023781212841855,
|
| 1196 |
+
"grad_norm": 2.35431470302546,
|
| 1197 |
+
"learning_rate": 5.83186458869115e-06,
|
| 1198 |
+
"loss": 0.51,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5053507728894173,
|
| 1203 |
+
"grad_norm": 2.3257622845834653,
|
| 1204 |
+
"learning_rate": 5.7806341605025264e-06,
|
| 1205 |
+
"loss": 0.5092,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.5083234244946492,
|
| 1210 |
+
"grad_norm": 2.236833604753037,
|
| 1211 |
+
"learning_rate": 5.7293195917246426e-06,
|
| 1212 |
+
"loss": 0.5014,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5112960760998811,
|
| 1217 |
+
"grad_norm": 2.408857775213423,
|
| 1218 |
+
"learning_rate": 5.67792641329411e-06,
|
| 1219 |
+
"loss": 0.4932,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.514268727705113,
|
| 1224 |
+
"grad_norm": 2.4984651682967782,
|
| 1225 |
+
"learning_rate": 5.6264601646204645e-06,
|
| 1226 |
+
"loss": 0.5,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.5172413793103449,
|
| 1231 |
+
"grad_norm": 2.6589983137124964,
|
| 1232 |
+
"learning_rate": 5.574926392989118e-06,
|
| 1233 |
+
"loss": 0.4953,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5202140309155767,
|
| 1238 |
+
"grad_norm": 2.2920034526589474,
|
| 1239 |
+
"learning_rate": 5.523330652963443e-06,
|
| 1240 |
+
"loss": 0.4918,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.5231866825208086,
|
| 1245 |
+
"grad_norm": 2.4555058214366414,
|
| 1246 |
+
"learning_rate": 5.471678505786063e-06,
|
| 1247 |
+
"loss": 0.5018,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.5261593341260404,
|
| 1252 |
+
"grad_norm": 2.5114137922653446,
|
| 1253 |
+
"learning_rate": 5.419975518779443e-06,
|
| 1254 |
+
"loss": 0.4941,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5291319857312723,
|
| 1259 |
+
"grad_norm": 2.271061287454104,
|
| 1260 |
+
"learning_rate": 5.36822726474582e-06,
|
| 1261 |
+
"loss": 0.4931,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.5321046373365041,
|
| 1266 |
+
"grad_norm": 2.381608236846904,
|
| 1267 |
+
"learning_rate": 5.3164393213665275e-06,
|
| 1268 |
+
"loss": 0.4785,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.535077288941736,
|
| 1273 |
+
"grad_norm": 2.3066959393356106,
|
| 1274 |
+
"learning_rate": 5.2646172706008154e-06,
|
| 1275 |
+
"loss": 0.49,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.5380499405469679,
|
| 1280 |
+
"grad_norm": 2.357712136319602,
|
| 1281 |
+
"learning_rate": 5.212766698084196e-06,
|
| 1282 |
+
"loss": 0.5027,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5410225921521997,
|
| 1287 |
+
"grad_norm": 2.5267610099653406,
|
| 1288 |
+
"learning_rate": 5.160893192526395e-06,
|
| 1289 |
+
"loss": 0.4777,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5439952437574316,
|
| 1294 |
+
"grad_norm": 2.359927663823654,
|
| 1295 |
+
"learning_rate": 5.109002345108971e-06,
|
| 1296 |
+
"loss": 0.4937,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.5469678953626635,
|
| 1301 |
+
"grad_norm": 2.41091168049318,
|
| 1302 |
+
"learning_rate": 5.0570997488826775e-06,
|
| 1303 |
+
"loss": 0.4757,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.5499405469678954,
|
| 1308 |
+
"grad_norm": 2.2779085550054305,
|
| 1309 |
+
"learning_rate": 5.005190998164614e-06,
|
| 1310 |
+
"loss": 0.4951,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5529131985731273,
|
| 1315 |
+
"grad_norm": 2.2695911460870417,
|
| 1316 |
+
"learning_rate": 4.953281687935236e-06,
|
| 1317 |
+
"loss": 0.4712,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5558858501783591,
|
| 1322 |
+
"grad_norm": 2.3975975966184198,
|
| 1323 |
+
"learning_rate": 4.901377413235312e-06,
|
| 1324 |
+
"loss": 0.4808,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.558858501783591,
|
| 1329 |
+
"grad_norm": 2.3802468272374253,
|
| 1330 |
+
"learning_rate": 4.849483768562849e-06,
|
| 1331 |
+
"loss": 0.4611,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.5618311533888228,
|
| 1336 |
+
"grad_norm": 2.324549924901845,
|
| 1337 |
+
"learning_rate": 4.797606347270104e-06,
|
| 1338 |
+
"loss": 0.4606,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5648038049940547,
|
| 1343 |
+
"grad_norm": 2.8248050417928727,
|
| 1344 |
+
"learning_rate": 4.7457507409606954e-06,
|
| 1345 |
+
