Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep09_20-07-18_COE-CS-sv003/events.out.tfevents.1725912462.COE-CS-sv003.860391.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1744 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: preference_p0.2_seed42_level2_raremix
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# preference_p0.2_seed42_level2_raremix
|
| 19 |
+
|
| 20 |
+
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 generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3221
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 4
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 1
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 59 |
+
| 0.3409 | 0.9996 | 1206 | 0.3221 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.43.4
|
| 65 |
+
- Pytorch 2.3.1+cu121
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995855781185247,
|
| 3 |
+
"total_flos": 252407174922240.0,
|
| 4 |
+
"train_loss": 0.5270945630461027,
|
| 5 |
+
"train_runtime": 23848.9709,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.619,
|
| 8 |
+
"train_steps_per_second": 0.051
|
| 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": "4.43.4"
|
| 6 |
+
}
|
runs/Sep09_20-07-18_COE-CS-sv003/events.out.tfevents.1725912462.COE-CS-sv003.860391.0
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 sha256:303fda33d0bbbc808747b8f3ffe6c17bd133038fc2acc1fd141e953ad84a2038
|
| 3 |
+
size 56823
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995855781185247,
|
| 3 |
+
"total_flos": 252407174922240.0,
|
| 4 |
+
"train_loss": 0.5270945630461027,
|
| 5 |
+
"train_runtime": 23848.9709,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.619,
|
| 8 |
+
"train_steps_per_second": 0.051
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995855781185247,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1206,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0008288437629506838,
|
| 13 |
+
"grad_norm": 23.821738606267694,
|
| 14 |
+
"learning_rate": 8.264462809917357e-08,
|
| 15 |
+
"loss": 1.4077,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004144218814753419,
|
| 20 |
+
"grad_norm": 22.834257268242467,
|
| 21 |
+
"learning_rate": 4.132231404958678e-07,
|
| 22 |
+
"loss": 1.4048,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.008288437629506838,
|
| 27 |
+
"grad_norm": 8.208014337309038,
|
| 28 |
+
"learning_rate": 8.264462809917356e-07,
|
| 29 |
+
"loss": 1.3206,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012432656444260257,
|
| 34 |
+
"grad_norm": 10.88562979999232,
|
| 35 |
+
"learning_rate": 1.2396694214876035e-06,
|
| 36 |
+
"loss": 1.1572,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016576875259013676,
|
| 41 |
+
"grad_norm": 3.02410216068558,
|
| 42 |
+
"learning_rate": 1.6528925619834712e-06,
|
| 43 |
+
"loss": 1.0108,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.020721094073767096,
|
| 48 |
+
"grad_norm": 2.9630819683565868,
|
| 49 |
+
"learning_rate": 2.066115702479339e-06,
|
| 50 |
+
"loss": 0.9599,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.024865312888520515,
|
| 55 |
+
"grad_norm": 2.450927822041959,
|
| 56 |
+
"learning_rate": 2.479338842975207e-06,
|
| 57 |
+
"loss": 0.9202,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.029009531703273934,
|
| 62 |
+
"grad_norm": 2.241659288093002,
|
| 63 |
+
"learning_rate": 2.8925619834710743e-06,
|
| 64 |
+
"loss": 0.9075,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03315375051802735,
|
| 69 |
+
"grad_norm": 2.2795745210790708,
|
| 70 |
+
"learning_rate": 3.3057851239669424e-06,
|
| 71 |
+
"loss": 0.8904,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03729796933278077,
|
| 76 |
+
"grad_norm": 2.2916121960785274,
|
| 77 |
+
"learning_rate": 3.71900826446281e-06,
|
| 78 |
+
"loss": 0.8778,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04144218814753419,
|
| 83 |
+
"grad_norm": 3.0108486369173444,
|
| 84 |
+
"learning_rate": 4.132231404958678e-06,
|
| 85 |
+
"loss": 0.8811,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04558640696228761,
|
| 90 |
+
"grad_norm": 2.34463490002114,
|
| 91 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 92 |
+
"loss": 0.8644,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04973062577704103,
|
| 97 |
+
"grad_norm": 2.2048136988502836,
|
| 98 |
+
"learning_rate": 4.958677685950414e-06,
|
| 99 |
+
"loss": 0.8658,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.053874844591794445,
|
| 104 |
+
"grad_norm": 2.360407044698775,
|
| 105 |
+
"learning_rate": 5.371900826446281e-06,
|
| 106 |
+
"loss": 0.8483,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.05801906340654787,
|
| 111 |
+
"grad_norm": 2.3750627177827437,
|
| 112 |
+
"learning_rate": 5.785123966942149e-06,
|
| 113 |
+
"loss": 0.829,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06216328222130128,
|
| 118 |
+
"grad_norm": 2.5351719045640424,
|
| 119 |
+
"learning_rate": 6.198347107438017e-06,
|
| 120 |
+
"loss": 0.8457,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.0663075010360547,
|
| 125 |
+
"grad_norm": 2.4658487406561163,
|
| 126 |
+
"learning_rate": 6.611570247933885e-06,
|
| 127 |
+
"loss": 0.8295,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07045171985080813,
|
| 132 |
+
"grad_norm": 2.552123954872006,
|
| 133 |
+
"learning_rate": 7.0247933884297525e-06,
|
| 134 |
+
"loss": 0.8248,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07459593866556154,
|
| 139 |
+
"grad_norm": 2.5523240708243984,
|
| 140 |
+
"learning_rate": 7.43801652892562e-06,
|
| 141 |
+
"loss": 0.8073,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07874015748031496,
|
| 146 |
+
"grad_norm": 2.6557558002422343,
|
| 147 |
+
"learning_rate": 7.851239669421489e-06,
|
| 148 |
+
"loss": 0.8227,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08288437629506838,
|
| 153 |
+
"grad_norm": 2.5132033700665164,
|
| 154 |
+
"learning_rate": 8.264462809917356e-06,
|
| 155 |
+
"loss": 0.803,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.0870285951098218,
|
| 160 |
+
"grad_norm": 2.720513367073119,
|
| 161 |
+
"learning_rate": 8.677685950413224e-06,
|
| 162 |
+
"loss": 0.8023,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09117281392457521,
|
| 167 |
+
"grad_norm": 2.9809398097562543,
|
| 168 |
+
"learning_rate": 9.090909090909091e-06,
|
| 169 |
+
