Model save
Browse files- README.md +60 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep17_09-59-04_COE-CS-sv003/events.out.tfevents.1726567448.COE-CS-sv003.3173796.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +2653 -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_syntaxdirtybatch16
|
| 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_syntaxdirtybatch16
|
| 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": 194304320471040.0,
|
| 4 |
+
"train_loss": 0.50882549257949,
|
| 5 |
+
"train_runtime": 16510.7518,
|
| 6 |
+
"train_samples": 98932,
|
| 7 |
+
"train_samples_per_second": 1.799,
|
| 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/Sep17_09-59-04_COE-CS-sv003/events.out.tfevents.1726567448.COE-CS-sv003.3173796.0
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:dec57665cff300a534f9853122f28bb38a8f4cf08f1012895f12f12c2f3561c9
|
| 3 |
+
size 84239
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 194304320471040.0,
|
| 4 |
+
"train_loss": 0.50882549257949,
|
| 5 |
+
"train_runtime": 16510.7518,
|
| 6 |
+
"train_samples": 98932,
|
| 7 |
+
"train_samples_per_second": 1.799,
|
| 8 |
+
"train_steps_per_second": 0.112
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2653 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1856,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0005387931034482759,
|
| 13 |
+
"grad_norm": 24.06527582915772,
|
| 14 |
+
"learning_rate": 5.376344086021506e-08,
|
| 15 |
+
"loss": 1.3568,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0026939655172413795,
|
| 20 |
+
"grad_norm": 23.2847675267083,
|
| 21 |
+
"learning_rate": 2.688172043010753e-07,
|
| 22 |
+
"loss": 1.3668,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.005387931034482759,
|
| 27 |
+
"grad_norm": 16.195930738756566,
|
| 28 |
+
"learning_rate": 5.376344086021506e-07,
|
| 29 |
+
"loss": 1.3204,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.008081896551724138,
|
| 34 |
+
"grad_norm": 12.068298869370592,
|
| 35 |
+
"learning_rate": 8.064516129032258e-07,
|
| 36 |
+
"loss": 1.153,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.010775862068965518,
|
| 41 |
+
"grad_norm": 8.564123494535863,
|
| 42 |
+
"learning_rate": 1.0752688172043011e-06,
|
| 43 |
+
"loss": 1.0452,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.013469827586206896,
|
| 48 |
+
"grad_norm": 3.533789309391932,
|
| 49 |
+
"learning_rate": 1.3440860215053765e-06,
|
| 50 |
+
"loss": 0.9515,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.016163793103448277,
|
| 55 |
+
"grad_norm": 3.24461197562523,
|
| 56 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 57 |
+
"loss": 0.9001,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.018857758620689655,
|
| 62 |
+
"grad_norm": 2.990611660406535,
|
| 63 |
+
"learning_rate": 1.881720430107527e-06,
|
| 64 |
+
"loss": 0.8773,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.021551724137931036,
|
| 69 |
+
"grad_norm": 3.0063853939062346,
|
| 70 |
+
"learning_rate": 2.1505376344086023e-06,
|
| 71 |
+
"loss": 0.851,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.024245689655172414,
|
| 76 |
+
"grad_norm": 2.956366561006899,
|
| 77 |
+
"learning_rate": 2.4193548387096776e-06,
|
| 78 |
+
"loss": 0.8574,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02693965517241379,
|
| 83 |
+
"grad_norm": 2.983398789032246,
|
| 84 |
+
"learning_rate": 2.688172043010753e-06,
|
| 85 |
+
"loss": 0.84,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.029633620689655173,
|
| 90 |
+
"grad_norm": 2.964731632227324,
|
| 91 |
+
"learning_rate": 2.9569892473118283e-06,
|
| 92 |
+
"loss": 0.824,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.032327586206896554,
|
| 97 |
+
"grad_norm": 2.9208803498660623,
|
| 98 |
+
"learning_rate": 3.225806451612903e-06,
|
| 99 |
+
"loss": 0.8138,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03502155172413793,
|
| 104 |
+
"grad_norm": 3.2063303145455366,
|
| 105 |
+
"learning_rate": 3.494623655913979e-06,
|
| 106 |
+
"loss": 0.8009,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03771551724137931,
|
| 111 |
+
"grad_norm": 3.242653708652505,
|
| 112 |
+
"learning_rate": 3.763440860215054e-06,
|
| 113 |
+
"loss": 0.792,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04040948275862069,
|
| 118 |
+
"grad_norm": 3.1462448663803846,
|
| 119 |
+
"learning_rate": 4.032258064516129e-06,
|
| 120 |
+
"loss": 0.7902,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04310344827586207,
|
| 125 |
+
"grad_norm": 3.0229975986392716,
|
| 126 |
+
"learning_rate": 4.3010752688172045e-06,
|
| 127 |
+
"loss": 0.7699,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.045797413793103446,
|
| 132 |
+
"grad_norm": 3.12423094671722,
|
| 133 |
+
"learning_rate": 4.56989247311828e-06,
|
| 134 |
+
"loss": 0.7644,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04849137931034483,
|
| 139 |
+
"grad_norm": 3.2796596768473902,
|
| 140 |
+
"learning_rate": 4.838709677419355e-06,
|
| 141 |
+
"loss": 0.7712,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05118534482758621,
|
| 146 |
+
"grad_norm": 3.0184242042359943,
|
| 147 |
+
"learning_rate": 5.1075268817204305e-06,
|
| 148 |
+
"loss": 0.7546,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05387931034482758,
|
| 153 |
+
"grad_norm": 3.0881392753326447,
|
| 154 |
+
"learning_rate": 5.376344086021506e-06,
|
| 155 |
+
"loss": 0.7487,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.056573275862068964,
|
| 160 |
+
"grad_norm": 3.4110841994799657,
|
| 161 |
+
"learning_rate": 5.645161290322582e-06,
|
| 162 |
+
"loss": 0.7496,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.059267241379310345,
|
| 167 |
+
"grad_norm": 2.92733810047956,
|
| 168 |
+
"learning_rate": 5.9139784946236566e-06,
|
| 169 |
+
"loss": 0.7368,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06196120689655173,
|
| 174 |
+
"grad_norm": 3.3139008810992046,
|
| 175 |
+
"learning_rate": 6.182795698924732e-06,
|
| 176 |
+
"loss": 0.7277,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06465517241379311,
|
| 181 |
+
"grad_norm": 3.1747479144288455,
|
| 182 |
+
"learning_rate": 6.451612903225806e-06,
|
| 183 |
+
"loss": 0.7283,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06734913793103449,
|
| 188 |
+
"grad_norm": 2.894519107469561,
|
| 189 |
+
"learning_rate": 6.720430107526882e-06,
|
| 190 |
+
"loss": 0.7282,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07004310344827586,
|
| 195 |
+
"grad_norm": 2.8405180587913987,
|
| 196 |
+
"learning_rate": 6.989247311827958e-06,
|
| 197 |
+
"loss": 0.7123,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07273706896551724,
|
| 202 |
+
"grad_norm": 2.7948188759602717,
|
| 203 |
+
"learning_rate": 7.258064516129033e-06,
|
| 204 |
+
"loss": 0.7193,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07543103448275862,
|
| 209 |
+
"grad_norm": 3.154756842274138,
|
| 210 |
+
"learning_rate": 7.526881720430108e-06,
|
| 211 |
+
"loss": 0.7207,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.078125,
|
| 216 |
+
"grad_norm": 2.9457108929499207,
|
| 217 |
+
"learning_rate": 7.795698924731183e-06,
|
| 218 |
+
"loss": 0.7212,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08081896551724138,
|
| 223 |
+
"grad_norm": 2.8503644648477517,
|
| 224 |
+
"learning_rate": 8.064516129032258e-06,
|
| 225 |
+
"loss": 0.72,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08351293103448276,
|
| 230 |
+
"grad_norm": 2.949964251276019,
|
| 231 |
+
"learning_rate": 8.333333333333334e-06,
|
| 232 |
+
"loss": 0.723,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.08620689655172414,
|
| 237 |
+
"grad_norm": 2.959116036250926,
|
| 238 |
+
"learning_rate": 8.602150537634409e-06,
|
| 239 |
+
"loss": 0.7158,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08890086206896551,
|
| 244 |
+
"grad_norm": 2.7803395603035517,
|
| 245 |
+
"learning_rate": 8.870967741935484e-06,
|
| 246 |
+
"loss": 0.7067,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09159482758620689,
|
| 251 |
+
"grad_norm": 2.8799202670097115,
|
| 252 |
+
"learning_rate": 9.13978494623656e-06,
|
| 253 |
+
"loss": 0.71,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.09428879310344827,
|
| 258 |
+
"grad_norm": 2.9537594310040687,
|
| 259 |
+
"learning_rate": 9.408602150537635e-06,
|
| 260 |
+
"loss": 0.7152,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.09698275862068965,
|
| 265 |
+
"grad_norm": 2.8628517050727873,
|
| 266 |
+
"learning_rate": 9.67741935483871e-06,
|
| 267 |
+
"loss": 0.7054,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09967672413793104,
|
| 272 |
+
"grad_norm": 2.8896943288351586,
|
| 273 |
+
"learning_rate": 9.946236559139786e-06,
|
| 274 |
+
"loss": 0.7235,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.10237068965517242,
|
| 279 |
+
"grad_norm": 2.938518709851193,
|
| 280 |
+
"learning_rate": 9.999858445152838e-06,
|
| 281 |
+
"loss": 0.7122,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1050646551724138,
|
| 286 |
+
"grad_norm": 2.58690085015114,
|
| 287 |
+
"learning_rate": 9.999283392323047e-06,
|
| 288 |
+
"loss": 0.7061,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.10775862068965517,
|
| 293 |
+
"grad_norm": 2.763129396160507,
|
| 294 |
+
"learning_rate": 9.998266045169356e-06,
|
| 295 |
+
"loss": 0.7063,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.11045258620689655,
|
| 300 |
+
"grad_norm": 2.816275952414151,
|
| 301 |
+
"learning_rate": 9.996806493698038e-06,
|
| 302 |
+
"loss": 0.7087,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.11314655172413793,
|
| 307 |
+
"grad_norm": 2.73738463168911,
|
| 308 |
+
"learning_rate": 9.994904867037867e-06,
|
| 309 |
+
"loss": 0.6986,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.11584051724137931,
|
| 314 |
+
"grad_norm": 2.810575578616004,
|
| 315 |
+
"learning_rate": 9.99256133342869e-06,
|
| 316 |
+
"loss": 0.6929,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.11853448275862069,
