Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Aug25_10-16-28_COE-CS-sv003/events.out.tfevents.1724581296.COE-CS-sv003.2840337.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1359 -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: direct_p0.1_seed42_level2_syntax
|
| 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 |
+
# direct_p0.1_seed42_level2_syntax
|
| 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: 0.2791
|
| 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: 2
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 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 |
+
| 0.3536 | 0.9997 | 930 | 0.2791 |
|
| 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": 0.999731255038968,
|
| 3 |
+
"total_flos": 194670734868480.0,
|
| 4 |
+
"train_loss": 0.5080837889384198,
|
| 5 |
+
"train_runtime": 21164.3008,
|
| 6 |
+
"train_samples": 98857,
|
| 7 |
+
"train_samples_per_second": 1.406,
|
| 8 |
+
"train_steps_per_second": 0.044
|
| 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/Aug25_10-16-28_COE-CS-sv003/events.out.tfevents.1724581296.COE-CS-sv003.2840337.0
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 sha256:19012b71e69a5cad28290906d49b55443e37bdf2855a8db721c14e1c41edd54a
|
| 3 |
+
size 45198
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.999731255038968,
|
| 3 |
+
"total_flos": 194670734868480.0,
|
| 4 |
+
"train_loss": 0.5080837889384198,
|
| 5 |
+
"train_runtime": 21164.3008,
|
| 6 |
+
"train_samples": 98857,
|
| 7 |
+
"train_samples_per_second": 1.406,
|
| 8 |
+
"train_steps_per_second": 0.044
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.999731255038968,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 930,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0010749798441279225,
|
| 13 |
+
"grad_norm": 22.998251618632413,
|
| 14 |
+
"learning_rate": 1.0752688172043012e-07,
|
| 15 |
+
"loss": 1.3109,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005374899220639613,
|
| 20 |
+
"grad_norm": 21.62666674963918,
|
| 21 |
+
"learning_rate": 5.376344086021506e-07,
|
| 22 |
+
"loss": 1.319,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.010749798441279226,
|
| 27 |
+
"grad_norm": 8.47868515286049,
|
| 28 |
+
"learning_rate": 1.0752688172043011e-06,
|
| 29 |
+
"loss": 1.201,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01612469766191884,
|
| 34 |
+
"grad_norm": 7.0045452722639245,
|
| 35 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 36 |
+
"loss": 1.0409,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.021499596882558453,
|
| 41 |
+
"grad_norm": 2.9866055931463724,
|
| 42 |
+
"learning_rate": 2.1505376344086023e-06,
|
| 43 |
+
"loss": 0.9079,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.026874496103198066,
|
| 48 |
+
"grad_norm": 2.466878497235169,
|
| 49 |
+
"learning_rate": 2.688172043010753e-06,
|
| 50 |
+
"loss": 0.8681,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03224939532383768,
|
| 55 |
+
"grad_norm": 2.1381469942804414,
|
| 56 |
+
"learning_rate": 3.225806451612903e-06,
|
| 57 |
+
"loss": 0.8354,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03762429454447729,
|
| 62 |
+
"grad_norm": 2.3822492851866888,
|
| 63 |
+
"learning_rate": 3.763440860215054e-06,
|
| 64 |
+
"loss": 0.8242,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.042999193765116905,
|
| 69 |
+
"grad_norm": 2.2460422471438446,
|
| 70 |
+
"learning_rate": 4.3010752688172045e-06,
|
| 71 |
+
"loss": 0.8055,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04837409298575652,
|
| 76 |
+
"grad_norm": 2.278945525704108,
|
| 77 |
+