"loss": 0.7967,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.09531703273932864,
|
| 174 |
+
"grad_norm": 2.6852876988337564,
|
| 175 |
+
"learning_rate": 9.50413223140496e-06,
|
| 176 |
+
"loss": 0.8083,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09946125155408206,
|
| 181 |
+
"grad_norm": 2.4634580540100686,
|
| 182 |
+
"learning_rate": 9.917355371900828e-06,
|
| 183 |
+
"loss": 0.7892,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.10360547036883548,
|
| 188 |
+
"grad_norm": 2.583731945309341,
|
| 189 |
+
"learning_rate": 9.999664652243188e-06,
|
| 190 |
+
"loss": 0.8053,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.10774968918358889,
|
| 195 |
+
"grad_norm": 2.6768428928051873,
|
| 196 |
+
"learning_rate": 9.99830237907608e-06,
|
| 197 |
+
"loss": 0.7899,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11189390799834231,
|
| 202 |
+
"grad_norm": 2.550586632842143,
|
| 203 |
+
"learning_rate": 9.995892506564461e-06,
|
| 204 |
+
"loss": 0.7825,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11603812681309573,
|
| 209 |
+
"grad_norm": 2.50256712970827,
|
| 210 |
+
"learning_rate": 9.992435539796e-06,
|
| 211 |
+
"loss": 0.7693,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12018234562784914,
|
| 216 |
+
"grad_norm": 2.542375468259113,
|
| 217 |
+
"learning_rate": 9.987932203319917e-06,
|
| 218 |
+
"loss": 0.7716,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12432656444260257,
|
| 223 |
+
"grad_norm": 2.354650001491699,
|
| 224 |
+
"learning_rate": 9.982383440995146e-06,
|
| 225 |
+
"loss": 0.7789,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.12847078325735597,
|
| 230 |
+
"grad_norm": 2.680500650181213,
|
| 231 |
+
"learning_rate": 9.975790415792497e-06,
|
| 232 |
+
"loss": 0.772,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1326150020721094,
|
| 237 |
+
"grad_norm": 2.8324037133090827,
|
| 238 |
+
"learning_rate": 9.968154509550914e-06,
|
| 239 |
+
"loss": 0.7574,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.13675922088686282,
|
| 244 |
+
"grad_norm": 3.314558520418501,
|
| 245 |
+
"learning_rate": 9.959477322687852e-06,
|
| 246 |
+
"loss": 0.7434,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14090343970161626,
|
| 251 |
+
"grad_norm": 2.558536518840115,
|
| 252 |
+
"learning_rate": 9.949760673863846e-06,
|
| 253 |
+
"loss": 0.7454,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.14504765851636967,
|
| 258 |
+
"grad_norm": 2.6087877711239247,
|
| 259 |
+
"learning_rate": 9.93900659960133e-06,
|
| 260 |
+
"loss": 0.7488,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14919187733112307,
|
| 265 |
+
"grad_norm": 2.4922551536546416,
|
| 266 |
+
"learning_rate": 9.927217353857809e-06,
|
| 267 |
+
"loss": 0.7453,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.1533360961458765,
|
| 272 |
+
"grad_norm": 2.4983517636117782,
|
| 273 |
+
"learning_rate": 9.914395407553444e-06,
|
| 274 |
+
"loss": 0.7441,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15748031496062992,
|
| 279 |
+
"grad_norm": 2.493536518057786,
|
| 280 |
+
"learning_rate": 9.900543448053164e-06,
|
| 281 |
+
"loss": 0.7435,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16162453377538333,
|
| 286 |
+
"grad_norm": 2.361368540133534,
|
| 287 |
+
"learning_rate": 9.885664378603432e-06,
|
| 288 |
+
"loss": 0.7216,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16576875259013676,
|
| 293 |
+
"grad_norm": 2.2001360959731486,
|
| 294 |
+
"learning_rate": 9.869761317723744e-06,
|
| 295 |
+
"loss": 0.728,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.16991297140489017,
|
| 300 |
+
"grad_norm": 2.305194442427537,
|
| 301 |
+
"learning_rate": 9.85283759855301e-06,
|
| 302 |
+
"loss": 0.7263,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1740571902196436,
|
| 307 |
+
"grad_norm": 2.208332719886559,
|
| 308 |
+
"learning_rate": 9.834896768150963e-06,
|
| 309 |
+
"loss": 0.7139,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.17820140903439702,
|
| 314 |
+
"grad_norm": 2.3264002622179887,
|
| 315 |
+
"learning_rate": 9.81594258675473e-06,
|
| 316 |
+
"loss": 0.7223,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18234562784915043,
|
| 321 |
+
"grad_norm": 2.3609080234642983,
|
| 322 |
+
"learning_rate": 9.795979026990717e-06,
|
| 323 |
+
"loss": 0.7031,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.18648984666390386,
|
| 328 |
+
"grad_norm": 2.3331179014344055,
|
| 329 |
+
"learning_rate": 9.775010273041975e-06,
|
| 330 |
+
"loss": 0.715,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.19063406547865727,
|
| 335 |
+
"grad_norm": 2.4595571627938724,
|
| 336 |
+
"learning_rate": 9.753040719771249e-06,
|
| 337 |
+
"loss": 0.7084,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.19477828429341068,
|
| 342 |
+
"grad_norm": 2.5273928971647823,
|
| 343 |
+
"learning_rate": 9.730074971799837e-06,
|
| 344 |
+
"loss": 0.6928,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19892250310816412,
|
| 349 |
+
"grad_norm": 2.4481147916191324,
|
| 350 |
+
"learning_rate": 9.706117842542517e-06,
|
| 351 |
+
"loss": 0.684,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.20306672192291753,
|
| 356 |
+
"grad_norm": 2.396714983793178,
|
| 357 |
+
"learning_rate": 9.681174353198687e-06,
|
| 358 |
+
"loss": 0.6942,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.20721094073767096,
|
| 363 |
+
"grad_norm": 2.23212792235539,
|
| 364 |
+
"learning_rate": 9.655249731699973e-06,
|
| 365 |
+
"loss": 0.6846,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.21135515955242437,
|
| 370 |
+
"grad_norm": 2.33058592821463,
|
| 371 |
+
"learning_rate": 9.628349411614503e-06,
|
| 372 |
+
"loss": 0.6819,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21549937836717778,
|
| 377 |
+
"grad_norm": 2.3204394270788966,
|
| 378 |
+
"learning_rate": 9.600479031008072e-06,
|
| 379 |
+
"loss": 0.6773,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.21964359718193122,
|
| 384 |
+
"grad_norm": 2.2382725360662308,
|
| 385 |
+
"learning_rate": 9.571644431262463e-06,
|
| 386 |
+
"loss": 0.6649,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22378781599668462,
|
| 391 |
+
"grad_norm": 2.2039133108908184,
|
| 392 |
+
"learning_rate": 9.54185165585114e-06,
|
| 393 |
+
"loss": 0.6537,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.22793203481143803,
|
| 398 |
+
"grad_norm": 2.4253359596794337,