|
| 321 |
+
"grad_norm": 2.6652685941669265,
|
| 322 |
+
"learning_rate": 9.989776100206547e-06,
|
| 323 |
+
"loss": 0.6898,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.12122844827586207,
|
| 328 |
+
"grad_norm": 2.7660230194471107,
|
| 329 |
+
"learning_rate": 9.986549413785323e-06,
|
| 330 |
+
"loss": 0.695,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.12392241379310345,
|
| 335 |
+
"grad_norm": 2.5553942202252466,
|
| 336 |
+
"learning_rate": 9.982881559634946e-06,
|
| 337 |
+
"loss": 0.7017,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.12661637931034483,
|
| 342 |
+
"grad_norm": 2.5245345530966192,
|
| 343 |
+
"learning_rate": 9.978772862256145e-06,
|
| 344 |
+
"loss": 0.6916,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.12931034482758622,
|
| 349 |
+
"grad_norm": 2.520167957976126,
|
| 350 |
+
"learning_rate": 9.97422368515172e-06,
|
| 351 |
+
"loss": 0.694,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.1320043103448276,
|
| 356 |
+
"grad_norm": 2.7125840301494706,
|
| 357 |
+
"learning_rate": 9.969234430794395e-06,
|
| 358 |
+
"loss": 0.6887,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.13469827586206898,
|
| 363 |
+
"grad_norm": 2.631424447595556,
|
| 364 |
+
"learning_rate": 9.96380554059121e-06,
|
| 365 |
+
"loss": 0.685,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.13739224137931033,
|
| 370 |
+
"grad_norm": 2.555021040773695,
|
| 371 |
+
"learning_rate": 9.957937494844472e-06,
|
| 372 |
+
"loss": 0.7004,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.1400862068965517,
|
| 377 |
+
"grad_norm": 2.539978410855113,
|
| 378 |
+
"learning_rate": 9.951630812709245e-06,
|
| 379 |
+
"loss": 0.6897,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.1427801724137931,
|
| 384 |
+
"grad_norm": 2.7494174109330842,
|
| 385 |
+
"learning_rate": 9.944886052147445e-06,
|
| 386 |
+
"loss": 0.6928,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.14547413793103448,
|
| 391 |
+
"grad_norm": 2.559956756758314,
|
| 392 |
+
"learning_rate": 9.937703809878455e-06,
|
| 393 |
+
"loss": 0.6813,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.14816810344827586,
|
| 398 |
+
"grad_norm": 2.525562445581053,
|
| 399 |
+
"learning_rate": 9.930084721326342e-06,
|
| 400 |
+
"loss": 0.6944,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.15086206896551724,
|
| 405 |
+
"grad_norm": 2.777619881263396,
|
| 406 |
+
"learning_rate": 9.92202946056364e-06,
|
| 407 |
+
"loss": 0.6745,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.15355603448275862,
|
| 412 |
+
"grad_norm": 2.4859789362282076,
|
| 413 |
+
"learning_rate": 9.913538740251711e-06,
|
| 414 |
+
"loss": 0.6527,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.15625,
|
| 419 |
+
"grad_norm": 2.4614571056065624,
|
| 420 |
+
"learning_rate": 9.904613311577696e-06,
|
| 421 |
+
"loss": 0.6673,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.15894396551724138,
|
| 426 |
+
"grad_norm": 2.503690727361147,
|
| 427 |
+
"learning_rate": 9.895253964188056e-06,
|
| 428 |
+
"loss": 0.6601,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.16163793103448276,
|
| 433 |
+
"grad_norm": 2.61491684131174,
|
| 434 |
+
"learning_rate": 9.885461526118713e-06,
|
| 435 |
+
"loss": 0.6629,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.16433189655172414,
|
| 440 |
+
"grad_norm": 2.563289578189323,
|
| 441 |
+
"learning_rate": 9.875236863721788e-06,
|
| 442 |
+
"loss": 0.6834,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.16702586206896552,
|
| 447 |
+
"grad_norm": 2.542961491155676,
|
| 448 |
+
"learning_rate": 9.864580881588958e-06,
|
| 449 |
+
"loss": 0.6634,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1697198275862069,
|
| 454 |
+
"grad_norm": 2.5998608415854774,
|
| 455 |
+
"learning_rate": 9.853494522471423e-06,
|
| 456 |
+
"loss": 0.6564,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.1724137931034483,
|
| 461 |
+
"grad_norm": 2.580998138867243,
|
| 462 |
+
"learning_rate": 9.841978767196495e-06,
|
| 463 |
+
"loss": 0.6522,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.17510775862068967,
|
| 468 |
+
"grad_norm": 2.462022076166109,
|
| 469 |
+
"learning_rate": 9.830034634580833e-06,
|
| 470 |
+
"loss": 0.6575,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.17780172413793102,
|
| 475 |
+
"grad_norm": 2.641866987114795,
|
| 476 |
+
"learning_rate": 9.8176631813403e-06,
|
| 477 |
+
"loss": 0.6654,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1804956896551724,
|
| 482 |
+
"grad_norm": 2.483224928563204,
|
| 483 |
+
"learning_rate": 9.804865501996472e-06,
|
| 484 |
+
"loss": 0.6687,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.18318965517241378,
|
| 489 |
+
"grad_norm": 2.6158710388060755,
|
| 490 |
+
"learning_rate": 9.79164272877981e-06,
|
| 491 |
+
"loss": 0.6606,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.18588362068965517,
|
| 496 |
+
"grad_norm": 2.6690109052148396,
|
| 497 |
+
"learning_rate": 9.777996031529486e-06,
|
| 498 |
+
"loss": 0.6587,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.18857758620689655,
|
| 503 |
+
"grad_norm": 2.5145797557443403,
|
| 504 |
+
"learning_rate": 9.763926617589883e-06,
|
| 505 |
+
"loss": 0.6455,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.19127155172413793,
|
| 510 |
+
"grad_norm": 2.34228188842774,
|
| 511 |
+
"learning_rate": 9.749435731703786e-06,
|
| 512 |
+
"loss": 0.6467,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.1939655172413793,
|
| 517 |
+
"grad_norm": 2.518236951767628,
|
| 518 |
+
"learning_rate": 9.734524655902253e-06,
|
| 519 |
+
"loss": 0.6651,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1966594827586207,
|
| 524 |
+
"grad_norm": 2.3327366524820423,
|
| 525 |
+
"learning_rate": 9.719194709391191e-06,
|
| 526 |
+
"loss": 0.6527,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.19935344827586207,
|
| 531 |
+
"grad_norm": 2.6721928236725425,
|
| 532 |
+
"learning_rate": 9.70344724843465e-06,
|
| 533 |
+
"loss": 0.6471,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.20204741379310345,
|
| 538 |
+
"grad_norm": 2.512497207087126,
|
| 539 |
+
"learning_rate": 9.687283666234823e-06,
|
| 540 |
+
"loss": 0.6345,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.20474137931034483,
|
| 545 |
+
"grad_norm": 2.5381248307269106,
|
| 546 |
+
"learning_rate": 9.670705392808796e-06,
|
| 547 |
+
"loss": 0.6549,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.20743534482758622,
|
| 552 |
+
"grad_norm": 2.489609282435604,
|
| 553 |
+
"learning_rate": 9.653713894862024e-06,
|
| 554 |
+
"loss": 0.6287,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.2101293103448276,
|
| 559 |
+
"grad_norm": 2.4187969624820767,
|
| 560 |
+
"learning_rate": 9.63631067565858e-06,
|
| 561 |
+
"loss": 0.6372,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.21282327586206898,
|
| 566 |
+
"grad_norm": 2.378128543534024,
|
| 567 |
+
"learning_rate": 9.618497274888147e-06,
|
| 568 |
+
"loss": 0.6344,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.21551724137931033,
|
| 573 |
+
"grad_norm": 2.3554799136699383,
|
| 574 |
+
"learning_rate": 9.600275268529809e-06,
|
| 575 |
+
"loss": 0.632,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2182112068965517,
|
| 580 |
+
"grad_norm": 2.9669359679831437,
|
| 581 |
+
"learning_rate": 9.58164626871261e-06,
|
| 582 |
+
"loss": 0.6409,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.2209051724137931,
|
| 587 |
+
"grad_norm": 2.510424077340063,
|
| 588 |
+
"learning_rate": 9.562611923572944e-06,
|
| 589 |
+
"loss": 0.6316,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.22359913793103448,
|
| 594 |
+
"grad_norm": 2.5067266793187843,
|
| 595 |
+
"learning_rate": 9.543173917108725e-06,
|
| 596 |
+
"loss": 0.6337,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.22629310344827586,
|
| 601 |
+
"grad_norm": 2.4014165442615627,
|
| 602 |
+
"learning_rate": 9.523333969030413e-06,
|
| 603 |
+
"loss": 0.6285,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.22898706896551724,
|
| 608 |
+
"grad_norm": 2.5503305669006266,
|
| 609 |
+
"learning_rate": 9.503093834608856e-06,
|
| 610 |
+
"loss": 0.6297,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.23168103448275862,
|
| 615 |
+
"grad_norm": 2.683370610867663,
|
| 616 |
+
"learning_rate": 9.482455304520013e-06,
|
| 617 |
+
"loss": 0.6222,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.234375,
|
| 622 |
+
"grad_norm": 2.3415254501274156,
|
| 623 |
+
"learning_rate": 9.46142020468652e-06,
|
| 624 |
+
"loss": 0.6181,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.23706896551724138,
|
| 629 |
+
"grad_norm": 2.4296203317167513,
|
| 630 |
+
"learning_rate": 9.439990396116149e-06,
|
| 631 |
+
"loss": 0.6191,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.23976293103448276,
|
| 636 |
+
"grad_norm": 2.4277540188724833,
|
| 637 |
+
"learning_rate": 9.418167774737173e-06,
|
| 638 |
+
"loss": 0.6218,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.24245689655172414,
|
| 643 |
+
"grad_norm": 2.594904022170311,
|
| 644 |
+
"learning_rate": 9.395954271230606e-06,
|
| 645 |
+
"loss": 0.622,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.24515086206896552,
|
| 650 |
+
"grad_norm": 2.347098862192039,
|
| 651 |
+
"learning_rate": 9.373351850859417e-06,
|
| 652 |
+
"loss": 0.6136,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.2478448275862069,
|
| 657 |
+
"grad_norm": 2.3928008650888204,
|
| 658 |
+
"learning_rate": 9.350362513294652e-06,
|
| 659 |
+
"loss": 0.6272,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.2505387931034483,
|
| 664 |
+
"grad_norm": 2.335542398750826,
|
| 665 |
+
"learning_rate": 9.326988292438514e-06,
|
| 666 |
+
"loss": 0.6245,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.25323275862068967,
|
| 671 |
+
"grad_norm": 2.3458410101982174,
|
| 672 |
+
"learning_rate": 9.30323125624443e-06,
|
| 673 |
+