"learning_rate": 4.838709677419355e-06,
|
| 78 |
+
"loss": 0.7808,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.05374899220639613,
|
| 83 |
+
"grad_norm": 2.3939238018515785,
|
| 84 |
+
"learning_rate": 5.376344086021506e-06,
|
| 85 |
+
"loss": 0.7718,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.059123891427035745,
|
| 90 |
+
"grad_norm": 2.4529746003373805,
|
| 91 |
+
"learning_rate": 5.9139784946236566e-06,
|
| 92 |
+
"loss": 0.7577,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06449879064767536,
|
| 97 |
+
"grad_norm": 2.370219230419958,
|
| 98 |
+
"learning_rate": 6.451612903225806e-06,
|
| 99 |
+
"loss": 0.7406,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06987368986831496,
|
| 104 |
+
"grad_norm": 2.5160763656892278,
|
| 105 |
+
"learning_rate": 6.989247311827958e-06,
|
| 106 |
+
"loss": 0.7328,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.07524858908895458,
|
| 111 |
+
"grad_norm": 2.2323762062076615,
|
| 112 |
+
"learning_rate": 7.526881720430108e-06,
|
| 113 |
+
"loss": 0.7049,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08062348830959419,
|
| 118 |
+
"grad_norm": 2.1957037704755717,
|
| 119 |
+
"learning_rate": 8.064516129032258e-06,
|
| 120 |
+
"loss": 0.7038,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08599838753023381,
|
| 125 |
+
"grad_norm": 2.263429588353797,
|
| 126 |
+
"learning_rate": 8.602150537634409e-06,
|
| 127 |
+
"loss": 0.7177,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.09137328675087342,
|
| 132 |
+
"grad_norm": 2.2491062827888757,
|
| 133 |
+
"learning_rate": 9.13978494623656e-06,
|
| 134 |
+
"loss": 0.7082,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09674818597151304,
|
| 139 |
+
"grad_norm": 2.3972214541569326,
|
| 140 |
+
"learning_rate": 9.67741935483871e-06,
|
| 141 |
+
"loss": 0.7052,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.10212308519215264,
|
| 146 |
+
"grad_norm": 2.442294992070258,
|
| 147 |
+
"learning_rate": 9.999859120828162e-06,
|
| 148 |
+
"loss": 0.6871,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.10749798441279226,
|
| 153 |
+
"grad_norm": 2.1737197659282677,
|
| 154 |
+
"learning_rate": 9.998274321315453e-06,
|
| 155 |
+
"loss": 0.691,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.11287288363343187,
|
| 160 |
+
"grad_norm": 2.086931041290223,
|
| 161 |
+
"learning_rate": 9.994929183335237e-06,
|
| 162 |
+
"loss": 0.6887,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.11824778285407149,
|
| 167 |
+
"grad_norm": 2.181755095183289,
|
| 168 |
+
"learning_rate": 9.989824885009142e-06,
|
| 169 |
+
"loss": 0.6761,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1236226820747111,
|
| 174 |
+
"grad_norm": 2.1430422893188195,
|
| 175 |
+
"learning_rate": 9.982963224016152e-06,
|
| 176 |
+
"loss": 0.6748,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12899758129535072,
|
| 181 |
+
"grad_norm": 2.0944055561946047,
|
| 182 |
+
"learning_rate": 9.974346616959476e-06,
|
| 183 |
+
"loss": 0.6782,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.13437248051599032,
|
| 188 |
+
"grad_norm": 2.7234289381522694,
|
| 189 |
+
"learning_rate": 9.963978098515468e-06,
|
| 190 |
+
"loss": 0.6717,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.13974737973662993,
|
| 195 |
+
"grad_norm": 2.2612331983977265,
|
| 196 |
+
"learning_rate": 9.951861320364822e-06,
|
| 197 |
+
"loss": 0.671,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.14512227895726956,
|
| 202 |
+
"grad_norm": 2.349078940825244,
|
| 203 |
+
"learning_rate": 9.938000549906509e-06,
|
| 204 |
+
"loss": 0.6628,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15049717817790917,