"loss": 0.4586,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.5677764565992865,
|
| 1350 |
+
"grad_norm": 2.3408008419334867,
|
| 1351 |
+
"learning_rate": 4.693922538886914e-06,
|
| 1352 |
+
"loss": 0.4673,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5707491082045184,
|
| 1357 |
+
"grad_norm": 2.455876677604174,
|
| 1358 |
+
"learning_rate": 4.642127327347292e-06,
|
| 1359 |
+
"loss": 0.4803,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.5737217598097503,
|
| 1364 |
+
"grad_norm": 2.4097659884184717,
|
| 1365 |
+
"learning_rate": 4.590370689084474e-06,
|
| 1366 |
+
"loss": 0.4634,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.5766944114149821,
|
| 1371 |
+
"grad_norm": 2.5668401837693033,
|
| 1372 |
+
"learning_rate": 4.53865820268349e-06,
|
| 1373 |
+
"loss": 0.4598,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.579667063020214,
|
| 1378 |
+
"grad_norm": 2.2667882653983566,
|
| 1379 |
+
"learning_rate": 4.486995441970468e-06,
|
| 1380 |
+
"loss": 0.4606,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.582639714625446,
|
| 1385 |
+
"grad_norm": 2.3952069585748728,
|
| 1386 |
+
"learning_rate": 4.435387975411849e-06,
|
| 1387 |
+
"loss": 0.4554,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.5856123662306778,
|
| 1392 |
+
"grad_norm": 2.280919958503882,
|
| 1393 |
+
"learning_rate": 4.383841365514208e-06,
|
| 1394 |
+
"loss": 0.4765,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5885850178359097,
|
| 1399 |
+
"grad_norm": 2.342556124656158,
|
| 1400 |
+
"learning_rate": 4.332361168224678e-06,
|
| 1401 |
+
"loss": 0.4613,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5915576694411415,
|
| 1406 |
+
"grad_norm": 2.2952593312149405,
|
| 1407 |
+
"learning_rate": 4.280952932332128e-06,
|
| 1408 |
+
"loss": 0.446,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.5945303210463734,
|
| 1413 |
+
"grad_norm": 2.3321748153973183,
|
| 1414 |
+
"learning_rate": 4.229622198869063e-06,
|
| 1415 |
+
"loss": 0.452,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5975029726516052,
|
| 1420 |
+
"grad_norm": 2.4823844105009423,
|
| 1421 |
+
"learning_rate": 4.178374500514397e-06,
|
| 1422 |
+
"loss": 0.449,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6004756242568371,
|
| 1427 |
+
"grad_norm": 2.2950369831862134,
|
| 1428 |
+
"learning_rate": 4.127215360997117e-06,
|
| 1429 |
+
"loss": 0.4549,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.603448275862069,
|
| 1434 |
+
"grad_norm": 2.5166575033757477,
|
| 1435 |
+
"learning_rate": 4.076150294500897e-06,
|
| 1436 |
+
"loss": 0.4519,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.6064209274673008,
|
| 1441 |
+
"grad_norm": 2.3807622926087664,
|
| 1442 |
+
"learning_rate": 4.0251848050697615e-06,
|
| 1443 |
+
"loss": 0.4559,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6093935790725327,
|
| 1448 |
+
"grad_norm": 2.351343124866575,
|
| 1449 |
+
"learning_rate": 3.974324386014828e-06,
|
| 1450 |
+
"loss": 0.4562,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.6123662306777645,
|
| 1455 |
+
"grad_norm": 2.2523827712367988,
|
| 1456 |
+
"learning_rate": 3.92357451932221e-06,
|
| 1457 |
+
"loss": 0.4453,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.6153388822829964,
|
| 1462 |
+
"grad_norm": 2.30496980280335,
|
| 1463 |
+
"learning_rate": 3.8729406750621486e-06,
|
| 1464 |
+
"loss": 0.4571,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.6183115338882283,
|
| 1469 |
+
"grad_norm": 2.27622501534253,
|
| 1470 |
+
"learning_rate": 3.82242831079941e-06,
|
| 1471 |
+
"loss": 0.4337,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.6212841854934602,
|
| 1476 |
+
"grad_norm": 2.2971541253075114,
|
| 1477 |
+
"learning_rate": 3.772042871005057e-06,
|
| 1478 |
+
"loss": 0.4417,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.6242568370986921,
|
| 1483 |
+
"grad_norm": 2.295568197082708,
|
| 1484 |
+
"learning_rate": 3.721789786469602e-06,
|
| 1485 |
+
"loss": 0.4482,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.6272294887039239,
|
| 1490 |
+
"grad_norm": 2.418242134420845,
|
| 1491 |
+
"learning_rate": 3.6716744737176567e-06,
|
| 1492 |
+
"loss": 0.4452,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.6302021403091558,
|
| 1497 |
+
"grad_norm": 2.258447637407748,
|
| 1498 |
+
"learning_rate": 3.6217023344241198e-06,
|
| 1499 |