"loss": 0.6176,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.25592672413793105,
|
| 678 |
+
"grad_norm": 2.5491037378725188,
|
| 679 |
+
"learning_rate": 9.279093506534085e-06,
|
| 680 |
+
"loss": 0.6039,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.25862068965517243,
|
| 685 |
+
"grad_norm": 2.35768113596503,
|
| 686 |
+
"learning_rate": 9.254577178811482e-06,
|
| 687 |
+
"loss": 0.6062,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.2613146551724138,
|
| 692 |
+
"grad_norm": 2.4427975704018072,
|
| 693 |
+
"learning_rate": 9.229684442074005e-06,
|
| 694 |
+
"loss": 0.6038,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.2640086206896552,
|
| 699 |
+
"grad_norm": 2.3518303928123183,
|
| 700 |
+
"learning_rate": 9.204417498620521e-06,
|
| 701 |
+
"loss": 0.6071,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.2667025862068966,
|
| 706 |
+
"grad_norm": 2.3978894249163285,
|
| 707 |
+
"learning_rate": 9.178778583856552e-06,
|
| 708 |
+
"loss": 0.6024,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.26939655172413796,
|
| 713 |
+
"grad_norm": 2.530047013657598,
|
| 714 |
+
"learning_rate": 9.152769966096483e-06,
|
| 715 |
+
"loss": 0.6028,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.27209051724137934,
|
| 720 |
+
"grad_norm": 2.4123317555719708,
|
| 721 |
+
"learning_rate": 9.126393946362906e-06,
|
| 722 |
+
"loss": 0.6083,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.27478448275862066,
|
| 727 |
+
"grad_norm": 2.4793056830777753,
|
| 728 |
+
"learning_rate": 9.099652858183027e-06,
|
| 729 |
+
"loss": 0.6051,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.27747844827586204,
|
| 734 |
+
"grad_norm": 2.372688897527012,
|
| 735 |
+
"learning_rate": 9.072549067382225e-06,
|
| 736 |
+
"loss": 0.6157,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.2801724137931034,
|
| 741 |
+
"grad_norm": 2.380240348074666,
|
| 742 |
+
"learning_rate": 9.045084971874738e-06,
|
| 743 |
+
"loss": 0.6073,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.2828663793103448,
|
| 748 |
+
"grad_norm": 2.545807161286919,
|
| 749 |
+
"learning_rate": 9.017263001451518e-06,
|
| 750 |
+
"loss": 0.5884,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.2855603448275862,
|
| 755 |
+
"grad_norm": 2.5935659051260824,
|
| 756 |
+
"learning_rate": 8.989085617565261e-06,
|
| 757 |
+
"loss": 0.5983,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.28825431034482757,
|
| 762 |
+
"grad_norm": 2.2548884783469836,
|
| 763 |
+
"learning_rate": 8.960555313112646e-06,
|
| 764 |
+
"loss": 0.5895,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.29094827586206895,
|
| 769 |
+
"grad_norm": 2.3534621434136533,
|
| 770 |
+
"learning_rate": 8.93167461221378e-06,
|
| 771 |
+
"loss": 0.5914,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.29364224137931033,
|
| 776 |
+
"grad_norm": 2.5336260688373495,
|
| 777 |
+
"learning_rate": 8.902446069988878e-06,
|
| 778 |
+
"loss": 0.5939,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.2963362068965517,
|
| 783 |
+
"grad_norm": 2.624683890197873,
|
| 784 |
+
"learning_rate": 8.87287227233222e-06,
|
| 785 |
+
"loss": 0.5836,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.2990301724137931,
|
| 790 |
+
"grad_norm": 2.3588318708883604,
|
| 791 |
+
"learning_rate": 8.842955835683368e-06,
|
| 792 |
+
"loss": 0.5786,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.3017241379310345,
|
| 797 |
+
"grad_norm": 2.501675897313923,
|
| 798 |
+
"learning_rate": 8.812699406795683e-06,
|
| 799 |
+
"loss": 0.5799,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.30441810344827586,
|
| 804 |
+
"grad_norm": 2.6078839400922424,
|
| 805 |
+
"learning_rate": 8.78210566250216e-06,
|
| 806 |
+
"loss": 0.5801,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.30711206896551724,
|
| 811 |
+
"grad_norm": 2.3496389383543135,
|
| 812 |
+
"learning_rate": 8.751177309478618e-06,
|
| 813 |
+
"loss": 0.5756,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.3098060344827586,
|
| 818 |
+
"grad_norm": 2.3002443057548727,
|
| 819 |
+
"learning_rate": 8.71991708400422e-06,
|
| 820 |
+
"loss": 0.5823,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.3125,
|
| 825 |
+
"grad_norm": 2.368311996486066,
|
| 826 |
+
"learning_rate": 8.688327751719403e-06,
|
| 827 |
+
"loss": 0.57,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.3151939655172414,
|
| 832 |
+
"grad_norm": 2.316476591326147,
|
| 833 |
+
"learning_rate": 8.656412107381187e-06,
|
| 834 |
+
"loss": 0.572,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.31788793103448276,
|
| 839 |
+
"grad_norm": 2.648056237571166,
|
| 840 |
+
"learning_rate": 8.624172974615926e-06,
|
| 841 |
+
"loss": 0.5759,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.32058189655172414,
|
| 846 |
+
"grad_norm": 2.5273275022283035,
|
| 847 |
+
"learning_rate": 8.591613205669494e-06,
|
| 848 |
+
"loss": 0.5751,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.3232758620689655,
|
| 853 |
+
"grad_norm": 2.3674743965920433,
|
| 854 |
+
"learning_rate": 8.558735681154944e-06,
|
| 855 |
+
"loss": 0.5525,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.3259698275862069,
|
| 860 |
+
"grad_norm": 2.334754085556647,
|
| 861 |
+
"learning_rate": 8.525543309797653e-06,
|
| 862 |
+
"loss": 0.5501,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.3286637931034483,
|
| 867 |
+
"grad_norm": 2.511690588702945,
|
| 868 |
+
"learning_rate": 8.492039028177985e-06,
|
| 869 |
+
"loss": 0.5703,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.33135775862068967,
|
| 874 |
+
"grad_norm": 2.41344799771138,
|
| 875 |
+
"learning_rate": 8.458225800471492e-06,
|
| 876 |
+
"loss": 0.5674,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.33405172413793105,
|
| 881 |
+
"grad_norm": 2.274991518802859,
|
| 882 |
+
"learning_rate": 8.424106618186653e-06,
|
| 883 |
+
"loss": 0.568,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.33674568965517243,
|
| 888 |
+
"grad_norm": 2.2914893865907375,
|
| 889 |
+
"learning_rate": 8.389684499900231e-06,
|
| 890 |
+
"loss": 0.5578,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.3394396551724138,
|
| 895 |
+
"grad_norm": 2.2271331744770175,
|
| 896 |
+
"learning_rate": 8.354962490990202e-06,
|
| 897 |
+
"loss": 0.554,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.3421336206896552,
|
| 902 |
+
"grad_norm": 2.346436964348071,
|
| 903 |
+
"learning_rate": 8.319943663366325e-06,
|
| 904 |
+
"loss": 0.5623,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.3448275862068966,
|
| 909 |
+
"grad_norm": 2.2365182629879707,
|
| 910 |
+
"learning_rate": 8.284631115198371e-06,
|
| 911 |
+
"loss": 0.5534,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.34752155172413796,
|
| 916 |
+
"grad_norm": 2.461241222937466,
|
| 917 |
+
"learning_rate": 8.24902797064203e-06,
|
| 918 |
+
"loss": 0.5564,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.35021551724137934,
|
| 923 |
+
"grad_norm": 2.442140982131872,
|
| 924 |
+
"learning_rate": 8.213137379562486e-06,
|
| 925 |
+
"loss": 0.5506,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.35290948275862066,
|
| 930 |
+
"grad_norm": 2.388325267487531,
|
| 931 |
+
"learning_rate": 8.176962517255776e-06,
|
| 932 |
+
"loss": 0.5531,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.35560344827586204,
|
| 937 |
+
"grad_norm": 2.398524248781268,
|
| 938 |
+
"learning_rate": 8.140506584167845e-06,
|
| 939 |
+
"loss": 0.5415,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.3582974137931034,
|
| 944 |
+
"grad_norm": 2.566763693618945,
|
| 945 |
+
"learning_rate": 8.103772805611403e-06,
|
| 946 |
+
"loss": 0.5616,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3609913793103448,
|
| 951 |
+
"grad_norm": 2.3106768834034805,
|
| 952 |
+
"learning_rate": 8.066764431480584e-06,
|
| 953 |
+
"loss": 0.5328,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.3636853448275862,
|
| 958 |
+
"grad_norm": 2.2940366514378425,
|
| 959 |
+
"learning_rate": 8.029484735963409e-06,
|
| 960 |
+
"loss": 0.5452,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.36637931034482757,
|
| 965 |
+
"grad_norm": 2.4096028111246652,
|
| 966 |
+
"learning_rate": 7.991937017252127e-06,
|
| 967 |
+
"loss": 0.5448,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.36907327586206895,
|
| 972 |
+
"grad_norm": 2.450510234216877,
|
| 973 |
+
"learning_rate": 7.95412459725141e-06,
|
| 974 |
+
"loss": 0.5407,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.37176724137931033,
|
| 979 |
+
"grad_norm": 2.498635611862816,
|
| 980 |
+
"learning_rate": 7.916050821284462e-06,
|
| 981 |
+
"loss": 0.536,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.3744612068965517,
|
| 986 |
+
"grad_norm": 2.3384557737181306,
|
| 987 |
+
"learning_rate": 7.877719057797055e-06,
|
| 988 |
+
"loss": 0.5404,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.3771551724137931,
|
| 993 |
+
"grad_norm": 2.395634299723523,
|
| 994 |
+
"learning_rate": 7.839132698059515e-06,
|
| 995 |
+
"loss": 0.5469,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.3798491379310345,
|
| 1000 |
+
"grad_norm": 2.528299315994187,
|
| 1001 |
+
"learning_rate": 7.800295155866688e-06,
|
| 1002 |
+
"loss": 0.5272,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.38254310344827586,
|
| 1007 |
+
"grad_norm": 2.383516192036904,
|
| 1008 |
+
"learning_rate": 7.761209867235924e-06,
|
| 1009 |
+
"loss": 0.5495,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.38523706896551724,
|
| 1014 |
+
"grad_norm": 2.3221638101603954,
|
| 1015 |
+
"learning_rate": 7.721880290103082e-06,
|
| 1016 |
+
"loss": 0.5517,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.3879310344827586,
|
| 1021 |
+
"grad_norm": 2.451275702370551,
|
| 1022 |
+
"learning_rate": 7.6823099040166e-06,
|
| 1023 |
+
"loss": 0.5195,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.390625,
|
| 1028 |
+
"grad_norm": 2.469988525493039,
|
| 1029 |