|
| 399 |
+
"learning_rate": 9.511106949072588e-06,
|
| 400 |
+
"loss": 0.6621,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.23207625362619147,
|
| 405 |
+
"grad_norm": 2.4527370719290915,
|
| 406 |
+
"learning_rate": 9.479416754741577e-06,
|
| 407 |
+
"loss": 0.6694,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.23622047244094488,
|
| 412 |
+
"grad_norm": 2.3817761190945514,
|
| 413 |
+
"learning_rate": 9.446787714838579e-06,
|
| 414 |
+
"loss": 0.6594,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.2403646912556983,
|
| 419 |
+
"grad_norm": 2.2516467162015594,
|
| 420 |
+
"learning_rate": 9.413226668117679e-06,
|
| 421 |
+
"loss": 0.6535,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.24450891007045172,
|
| 426 |
+
"grad_norm": 2.516472366579631,
|
| 427 |
+
"learning_rate": 9.37874064867323e-06,
|
| 428 |
+
"loss": 0.6558,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24865312888520513,
|
| 433 |
+
"grad_norm": 2.4095497698840336,
|
| 434 |
+
"learning_rate": 9.343336884465577e-06,
|
| 435 |
+
"loss": 0.6456,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.25279734769995854,
|
| 440 |
+
"grad_norm": 2.4199182947381024,
|
| 441 |
+
"learning_rate": 9.307022795806125e-06,
|
| 442 |
+
"loss": 0.6406,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25694156651471195,
|
| 447 |
+
"grad_norm": 2.282073481167692,
|
| 448 |
+
"learning_rate": 9.26980599380213e-06,
|
| 449 |
+
"loss": 0.6339,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2610857853294654,
|
| 454 |
+
"grad_norm": 2.441801633470137,
|
| 455 |
+
"learning_rate": 9.231694278761455e-06,
|
| 456 |
+
"loss": 0.6326,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2652300041442188,
|
| 461 |
+
"grad_norm": 12.39175458554138,
|
| 462 |
+
"learning_rate": 9.192695638557723e-06,
|
| 463 |
+
"loss": 0.6356,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.26937422295897223,
|
| 468 |
+
"grad_norm": 2.5618372097096525,
|
| 469 |
+
"learning_rate": 9.1528182469561e-06,
|
| 470 |
+
"loss": 0.6252,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.27351844177372564,
|
| 475 |
+
"grad_norm": 2.4608597563280967,
|
| 476 |
+
"learning_rate": 9.112070461900178e-06,
|
| 477 |
+
"loss": 0.6119,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.27766266058847905,
|
| 482 |
+
"grad_norm": 2.312033920022348,
|
| 483 |
+
"learning_rate": 9.070460823760197e-06,
|
| 484 |
+
"loss": 0.6216,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.2818068794032325,
|
| 489 |
+
"grad_norm": 2.2955010300704344,
|
| 490 |
+
"learning_rate": 9.027998053543079e-06,
|
| 491 |
+
"loss": 0.6216,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.2859510982179859,
|
| 496 |
+
"grad_norm": 2.2889198622068783,
|
| 497 |
+
"learning_rate": 8.984691051064576e-06,
|
| 498 |
+
"loss": 0.6104,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.29009531703273933,
|
| 503 |
+
"grad_norm": 2.2147528522580844,
|
| 504 |
+
"learning_rate": 8.94054889308395e-06,
|
| 505 |
+
"loss": 0.6096,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.29423953584749274,
|
| 510 |
+
"grad_norm": 2.3586059493212814,
|
| 511 |
+
"learning_rate": 8.895580831401563e-06,
|
| 512 |
+
"loss": 0.6126,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.29838375466224615,
|
| 517 |
+
"grad_norm": 2.7570148244223924,
|
| 518 |
+
"learning_rate": 8.849796290919787e-06,
|
| 519 |
+
"loss": 0.6102,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3025279734769996,
|
| 524 |
+
"grad_norm": 2.2730196820740667,
|
| 525 |
+
"learning_rate": 8.803204867667624e-06,
|
| 526 |
+
"loss": 0.6037,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.306672192291753,
|
| 531 |
+
"grad_norm": 2.27164079566725,
|
| 532 |
+
"learning_rate": 8.755816326789469e-06,
|
| 533 |
+
"loss": 0.601,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.31081641110650643,
|
| 538 |
+
"grad_norm": 2.2763704686366557,
|
| 539 |
+
"learning_rate": 8.70764060049842e-06,
|
| 540 |
+
"loss": 0.5829,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.31496062992125984,
|
| 545 |
+
"grad_norm": 2.265603504905875,
|
| 546 |
+
"learning_rate": 8.658687785994579e-06,
|
| 547 |
+
"loss": 0.5957,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.31910484873601325,
|
| 552 |
+
"grad_norm": 2.4701408773246203,
|
| 553 |
+
"learning_rate": 8.608968143348765e-06,
|
| 554 |
+
"loss": 0.5846,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.32324906755076666,
|
| 559 |
+
"grad_norm": 2.2590604345543897,
|
| 560 |
+
"learning_rate": 8.558492093352098e-06,
|
| 561 |
+
"loss": 0.5948,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3273932863655201,
|
| 566 |
+
"grad_norm": 2.112110217235179,
|
| 567 |
+
"learning_rate": 8.50727021533189e-06,
|
| 568 |
+
"loss": 0.5897,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.33153750518027353,
|
| 573 |
+
"grad_norm": 2.2220762245644297,
|
| 574 |
+
"learning_rate": 8.455313244934324e-06,
|
| 575 |
+
"loss": 0.5686,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.33568172399502694,
|
| 580 |
+
"grad_norm": 2.4588674796101087,
|
| 581 |
+
"learning_rate": 8.402632071874348e-06,
|
| 582 |
+
"loss": 0.5791,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.33982594280978035,
|
| 587 |
+
"grad_norm": 2.120301054281535,
|
| 588 |
+
"learning_rate": 8.349237737653288e-06,
|
| 589 |
+
"loss": 0.5761,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.34397016162453375,
|
| 594 |
+
"grad_norm": 2.27000349226283,
|
| 595 |
+
"learning_rate": 8.29514143324466e-06,
|
| 596 |
+
"loss": 0.5664,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.3481143804392872,
|
| 601 |
+
"grad_norm": 2.209196060426881,
|
| 602 |
+
"learning_rate": 8.24035449674863e-06,
|
| 603 |
+
"loss": 0.5598,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.3522585992540406,
|
| 608 |
+
"grad_norm": 2.765263815929266,
|
| 609 |
+
"learning_rate": 8.184888411015655e-06,
|
| 610 |
+
"loss": 0.5571,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.35640281806879404,
|
| 615 |
+
"grad_norm": 2.3926237887826405,
|
| 616 |
+
"learning_rate": 8.128754801239781e-06,
|
| 617 |
+
"loss": 0.556,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.36054703688354744,
|
| 622 |
+
"grad_norm": 2.4696018462025506,
|
| 623 |
+
"learning_rate": 8.071965432522107e-06,
|
| 624 |
+