+
"loss": 0.458,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.6331747919143876,
|
| 1504 |
+
"grad_norm": 2.3383623329057732,
|
| 1505 |
+
"learning_rate": 3.57187875483194e-06,
|
| 1506 |
+
"loss": 0.4484,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.6361474435196195,
|
| 1511 |
+
"grad_norm": 2.2709297436937885,
|
| 1512 |
+
"learning_rate": 3.5222091051715803e-06,
|
| 1513 |
+
"loss": 0.4385,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6391200951248514,
|
| 1518 |
+
"grad_norm": 2.3001869154507357,
|
| 1519 |
+
"learning_rate": 3.472698739082172e-06,
|
| 1520 |
+
"loss": 0.4409,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.6420927467300832,
|
| 1525 |
+
"grad_norm": 2.2279803463182395,
|
| 1526 |
+
"learning_rate": 3.423352993034482e-06,
|
| 1527 |
+
"loss": 0.428,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.6450653983353151,
|
| 1532 |
+
"grad_norm": 2.1572728551701723,
|
| 1533 |
+
"learning_rate": 3.374177185755721e-06,
|
| 1534 |
+
"loss": 0.4195,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.6480380499405469,
|
| 1539 |
+
"grad_norm": 2.30995305892372,
|
| 1540 |
+
"learning_rate": 3.3251766176562605e-06,
|
| 1541 |
+
"loss": 0.4387,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.6510107015457788,
|
| 1546 |
+
"grad_norm": 2.363018968058027,
|
| 1547 |
+
"learning_rate": 3.2763565702583322e-06,
|
| 1548 |
+
"loss": 0.428,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.6539833531510107,
|
| 1553 |
+
"grad_norm": 2.3825197647163137,
|
| 1554 |
+
"learning_rate": 3.227722305626761e-06,
|
| 1555 |
+
"loss": 0.4299,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.6569560047562426,
|
| 1560 |
+
"grad_norm": 2.16179977498919,
|
| 1561 |
+
"learning_rate": 3.1792790658017874e-06,
|
| 1562 |
+
"loss": 0.4327,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.6599286563614745,
|
| 1567 |
+
"grad_norm": 2.175753238496728,
|
| 1568 |
+
"learning_rate": 3.1310320722340636e-06,
|
| 1569 |
+
"loss": 0.4204,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.6629013079667063,
|
| 1574 |
+
"grad_norm": 2.222441260772541,
|
| 1575 |
+
"learning_rate": 3.082986525221851e-06,
|
| 1576 |
+
"loss": 0.4316,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.6658739595719382,
|
| 1581 |
+
"grad_norm": 2.2178029194036415,
|
| 1582 |
+
"learning_rate": 3.035147603350511e-06,
|
| 1583 |
+
"loss": 0.4231,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.66884661117717,
|
| 1588 |
+
"grad_norm": 2.3519506089063786,
|
| 1589 |
+
"learning_rate": 2.9875204629343333e-06,
|
| 1590 |
+
"loss": 0.4231,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6718192627824019,
|
| 1595 |
+
"grad_norm": 2.248473095466383,
|
| 1596 |
+
"learning_rate": 2.940110237460758e-06,
|
| 1597 |
+
"loss": 0.4166,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6747919143876338,
|
| 1602 |
+
"grad_norm": 2.3278826893891793,
|
| 1603 |
+
"learning_rate": 2.8929220370370705e-06,
|
| 1604 |
+
"loss": 0.4184,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6777645659928656,
|
| 1609 |
+
"grad_norm": 2.2527103466010794,
|
| 1610 |
+
"learning_rate": 2.845960947839598e-06,
|
| 1611 |
+
"loss": 0.4253,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.6807372175980975,
|
| 1616 |
+
"grad_norm": 2.3636767593489836,
|
| 1617 |
+
"learning_rate": 2.7992320315655043e-06,
|
| 1618 |
+
"loss": 0.4294,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6837098692033293,
|
| 1623 |
+
"grad_norm": 2.2384821444252543,
|
| 1624 |
+
"learning_rate": 2.752740324887219e-06,
|
| 1625 |
+
"loss": 0.4164,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6866825208085613,
|
| 1630 |
+
"grad_norm": 2.3602120268768783,
|
| 1631 |
+
"learning_rate": 2.706490838909547e-06,
|
| 1632 |
+
"loss": 0.4244,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.6896551724137931,
|
| 1637 |
+
"grad_norm": 2.474112669222775,
|
| 1638 |
+
"learning_rate": 2.6604885586295636e-06,
|
| 1639 |
+
"loss": 0.4137,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.692627824019025,
|
| 1644 |
+
"grad_norm": 2.2552175118807605,
|
| 1645 |
+
"learning_rate": 2.6147384423992893e-06,
|
| 1646 |
+
"loss": 0.428,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.6956004756242569,
|
| 1651 |
+
"grad_norm": 2.4189395286363258,
|
| 1652 |
+