+
"learning_rate": 7.64250220982966e-06,
|
| 1030 |
+
"loss": 0.5151,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.3933189655172414,
|
| 1035 |
+
"grad_norm": 2.4698654498618016,
|
| 1036 |
+
"learning_rate": 7.602460729390455e-06,
|
| 1037 |
+
"loss": 0.5296,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.39601293103448276,
|
| 1042 |
+
"grad_norm": 2.433689149450146,
|
| 1043 |
+
"learning_rate": 7.562189005230609e-06,
|
| 1044 |
+
"loss": 0.5122,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.39870689655172414,
|
| 1049 |
+
"grad_norm": 2.317764828643439,
|
| 1050 |
+
"learning_rate": 7.521690600251765e-06,
|
| 1051 |
+
"loss": 0.5389,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.4014008620689655,
|
| 1056 |
+
"grad_norm": 2.3785211168925997,
|
| 1057 |
+
"learning_rate": 7.480969097410369e-06,
|
| 1058 |
+
"loss": 0.5342,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.4040948275862069,
|
| 1063 |
+
"grad_norm": 2.352268614869421,
|
| 1064 |
+
"learning_rate": 7.4400280994006765e-06,
|
| 1065 |
+
"loss": 0.5222,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.4067887931034483,
|
| 1070 |
+
"grad_norm": 2.3334817294609844,
|
| 1071 |
+
"learning_rate": 7.398871228336022e-06,
|
| 1072 |
+
"loss": 0.5148,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.40948275862068967,
|
| 1077 |
+
"grad_norm": 2.2180745679186513,
|
| 1078 |
+
"learning_rate": 7.357502125428359e-06,
|
| 1079 |
+
"loss": 0.5269,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.41217672413793105,
|
| 1084 |
+
"grad_norm": 2.4024098190438448,
|
| 1085 |
+
"learning_rate": 7.315924450666129e-06,
|
| 1086 |
+
"loss": 0.5252,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.41487068965517243,
|
| 1091 |
+
"grad_norm": 2.4847050155908326,
|
| 1092 |
+
"learning_rate": 7.274141882490435e-06,
|
| 1093 |
+
"loss": 0.5215,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.4175646551724138,
|
| 1098 |
+
"grad_norm": 2.3489603723016423,
|
| 1099 |
+
"learning_rate": 7.23215811746963e-06,
|
| 1100 |
+
"loss": 0.5331,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.4202586206896552,
|
| 1105 |
+
"grad_norm": 2.3846378852084276,
|
| 1106 |
+
"learning_rate": 7.189976869972249e-06,
|
| 1107 |
+
"loss": 0.526,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.4229525862068966,
|
| 1112 |
+
"grad_norm": 2.2721960920466087,
|
| 1113 |
+
"learning_rate": 7.147601871838419e-06,
|
| 1114 |
+
"loss": 0.5111,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.42564655172413796,
|
| 1119 |
+
"grad_norm": 2.242972711736404,
|
| 1120 |
+
"learning_rate": 7.105036872049676e-06,
|
| 1121 |
+
"loss": 0.5079,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.42834051724137934,
|
| 1126 |
+
"grad_norm": 2.5168627834860944,
|
| 1127 |
+
"learning_rate": 7.0622856363973e-06,
|
| 1128 |
+
"loss": 0.5037,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.43103448275862066,
|
| 1133 |
+
"grad_norm": 2.3034024680284797,
|
| 1134 |
+
"learning_rate": 7.019351947149149e-06,
|
| 1135 |
+
"loss": 0.5037,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.43372844827586204,
|
| 1140 |
+
"grad_norm": 2.3169182311354204,
|
| 1141 |
+
"learning_rate": 6.976239602715025e-06,
|
| 1142 |
+
"loss": 0.5244,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4364224137931034,
|
| 1147 |
+
"grad_norm": 2.342523099764779,
|
| 1148 |
+
"learning_rate": 6.932952417310634e-06,
|
| 1149 |
+
"loss": 0.4955,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.4391163793103448,
|
| 1154 |
+
"grad_norm": 2.4079674615936213,
|
| 1155 |
+
"learning_rate": 6.889494220620135e-06,
|
| 1156 |
+
"loss": 0.5039,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4418103448275862,
|
| 1161 |
+
"grad_norm": 2.2705187143965704,
|
| 1162 |
+
"learning_rate": 6.8458688574573164e-06,
|
| 1163 |
+
"loss": 0.4921,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.44450431034482757,
|
| 1168 |
+
"grad_norm": 2.3040634798061053,
|
| 1169 |
+
"learning_rate": 6.8020801874254425e-06,
|
| 1170 |
+
"loss": 0.4952,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.44719827586206895,
|
| 1175 |
+
"grad_norm": 2.283780585980132,
|
| 1176 |
+
"learning_rate": 6.758132084575791e-06,
|
| 1177 |
+
"loss": 0.5204,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.44989224137931033,
|
| 1182 |
+
"grad_norm": 2.2311658006536175,
|
| 1183 |
+
"learning_rate": 6.7140284370649015e-06,
|
| 1184 |
+
"loss": 0.5062,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.4525862068965517,
|
| 1189 |
+
"grad_norm": 2.381000659447914,
|
| 1190 |
+
"learning_rate": 6.6697731468105985e-06,
|
| 1191 |
+
"loss": 0.5054,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.4552801724137931,
|
| 1196 |
+
"grad_norm": 2.5645822620698295,
|
| 1197 |
+
"learning_rate": 6.625370129146771e-06,
|
| 1198 |
+
"loss": 0.4967,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.4579741379310345,
|
| 1203 |
+
"grad_norm": 2.518018472550615,
|
| 1204 |
+
"learning_rate": 6.580823312476976e-06,
|
| 1205 |
+
"loss": 0.5057,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.46066810344827586,
|
| 1210 |
+
"grad_norm": 2.3310109009449937,
|
| 1211 |
+
"learning_rate": 6.536136637926898e-06,
|
| 1212 |
+
"loss": 0.4923,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.46336206896551724,
|
| 1217 |
+
"grad_norm": 2.4572949530360235,
|
| 1218 |
+
"learning_rate": 6.491314058995653e-06,
|
| 1219 |
+
"loss": 0.4923,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.4660560344827586,
|
| 1224 |
+
"grad_norm": 2.333469399501826,
|
| 1225 |
+
"learning_rate": 6.446359541206042e-06,
|
| 1226 |
+
"loss": 0.4984,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.46875,
|
| 1231 |
+
"grad_norm": 2.3170414009513287,
|
| 1232 |
+
"learning_rate": 6.401277061753689e-06,
|
| 1233 |
+
"loss": 0.4805,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.4714439655172414,
|
| 1238 |
+
"grad_norm": 2.3105233267502068,
|
| 1239 |
+
"learning_rate": 6.356070609155188e-06,
|
| 1240 |
+
"loss": 0.4857,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.47413793103448276,
|
| 1245 |
+
"grad_norm": 2.406900488225167,
|
| 1246 |
+
"learning_rate": 6.310744182895231e-06,
|
| 1247 |
+
"loss": 0.474,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.47683189655172414,
|
| 1252 |
+
"grad_norm": 2.3233269304186246,
|
| 1253 |
+
"learning_rate": 6.265301793072762e-06,
|
| 1254 |
+
"loss": 0.4947,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.4795258620689655,
|
| 1259 |
+
"grad_norm": 2.336797328678939,
|
| 1260 |
+
"learning_rate": 6.219747460046203e-06,
|
| 1261 |
+
"loss": 0.4771,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.4822198275862069,
|
| 1266 |
+
"grad_norm": 2.3058756900360566,
|
| 1267 |
+
"learning_rate": 6.17408521407776e-06,
|
| 1268 |
+
"loss": 0.4791,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.4849137931034483,
|
| 1273 |
+
"grad_norm": 2.467884893673803,
|
| 1274 |
+
"learning_rate": 6.128319094976869e-06,
|
| 1275 |
+
"loss": 0.492,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.48760775862068967,
|
| 1280 |
+
"grad_norm": 2.3280199883273047,
|
| 1281 |
+
"learning_rate": 6.0824531517427765e-06,
|
| 1282 |
+
"loss": 0.4816,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.49030172413793105,
|
| 1287 |
+
"grad_norm": 2.2642826853033053,
|
| 1288 |
+
"learning_rate": 6.03649144220633e-06,
|
| 1289 |
+
"loss": 0.4805,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.49299568965517243,
|
| 1294 |
+
"grad_norm": 2.2845546468033007,
|
| 1295 |
+
"learning_rate": 5.990438032670968e-06,
|
| 1296 |
+
"loss": 0.4804,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.4956896551724138,
|
| 1301 |
+
"grad_norm": 2.320099011292584,
|
| 1302 |
+
"learning_rate": 5.944296997552968e-06,
|
| 1303 |
+
"loss": 0.4807,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.4983836206896552,
|
| 1308 |
+
"grad_norm": 2.4032671750639607,
|
| 1309 |
+
"learning_rate": 5.898072419020978e-06,
|
| 1310 |
+
"loss": 0.479,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.5010775862068966,
|
| 1315 |
+
"grad_norm": 2.3454490179654948,
|
| 1316 |
+
"learning_rate": 5.851768386634863e-06,
|
| 1317 |
+
"loss": 0.4657,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5037715517241379,
|
| 1322 |
+
"grad_norm": 2.2272370976346707,
|
| 1323 |
+
"learning_rate": 5.805388996983891e-06,
|
| 1324 |
+
"loss": 0.4778,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5064655172413793,
|
| 1329 |
+
"grad_norm": 2.399429478516486,
|
| 1330 |
+
"learning_rate": 5.758938353324308e-06,
|
| 1331 |
+
"loss": 0.4766,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.5091594827586207,
|
| 1336 |
+
"grad_norm": 2.2479225788941726,
|
| 1337 |
+
"learning_rate": 5.712420565216305e-06,
|
| 1338 |
+
"loss": 0.4689,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5118534482758621,
|
| 1343 |
+
"grad_norm": 2.333910684063406,
|
| 1344 |
+
"learning_rate": 5.66583974816045e-06,
|
| 1345 |
+
"loss": 0.4689,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.5145474137931034,
|
| 1350 |
+
"grad_norm": 2.494414220923278,
|
| 1351 |
+
"learning_rate": 5.619200023233582e-06,
|
| 1352 |
+
"loss": 0.4654,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5172413793103449,
|
| 1357 |
+
"grad_norm": 2.4303474928270314,
|
| 1358 |
+
"learning_rate": 5.572505516724207e-06,
|
| 1359 |
+
"loss": 0.4841,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.5199353448275862,
|
| 1364 |
+
"grad_norm": 2.3290300558522605,
|
| 1365 |
+
"learning_rate": 5.52576035976744e-06,
|
| 1366 |
+
"loss": 0.4631,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.5226293103448276,
|
| 1371 |
+
"grad_norm": 2.303763077645539,
|
| 1372 |
+
"learning_rate": 5.478968687979527e-06,
|
| 1373 |
+
"loss": 0.4535,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.525323275862069,
|
| 1378 |
+
"grad_norm": 2.3158015015015367,