"loss": 0.5614,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.36469125569830085,
|
| 629 |
+
"grad_norm": 2.2772583844160614,
|
| 630 |
+
"learning_rate": 8.01453220740492e-06,
|
| 631 |
+
"loss": 0.5521,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.36883547451305426,
|
| 636 |
+
"grad_norm": 2.374847612226747,
|
| 637 |
+
"learning_rate": 7.956467163377037e-06,
|
| 638 |
+
"loss": 0.5495,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3729796933278077,
|
| 643 |
+
"grad_norm": 2.2043358974290386,
|
| 644 |
+
"learning_rate": 7.89778247035085e-06,
|
| 645 |
+
"loss": 0.5427,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.37712391214256114,
|
| 650 |
+
"grad_norm": 2.331068862386996,
|
| 651 |
+
"learning_rate": 7.838490428111625e-06,
|
| 652 |
+
"loss": 0.5449,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.38126813095731454,
|
| 657 |
+
"grad_norm": 2.2139576546877713,
|
| 658 |
+
"learning_rate": 7.77860346373957e-06,
|
| 659 |
+
"loss": 0.5561,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.38541234977206795,
|
| 664 |
+
"grad_norm": 2.1991958487671655,
|
| 665 |
+
"learning_rate": 7.718134129005238e-06,
|
| 666 |
+
"loss": 0.5419,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38955656858682136,
|
| 671 |
+
"grad_norm": 2.1821797937738396,
|
| 672 |
+
"learning_rate": 7.657095097738793e-06,
|
| 673 |
+
"loss": 0.5451,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3937007874015748,
|
| 678 |
+
"grad_norm": 2.2186951662903063,
|
| 679 |
+
"learning_rate": 7.59549916317367e-06,
|
| 680 |
+
"loss": 0.5347,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.39784500621632823,
|
| 685 |
+
"grad_norm": 2.3212871580558287,
|
| 686 |
+
"learning_rate": 7.533359235265248e-06,
|
| 687 |
+
"loss": 0.5382,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.40198922503108164,
|
| 692 |
+
"grad_norm": 2.1540998726161753,
|
| 693 |
+
"learning_rate": 7.470688337985029e-06,
|
| 694 |
+
"loss": 0.5212,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.40613344384583505,
|
| 699 |
+
"grad_norm": 2.1735121794127132,
|
| 700 |
+
"learning_rate": 7.407499606590934e-06,
|
| 701 |
+
"loss": 0.5312,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.41027766266058846,
|
| 706 |
+
"grad_norm": 2.173386732621735,
|
| 707 |
+
"learning_rate": 7.343806284874268e-06,
|
| 708 |
+
"loss": 0.5273,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4144218814753419,
|
| 713 |
+
"grad_norm": 2.127262862741766,
|
| 714 |
+
"learning_rate": 7.279621722383939e-06,
|
| 715 |
+
"loss": 0.5145,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.41856610029009533,
|
| 720 |
+
"grad_norm": 2.146219494441019,
|
| 721 |
+
"learning_rate": 7.214959371628522e-06,
|
| 722 |
+
"loss": 0.5225,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.42271031910484874,
|
| 727 |
+
"grad_norm": 2.046689251344904,
|
| 728 |
+
"learning_rate": 7.149832785256718e-06,
|
| 729 |
+
"loss": 0.511,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.42685453791960215,
|
| 734 |
+
"grad_norm": 2.1558137201613423,
|
| 735 |
+
"learning_rate": 7.084255613216855e-06,
|
| 736 |
+
"loss": 0.5103,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.43099875673435556,
|
| 741 |
+
"grad_norm": 2.240438771177761,
|
| 742 |
+
"learning_rate": 7.018241599895974e-06,
|
| 743 |
+
"loss": 0.5187,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.43514297554910897,
|
| 748 |
+
"grad_norm": 2.1251451886790775,
|
| 749 |
+
"learning_rate": 6.95180458123913e-06,
|
| 750 |
+
"loss": 0.509,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.43928719436386243,
|
| 755 |
+
"grad_norm": 2.1265555528429743,
|
| 756 |
+
"learning_rate": 6.8849584818494984e-06,
|
| 757 |
+
"loss": 0.5133,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.44343141317861584,
|
| 762 |
+
"grad_norm": 2.1752821858955143,
|
| 763 |
+
"learning_rate": 6.817717312069913e-06,
|
| 764 |
+
"loss": 0.5102,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.44757563199336925,
|
| 769 |
+
"grad_norm": 1.9742904998884219,
|
| 770 |
+
"learning_rate": 6.750095165046415e-06,
|
| 771 |
+
"loss": 0.4997,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.45171985080812266,
|
| 776 |
+
"grad_norm": 2.131305839198853,
|
| 777 |
+
"learning_rate": 6.682106213774459e-06,
|
| 778 |
+
"loss": 0.5023,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.45586406962287607,
|
| 783 |
+
"grad_norm": 2.31125121725231,
|
| 784 |
+
"learning_rate": 6.6137647081283776e-06,
|
| 785 |
+
"loss": 0.4836,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.46000828843762953,
|
| 790 |
+
"grad_norm": 2.2445463529407705,
|
| 791 |
+
"learning_rate": 6.545084971874738e-06,
|
| 792 |
+
"loss": 0.5052,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.46415250725238294,
|
| 797 |
+
"grad_norm": 2.0590014501028078,
|
| 798 |
+
"learning_rate": 6.476081399670212e-06,
|
| 799 |
+
"loss": 0.4769,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.46829672606713635,
|
| 804 |
+
"grad_norm": 2.1235457676935554,
|
| 805 |
+
"learning_rate": 6.406768454044581e-06,
|
| 806 |
+
"loss": 0.482,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.47244094488188976,
|
| 811 |
+
"grad_norm": 2.245932227710593,
|
| 812 |
+
"learning_rate": 6.337160662369519e-06,
|
| 813 |
+
"loss": 0.4797,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.47658516369664317,
|
| 818 |
+
"grad_norm": 2.4691296526493414,
|
| 819 |
+
"learning_rate": 6.267272613813789e-06,
|
| 820 |
+
"loss": 0.48,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.4807293825113966,
|
| 825 |
+
"grad_norm": 2.0821407072798377,
|
| 826 |
+
"learning_rate": 6.19711895628548e-06,
|
| 827 |
+
"loss": 0.4775,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.48487360132615004,
|
| 832 |
+
"grad_norm": 2.2231462845429553,
|
| 833 |
+
"learning_rate": 6.126714393361939e-06,
|
| 834 |
+
"loss": 0.4791,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.48901782014090345,
|
| 839 |
+
"grad_norm": 2.2327431903192756,
|
| 840 |
+
"learning_rate": 6.056073681208038e-06,
|
| 841 |
+
"loss": 0.4687,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.49316203895565686,
|
| 846 |
+
"grad_norm": 2.171485152388387,
|
| 847 |
+
"learning_rate": 5.985211625483403e-06,
|
| 848 |
+
"loss": 0.4773,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.49730625777041026,
|