"learning_rate": 2.5692454213912655e-06,
|
| 1653 |
+
"loss": 0.4244,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.6985731272294887,
|
| 1658 |
+
"grad_norm": 2.240213088622091,
|
| 1659 |
+
"learning_rate": 2.5240143990670513e-06,
|
| 1660 |
+
"loss": 0.4117,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.7015457788347206,
|
| 1665 |
+
"grad_norm": 2.2726272120032283,
|
| 1666 |
+
"learning_rate": 2.479050250648692e-06,
|
| 1667 |
+
"loss": 0.4296,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.7045184304399524,
|
| 1672 |
+
"grad_norm": 2.1850341107989975,
|
| 1673 |
+
"learning_rate": 2.4343578225932573e-06,
|
| 1674 |
+
"loss": 0.4132,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.7074910820451843,
|
| 1679 |
+
"grad_norm": 2.272873233207882,
|
| 1680 |
+
"learning_rate": 2.389941932070455e-06,
|
| 1681 |
+
"loss": 0.3981,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.7104637336504162,
|
| 1686 |
+
"grad_norm": 2.252150495601297,
|
| 1687 |
+
"learning_rate": 2.345807366443419e-06,
|
| 1688 |
+
"loss": 0.4115,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.713436385255648,
|
| 1693 |
+
"grad_norm": 2.266551085513327,
|
| 1694 |
+
"learning_rate": 2.3019588827527017e-06,
|
| 1695 |
+
"loss": 0.4086,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.7164090368608799,
|
| 1700 |
+
"grad_norm": 2.332350830052582,
|
| 1701 |
+
"learning_rate": 2.2584012072035366e-06,
|
| 1702 |
+
"loss": 0.4089,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.7193816884661117,
|
| 1707 |
+
"grad_norm": 2.2344702253310715,
|
| 1708 |
+
"learning_rate": 2.21513903465643e-06,
|
| 1709 |
+
"loss": 0.3998,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.7223543400713437,
|
| 1714 |
+
"grad_norm": 2.3267615219996935,
|
| 1715 |
+
"learning_rate": 2.1721770281211162e-06,
|
| 1716 |
+
"loss": 0.4039,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.7253269916765755,
|
| 1721 |
+
"grad_norm": 2.2320045041894945,
|
| 1722 |
+
"learning_rate": 2.1295198182539627e-06,
|
| 1723 |
+
"loss": 0.4106,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.7282996432818074,
|
| 1728 |
+
"grad_norm": 2.3252249478957574,
|
| 1729 |
+
"learning_rate": 2.0871720028588516e-06,
|
| 1730 |
+
"loss": 0.4067,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.7312722948870393,
|
| 1735 |
+
"grad_norm": 2.2267058392084604,
|
| 1736 |
+
"learning_rate": 2.045138146391607e-06,
|
| 1737 |
+
"loss": 0.4086,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7342449464922711,
|
| 1742 |
+
"grad_norm": 2.411234372389695,
|
| 1743 |
+
"learning_rate": 2.0034227794680195e-06,
|
| 1744 |
+
"loss": 0.3969,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.737217598097503,
|
| 1749 |
+
"grad_norm": 2.1311399653064518,
|
| 1750 |
+
"learning_rate": 1.962030398375506e-06,
|
| 1751 |
+
"loss": 0.4165,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.7401902497027348,
|
| 1756 |
+
"grad_norm": 2.3782226385738836,
|
| 1757 |
+
"learning_rate": 1.920965464588481e-06,
|
| 1758 |
+
"loss": 0.3987,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.7431629013079667,
|
| 1763 |
+
"grad_norm": 2.3739915931205076,
|
| 1764 |
+
"learning_rate": 1.8802324042874847e-06,
|
| 1765 |
+
"loss": 0.3995,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.7461355529131986,
|
| 1770 |
+
"grad_norm": 2.3894925514110965,
|
| 1771 |
+
"learning_rate": 1.8398356078820934e-06,
|
| 1772 |
+
"loss": 0.3906,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.7491082045184304,
|
| 1777 |
+
"grad_norm": 2.3093439961839657,
|
| 1778 |
+
"learning_rate": 1.7997794295377098e-06,
|
| 1779 |
+
"loss": 0.3917,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.7520808561236623,
|
| 1784 |
+
"grad_norm": 2.319382769614651,
|
| 1785 |
+
"learning_rate": 1.7600681867062469e-06,
|
| 1786 |
+
"loss": 0.3885,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.7550535077288941,
|
| 1791 |
+
"grad_norm": 2.2803304350831413,
|
| 1792 |
+
"learning_rate": 1.7207061596607694e-06,
|
| 1793 |
+
"loss": 0.3927,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.7580261593341261,
|
| 1798 |
+
"grad_norm": 2.3220946916005567,
|
| 1799 |
+
"learning_rate": 1.6816975910341526e-06,
|
| 1800 |
+
"loss": 0.3962,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.760998810939358,