|
| 209 |
+
"grad_norm": 2.213915224858813,
|
| 210 |
+
"learning_rate": 9.922400668754833e-06,
|
| 211 |
+
"loss": 0.6578,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.15587207739854878,
|
| 216 |
+
"grad_norm": 2.0247679479977947,
|
| 217 |
+
"learning_rate": 9.905067171020185e-06,
|
| 218 |
+
"loss": 0.6621,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16124697661918838,
|
| 223 |
+
"grad_norm": 2.175459644155833,
|
| 224 |
+
"learning_rate": 9.88600616137407e-06,
|
| 225 |
+
"loss": 0.6539,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.16662187583982802,
|
| 230 |
+
"grad_norm": 1.9231116317571189,
|
| 231 |
+
"learning_rate": 9.86522435289912e-06,
|
| 232 |
+
"loss": 0.6486,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17199677506046762,
|
| 237 |
+
"grad_norm": 1.9429182926189486,
|
| 238 |
+
"learning_rate": 9.8427290647248e-06,
|
| 239 |
+
"loss": 0.6446,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.17737167428110723,
|
| 244 |
+
"grad_norm": 2.029616741174372,
|
| 245 |
+
"learning_rate": 9.818528219449705e-06,
|
| 246 |
+
"loss": 0.6393,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.18274657350174683,
|
| 251 |
+
"grad_norm": 1.954236053756045,
|
| 252 |
+
"learning_rate": 9.792630340351301e-06,
|
| 253 |
+
"loss": 0.6505,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.18812147272238647,
|
| 258 |
+
"grad_norm": 2.0238728155049994,
|
| 259 |
+
"learning_rate": 9.765044548384113e-06,
|
| 260 |
+
"loss": 0.6345,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.19349637194302607,
|
| 265 |
+
"grad_norm": 1.9933506258733436,
|
| 266 |
+
"learning_rate": 9.735780558967434e-06,
|
| 267 |
+
"loss": 0.6321,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.19887127116366568,
|
| 272 |
+
"grad_norm": 2.159514610870395,
|
| 273 |
+
"learning_rate": 9.70484867856365e-06,
|
| 274 |
+
"loss": 0.6307,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2042461703843053,
|
| 279 |
+
"grad_norm": 1.8959726839851836,
|
| 280 |
+
"learning_rate": 9.67225980104841e-06,
|
| 281 |
+
"loss": 0.6344,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.20962106960494492,
|
| 286 |
+
"grad_norm": 1.9231014581432677,
|
| 287 |
+
"learning_rate": 9.638025403873939e-06,
|
| 288 |
+
"loss": 0.6354,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.21499596882558453,
|
| 293 |
+
"grad_norm": 1.9470579040757032,
|
| 294 |
+
"learning_rate": 9.602157544026785e-06,
|
| 295 |
+
"loss": 0.6213,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.22037086804622413,
|
| 300 |
+
"grad_norm": 2.1141633711901293,
|
| 301 |
+
"learning_rate": 9.564668853781483e-06,
|
| 302 |
+
"loss": 0.6287,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.22574576726686374,
|
| 307 |
+
"grad_norm": 2.094733969067925,
|
| 308 |
+
"learning_rate": 9.525572536251608e-06,
|
| 309 |
+
"loss": 0.6184,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.23112066648750335,
|
| 314 |
+
"grad_norm": 1.8594092068711054,
|
| 315 |
+
"learning_rate": 9.484882360739772e-06,
|
| 316 |
+
"loss": 0.6049,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.23649556570814298,
|
| 321 |
+
"grad_norm": 1.8042100641048069,
|
| 322 |
+
"learning_rate": 9.442612657888237e-06,
|
| 323 |
+
"loss": 0.604,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24187046492878259,
|
| 328 |
+
"grad_norm": 1.9491363567278153,
|
| 329 |
+
"learning_rate": 9.398778314631801e-06,
|
| 330 |
+
"loss": 0.5935,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2472453641494222,
|
| 335 |
+
"grad_norm": 2.0060700754274112,