|
| 1379 |
+
"learning_rate": 5.432134641091945e-06,
|
| 1380 |
+
"loss": 0.4653,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.5280172413793104,
|
| 1385 |
+
"grad_norm": 2.412268625727716,
|
| 1386 |
+
"learning_rate": 5.3852623625851655e-06,
|
| 1387 |
+
"loss": 0.4553,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.5307112068965517,
|
| 1392 |
+
"grad_norm": 2.4152646593142477,
|
| 1393 |
+
"learning_rate": 5.338355999322069e-06,
|
| 1394 |
+
"loss": 0.459,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.5334051724137931,
|
| 1399 |
+
"grad_norm": 2.3009383932051186,
|
| 1400 |
+
"learning_rate": 5.291419701181069e-06,
|
| 1401 |
+
"loss": 0.4574,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5360991379310345,
|
| 1406 |
+
"grad_norm": 2.3404820672273683,
|
| 1407 |
+
"learning_rate": 5.244457620688962e-06,
|
| 1408 |
+
"loss": 0.4457,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.5387931034482759,
|
| 1413 |
+
"grad_norm": 2.2918401803413277,
|
| 1414 |
+
"learning_rate": 5.197473912653549e-06,
|
| 1415 |
+
"loss": 0.4625,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.5414870689655172,
|
| 1420 |
+
"grad_norm": 2.330307145203118,
|
| 1421 |
+
"learning_rate": 5.150472733796053e-06,
|
| 1422 |
+
"loss": 0.4614,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.5441810344827587,
|
| 1427 |
+
"grad_norm": 2.317228108453964,
|
| 1428 |
+
"learning_rate": 5.103458242383371e-06,
|
| 1429 |
+
"loss": 0.4346,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.546875,
|
| 1434 |
+
"grad_norm": 2.246449210384358,
|
| 1435 |
+
"learning_rate": 5.056434597860176e-06,
|
| 1436 |
+
"loss": 0.4332,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.5495689655172413,
|
| 1441 |
+
"grad_norm": 2.2315633880832917,
|
| 1442 |
+
"learning_rate": 5.009405960480937e-06,
|
| 1443 |
+
"loss": 0.4374,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.5522629310344828,
|
| 1448 |
+
"grad_norm": 2.236917389881302,
|
| 1449 |
+
"learning_rate": 4.962376490941846e-06,
|
| 1450 |
+
"loss": 0.4443,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.5549568965517241,
|
| 1455 |
+
"grad_norm": 2.2257101057521953,
|
| 1456 |
+
"learning_rate": 4.915350350012714e-06,
|
| 1457 |
+
"loss": 0.4485,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5576508620689655,
|
| 1462 |
+
"grad_norm": 2.2768475081245696,
|
| 1463 |
+
"learning_rate": 4.868331698168875e-06,
|
| 1464 |
+
"loss": 0.456,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.5603448275862069,
|
| 1469 |
+
"grad_norm": 2.2588873812858243,
|
| 1470 |
+
"learning_rate": 4.82132469522308e-06,
|
| 1471 |
+
"loss": 0.4531,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.5630387931034483,
|
| 1476 |
+
"grad_norm": 2.2517674521156414,
|
| 1477 |
+
"learning_rate": 4.774333499957488e-06,
|
| 1478 |
+
"loss": 0.4439,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.5657327586206896,
|
| 1483 |
+
"grad_norm": 2.3879681903493277,
|
| 1484 |
+
"learning_rate": 4.727362269755736e-06,
|
| 1485 |
+
"loss": 0.4507,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.568426724137931,
|
| 1490 |
+
"grad_norm": 2.2168932530530654,
|
| 1491 |
+
"learning_rate": 4.68041516023511e-06,
|
| 1492 |
+
"loss": 0.4436,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.5711206896551724,
|
| 1497 |
+
"grad_norm": 2.328909950607463,
|
| 1498 |
+
"learning_rate": 4.633496324878906e-06,
|
| 1499 |
+
"loss": 0.4408,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.5738146551724138,
|
| 1504 |
+
"grad_norm": 2.2564887174276183,
|
| 1505 |
+
"learning_rate": 4.586609914668963e-06,
|
| 1506 |
+
"loss": 0.4516,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.5765086206896551,
|
| 1511 |
+
"grad_norm": 2.2979177074885424,
|
| 1512 |
+
"learning_rate": 4.539760077718416e-06,
|
| 1513 |
+
"loss": 0.4389,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.5792025862068966,
|
| 1518 |
+
"grad_norm": 2.2933960847054515,
|
| 1519 |
+
"learning_rate": 4.492950958904707e-06,
|
| 1520 |
+
"loss": 0.4266,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.5818965517241379,
|
| 1525 |
+
"grad_norm": 2.2594325799250594,
|
| 1526 |
+
"learning_rate": 4.4461866995028776e-06,
|
| 1527 |
+
"loss": 0.427,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.5845905172413793,
|
| 1532 |
+
"grad_norm": 2.349659814217747,
|
| 1533 |
+
"learning_rate": 4.399471436819199e-06,
|
| 1534 |
+
"loss": 0.4346,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.5872844827586207,
|
| 1539 |
+
"grad_norm": 2.297930957947952,
|
| 1540 |
+
"learning_rate": 4.352809303825115e-06,
|
| 1541 |
+
"loss": 0.4279,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.5899784482758621,
|
| 1546 |
+
"grad_norm": 2.202712644399629,
|
| 1547 |
+
"learning_rate": 4.306204428791609e-06,
|
| 1548 |
+
"loss": 0.4291,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.5926724137931034,
|
| 1553 |
+
"grad_norm": 2.2128476870439813,
|
| 1554 |
+
"learning_rate": 4.259660934923965e-06,
|
| 1555 |
+
"loss": 0.44,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.5953663793103449,
|
| 1560 |
+
"grad_norm": 2.367627389505961,
|
| 1561 |
+
"learning_rate": 4.213182939996978e-06,
|
| 1562 |
+
"loss": 0.4379,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.5980603448275862,
|
| 1567 |
+
"grad_norm": 2.274117011259563,
|
| 1568 |
+
"learning_rate": 4.166774555990654e-06,
|
| 1569 |
+
"loss": 0.4344,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.6007543103448276,
|
| 1574 |
+
"grad_norm": 2.2261394360036983,
|
| 1575 |
+
"learning_rate": 4.120439888726407e-06,
|
| 1576 |
+
"loss": 0.4142,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.603448275862069,
|
| 1581 |
+
"grad_norm": 2.1852891937100436,
|
| 1582 |
+
"learning_rate": 4.074183037503827e-06,
|
| 1583 |
+
"loss": 0.4266,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.6061422413793104,
|
| 1588 |
+
"grad_norm": 2.3083672939605053,
|
| 1589 |
+
"learning_rate": 4.028008094737989e-06,
|
| 1590 |
+
"loss": 0.4394,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.6088362068965517,
|
| 1595 |
+
"grad_norm": 2.2610041056896963,
|
| 1596 |
+
"learning_rate": 3.981919145597404e-06,
|
| 1597 |
+
"loss": 0.4128,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.6115301724137931,
|
| 1602 |
+
"grad_norm": 2.19751146715402,
|
| 1603 |
+
"learning_rate": 3.935920267642592e-06,
|
| 1604 |
+
"loss": 0.4227,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.6142241379310345,
|
| 1609 |
+
"grad_norm": 2.3415136999781963,
|
| 1610 |
+
"learning_rate": 3.890015530465342e-06,
|
| 1611 |
+
"loss": 0.4133,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.6169181034482759,
|
| 1616 |
+
"grad_norm": 2.291673599344672,
|
| 1617 |
+
"learning_rate": 3.844208995328659e-06,
|
| 1618 |
+
"loss": 0.4192,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.6196120689655172,
|
| 1623 |
+
"grad_norm": 2.2459859353779508,
|
| 1624 |
+
"learning_rate": 3.7985047148074584e-06,
|
| 1625 |
+
"loss": 0.4257,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6223060344827587,
|
| 1630 |
+
"grad_norm": 2.3753214874892072,
|
| 1631 |
+
"learning_rate": 3.75290673243004e-06,
|
| 1632 |
+
"loss": 0.421,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.625,
|
| 1637 |
+
"grad_norm": 2.181100394703554,
|
| 1638 |
+
"learning_rate": 3.707419082320336e-06,
|
| 1639 |
+
"loss": 0.4287,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.6276939655172413,
|
| 1644 |
+
"grad_norm": 2.242465849693457,
|
| 1645 |
+
"learning_rate": 3.6620457888410143e-06,
|
| 1646 |
+
"loss": 0.4143,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.6303879310344828,
|
| 1651 |
+
"grad_norm": 2.3646959150338813,
|
| 1652 |
+
"learning_rate": 3.616790866237433e-06,
|
| 1653 |
+
"loss": 0.4045,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.6330818965517241,
|
| 1658 |
+
"grad_norm": 2.312802724452316,
|
| 1659 |
+
"learning_rate": 3.5716583182825023e-06,
|
| 1660 |
+
"loss": 0.4248,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.6357758620689655,
|
| 1665 |
+
"grad_norm": 2.208443511882899,
|
| 1666 |
+
"learning_rate": 3.5266521379224506e-06,
|
| 1667 |
+
"loss": 0.4135,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.6384698275862069,
|
| 1672 |
+
"grad_norm": 2.2774985396607046,
|
| 1673 |
+
"learning_rate": 3.4817763069235747e-06,
|
| 1674 |
+
"loss": 0.4028,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6411637931034483,
|
| 1679 |
+
"grad_norm": 2.3080269121559898,
|
| 1680 |
+
"learning_rate": 3.4370347955199634e-06,
|
| 1681 |
+
"loss": 0.4086,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6438577586206896,
|
| 1686 |
+
"grad_norm": 2.3130128907712355,
|
| 1687 |
+
"learning_rate": 3.392431562062238e-06,
|
| 1688 |
+
"loss": 0.408,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.646551724137931,
|
| 1693 |
+
"grad_norm": 2.2776700595089676,
|
| 1694 |
+
"learning_rate": 3.347970552667361e-06,
|
| 1695 |
+
"loss": 0.4159,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.6492456896551724,
|
| 1700 |
+
"grad_norm": 2.1524296489308576,
|
| 1701 |
+
"learning_rate": 3.303655700869507e-06,
|
| 1702 |
+
"loss": 0.4035,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.6519396551724138,
|
| 1707 |
+
"grad_norm": 2.2146294105038185,
|
| 1708 |
+
"learning_rate": 3.259490927272071e-06,
|
| 1709 |
+
"loss": 0.4012,
|
| 1710 |
+
"step": 1210
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.6546336206896551,
|
| 1714 |
+
"grad_norm": 2.2480654104489752,
|
| 1715 |
+
"learning_rate": 3.2154801392007883e-06,
|
| 1716 |
+
"loss": 0.4153,
|
| 1717 |
+
"step": 1215
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.6573275862068966,
|
| 1721 |
+
"grad_norm": 2.169871400965887,
|
| 1722 |
+
"learning_rate": 3.171627230358063e-06,
|
| 1723 |
+
"loss": 0.404,
|
| 1724 |
+
"step": 1220
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.6600215517241379,