|
| 1805 |
+
"grad_norm": 2.264317075137385,
|
| 1806 |
+
"learning_rate": 1.6430466853617788e-06,
|
| 1807 |
+
"loss": 0.3978,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.7639714625445898,
|
| 1812 |
+
"grad_norm": 2.1705446882611654,
|
| 1813 |
+
"learning_rate": 1.6047576086283613e-06,
|
| 1814 |
+
"loss": 0.3912,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.7669441141498217,
|
| 1819 |
+
"grad_norm": 2.291864149582287,
|
| 1820 |
+
"learning_rate": 1.566834487818909e-06,
|
| 1821 |
+
"loss": 0.3997,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.7699167657550535,
|
| 1826 |
+
"grad_norm": 2.2779523408752276,
|
| 1827 |
+
"learning_rate": 1.5292814104739012e-06,
|
| 1828 |
+
"loss": 0.4015,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.7728894173602854,
|
| 1833 |
+
"grad_norm": 2.2360566853344532,
|
| 1834 |
+
"learning_rate": 1.492102424248717e-06,
|
| 1835 |
+
"loss": 0.3936,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.7758620689655172,
|
| 1840 |
+
"grad_norm": 2.3193326093728395,
|
| 1841 |
+
"learning_rate": 1.455301536477348e-06,
|
| 1842 |
+
"loss": 0.4006,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7788347205707491,
|
| 1847 |
+
"grad_norm": 2.241071015791803,
|
| 1848 |
+
"learning_rate": 1.4188827137404814e-06,
|
| 1849 |
+
"loss": 0.3953,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.781807372175981,
|
| 1854 |
+
"grad_norm": 2.3345320959262397,
|
| 1855 |
+
"learning_rate": 1.3828498814379526e-06,
|
| 1856 |
+
"loss": 0.3827,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7847800237812128,
|
| 1861 |
+
"grad_norm": 2.255050340004342,
|
| 1862 |
+
"learning_rate": 1.3472069233656455e-06,
|
| 1863 |
+
"loss": 0.395,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7877526753864447,
|
| 1868 |
+
"grad_norm": 2.182203091512302,
|
| 1869 |
+
"learning_rate": 1.3119576812968893e-06,
|
| 1870 |
+
"loss": 0.3889,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7907253269916765,
|
| 1875 |
+
"grad_norm": 2.266179435014493,
|
| 1876 |
+
"learning_rate": 1.2771059545683612e-06,
|
| 1877 |
+
"loss": 0.3974,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.7936979785969085,
|
| 1882 |
+
"grad_norm": 2.3267812132219663,
|
| 1883 |
+
"learning_rate": 1.242655499670583e-06,
|
| 1884 |
+
"loss": 0.3827,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.7966706302021404,
|
| 1889 |
+
"grad_norm": 2.1058933825314736,
|
| 1890 |
+
"learning_rate": 1.2086100298430225e-06,
|
| 1891 |
+
"loss": 0.3833,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.7996432818073722,
|
| 1896 |
+
"grad_norm": 2.1268029483679514,
|
| 1897 |
+
"learning_rate": 1.1749732146738651e-06,
|
| 1898 |
+
"loss": 0.3866,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.8026159334126041,
|
| 1903 |
+
"grad_norm": 2.1738354617676854,
|
| 1904 |
+
"learning_rate": 1.1417486797044886e-06,
|
| 1905 |
+
"loss": 0.3791,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.8055885850178359,
|
| 1910 |
+
"grad_norm": 2.160878200122144,
|
| 1911 |
+
"learning_rate": 1.1089400060386801e-06,
|
| 1912 |
+
"loss": 0.3755,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.8085612366230678,
|
| 1917 |
+
"grad_norm": 2.129626397999257,
|
| 1918 |
+
"learning_rate": 1.0765507299566552e-06,
|
| 1919 |
+
"loss": 0.372,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.8115338882282996,
|
| 1924 |
+
"grad_norm": 2.3501282748597947,
|
| 1925 |
+
"learning_rate": 1.0445843425338902e-06,
|
| 1926 |
+
"loss": 0.3856,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.8145065398335315,
|
| 1931 |
+
"grad_norm": 2.2841395141791883,
|
| 1932 |
+
"learning_rate": 1.0130442892648434e-06,
|
| 1933 |
+
"loss": 0.383,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.8174791914387634,
|
| 1938 |
+
"grad_norm": 2.2929912740203333,
|
| 1939 |
+
"learning_rate": 9.819339696915848e-07,
|
| 1940 |
+
"loss": 0.3826,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.8204518430439952,
|
| 1945 |
+
"grad_norm": 2.0935559084604436,
|
| 1946 |
+
"learning_rate": 9.512567370373643e-07,
|
| 1947 |
+
"loss": 0.3846,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.8234244946492271,
|
| 1952 |
+
"grad_norm": 2.2050607660086574,
|
| 1953 |
+
"learning_rate": 9.210158978452033e-07,
|
| 1954 |
+