| 853 |
+
"grad_norm": 2.383751329793211,
|
| 854 |
+
"learning_rate": 5.914143078239293e-06,
|
| 855 |
+
"loss": 0.4841,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5014504765851637,
|
| 860 |
+
"grad_norm": 2.1730844882589158,
|
| 861 |
+
"learning_rate": 5.842882934805731e-06,
|
| 862 |
+
"loss": 0.479,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5055946953999171,
|
| 867 |
+
"grad_norm": 2.072456765223728,
|
| 868 |
+
"learning_rate": 5.771446130669589e-06,
|
| 869 |
+
"loss": 0.4683,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5097389142146705,
|
| 874 |
+
"grad_norm": 2.048482336533146,
|
| 875 |
+
"learning_rate": 5.6998476383442345e-06,
|
| 876 |
+
"loss": 0.4698,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5138831330294239,
|
| 881 |
+
"grad_norm": 2.3268647107802702,
|
| 882 |
+
"learning_rate": 5.628102464231429e-06,
|
| 883 |
+
"loss": 0.4667,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5180273518441774,
|
| 888 |
+
"grad_norm": 2.15935166681747,
|
| 889 |
+
"learning_rate": 5.556225645476119e-06,
|
| 890 |
+
"loss": 0.4719,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5221715706589308,
|
| 895 |
+
"grad_norm": 2.2554049828411835,
|
| 896 |
+
"learning_rate": 5.4842322468147926e-06,
|
| 897 |
+
"loss": 0.4627,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5263157894736842,
|
| 902 |
+
"grad_norm": 2.16547540035252,
|
| 903 |
+
"learning_rate": 5.412137357418037e-06,
|
| 904 |
+
"loss": 0.4542,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5304600082884376,
|
| 909 |
+
"grad_norm": 2.205449973964332,
|
| 910 |
+
"learning_rate": 5.339956087727985e-06,
|
| 911 |
+
"loss": 0.4638,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.534604227103191,
|
| 916 |
+
"grad_norm": 2.046592350153715,
|
| 917 |
+
"learning_rate": 5.2677035662913116e-06,
|
| 918 |
+
"loss": 0.4504,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5387484459179445,
|
| 923 |
+
"grad_norm": 2.1937309067407114,
|
| 924 |
+
"learning_rate": 5.195394936588409e-06,
|
| 925 |
+
"loss": 0.4401,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.5428926647326979,
|
| 930 |
+
"grad_norm": 2.2350791342967797,
|
| 931 |
+
"learning_rate": 5.123045353859465e-06,
|
| 932 |
+
"loss": 0.4508,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5470368835474513,
|
| 937 |
+
"grad_norm": 2.1319372468329645,
|
| 938 |
+
"learning_rate": 5.050669981928056e-06,
|
| 939 |
+
"loss": 0.4521,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.5511811023622047,
|
| 944 |
+
"grad_norm": 2.130774233274741,
|
| 945 |
+
"learning_rate": 4.978283990022936e-06,
|
| 946 |
+
"loss": 0.4493,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.5553253211769581,
|
| 951 |
+
"grad_norm": 2.008484642041683,
|
| 952 |
+
"learning_rate": 4.905902549598719e-06,
|
| 953 |
+
"loss": 0.4325,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.5594695399917116,
|
| 958 |
+
"grad_norm": 2.0574926912311344,
|
| 959 |
+
"learning_rate": 4.833540831156062e-06,
|
| 960 |
+
"loss": 0.4453,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.563613758806465,
|
| 965 |
+
"grad_norm": 2.2090128918878174,
|
| 966 |
+
"learning_rate": 4.761214001062079e-06,
|
| 967 |
+
"loss": 0.4353,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.5677579776212184,
|
| 972 |
+
"grad_norm": 2.0771401122898197,
|
| 973 |
+
"learning_rate": 4.688937218371592e-06,
|
| 974 |
+
"loss": 0.4322,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.5719021964359718,
|
| 979 |
+
"grad_norm": 2.091649616042253,
|
| 980 |
+
"learning_rate": 4.616725631649938e-06,
|
| 981 |
+
"loss": 0.4353,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.5760464152507252,
|
| 986 |
+
"grad_norm": 2.140897800881621,
|
| 987 |
+
"learning_rate": 4.544594375797969e-06,
|
| 988 |
+
"loss": 0.4286,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.5801906340654787,
|
| 993 |
+
"grad_norm": 2.3556886559066887,
|
| 994 |
+
"learning_rate": 4.472558568879901e-06,
|
| 995 |
+
"loss": 0.4291,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.5843348528802321,
|
| 1000 |
+
"grad_norm": 2.061915937329502,
|
| 1001 |
+
"learning_rate": 4.400633308954713e-06,
|
| 1002 |
+
"loss": 0.4261,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.5884790716949855,
|
| 1007 |
+
"grad_norm": 2.1754455938746218,
|
| 1008 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 1009 |
+
"loss": 0.4263,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.5926232905097389,
|
| 1014 |
+
"grad_norm": 2.047663516312869,
|
| 1015 |
+
"learning_rate": 4.257174703311032e-06,
|
| 1016 |
+
"loss": 0.4326,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.5967675093244923,
|
| 1021 |
+
"grad_norm": 2.002919898924837,
|
| 1022 |
+
"learning_rate": 4.185671425229477e-06,
|
| 1023 |
+
"loss": 0.429,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6009117281392458,
|
| 1028 |
+
"grad_norm": 2.055858095540348,
|
| 1029 |
+
"learning_rate": 4.11433882311277e-06,
|
| 1030 |
+
"loss": 0.4227,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6050559469539992,
|
| 1035 |
+
"grad_norm": 2.098430357886563,
|
| 1036 |
+
"learning_rate": 4.043191847634469e-06,
|
| 1037 |
+
"loss": 0.4145,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6092001657687526,
|
| 1042 |
+
"grad_norm": 2.113187936891634,
|
| 1043 |
+
"learning_rate": 3.9722454105624545e-06,
|
| 1044 |
+
"loss": 0.421,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.613344384583506,
|
| 1049 |
+
"grad_norm": 2.1821256779062397,
|
| 1050 |
+
"learning_rate": 3.901514381633555e-06,
|
| 1051 |
+
"loss": 0.4095,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6174886033982594,
|
| 1056 |
+
"grad_norm": 2.087497370021808,
|
| 1057 |
+
"learning_rate": 3.831013585436985e-06,
|
| 1058 |
+
"loss": 0.4209,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6216328222130129,
|
| 1063 |
+
"grad_norm": 2.1375456510365654,
|
| 1064 |
+
"learning_rate": 3.7607577983072486e-06,
|
| 1065 |
+
"loss": 0.4123,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6257770410277662,
|
| 1070 |
+
"grad_norm": 2.1081763007416034,
|
| 1071 |
+
"learning_rate": 3.6907617452271394e-06,
|
| 1072 |
+
"loss": 0.4049,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.6299212598425197,
|
| 1077 |
+
"grad_norm": 2.1448026787250636,
|
| 1078 |
+