|
| 1728 |
+
"grad_norm": 2.4015866937415056,
|
| 1729 |
+
"learning_rate": 3.1279360804784785e-06,
|
| 1730 |
+
"loss": 0.4063,
|
| 1731 |
+
"step": 1225
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.6627155172413793,
|
| 1735 |
+
"grad_norm": 2.3038799378482557,
|
| 1736 |
+
"learning_rate": 3.084410554985553e-06,
|
| 1737 |
+
"loss": 0.3898,
|
| 1738 |
+
"step": 1230
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.6654094827586207,
|
| 1742 |
+
"grad_norm": 2.198625588166285,
|
| 1743 |
+
"learning_rate": 3.0410545046497553e-06,
|
| 1744 |
+
"loss": 0.4035,
|
| 1745 |
+
"step": 1235
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.6681034482758621,
|
| 1749 |
+
"grad_norm": 2.1950219963512176,
|
| 1750 |
+
"learning_rate": 2.9978717652478343e-06,
|
| 1751 |
+
"loss": 0.3902,
|
| 1752 |
+
"step": 1240
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.6707974137931034,
|
| 1756 |
+
"grad_norm": 2.247458718435766,
|
| 1757 |
+
"learning_rate": 2.954866157223445e-06,
|
| 1758 |
+
"loss": 0.4082,
|
| 1759 |
+
"step": 1245
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.6734913793103449,
|
| 1763 |
+
"grad_norm": 2.2241261994844588,
|
| 1764 |
+
"learning_rate": 2.9120414853491574e-06,
|
| 1765 |
+
"loss": 0.404,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.6761853448275862,
|
| 1770 |
+
"grad_norm": 2.1606540598223103,
|
| 1771 |
+
"learning_rate": 2.86940153838984e-06,
|
| 1772 |
+
"loss": 0.3948,
|
| 1773 |
+
"step": 1255
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.6788793103448276,
|
| 1777 |
+
"grad_norm": 2.0718054651873437,
|
| 1778 |
+
"learning_rate": 2.826950088767469e-06,
|
| 1779 |
+
"loss": 0.3927,
|
| 1780 |
+
"step": 1260
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.681573275862069,
|
| 1784 |
+
"grad_norm": 2.227847088159035,
|
| 1785 |
+
"learning_rate": 2.784690892227363e-06,
|
| 1786 |
+
"loss": 0.3903,
|
| 1787 |
+
"step": 1265
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.6842672413793104,
|
| 1791 |
+
"grad_norm": 2.207892303296737,
|
| 1792 |
+
"learning_rate": 2.7426276875059145e-06,
|
| 1793 |
+
"loss": 0.3955,
|
| 1794 |
+
"step": 1270
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.6869612068965517,
|
| 1798 |
+
"grad_norm": 2.1465153515114093,
|
| 1799 |
+
"learning_rate": 2.700764195999819e-06,
|
| 1800 |
+
"loss": 0.3788,
|
| 1801 |
+
"step": 1275
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.6896551724137931,
|
| 1805 |
+
"grad_norm": 2.223157201107058,
|
| 1806 |
+
"learning_rate": 2.6591041214368383e-06,
|
| 1807 |
+
"loss": 0.4053,
|
| 1808 |
+
"step": 1280
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.6923491379310345,
|
| 1812 |
+
"grad_norm": 2.392548147708553,
|
| 1813 |
+
"learning_rate": 2.6176511495481172e-06,
|
| 1814 |
+
"loss": 0.3834,
|
| 1815 |
+
"step": 1285
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.6950431034482759,
|
| 1819 |
+
"grad_norm": 2.059476074487736,
|
| 1820 |
+
"learning_rate": 2.5764089477421067e-06,
|
| 1821 |
+
"loss": 0.3857,
|
| 1822 |
+
"step": 1290
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.6977370689655172,
|
| 1826 |
+
"grad_norm": 2.157455657651667,
|
| 1827 |
+
"learning_rate": 2.5353811647801107e-06,
|
| 1828 |
+
"loss": 0.3884,
|
| 1829 |
+
"step": 1295
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.7004310344827587,
|
| 1833 |
+
"grad_norm": 2.307643086382308,
|
| 1834 |
+
"learning_rate": 2.4945714304534584e-06,
|
| 1835 |
+
"loss": 0.3815,
|
| 1836 |
+
"step": 1300
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.703125,
|
| 1840 |
+
"grad_norm": 2.26315069416342,
|
| 1841 |
+
"learning_rate": 2.453983355262382e-06,
|
| 1842 |
+
"loss": 0.3865,
|
| 1843 |
+
"step": 1305
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.7058189655172413,
|
| 1847 |
+
"grad_norm": 2.332313222729813,
|
| 1848 |
+
"learning_rate": 2.413620530096592e-06,
|
| 1849 |
+
"loss": 0.391,
|
| 1850 |
+
"step": 1310
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.7085129310344828,
|
| 1854 |
+
"grad_norm": 2.1418117590999413,
|
| 1855 |
+
"learning_rate": 2.373486525917575e-06,
|
| 1856 |
+
"loss": 0.3912,
|
| 1857 |
+
"step": 1315
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.7112068965517241,
|
| 1861 |
+
"grad_norm": 2.178180423311831,
|
| 1862 |
+
"learning_rate": 2.333584893442675e-06,
|
| 1863 |
+
"loss": 0.3854,
|
| 1864 |
+
"step": 1320
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.7139008620689655,
|
| 1868 |
+
"grad_norm": 2.151591142836586,
|
| 1869 |
+
"learning_rate": 2.2939191628309482e-06,
|
| 1870 |
+
"loss": 0.3815,
|
| 1871 |
+
"step": 1325
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.7165948275862069,
|
| 1875 |
+
"grad_norm": 2.1488408048158916,
|
| 1876 |
+
"learning_rate": 2.254492843370857e-06,
|
| 1877 |
+
"loss": 0.3741,
|
| 1878 |
+
"step": 1330
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.7192887931034483,
|
| 1882 |
+
"grad_norm": 2.3225770656541624,
|
| 1883 |
+
"learning_rate": 2.2153094231697807e-06,
|
| 1884 |
+
"loss": 0.3865,
|
| 1885 |
+
"step": 1335
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.7219827586206896,
|
| 1889 |
+
"grad_norm": 2.225461569667121,
|
| 1890 |
+
"learning_rate": 2.1763723688454297e-06,
|
| 1891 |
+
"loss": 0.389,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.724676724137931,
|
| 1896 |
+
"grad_norm": 2.310688191216032,
|
| 1897 |
+
"learning_rate": 2.1376851252191465e-06,
|
| 1898 |
+
"loss": 0.3905,
|
| 1899 |
+
"step": 1345
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.7273706896551724,
|
| 1903 |
+
"grad_norm": 2.206817710811153,
|
| 1904 |
+
"learning_rate": 2.09925111501113e-06,
|
| 1905 |
+
"loss": 0.3705,
|
| 1906 |
+
"step": 1350
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.7300646551724138,
|
| 1910 |
+
"grad_norm": 2.194541840528301,
|
| 1911 |
+
"learning_rate": 2.061073738537635e-06,
|
| 1912 |
+
"loss": 0.38,
|
| 1913 |
+
"step": 1355
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.7327586206896551,
|
| 1917 |
+
"grad_norm": 2.1363777762782568,
|
| 1918 |
+
"learning_rate": 2.0231563734101245e-06,
|
| 1919 |
+
"loss": 0.3826,
|
| 1920 |
+
"step": 1360
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.7354525862068966,
|
| 1924 |
+
"grad_norm": 2.043722143372559,
|
| 1925 |
+
"learning_rate": 1.9855023742364647e-06,
|
| 1926 |
+
"loss": 0.3722,
|
| 1927 |
+
"step": 1365
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.7381465517241379,
|
| 1931 |
+
"grad_norm": 2.296022903294665,
|
| 1932 |
+
"learning_rate": 1.9481150723241236e-06,
|
| 1933 |
+
"loss": 0.3836,
|
| 1934 |
+
"step": 1370
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.7408405172413793,
|
| 1938 |
+
"grad_norm": 2.1320085273295333,
|
| 1939 |
+
"learning_rate": 1.9109977753854496e-06,
|
| 1940 |
+
"loss": 0.367,
|
| 1941 |
+
"step": 1375
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.7435344827586207,
|
| 1945 |
+
"grad_norm": 2.126131429150438,
|
| 1946 |
+
"learning_rate": 1.8741537672450406e-06,
|
| 1947 |
+
"loss": 0.3756,
|
| 1948 |
+
"step": 1380
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.7462284482758621,
|
| 1952 |
+
"grad_norm": 2.3054341669665708,
|
| 1953 |
+
"learning_rate": 1.8375863075492062e-06,
|
| 1954 |
+
"loss": 0.3737,
|
| 1955 |
+
"step": 1385
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.7489224137931034,
|
| 1959 |
+
"grad_norm": 2.3340813640902867,
|
| 1960 |
+
"learning_rate": 1.8012986314775888e-06,
|
| 1961 |
+
"loss": 0.3694,
|
| 1962 |
+
"step": 1390
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7516163793103449,
|
| 1966 |
+
"grad_norm": 2.1335614766566544,
|
| 1967 |
+
"learning_rate": 1.7652939494569428e-06,
|
| 1968 |
+
"loss": 0.3706,
|
| 1969 |
+
"step": 1395
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.7543103448275862,
|
| 1973 |
+
"grad_norm": 2.135867482259856,
|
| 1974 |
+
"learning_rate": 1.7295754468771026e-06,
|
| 1975 |
+
"loss": 0.3826,
|
| 1976 |
+
"step": 1400
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.7570043103448276,
|
| 1980 |
+
"grad_norm": 2.253239028561062,
|
| 1981 |
+
"learning_rate": 1.6941462838091643e-06,
|
| 1982 |
+
"loss": 0.3879,
|
| 1983 |
+
"step": 1405
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.759698275862069,
|
| 1987 |
+
"grad_norm": 2.1899554008641613,
|
| 1988 |
+
"learning_rate": 1.6590095947259083e-06,
|
| 1989 |
+
"loss": 0.3657,
|
| 1990 |
+
"step": 1410
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.7623922413793104,
|
| 1994 |
+
"grad_norm": 1.9335639886365577,
|
| 1995 |
+
"learning_rate": 1.6241684882244952e-06,
|
| 1996 |
+
"loss": 0.3647,
|
| 1997 |
+
"step": 1415
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.7650862068965517,
|
| 2001 |
+
"grad_norm": 2.158271364922754,
|
| 2002 |
+
"learning_rate": 1.5896260467514335e-06,
|
| 2003 |
+
"loss": 0.3613,
|
| 2004 |
+
"step": 1420
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.7677801724137931,
|
| 2008 |
+
"grad_norm": 2.283426548356461,
|
| 2009 |
+
"learning_rate": 1.5553853263298741e-06,
|
| 2010 |
+
"loss": 0.3804,
|
| 2011 |
+
"step": 1425
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.7704741379310345,
|
| 2015 |
+
"grad_norm": 1.973245710047114,
|
| 2016 |
+
"learning_rate": 1.521449356289245e-06,
|
| 2017 |
+
"loss": 0.3616,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.7731681034482759,
|
| 2022 |
+
"grad_norm": 2.176003470736959,
|
| 2023 |
+
"learning_rate": 1.4878211389972369e-06,
|
| 2024 |
+
"loss": 0.3594,
|
| 2025 |
+
"step": 1435
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.7758620689655172,
|
| 2029 |
+
"grad_norm": 2.350333157030792,
|
| 2030 |
+
"learning_rate": 1.454503649594176e-06,
|
| 2031 |
+
"loss": 0.3745,
|
| 2032 |
+
"step": 1440
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.7785560344827587,
|
| 2036 |
+
"grad_norm": 2.1046600168472254,