"loss": 0.3831,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.8263971462544589,
|
| 1959 |
+
"grad_norm": 2.365214622091771,
|
| 1960 |
+
"learning_rate": 8.912147116214842e-07,
|
| 1961 |
+
"loss": 0.3766,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.8293697978596909,
|
| 1966 |
+
"grad_norm": 2.2601705624692547,
|
| 1967 |
+
"learning_rate": 8.618563904846294e-07,
|
| 1968 |
+
"loss": 0.3804,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.8323424494649228,
|
| 1973 |
+
"grad_norm": 2.4159041452669117,
|
| 1974 |
+
"learning_rate": 8.329440988188886e-07,
|
| 1975 |
+
"loss": 0.3924,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.8353151010701546,
|
| 1980 |
+
"grad_norm": 2.1795173707942643,
|
| 1981 |
+
"learning_rate": 8.04480952933257e-07,
|
| 1982 |
+
"loss": 0.3754,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.8382877526753865,
|
| 1987 |
+
"grad_norm": 2.2351438825547896,
|
| 1988 |
+
"learning_rate": 7.764700207255904e-07,
|
| 1989 |
+
"loss": 0.3897,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.8412604042806183,
|
| 1994 |
+
"grad_norm": 2.20058726362207,
|
| 1995 |
+
"learning_rate": 7.489143213519301e-07,
|
| 1996 |
+
"loss": 0.3775,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.8442330558858502,
|
| 2001 |
+
"grad_norm": 2.3495313166309213,
|
| 2002 |
+
"learning_rate": 7.218168249010821e-07,
|
| 2003 |
+
"loss": 0.3795,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.847205707491082,
|
| 2008 |
+
"grad_norm": 2.068114427890453,
|
| 2009 |
+
"learning_rate": 6.951804520744915e-07,
|
| 2010 |
+
"loss": 0.3754,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.8501783590963139,
|
| 2015 |
+
"grad_norm": 2.3055094145170445,
|
| 2016 |
+
"learning_rate": 6.690080738714267e-07,
|
| 2017 |
+
"loss": 0.3871,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.8531510107015458,
|
| 2022 |
+
"grad_norm": 2.1607153035130953,
|
| 2023 |
+
"learning_rate": 6.433025112795383e-07,
|
| 2024 |
+
"loss": 0.3649,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.8561236623067776,
|
| 2029 |
+
"grad_norm": 2.3452133211542847,
|
| 2030 |
+
"learning_rate": 6.180665349707892e-07,
|
| 2031 |
+
"loss": 0.3789,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.8590963139120095,
|
| 2036 |
+
"grad_norm": 2.270134523374029,
|
| 2037 |
+
"learning_rate": 5.93302865002825e-07,
|
| 2038 |
+
"loss": 0.3774,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.8620689655172413,
|
| 2043 |
+
"grad_norm": 2.188053068739294,
|
| 2044 |
+
"learning_rate": 5.69014170525794e-07,
|
| 2045 |
+
"loss": 0.3769,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.8650416171224733,
|
| 2050 |
+
"grad_norm": 2.1512178822513772,
|
| 2051 |
+
"learning_rate": 5.452030694946448e-07,
|
| 2052 |
+
"loss": 0.3766,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.8680142687277052,
|
| 2057 |
+
"grad_norm": 2.5248216489482314,
|
| 2058 |
+
"learning_rate": 5.21872128386961e-07,
|
| 2059 |
+
"loss": 0.3685,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.870986920332937,
|
| 2064 |
+
"grad_norm": 2.1936261850407455,
|
| 2065 |
+
"learning_rate": 4.990238619263232e-07,
|
| 2066 |
+
"loss": 0.3755,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.8739595719381689,
|
| 2071 |
+
"grad_norm": 2.0674457126577956,
|
| 2072 |
+
"learning_rate": 4.7666073281126713e-07,
|
| 2073 |
+
"loss": 0.37,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.8769322235434007,
|
| 2078 |
+
"grad_norm": 2.4393074814620705,
|
| 2079 |
+
"learning_rate": 4.547851514498386e-07,
|
| 2080 |
+
"loss": 0.3743,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.8799048751486326,
|
| 2085 |
+
"grad_norm": 2.2218679471161984,
|
| 2086 |
+
"learning_rate": 4.333994756997878e-07,
|
| 2087 |
+
"loss": 0.3737,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.8828775267538644,
|
| 2092 |
+
"grad_norm": 2.326578195058314,
|
| 2093 |
+
"learning_rate": 4.125060106144313e-07,
|
| 2094 |
+
"loss": 0.3706,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.8858501783590963,
|
| 2099 |
+
"grad_norm": 2.159799023836089,
|
| 2100 |
+
"learning_rate": 3.921070081941969e-07,
|
| 2101 |
+
"loss": 0.3757,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.8888228299643282,
|
| 2106 |
+
"grad_norm": 2.0971056501716543,
|
| 2107 |
+
"learning_rate": 3.72204667143895e-07,