"learning_rate": 3.621040096741526e-06,
|
| 1079 |
+
"loss": 0.4159,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6340654786572731,
|
| 1084 |
+
"grad_norm": 2.1199166483261824,
|
| 1085 |
+
"learning_rate": 3.55160746588254e-06,
|
| 1086 |
+
"loss": 0.4071,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6382096974720265,
|
| 1091 |
+
"grad_norm": 2.023385824501021,
|
| 1092 |
+
"learning_rate": 3.482478405106803e-06,
|
| 1093 |
+
"loss": 0.409,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.64235391628678,
|
| 1098 |
+
"grad_norm": 2.049301320892124,
|
| 1099 |
+
"learning_rate": 3.4136674032453787e-06,
|
| 1100 |
+
"loss": 0.4114,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6464981351015333,
|
| 1105 |
+
"grad_norm": 2.049238108716136,
|
| 1106 |
+
"learning_rate": 3.34518888246703e-06,
|
| 1107 |
+
"loss": 0.4051,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.6506423539162868,
|
| 1112 |
+
"grad_norm": 2.1220065162587036,
|
| 1113 |
+
"learning_rate": 3.2770571952554674e-06,
|
| 1114 |
+
"loss": 0.4012,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.6547865727310402,
|
| 1119 |
+
"grad_norm": 2.036047531360177,
|
| 1120 |
+
"learning_rate": 3.2092866214011984e-06,
|
| 1121 |
+
"loss": 0.4126,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.6589307915457936,
|
| 1126 |
+
"grad_norm": 2.1291206967434593,
|
| 1127 |
+
"learning_rate": 3.141891365008609e-06,
|
| 1128 |
+
"loss": 0.4119,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.6630750103605471,
|
| 1133 |
+
"grad_norm": 2.07461368161324,
|
| 1134 |
+
"learning_rate": 3.0748855515189104e-06,
|
| 1135 |
+
"loss": 0.3945,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.6672192291753004,
|
| 1140 |
+
"grad_norm": 1.9714918496227842,
|
| 1141 |
+
"learning_rate": 3.00828322474958e-06,
|
| 1142 |
+
"loss": 0.3954,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.6713634479900539,
|
| 1147 |
+
"grad_norm": 3.9519332717986444,
|
| 1148 |
+
"learning_rate": 2.942098343950891e-06,
|
| 1149 |
+
"loss": 0.4031,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.6755076668048073,
|
| 1154 |
+
"grad_norm": 2.1077325411543293,
|
| 1155 |
+
"learning_rate": 2.8763447808801914e-06,
|
| 1156 |
+
"loss": 0.3884,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.6796518856195607,
|
| 1161 |
+
"grad_norm": 2.025521267691112,
|
| 1162 |
+
"learning_rate": 2.8110363168944976e-06,
|
| 1163 |
+
"loss": 0.394,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.6837961044343142,
|
| 1168 |
+
"grad_norm": 2.130847414216846,
|
| 1169 |
+
"learning_rate": 2.7461866400620506e-06,
|
| 1170 |
+
"loss": 0.3857,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.6879403232490675,
|
| 1175 |
+
"grad_norm": 2.0051322597023566,
|
| 1176 |
+
"learning_rate": 2.6818093422934254e-06,
|
| 1177 |
+
"loss": 0.3906,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.692084542063821,
|
| 1182 |
+
"grad_norm": 2.001609177757284,
|
| 1183 |
+
"learning_rate": 2.617917916492776e-06,
|
| 1184 |
+
"loss": 0.3921,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.6962287608785744,
|
| 1189 |
+
"grad_norm": 2.072211567891342,
|
| 1190 |
+
"learning_rate": 2.5545257537298497e-06,
|
| 1191 |
+
"loss": 0.3982,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7003729796933278,
|
| 1196 |
+
"grad_norm": 1.9935034929673958,
|
| 1197 |
+
"learning_rate": 2.491646140433346e-06,
|
| 1198 |
+
"loss": 0.3798,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7045171985080813,
|
| 1203 |
+
"grad_norm": 1.9339328870220762,
|
| 1204 |
+
"learning_rate": 2.4292922556061877e-06,
|
| 1205 |
+
"loss": 0.3853,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7086614173228346,
|
| 1210 |
+
"grad_norm": 2.1038621746542767,
|
| 1211 |
+
"learning_rate": 2.367477168063326e-06,
|
| 1212 |
+
"loss": 0.3817,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7128056361375881,
|
| 1217 |
+
"grad_norm": 2.0504707093576777,
|
| 1218 |
+
"learning_rate": 2.3062138336926406e-06,
|
| 1219 |
+
"loss": 0.3828,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7169498549523415,
|
| 1224 |
+
"grad_norm": 2.128613755893242,
|
| 1225 |
+
"learning_rate": 2.245515092739488e-06,
|
| 1226 |
+
"loss": 0.3854,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7210940737670949,
|
| 1231 |
+
"grad_norm": 2.021286433659744,
|
| 1232 |
+
"learning_rate": 2.185393667115513e-06,
|
| 1233 |
+
"loss": 0.3767,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7252382925818484,
|
| 1238 |
+
"grad_norm": 2.175790029610662,
|
| 1239 |
+
"learning_rate": 2.125862157732245e-06,
|
| 1240 |
+
"loss": 0.3752,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7293825113966017,
|
| 1245 |
+
"grad_norm": 2.055231327953937,
|
| 1246 |
+
"learning_rate": 2.066933041860059e-06,
|
| 1247 |
+
"loss": 0.3797,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.7335267302113552,
|
| 1252 |
+
"grad_norm": 2.0609885500688745,
|
| 1253 |
+
"learning_rate": 2.0086186705130545e-06,
|
| 1254 |
+
"loss": 0.3798,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.7376709490261085,
|
| 1259 |
+
"grad_norm": 1.9460493213850336,
|
| 1260 |
+
"learning_rate": 1.9509312658603954e-06,
|
| 1261 |
+
"loss": 0.3716,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.741815167840862,
|
| 1266 |
+
"grad_norm": 2.107550534612032,
|
| 1267 |
+
"learning_rate": 1.8938829186646484e-06,
|
| 1268 |
+
"loss": 0.3812,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.7459593866556155,
|
| 1273 |
+
"grad_norm": 1.9693264223542786,
|
| 1274 |
+
"learning_rate": 1.8374855857476687e-06,
|
| 1275 |
+
"loss": 0.371,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.7501036054703688,
|
| 1280 |
+
"grad_norm": 2.0116271854033188,
|
| 1281 |
+
"learning_rate": 1.7817510874845585e-06,
|
| 1282 |
+
"loss": 0.3705,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.7542478242851223,
|
| 1287 |
+
"grad_norm": 1.9693053868651615,
|
| 1288 |
+
"learning_rate": 1.7266911053262196e-06,
|
| 1289 |
+
"loss": 0.3676,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.7583920430998756,
|
| 1294 |
+
"grad_norm": 2.1020529435678186,
|
| 1295 |
+
"learning_rate": 1.6723171793510363e-06,
|
| 1296 |
+
"loss": 0.3737,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.7625362619146291,
|
| 1301 |
+
"grad_norm": 2.093530940289316,
|
| 1302 |
+