|
| 2037 |
+
"learning_rate": 1.421499835729812e-06,
|
| 2038 |
+
"loss": 0.3614,
|
| 2039 |
+
"step": 1445
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.78125,
|
| 2043 |
+
"grad_norm": 2.2403959550973376,
|
| 2044 |
+
"learning_rate": 1.3888126173025412e-06,
|
| 2045 |
+
"loss": 0.3667,
|
| 2046 |
+
"step": 1450
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.7839439655172413,
|
| 2050 |
+
"grad_norm": 2.2036204076799244,
|
| 2051 |
+
"learning_rate": 1.3564448862010653e-06,
|
| 2052 |
+
"loss": 0.3719,
|
| 2053 |
+
"step": 1455
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.7866379310344828,
|
| 2057 |
+
"grad_norm": 2.1004023468667223,
|
| 2058 |
+
"learning_rate": 1.3243995060485537e-06,
|
| 2059 |
+
"loss": 0.3609,
|
| 2060 |
+
"step": 1460
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.7893318965517241,
|
| 2064 |
+
"grad_norm": 2.049485866619644,
|
| 2065 |
+
"learning_rate": 1.2926793119492848e-06,
|
| 2066 |
+
"loss": 0.3562,
|
| 2067 |
+
"step": 1465
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.7920258620689655,
|
| 2071 |
+
"grad_norm": 2.2562907662057015,
|
| 2072 |
+
"learning_rate": 1.2612871102378305e-06,
|
| 2073 |
+
"loss": 0.3638,
|
| 2074 |
+
"step": 1470
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.7947198275862069,
|
| 2078 |
+
"grad_norm": 2.0015131375954045,
|
| 2079 |
+
"learning_rate": 1.230225678230766e-06,
|
| 2080 |
+
"loss": 0.3523,
|
| 2081 |
+
"step": 1475
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.7974137931034483,
|
| 2085 |
+
"grad_norm": 1.9761111123797053,
|
| 2086 |
+
"learning_rate": 1.1994977639809575e-06,
|
| 2087 |
+
"loss": 0.3605,
|
| 2088 |
+
"step": 1480
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.8001077586206896,
|
| 2092 |
+
"grad_norm": 2.1818297029398916,
|
| 2093 |
+
"learning_rate": 1.169106086034446e-06,
|
| 2094 |
+
"loss": 0.369,
|
| 2095 |
+
"step": 1485
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.802801724137931,
|
| 2099 |
+
"grad_norm": 2.2176123875649782,
|
| 2100 |
+
"learning_rate": 1.1390533331899235e-06,
|
| 2101 |
+
"loss": 0.359,
|
| 2102 |
+
"step": 1490
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.8054956896551724,
|
| 2106 |
+
"grad_norm": 2.1415950875401952,
|
| 2107 |
+
"learning_rate": 1.109342164260853e-06,
|
| 2108 |
+
"loss": 0.365,
|
| 2109 |
+
"step": 1495
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.8081896551724138,
|
| 2113 |
+
"grad_norm": 1.9579230862394106,
|
| 2114 |
+
"learning_rate": 1.079975207840247e-06,
|
| 2115 |
+
"loss": 0.3475,
|
| 2116 |
+
"step": 1500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.8108836206896551,
|
| 2120 |
+
"grad_norm": 1.9891326864430916,
|
| 2121 |
+
"learning_rate": 1.050955062068098e-06,
|
| 2122 |
+
"loss": 0.3636,
|
| 2123 |
+
"step": 1505
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.8135775862068966,
|
| 2127 |
+
"grad_norm": 2.1589113372475826,
|
| 2128 |
+
"learning_rate": 1.0222842944015327e-06,
|
| 2129 |
+
"loss": 0.3637,
|
| 2130 |
+
"step": 1510
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.8162715517241379,
|
| 2134 |
+
"grad_norm": 2.2093770653678817,
|
| 2135 |
+
"learning_rate": 9.939654413876493e-07,
|
| 2136 |
+
"loss": 0.3704,
|
| 2137 |
+
"step": 1515
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.8189655172413793,
|
| 2141 |
+
"grad_norm": 2.117779906161616,
|
| 2142 |
+
"learning_rate": 9.660010084391197e-07,
|
| 2143 |
+
"loss": 0.3549,
|
| 2144 |
+
"step": 1520
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.8216594827586207,
|
| 2148 |
+
"grad_norm": 2.2081164429406623,
|
| 2149 |
+
"learning_rate": 9.383934696125213e-07,
|
| 2150 |
+
"loss": 0.3637,
|
| 2151 |
+
"step": 1525
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.8243534482758621,
|
| 2155 |
+
"grad_norm": 2.0797066327192915,
|
| 2156 |
+
"learning_rate": 9.111452673894589e-07,
|
| 2157 |
+
"loss": 0.355,
|
| 2158 |
+
"step": 1530
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.8270474137931034,
|
| 2162 |
+
"grad_norm": 1.9884207565802496,
|
| 2163 |
+
"learning_rate": 8.842588124604695e-07,
|
| 2164 |
+
"loss": 0.3598,
|
| 2165 |
+
"step": 1535
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8297413793103449,
|
| 2169 |
+
"grad_norm": 1.9966503677289194,
|
| 2170 |
+
"learning_rate": 8.577364835117552e-07,
|
| 2171 |
+
"loss": 0.3503,
|
| 2172 |
+
"step": 1540
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.8324353448275862,
|
| 2176 |
+
"grad_norm": 2.0974426601893006,
|
| 2177 |
+
"learning_rate": 8.315806270147237e-07,
|
| 2178 |
+
"loss": 0.3513,
|
| 2179 |
+
"step": 1545
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8351293103448276,
|
| 2183 |
+
"grad_norm": 2.0409953572157264,
|
| 2184 |
+
"learning_rate": 8.057935570184e-07,
|
| 2185 |
+
"loss": 0.353,
|
| 2186 |
+
"step": 1550
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.837823275862069,
|
| 2190 |
+
"grad_norm": 2.05994767546201,
|
| 2191 |
+
"learning_rate": 7.803775549447017e-07,
|
| 2192 |
+
"loss": 0.3612,
|
| 2193 |
+
"step": 1555
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.8405172413793104,
|
| 2197 |
+
"grad_norm": 1.9798689534701572,
|
| 2198 |
+
"learning_rate": 7.553348693865897e-07,
|
| 2199 |
+
"loss": 0.3433,
|
| 2200 |
+
"step": 1560
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.8432112068965517,
|
| 2204 |
+
"grad_norm": 2.0314728151818557,
|
| 2205 |
+
"learning_rate": 7.306677159091385e-07,
|
| 2206 |
+
"loss": 0.3554,
|
| 2207 |
+
"step": 1565
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.8459051724137931,
|
| 2211 |
+
"grad_norm": 2.1770521072409665,
|
| 2212 |
+
"learning_rate": 7.06378276853516e-07,
|
| 2213 |
+
"loss": 0.3434,
|
| 2214 |
+
"step": 1570
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.8485991379310345,
|
| 2218 |
+
"grad_norm": 3.199094357987707,
|
| 2219 |
+
"learning_rate": 6.824687011439168e-07,
|
| 2220 |
+
"loss": 0.3555,
|
| 2221 |
+
"step": 1575
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8512931034482759,
|
| 2225 |
+
"grad_norm": 2.0350410942770267,
|
| 2226 |
+
"learning_rate": 6.589411040974369e-07,
|
| 2227 |
+
"loss": 0.3455,
|
| 2228 |
+
"step": 1580
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8539870689655172,
|
| 2232 |
+
"grad_norm": 2.0106939788979994,
|
| 2233 |
+
"learning_rate": 6.35797567236926e-07,
|
| 2234 |
+
"loss": 0.342,
|
| 2235 |
+
"step": 1585
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8566810344827587,
|
| 2239 |
+
"grad_norm": 2.0462922997663333,
|
| 2240 |
+
"learning_rate": 6.130401381068424e-07,
|
| 2241 |
+
"loss": 0.3484,
|
| 2242 |
+
"step": 1590
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.859375,
|
| 2246 |
+
"grad_norm": 1.9989302742973973,
|
| 2247 |
+
"learning_rate": 5.906708300920916e-07,
|
| 2248 |
+
"loss": 0.358,
|
| 2249 |
+
"step": 1595
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.8620689655172413,
|
| 2253 |
+
"grad_norm": 2.1421705464248997,
|
| 2254 |
+
"learning_rate": 5.686916222399069e-07,
|
| 2255 |
+
"loss": 0.3479,
|
| 2256 |
+
"step": 1600
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.8647629310344828,
|
| 2260 |
+
"grad_norm": 1.8665911668349293,
|
| 2261 |
+
"learning_rate": 5.471044590847569e-07,
|
| 2262 |
+
"loss": 0.3485,
|
| 2263 |
+
"step": 1605
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.8674568965517241,
|
| 2267 |
+
"grad_norm": 2.252328311927183,
|
| 2268 |
+
"learning_rate": 5.259112504763115e-07,
|
| 2269 |
+
"loss": 0.3537,
|
| 2270 |
+
"step": 1610
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.8701508620689655,
|
| 2274 |
+
"grad_norm": 2.242291713625665,
|
| 2275 |
+
"learning_rate": 5.051138714104726e-07,
|
| 2276 |
+
"loss": 0.3493,
|
| 2277 |
+
"step": 1615
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.8728448275862069,
|
| 2281 |
+
"grad_norm": 1.9256177965601142,
|
| 2282 |
+
"learning_rate": 4.847141618634899e-07,
|
| 2283 |
+
"loss": 0.346,
|
| 2284 |
+
"step": 1620
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.8755387931034483,
|
| 2288 |
+
"grad_norm": 2.0978920858884806,
|
| 2289 |
+
"learning_rate": 4.647139266291789e-07,
|
| 2290 |
+
"loss": 0.3447,
|
| 2291 |
+
"step": 1625
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.8782327586206896,
|
| 2295 |
+
"grad_norm": 2.1438665447656424,
|
| 2296 |
+
"learning_rate": 4.4511493515924373e-07,
|
| 2297 |
+
"loss": 0.3467,
|
| 2298 |
+
"step": 1630
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.880926724137931,
|
| 2302 |
+
"grad_norm": 1.943275187391926,
|
| 2303 |
+
"learning_rate": 4.2591892140673383e-07,
|
| 2304 |
+
"loss": 0.359,
|
| 2305 |
+
"step": 1635
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.8836206896551724,
|
| 2309 |
+
"grad_norm": 1.9691693184683765,
|
| 2310 |
+
"learning_rate": 4.0712758367263573e-07,
|
| 2311 |
+
"loss": 0.3453,
|
| 2312 |
+
"step": 1640
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.8863146551724138,
|
| 2316 |
+
"grad_norm": 2.2550989234096432,
|
| 2317 |
+
"learning_rate": 3.8874258445562694e-07,
|
| 2318 |
+
"loss": 0.354,
|
| 2319 |
+
"step": 1645
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.8890086206896551,
|
| 2323 |
+
"grad_norm": 1.9743645882114702,
|
| 2324 |
+
"learning_rate": 3.7076555030498505e-07,
|
| 2325 |
+
"loss": 0.3545,
|
| 2326 |
+
"step": 1650
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.8917025862068966,
|
| 2330 |
+
"grad_norm": 2.069394313953148,
|
| 2331 |
+
"learning_rate": 3.531980716766914e-07,
|
| 2332 |
+
"loss": 0.3465,
|
| 2333 |
+
"step": 1655
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.8943965517241379,
|
| 2337 |
+
"grad_norm": 2.084992853821571,
|
| 2338 |
+
"learning_rate": 3.3604170279271375e-07,
|
| 2339 |
+
"loss": 0.347,
|
| 2340 |
+
"step": 1660
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.8970905172413793,
|
| 2344 |
+
"grad_norm": 2.028486932834069,
|
| 2345 |