|
| 336 |
+
"learning_rate": 9.353394768954791e-06,
|
| 337 |
+
"loss": 0.5973,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.2526202633700618,
|
| 342 |
+
"grad_norm": 2.323587224840248,
|
| 343 |
+
"learning_rate": 9.30647800445397e-06,
|
| 344 |
+
"loss": 0.602,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.25799516259070143,
|
| 349 |
+
"grad_norm": 2.2542109995103985,
|
| 350 |
+
"learning_rate": 9.258044544709276e-06,
|
| 351 |
+
"loss": 0.6005,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.26337006181134104,
|
| 356 |
+
"grad_norm": 2.205069286015657,
|
| 357 |
+
"learning_rate": 9.208111447464407e-06,
|
| 358 |
+
"loss": 0.5937,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.26874496103198064,
|
| 363 |
+
"grad_norm": 1.979112533465105,
|
| 364 |
+
"learning_rate": 9.156696298619266e-06,
|
| 365 |
+
"loss": 0.5905,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.27411986025262025,
|
| 370 |
+
"grad_norm": 2.171300635630568,
|
| 371 |
+
"learning_rate": 9.103817206036383e-06,
|
| 372 |
+
"loss": 0.5885,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.27949475947325986,
|
| 377 |
+
"grad_norm": 1.9064161905725763,
|
| 378 |
+
"learning_rate": 9.049492793163539e-06,
|
| 379 |
+
"loss": 0.5898,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.28486965869389946,
|
| 384 |
+
"grad_norm": 1.9617828705521112,
|
| 385 |
+
"learning_rate": 8.993742192474773e-06,
|
| 386 |
+
"loss": 0.5831,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2902445579145391,
|
| 391 |
+
"grad_norm": 1.8575944912932347,
|
| 392 |
+
"learning_rate": 8.936585038732143e-06,
|
| 393 |
+
"loss": 0.5751,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.29561945713517873,
|
| 398 |
+
"grad_norm": 1.9607189835672174,
|
| 399 |
+
"learning_rate": 8.878041462070556e-06,
|
| 400 |
+
"loss": 0.5795,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.30099435635581834,
|
| 405 |
+
"grad_norm": 1.9827526904209154,
|
| 406 |
+
"learning_rate": 8.818132080908178e-06,
|
| 407 |
+
"loss": 0.5756,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.30636925557645794,
|
| 412 |
+
"grad_norm": 1.9289388619958865,
|
| 413 |
+
"learning_rate": 8.756877994684818e-06,
|
| 414 |
+
"loss": 0.5797,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31174415479709755,
|
| 419 |
+
"grad_norm": 1.9423515794251163,
|
| 420 |
+
"learning_rate": 8.694300776430958e-06,
|
| 421 |
+
"loss": 0.5654,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.31711905401773716,
|
| 426 |
+
"grad_norm": 2.133199145110774,
|
| 427 |
+
"learning_rate": 8.630422465169947e-06,
|
| 428 |
+
"loss": 0.5586,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32249395323837676,
|
| 433 |
+
"grad_norm": 2.2051473612841845,
|
| 434 |
+
"learning_rate": 8.565265558156101e-06,
|
| 435 |
+
"loss": 0.5674,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.32786885245901637,
|
| 440 |
+
"grad_norm": 1.94675668742253,
|
| 441 |
+
"learning_rate": 8.498853002951414e-06,
|
| 442 |
+
"loss": 0.5572,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33324375167965603,
|
| 447 |
+
"grad_norm": 2.046407155545796,
|
| 448 |
+
"learning_rate": 8.43120818934367e-06,
|
| 449 |
+
"loss": 0.5535,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.33861865090029564,
|
| 454 |
+
"grad_norm": 2.0046384820796486,
|
| 455 |
+
"learning_rate": 8.362354941108803e-06,
|
| 456 |
+
"loss": 0.5577,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34399355012093524,
|
| 461 |
+
"grad_norm": 2.0243084631372223,
|
| 462 |
+
"learning_rate": 8.292317507620438e-06,
|
| 463 |
+