"learning_rate": 1.6186407058461622e-06,
|
| 1303 |
+
"loss": 0.3797,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.7666804807293826,
|
| 1308 |
+
"grad_norm": 2.0472605324094326,
|
| 1309 |
+
"learning_rate": 1.5656729349189742e-06,
|
| 1310 |
+
"loss": 0.3716,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.7708246995441359,
|
| 1315 |
+
"grad_norm": 2.0335898500157925,
|
| 1316 |
+
"learning_rate": 1.5134249681391416e-06,
|
| 1317 |
+
"loss": 0.3672,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.7749689183588894,
|
| 1322 |
+
"grad_norm": 1.9454457763257478,
|
| 1323 |
+
"learning_rate": 1.4619077562118477e-06,
|
| 1324 |
+
"loss": 0.368,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.7791131371736427,
|
| 1329 |
+
"grad_norm": 2.057587525250662,
|
| 1330 |
+
"learning_rate": 1.411132096682606e-06,
|
| 1331 |
+
"loss": 0.3694,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.7832573559883962,
|
| 1336 |
+
"grad_norm": 2.1292730946235934,
|
| 1337 |
+
"learning_rate": 1.3611086316742057e-06,
|
| 1338 |
+
"loss": 0.3595,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.7874015748031497,
|
| 1343 |
+
"grad_norm": 2.022478659877928,
|
| 1344 |
+
"learning_rate": 1.3118478456562073e-06,
|
| 1345 |
+
"loss": 0.3635,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.791545793617903,
|
| 1350 |
+
"grad_norm": 2.0367686920587857,
|
| 1351 |
+
"learning_rate": 1.2633600632474962e-06,
|
| 1352 |
+
"loss": 0.3593,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.7956900124326565,
|
| 1357 |
+
"grad_norm": 2.1462356201632065,
|
| 1358 |
+
"learning_rate": 1.2156554470523364e-06,
|
| 1359 |
+
"loss": 0.3589,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.7998342312474098,
|
| 1364 |
+
"grad_norm": 2.068674533072379,
|
| 1365 |
+
"learning_rate": 1.1687439955303764e-06,
|
| 1366 |
+
"loss": 0.3645,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8039784500621633,
|
| 1371 |
+
"grad_norm": 2.107218769695033,
|
| 1372 |
+
"learning_rate": 1.1226355409010686e-06,
|
| 1373 |
+
"loss": 0.3629,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8081226688769167,
|
| 1378 |
+
"grad_norm": 2.1600739342990427,
|
| 1379 |
+
"learning_rate": 1.0773397470829145e-06,
|
| 1380 |
+
"loss": 0.3509,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8122668876916701,
|
| 1385 |
+
"grad_norm": 2.056346466443948,
|
| 1386 |
+
"learning_rate": 1.032866107667999e-06,
|
| 1387 |
+
"loss": 0.3642,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.8164111065064236,
|
| 1392 |
+
"grad_norm": 2.055999415717534,
|
| 1393 |
+
"learning_rate": 9.892239439322243e-07,
|
| 1394 |
+
"loss": 0.3608,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.8205553253211769,
|
| 1399 |
+
"grad_norm": 1.9865625625009857,
|
| 1400 |
+
"learning_rate": 9.464224028816427e-07,
|
| 1401 |
+
"loss": 0.352,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8246995441359304,
|
| 1406 |
+
"grad_norm": 2.090284485836539,
|
| 1407 |
+
"learning_rate": 9.044704553353323e-07,
|
| 1408 |
+
"loss": 0.3552,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8288437629506838,
|
| 1413 |
+
"grad_norm": 2.0868083838688585,
|
| 1414 |
+
"learning_rate": 8.633768940451981e-07,
|
| 1415 |
+
"loss": 0.3494,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.8329879817654372,
|
| 1420 |
+
"grad_norm": 2.0849345095616507,
|
| 1421 |
+
"learning_rate": 8.231503318530814e-07,
|
| 1422 |
+
"loss": 0.3503,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.8371322005801907,
|
| 1427 |
+
"grad_norm": 2.036555088205375,
|
| 1428 |
+
"learning_rate": 7.837991998855899e-07,
|
| 1429 |
+
"loss": 0.3532,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.841276419394944,
|
| 1434 |
+
"grad_norm": 1.9647600324287684,
|
| 1435 |
+
"learning_rate": 7.453317457870096e-07,
|
| 1436 |
+
"loss": 0.3526,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.8454206382096975,
|
| 1441 |
+
"grad_norm": 1.9946404926738106,
|
| 1442 |
+
"learning_rate": 7.077560319906696e-07,
|
| 1443 |
+
"loss": 0.3507,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.8495648570244508,
|
| 1448 |
+
"grad_norm": 2.0929585255558805,
|
| 1449 |
+
"learning_rate": 6.710799340291341e-07,
|
| 1450 |
+
"loss": 0.3565,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.8537090758392043,
|
| 1455 |
+
"grad_norm": 1.9862050269807172,
|
| 1456 |
+
"learning_rate": 6.353111388835564e-07,
|
| 1457 |
+
"loss": 0.3504,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.8578532946539578,
|
| 1462 |
+
"grad_norm": 2.027382864636772,
|
| 1463 |
+
"learning_rate": 6.00457143372557e-07,
|
| 1464 |
+
"loss": 0.352,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.8619975134687111,
|
| 1469 |
+
"grad_norm": 2.090716583561947,
|
| 1470 |
+
"learning_rate": 5.665252525809583e-07,
|
| 1471 |
+
"loss": 0.3425,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.8661417322834646,
|
| 1476 |
+
"grad_norm": 2.06905352203202,
|
| 1477 |
+
"learning_rate": 5.335225783287051e-07,
|
| 1478 |
+
"loss": 0.3407,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8702859510982179,
|
| 1483 |
+
"grad_norm": 2.125696851804249,
|
| 1484 |
+
"learning_rate": 5.014560376802913e-07,
|
| 1485 |
+
"loss": 0.3487,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.8744301699129714,
|
| 1490 |
+
"grad_norm": 1.9923666150875952,
|
| 1491 |
+
"learning_rate": 4.703323514950042e-07,
|
| 1492 |
+
"loss": 0.3409,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.8785743887277249,
|
| 1497 |
+
"grad_norm": 2.0327181763907736,
|
| 1498 |
+
"learning_rate": 4.401580430182928e-07,
|
| 1499 |
+
"loss": 0.3506,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.8827186075424782,
|
| 1504 |
+
"grad_norm": 2.255853441666556,
|
| 1505 |
+
"learning_rate": 4.1093943651455305e-07,
|
| 1506 |
+
"loss": 0.3459,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.8868628263572317,
|
| 1511 |
+
"grad_norm": 2.0691292772221663,
|
| 1512 |
+
"learning_rate": 3.826826559416219e-07,
|
| 1513 |
+
"loss": 0.3483,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.891007045171985,
|
| 1518 |
+
"grad_norm": 2.0290765748725605,
|
| 1519 |
+
"learning_rate": 3.5539362366724784e-07,
|
| 1520 |
+
"loss": 0.3501,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.8951512639867385,
|
| 1525 |
+
"grad_norm": 2.1150371568126975,
|
| 1526 |
+