+
"learning_rate": 3.1929796150351076e-07,
|
| 2346 |
+
"loss": 0.3385,
|
| 2347 |
+
"step": 1665
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.8997844827586207,
|
| 2351 |
+
"grad_norm": 1.9042104552013777,
|
| 2352 |
+
"learning_rate": 3.02968329153735e-07,
|
| 2353 |
+
"loss": 0.3456,
|
| 2354 |
+
"step": 1670
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9024784482758621,
|
| 2358 |
+
"grad_norm": 2.138202184025318,
|
| 2359 |
+
"learning_rate": 2.870542504511864e-07,
|
| 2360 |
+
"loss": 0.3524,
|
| 2361 |
+
"step": 1675
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9051724137931034,
|
| 2365 |
+
"grad_norm": 2.0791032572613615,
|
| 2366 |
+
"learning_rate": 2.7155713333898826e-07,
|
| 2367 |
+
"loss": 0.3557,
|
| 2368 |
+
"step": 1680
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.9078663793103449,
|
| 2372 |
+
"grad_norm": 2.032552582124559,
|
| 2373 |
+
"learning_rate": 2.564783488710293e-07,
|
| 2374 |
+
"loss": 0.3472,
|
| 2375 |
+
"step": 1685
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9105603448275862,
|
| 2379 |
+
"grad_norm": 2.0702198858374063,
|
| 2380 |
+
"learning_rate": 2.4181923109066254e-07,
|
| 2381 |
+
"loss": 0.3423,
|
| 2382 |
+
"step": 1690
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.9132543103448276,
|
| 2386 |
+
"grad_norm": 2.223955152789369,
|
| 2387 |
+
"learning_rate": 2.2758107691268294e-07,
|
| 2388 |
+
"loss": 0.353,
|
| 2389 |
+
"step": 1695
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.915948275862069,
|
| 2393 |
+
"grad_norm": 2.151000423198189,
|
| 2394 |
+
"learning_rate": 2.1376514600858212e-07,
|
| 2395 |
+
"loss": 0.3446,
|
| 2396 |
+
"step": 1700
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.9186422413793104,
|
| 2400 |
+
"grad_norm": 1.9722858881802758,
|
| 2401 |
+
"learning_rate": 2.003726606951084e-07,
|
| 2402 |
+
"loss": 0.3423,
|
| 2403 |
+
"step": 1705
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.9213362068965517,
|
| 2407 |
+
"grad_norm": 2.152676598806774,
|
| 2408 |
+
"learning_rate": 1.874048058261252e-07,
|
| 2409 |
+
"loss": 0.3566,
|
| 2410 |
+
"step": 1710
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9240301724137931,
|
| 2414 |
+
"grad_norm": 2.14241065854355,
|
| 2415 |
+
"learning_rate": 1.7486272868778299e-07,
|
| 2416 |
+
"loss": 0.3451,
|
| 2417 |
+
"step": 1715
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.9267241379310345,
|
| 2421 |
+
"grad_norm": 1.9240645550272026,
|
| 2422 |
+
"learning_rate": 1.62747538897019e-07,
|
| 2423 |
+
"loss": 0.3526,
|
| 2424 |
+
"step": 1720
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.9294181034482759,
|
| 2428 |
+
"grad_norm": 1.9864527165081682,
|
| 2429 |
+
"learning_rate": 1.5106030830338791e-07,
|
| 2430 |
+
"loss": 0.3414,
|
| 2431 |
+
"step": 1725
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.9321120689655172,
|
| 2435 |
+
"grad_norm": 1.891840587890648,
|
| 2436 |
+
"learning_rate": 1.3980207089423326e-07,
|
| 2437 |
+
"loss": 0.3507,
|
| 2438 |
+
"step": 1730
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.9348060344827587,
|
| 2442 |
+
"grad_norm": 2.197241548310695,
|
| 2443 |
+
"learning_rate": 1.2897382270320947e-07,
|
| 2444 |
+
"loss": 0.3415,
|
| 2445 |
+
"step": 1735
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.9375,
|
| 2449 |
+
"grad_norm": 2.1206142876832708,
|
| 2450 |
+
"learning_rate": 1.1857652172215905e-07,
|
| 2451 |
+
"loss": 0.3453,
|
| 2452 |
+
"step": 1740
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.9401939655172413,
|
| 2456 |
+
"grad_norm": 2.0575425778092375,
|
| 2457 |
+
"learning_rate": 1.0861108781636099e-07,
|
| 2458 |
+
"loss": 0.3414,
|
| 2459 |
+
"step": 1745
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.9428879310344828,
|
| 2463 |
+
"grad_norm": 2.067217232750268,
|
| 2464 |
+
"learning_rate": 9.907840264314572e-08,
|
| 2465 |
+
"loss": 0.3429,
|
| 2466 |
+
"step": 1750
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.9455818965517241,
|
| 2470 |
+
"grad_norm": 2.08954775323305,
|
| 2471 |
+
"learning_rate": 8.997930957389433e-08,
|
| 2472 |
+
"loss": 0.3406,
|
| 2473 |
+
"step": 1755
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.9482758620689655,
|
| 2477 |
+
"grad_norm": 2.0413104358527865,
|
| 2478 |
+
"learning_rate": 8.13146136194265e-08,
|
| 2479 |
+
"loss": 0.3544,
|
| 2480 |
+
"step": 1760
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.9509698275862069,
|
| 2484 |
+
"grad_norm": 1.9504574949587095,
|
| 2485 |
+
"learning_rate": 7.308508135877745e-08,
|
| 2486 |
+
"loss": 0.3515,
|
| 2487 |
+
"step": 1765
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9536637931034483,
|
| 2491 |
+
"grad_norm": 2.0325177039467266,
|
| 2492 |
+
"learning_rate": 6.52914408713784e-08,
|
| 2493 |
+
"loss": 0.3422,
|
| 2494 |
+
"step": 1770
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9563577586206896,
|
| 2498 |
+
"grad_norm": 2.080402951454278,
|
| 2499 |
+
"learning_rate": 5.7934381672640206e-08,
|
| 2500 |
+
"loss": 0.3302,
|
| 2501 |
+
"step": 1775
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.959051724137931,
|
| 2505 |
+
"grad_norm": 1.9103094146698458,
|
| 2506 |
+
"learning_rate": 5.101455465295557e-08,
|
| 2507 |
+
"loss": 0.3388,
|
| 2508 |
+
"step": 1780
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.9617456896551724,
|
| 2512 |
+
"grad_norm": 2.0461617336274665,
|
| 2513 |
+
"learning_rate": 4.453257202011008e-08,
|
| 2514 |
+
"loss": 0.3437,
|
| 2515 |
+
"step": 1785
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.9644396551724138,
|
| 2519 |
+
"grad_norm": 1.8955751541723638,
|
| 2520 |
+
"learning_rate": 3.848900724511828e-08,
|
| 2521 |
+
"loss": 0.3448,
|
| 2522 |
+
"step": 1790
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.9671336206896551,
|
| 2526 |
+
"grad_norm": 1.8502858059698502,
|
| 2527 |
+
"learning_rate": 3.28843950114921e-08,
|
| 2528 |
+
"loss": 0.3318,
|
| 2529 |
+
"step": 1795
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.9698275862068966,
|
| 2533 |
+
"grad_norm": 1.9634830726403167,
|
| 2534 |
+
"learning_rate": 2.771923116793307e-08,
|
| 2535 |
+
"loss": 0.3506,
|
| 2536 |
+
"step": 1800
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.9725215517241379,
|
| 2540 |
+
"grad_norm": 2.12551984941854,
|
| 2541 |
+
"learning_rate": 2.299397268446413e-08,
|
| 2542 |
+
"loss": 0.3425,
|
| 2543 |
+
"step": 1805
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.9752155172413793,
|
| 2547 |
+
"grad_norm": 2.4278727464472136,
|
| 2548 |
+
"learning_rate": 1.8709037612003044e-08,
|
| 2549 |
+
"loss": 0.3471,
|
| 2550 |
+
"step": 1810
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.9779094827586207,
|
| 2554 |
+
"grad_norm": 2.191866602098634,
|
| 2555 |
+
"learning_rate": 1.4864805045373687e-08,
|
| 2556 |
+
"loss": 0.3384,
|
| 2557 |
+
"step": 1815
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.9806034482758621,
|
| 2561 |
+
"grad_norm": 2.128906961450063,
|
| 2562 |
+
"learning_rate": 1.1461615089770062e-08,
|
| 2563 |
+
"loss": 0.349,
|
| 2564 |
+
"step": 1820
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.9832974137931034,
|
| 2568 |
+
"grad_norm": 2.0846719469136916,
|
| 2569 |
+
"learning_rate": 8.499768830663723e-09,
|
| 2570 |
+
"loss": 0.3357,
|
| 2571 |
+
"step": 1825
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.9859913793103449,
|
| 2575 |
+
"grad_norm": 2.319036063763146,
|
| 2576 |
+
"learning_rate": 5.979528307168414e-09,
|
| 2577 |
+
"loss": 0.3402,
|
| 2578 |
+
"step": 1830
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.9886853448275862,
|
| 2582 |
+
"grad_norm": 2.0237346794749858,
|
| 2583 |
+
"learning_rate": 3.901116488855827e-09,
|
| 2584 |
+
"loss": 0.3554,
|
| 2585 |
+
"step": 1835
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.9913793103448276,
|
| 2589 |
+
"grad_norm": 2.007135214089839,
|
| 2590 |
+
"learning_rate": 2.264717256030835e-09,
|
| 2591 |
+
"loss": 0.3462,
|
| 2592 |
+
"step": 1840
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.994073275862069,
|
| 2596 |
+
"grad_norm": 1.994084875393067,
|
| 2597 |
+
"learning_rate": 1.0704753834600567e-09,
|
| 2598 |
+
"loss": 0.3455,
|
| 2599 |
+
"step": 1845
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.9967672413793104,
|
| 2603 |
+
"grad_norm": 2.1211709513233856,
|
| 2604 |
+
"learning_rate": 3.184965275676577e-10,
|
| 2605 |
+
"loss": 0.3438,
|
| 2606 |
+
"step": 1850
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.9994612068965517,
|
| 2610 |
+
"grad_norm": 2.0397937800653443,
|
| 2611 |
+
"learning_rate": 8.847217084495541e-12,
|
| 2612 |
+
"loss": 0.3482,
|
| 2613 |
+
"step": 1855
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 1.0,
|
| 2617 |
+
"eval_runtime": 3.3988,
|
| 2618 |
+
"eval_samples_per_second": 2.942,
|
| 2619 |
+
"eval_steps_per_second": 0.883,
|
| 2620 |
+
"step": 1856
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 1.0,
|
| 2624 |
+
"step": 1856,
|
| 2625 |
+
"total_flos": 194304320471040.0,
|
| 2626 |
+
"train_loss": 0.50882549257949,
|
| 2627 |
+
"train_runtime": 16510.7518,
|
| 2628 |
+
"train_samples_per_second": 1.799,
|
| 2629 |
+
"train_steps_per_second": 0.112
|
| 2630 |
+
}
|
| 2631 |
+
],
|
| 2632 |
+
"logging_steps": 5,
|
| 2633 |
+
"max_steps": 1856,
|
| 2634 |
+
"num_input_tokens_seen": 0,
|
| 2635 |
+
"num_train_epochs": 1,
|
| 2636 |
+
"save_steps": 100,
|
| 2637 |
+
"stateful_callbacks": {
|
| 2638 |
+
"TrainerControl": {
|
| 2639 |
+
"args": {
|
| 2640 |
+
"should_epoch_stop": false,
|
| 2641 |
+
"should_evaluate": false,
|
| 2642 |
+
"should_log": false,
|
| 2643 |
+
"should_save": true,
|
| 2644 |
+
"should_training_stop": true
|
| 2645 |
+
},
|
| 2646 |
+
"attributes": {}
|
| 2647 |
+
}
|
| 2648 |
+
},
|
| 2649 |
+
"total_flos": 194304320471040.0,
|
| 2650 |
+
"train_batch_size": 4,
|
| 2651 |
+
"trial_name": null,
|
| 2652 |
+
"trial_params": null
|
| 2653 |
+
}
|