|
| 2108 |
+
"loss": 0.3662,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.89179548156956,
|
| 2113 |
+
"grad_norm": 2.2898930751852817,
|
| 2114 |
+
"learning_rate": 3.528011326357306e-07,
|
| 2115 |
+
"loss": 0.3803,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.8947681331747919,
|
| 2120 |
+
"grad_norm": 2.276170558283118,
|
| 2121 |
+
"learning_rate": 3.338984960780856e-07,
|
| 2122 |
+
"loss": 0.3696,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8977407847800237,
|
| 2127 |
+
"grad_norm": 2.151976309053238,
|
| 2128 |
+
"learning_rate": 3.154987948901006e-07,
|
| 2129 |
+
"loss": 0.3856,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.9007134363852557,
|
| 2134 |
+
"grad_norm": 2.168451215561875,
|
| 2135 |
+
"learning_rate": 2.9760401228206394e-07,
|
| 2136 |
+
"loss": 0.3773,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.9036860879904876,
|
| 2141 |
+
"grad_norm": 2.2792459501817155,
|
| 2142 |
+
"learning_rate": 2.802160770416584e-07,
|
| 2143 |
+
"loss": 0.3707,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.9066587395957194,
|
| 2148 |
+
"grad_norm": 2.4152961249318436,
|
| 2149 |
+
"learning_rate": 2.633368633260658e-07,
|
| 2150 |
+
"loss": 0.3664,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.9096313912009513,
|
| 2155 |
+
"grad_norm": 2.2767769677463066,
|
| 2156 |
+
"learning_rate": 2.469681904599569e-07,
|
| 2157 |
+
"loss": 0.3786,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.9126040428061831,
|
| 2162 |
+
"grad_norm": 2.3341884568313795,
|
| 2163 |
+
"learning_rate": 2.3111182273940103e-07,
|
| 2164 |
+
"loss": 0.366,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.915576694411415,
|
| 2169 |
+
"grad_norm": 2.3090738993253064,
|
| 2170 |
+
"learning_rate": 2.1576946924169785e-07,
|
| 2171 |
+
"loss": 0.3682,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.9185493460166468,
|
| 2176 |
+
"grad_norm": 2.2708470444789968,
|
| 2177 |
+
"learning_rate": 2.009427836411665e-07,
|
| 2178 |
+
"loss": 0.367,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.9215219976218787,
|
| 2183 |
+
"grad_norm": 2.0757645629730543,
|
| 2184 |
+
"learning_rate": 1.8663336403090482e-07,
|
| 2185 |
+
"loss": 0.3664,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.9244946492271106,
|
| 2190 |
+
"grad_norm": 2.424017703704812,
|
| 2191 |
+
"learning_rate": 1.7284275275053663e-07,
|
| 2192 |
+
"loss": 0.3792,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.9274673008323424,
|
| 2197 |
+
"grad_norm": 2.127097574037306,
|
| 2198 |
+
"learning_rate": 1.59572436219973e-07,
|
| 2199 |
+
"loss": 0.3542,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.9304399524375743,
|
| 2204 |
+
"grad_norm": 2.3260445722240015,
|
| 2205 |
+
"learning_rate": 1.4682384477919808e-07,
|
| 2206 |
+
"loss": 0.3675,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.9334126040428062,
|
| 2211 |
+
"grad_norm": 2.39014963013141,
|
| 2212 |
+
"learning_rate": 1.345983525340988e-07,
|
| 2213 |
+
"loss": 0.3667,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.9363852556480381,
|
| 2218 |
+
"grad_norm": 2.2694068787756247,
|
| 2219 |
+
"learning_rate": 1.228972772083592e-07,
|
| 2220 |
+
"loss": 0.37,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.93935790725327,
|
| 2225 |
+
"grad_norm": 2.3620320947289604,
|
| 2226 |
+
"learning_rate": 1.1172188000142803e-07,
|
| 2227 |
+
"loss": 0.3727,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.9423305588585018,
|
| 2232 |
+
"grad_norm": 2.187390021455131,
|
| 2233 |
+
"learning_rate": 1.0107336545258084e-07,
|
| 2234 |
+
"loss": 0.3587,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.9453032104637337,
|
| 2239 |
+
"grad_norm": 2.2100838643930034,
|
| 2240 |
+
"learning_rate": 9.095288131108937e-08,
|
| 2241 |
+
"loss": 0.3673,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.9482758620689655,
|
| 2246 |
+
"grad_norm": 2.293416030314438,
|
| 2247 |
+
"learning_rate": 8.136151841250938e-08,
|
| 2248 |
+
"loss": 0.3783,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.9512485136741974,
|
| 2253 |
+
"grad_norm": 2.178738314835226,
|
| 2254 |
+
"learning_rate": 7.230031056110864e-08,
|
| 2255 |
+
"loss": 0.3731,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.9542211652794292,
|
| 2260 |
+
"grad_norm": 2.2670575062833165,