"loss": 0.566,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.34936844934157485,
|
| 468 |
+
"grad_norm": 1.8780763393652544,
|
| 469 |
+
"learning_rate": 8.221120555309511e-06,
|
| 470 |
+
"loss": 0.5471,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35474334856221446,
|
| 475 |
+
"grad_norm": 2.0125466037004967,
|
| 476 |
+
"learning_rate": 8.148789158977012e-06,
|
| 477 |
+
"loss": 0.55,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.36011824778285406,
|
| 482 |
+
"grad_norm": 2.111876068514048,
|
| 483 |
+
"learning_rate": 8.075348792962924e-06,
|
| 484 |
+
"loss": 0.542,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.36549314700349367,
|
| 489 |
+
"grad_norm": 1.831727662600693,
|
| 490 |
+
"learning_rate": 8.000825322174424e-06,
|
| 491 |
+
"loss": 0.541,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3708680462241333,
|
| 496 |
+
"grad_norm": 1.957058515389012,
|
| 497 |
+
"learning_rate": 7.925244992976538e-06,
|
| 498 |
+
"loss": 0.525,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.37624294544477294,
|
| 503 |
+
"grad_norm": 2.016623611705091,
|
| 504 |
+
"learning_rate": 7.848634423948468e-06,
|
| 505 |
+
"loss": 0.5294,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.38161784466541254,
|
| 510 |
+
"grad_norm": 1.9380904809426653,
|
| 511 |
+
"learning_rate": 7.7710205965088e-06,
|
| 512 |
+
"loss": 0.5324,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.38699274388605215,
|
| 517 |
+
"grad_norm": 2.0054637192864746,
|
| 518 |
+
"learning_rate": 7.692430845412946e-06,
|
| 519 |
+
"loss": 0.5276,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.39236764310669175,
|
| 524 |
+
"grad_norm": 2.201718543185445,
|
| 525 |
+
"learning_rate": 7.612892849126132e-06,
|
| 526 |
+
"loss": 0.5286,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.39774254232733136,
|
| 531 |
+
"grad_norm": 1.9346693875946135,
|
| 532 |
+
"learning_rate": 7.532434620075349e-06,
|
| 533 |
+
"loss": 0.5217,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.40311744154797097,
|
| 538 |
+
"grad_norm": 2.046737331443054,
|
| 539 |
+
"learning_rate": 7.451084494783668e-06,
|
| 540 |
+
"loss": 0.5196,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4084923407686106,
|
| 545 |
+
"grad_norm": 1.9926284827905993,
|
| 546 |
+
"learning_rate": 7.368871123890425e-06,
|
| 547 |
+
"loss": 0.5186,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4138672399892502,
|
| 552 |
+
"grad_norm": 2.0164701987233133,
|
| 553 |
+
"learning_rate": 7.285823462060776e-06,
|
| 554 |
+
"loss": 0.5155,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.41924213920988984,
|
| 559 |
+
"grad_norm": 1.821494525655949,
|
| 560 |
+
"learning_rate": 7.201970757788172e-06,
|
| 561 |
+
"loss": 0.5094,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.42461703843052945,
|
| 566 |
+
"grad_norm": 2.0350416485078533,
|
| 567 |
+
"learning_rate": 7.117342543093358e-06,
|
| 568 |
+
"loss": 0.5051,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.42999193765116905,
|
| 573 |
+
"grad_norm": 1.9177286245297331,
|
| 574 |
+
"learning_rate": 7.031968623123503e-06,
|
| 575 |
+
"loss": 0.5037,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.43536683687180866,
|
| 580 |
+
"grad_norm": 1.8060468183436844,
|
| 581 |
+
"learning_rate": 6.945879065655164e-06,
|
| 582 |
+
"loss": 0.5091,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44074173609244827,
|
| 587 |
+
"grad_norm": 2.0324990194845425,
|
| 588 |
+
"learning_rate": 6.859104190504725e-06,
|
| 589 |
+
"loss": 0.5081,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4461166353130879,
|