"learning_rate": 3.290780592278148e-07,
|
| 1527 |
+
"loss": 0.3442,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.899295482801492,
|
| 1532 |
+
"grad_norm": 1.9671376281528878,
|
| 1533 |
+
"learning_rate": 3.0374147812958387e-07,
|
| 1534 |
+
"loss": 0.3431,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.9034397016162453,
|
| 1539 |
+
"grad_norm": 2.046538088407744,
|
| 1540 |
+
"learning_rate": 2.7938919069268654e-07,
|
| 1541 |
+
"loss": 0.337,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.9075839204309988,
|
| 1546 |
+
"grad_norm": 2.0585547681661756,
|
| 1547 |
+
"learning_rate": 2.5602630093813253e-07,
|
| 1548 |
+
"loss": 0.3452,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.9117281392457521,
|
| 1553 |
+
"grad_norm": 2.080490788044654,
|
| 1554 |
+
"learning_rate": 2.3365770551805223e-07,
|
| 1555 |
+
"loss": 0.3399,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.9158723580605056,
|
| 1560 |
+
"grad_norm": 2.040411049775766,
|
| 1561 |
+
"learning_rate": 2.1228809268940164e-07,
|
| 1562 |
+
"loss": 0.3393,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.9200165768752591,
|
| 1567 |
+
"grad_norm": 2.0655064123833498,
|
| 1568 |
+
"learning_rate": 1.919219413313478e-07,
|
| 1569 |
+
"loss": 0.3395,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.9241607956900124,
|
| 1574 |
+
"grad_norm": 2.140596373973613,
|
| 1575 |
+
"learning_rate": 1.725635200065323e-07,
|
| 1576 |
+
"loss": 0.3405,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9283050145047659,
|
| 1581 |
+
"grad_norm": 1.986374862328418,
|
| 1582 |
+
"learning_rate": 1.5421688606642392e-07,
|
| 1583 |
+
"loss": 0.3428,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.9324492333195192,
|
| 1588 |
+
"grad_norm": 2.040129619292376,
|
| 1589 |
+
"learning_rate": 1.3688588480092913e-07,
|
| 1590 |
+
"loss": 0.3446,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9365934521342727,
|
| 1595 |
+
"grad_norm": 2.01389490087078,
|
| 1596 |
+
"learning_rate": 1.205741486324552e-07,
|
| 1597 |
+
"loss": 0.3397,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.9407376709490262,
|
| 1602 |
+
"grad_norm": 2.1289409520473326,
|
| 1603 |
+
"learning_rate": 1.0528509635458873e-07,
|
| 1604 |
+
"loss": 0.3401,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.9448818897637795,
|
| 1609 |
+
"grad_norm": 2.0835955722730697,
|
| 1610 |
+
"learning_rate": 9.102193241554757e-08,
|
| 1611 |
+
"loss": 0.3415,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.949026108578533,
|
| 1616 |
+
"grad_norm": 2.122449489250868,
|
| 1617 |
+
"learning_rate": 7.778764624655433e-08,
|
| 1618 |
+
"loss": 0.3437,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.9531703273932863,
|
| 1623 |
+
"grad_norm": 2.0577943752263836,
|
| 1624 |
+
"learning_rate": 6.558501163527964e-08,
|
| 1625 |
+
"loss": 0.3388,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.9573145462080398,
|
| 1630 |
+
"grad_norm": 2.126069664831503,
|
| 1631 |
+
"learning_rate": 5.44165861444812e-08,
|
| 1632 |
+
"loss": 0.337,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.9614587650227931,
|
| 1637 |
+
"grad_norm": 1.998215049010736,
|
| 1638 |
+
"learning_rate": 4.428471057596362e-08,
|
| 1639 |
+
"loss": 0.3378,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.9656029838375466,
|
| 1644 |
+
"grad_norm": 2.0929533756003904,
|
| 1645 |
+
"learning_rate": 3.519150847996422e-08,
|
| 1646 |
+
"loss": 0.3379,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.9697472026523001,
|
| 1651 |
+
"grad_norm": 2.0561899209040186,
|
| 1652 |
+
"learning_rate": 2.713888571007739e-08,
|
| 1653 |
+
"loss": 0.3388,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.9738914214670534,
|
| 1658 |
+
"grad_norm": 1.9664762265851157,
|
| 1659 |
+
"learning_rate": 2.012853002380466e-08,
|
| 1660 |
+
"loss": 0.3396,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.9780356402818069,
|
| 1665 |
+
"grad_norm": 1.999931793720276,
|
| 1666 |
+
"learning_rate": 1.4161910728816009e-08,
|
| 1667 |
+
"loss": 0.3408,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.9821798590965602,
|
| 1672 |
+
"grad_norm": 2.099348366631809,
|
| 1673 |
+
"learning_rate": 9.240278374995637e-09,
|
| 1674 |
+
"loss": 0.3438,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.9863240779113137,
|
| 1679 |
+
"grad_norm": 2.0961585662402937,
|
| 1680 |
+
"learning_rate": 5.364664492337746e-09,
|
| 1681 |
+
"loss": 0.3382,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.9904682967260672,
|
| 1686 |
+
"grad_norm": 2.0713909816710956,
|
| 1687 |
+
"learning_rate": 2.5358813747500266e-09,
|
| 1688 |
+
"loss": 0.3392,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.9946125155408205,
|
| 1693 |
+
"grad_norm": 2.0497170104333793,
|
| 1694 |
+
"learning_rate": 7.545219097987444e-10,
|
| 1695 |
+
"loss": 0.333,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.998756734355574,
|
| 1700 |
+
"grad_norm": 2.039086392116031,
|
| 1701 |
+
"learning_rate": 2.0959454449243076e-11,
|
| 1702 |
+
"loss": 0.3409,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.9995855781185247,
|
| 1707 |
+
"eval_loss": 0.3220805823802948,
|
| 1708 |
+
"eval_runtime": 1.1842,
|
| 1709 |
+
"eval_samples_per_second": 2.533,
|
| 1710 |
+
"eval_steps_per_second": 0.844,
|
| 1711 |
+
"step": 1206
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.9995855781185247,
|
| 1715 |
+
"step": 1206,
|
| 1716 |
+
"total_flos": 252407174922240.0,
|
| 1717 |
+
"train_loss": 0.5270945630461027,
|
| 1718 |
+
"train_runtime": 23848.9709,
|
| 1719 |
+
"train_samples_per_second": 1.619,
|
| 1720 |
+
"train_steps_per_second": 0.051
|
| 1721 |
+
}
|
| 1722 |
+
],
|
| 1723 |
+
"logging_steps": 5,
|
| 1724 |
+
"max_steps": 1206,
|
| 1725 |
+
"num_input_tokens_seen": 0,
|
| 1726 |
+
"num_train_epochs": 1,
|
| 1727 |
+
"save_steps": 100,
|
| 1728 |
+
"stateful_callbacks": {
|
| 1729 |
+
"TrainerControl": {
|
| 1730 |
+
"args": {
|
| 1731 |
+
"should_epoch_stop": false,
|
| 1732 |
+
"should_evaluate": false,
|
| 1733 |
+
"should_log": false,
|
| 1734 |
+
"should_save": true,
|
| 1735 |
+
"should_training_stop": true
|
| 1736 |
+
},
|
| 1737 |
+
"attributes": {}
|
| 1738 |
+
}
|
| 1739 |
+
},
|
| 1740 |
+
"total_flos": 252407174922240.0,
|
| 1741 |
+
"train_batch_size": 4,
|
| 1742 |
+
"trial_name": null,
|
| 1743 |
+
"trial_params": null
|
| 1744 |
+
}
|