|
| 2261 |
+
"learning_rate": 6.377023441843599e-08,
|
| 2262 |
+
"loss": 0.373,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.9571938168846611,
|
| 2267 |
+
"grad_norm": 2.1567401585206514,
|
| 2268 |
+
"learning_rate": 5.577220939805117e-08,
|
| 2269 |
+
"loss": 0.3699,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.960166468489893,
|
| 2274 |
+
"grad_norm": 2.0789730650126,
|
| 2275 |
+
"learning_rate": 4.830709756642904e-08,
|
| 2276 |
+
"loss": 0.366,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.9631391200951248,
|
| 2281 |
+
"grad_norm": 2.157814350971754,
|
| 2282 |
+
"learning_rate": 4.1375703550038394e-08,
|
| 2283 |
+
"loss": 0.3633,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.9661117717003567,
|
| 2288 |
+
"grad_norm": 2.1100943054104344,
|
| 2289 |
+
"learning_rate": 3.4978774448617414e-08,
|
| 2290 |
+
"loss": 0.3519,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.9690844233055886,
|
| 2295 |
+
"grad_norm": 2.2083883883509743,
|
| 2296 |
+
"learning_rate": 2.9116999754646437e-08,
|
| 2297 |
+
"loss": 0.3613,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.9720570749108205,
|
| 2302 |
+
"grad_norm": 2.2428508865311527,
|
| 2303 |
+
"learning_rate": 2.3791011279033492e-08,
|
| 2304 |
+
"loss": 0.3644,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.9750297265160524,
|
| 2309 |
+
"grad_norm": 2.1651670922102872,
|
| 2310 |
+
"learning_rate": 1.9001383083011028e-08,
|
| 2311 |
+
"loss": 0.3662,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.9780023781212842,
|
| 2316 |
+
"grad_norm": 2.3186672122830716,
|
| 2317 |
+
"learning_rate": 1.4748631416262593e-08,
|
| 2318 |
+
"loss": 0.3606,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.9809750297265161,
|
| 2323 |
+
"grad_norm": 2.2616261488795617,
|
| 2324 |
+
"learning_rate": 1.103321466128071e-08,
|
| 2325 |
+
"loss": 0.3603,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.9839476813317479,
|
| 2330 |
+
"grad_norm": 2.277277885300596,
|
| 2331 |
+
"learning_rate": 7.855533283955829e-09,
|
| 2332 |
+
"loss": 0.3657,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.9869203329369798,
|
| 2337 |
+
"grad_norm": 2.1694357282951566,
|
| 2338 |
+
"learning_rate": 5.215929790416407e-09,
|
| 2339 |
+
"loss": 0.363,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.9898929845422116,
|
| 2344 |
+
"grad_norm": 2.2318921404664795,
|
| 2345 |
+
"learning_rate": 3.1146886901090024e-09,
|
| 2346 |
+
"loss": 0.3603,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.9928656361474435,
|
| 2351 |
+
"grad_norm": 2.209506235328767,
|
| 2352 |
+
"learning_rate": 1.5520364651344655e-09,
|
| 2353 |
+
"loss": 0.3624,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9958382877526754,
|
| 2358 |
+
"grad_norm": 2.184944707544881,
|
| 2359 |
+
"learning_rate": 5.281415458346928e-10,
|
| 2360 |
+
"loss": 0.3688,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9988109393579072,
|
| 2365 |
+
"grad_norm": 2.267638514087637,
|
| 2366 |
+
"learning_rate": 4.3114292641033286e-11,
|
| 2367 |
+
"loss": 0.3663,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.0,
|
| 2372 |
+
"eval_runtime": 3.3713,
|
| 2373 |
+
"eval_samples_per_second": 2.966,
|
| 2374 |
+
"eval_steps_per_second": 0.89,
|
| 2375 |
+
"step": 1682
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.0,
|
| 2379 |
+
"step": 1682,
|
| 2380 |
+
"total_flos": 176088290426880.0,
|
| 2381 |
+
"train_loss": 0.5311898304931332,
|
| 2382 |
+
"train_runtime": 14992.3235,
|
| 2383 |
+
"train_samples_per_second": 1.795,
|
| 2384 |
+
"train_steps_per_second": 0.112
|
| 2385 |
+
}
|
| 2386 |
+
],
|
| 2387 |
+
"logging_steps": 5,
|
| 2388 |
+
"max_steps": 1682,
|
| 2389 |
+
"num_input_tokens_seen": 0,
|
| 2390 |
+
"num_train_epochs": 1,
|
| 2391 |
+
"save_steps": 100,
|
| 2392 |
+
"stateful_callbacks": {
|
| 2393 |
+
"TrainerControl": {
|
| 2394 |
+
"args": {
|
| 2395 |
+
"should_epoch_stop": false,
|
| 2396 |
+
"should_evaluate": false,
|
| 2397 |
+
"should_log": false,
|
| 2398 |
+
"should_save": true,
|
| 2399 |
+
"should_training_stop": true
|
| 2400 |
+
},
|
| 2401 |
+
"attributes": {}
|
| 2402 |
+
}
|
| 2403 |
+
},
|
| 2404 |
+
"total_flos": 176088290426880.0,
|
| 2405 |
+
"train_batch_size": 4,
|
| 2406 |
+
"trial_name": null,
|
| 2407 |
+
"trial_params": null
|
| 2408 |
+
}
|