| 594 |
+
"grad_norm": 1.9781738403258928,
|
| 595 |
+
"learning_rate": 6.771674558850088e-06,
|
| 596 |
+
"loss": 0.4978,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4514915345337275,
|
| 601 |
+
"grad_norm": 1.967394802071695,
|
| 602 |
+
"learning_rate": 6.6836209624673575e-06,
|
| 603 |
+
"loss": 0.4993,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4568664337543671,
|
| 608 |
+
"grad_norm": 1.8301107915867578,
|
| 609 |
+
"learning_rate": 6.5949744128863026e-06,
|
| 610 |
+
"loss": 0.4951,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.4622413329750067,
|
| 615 |
+
"grad_norm": 1.8666451752143274,
|
| 616 |
+
"learning_rate": 6.5057661304684314e-06,
|
| 617 |
+
"loss": 0.4929,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.46761623219564635,
|
| 622 |
+
"grad_norm": 1.820566898851988,
|
| 623 |
+
"learning_rate": 6.41602753341152e-06,
|
| 624 |
+
"loss": 0.4925,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47299113141628596,
|
| 629 |
+
"grad_norm": 1.972020976387126,
|
| 630 |
+
"learning_rate": 6.32579022668446e-06,
|
| 631 |
+
"loss": 0.4869,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.47836603063692557,
|
| 636 |
+
"grad_norm": 1.9421491239061908,
|
| 637 |
+
"learning_rate": 6.235085990896317e-06,
|
| 638 |
+
"loss": 0.4757,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48374092985756517,
|
| 643 |
+
"grad_norm": 1.9181960459695213,
|
| 644 |
+
"learning_rate": 6.143946771103561e-06,
|
| 645 |
+
"loss": 0.4941,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4891158290782048,
|
| 650 |
+
"grad_norm": 1.9219139761794142,
|
| 651 |
+
"learning_rate": 6.052404665559342e-06,
|
| 652 |
+
"loss": 0.468,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.4944907282988444,
|
| 657 |
+
"grad_norm": 1.9586485250210308,
|
| 658 |
+
"learning_rate": 5.960491914408846e-06,
|
| 659 |
+
"loss": 0.4704,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.499865627519484,
|
| 664 |
+
"grad_norm": 1.978155481583312,
|
| 665 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 666 |
+
"loss": 0.4891,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5052405267401237,
|
| 671 |
+
"grad_norm": 1.9491669694735005,
|
| 672 |
+
"learning_rate": 5.775684077156133e-06,
|
| 673 |
+
"loss": 0.4689,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5106154259607633,
|
| 678 |
+
"grad_norm": 1.9616828525043124,
|
| 679 |
+
"learning_rate": 5.682854078386882e-06,
|
| 680 |
+
"loss": 0.4722,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5159903251814029,
|
| 685 |
+
"grad_norm": 1.9497396606270447,
|
| 686 |
+
"learning_rate": 5.5897835857542315e-06,
|
| 687 |
+
"loss": 0.4624,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5213652244020425,
|
| 692 |
+
"grad_norm": 1.895936510041223,
|
| 693 |
+
"learning_rate": 5.496505377684858e-06,
|
| 694 |
+
"loss": 0.4519,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5267401236226821,
|
| 699 |
+
"grad_norm": 1.97427958718019,
|
| 700 |
+
"learning_rate": 5.4030523057605865e-06,
|
| 701 |
+
"loss": 0.4671,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5321150228433217,
|
| 706 |
+
"grad_norm": 1.99020514417267,
|
| 707 |
+
"learning_rate": 5.30945728314841e-06,
|
| 708 |
+
"loss": 0.4555,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5374899220639613,
|
| 713 |
+
"grad_norm": 1.834260157432595,
|
| 714 |
+
"learning_rate": 5.215753273008828e-06,
|
| 715 |
+
"loss": 0.4592,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5428648212846009,
|
| 720 |
+
"grad_norm": 2.07183045007662,
|
| 721 |
+
"learning_rate": 5.1219732768865744e-06,
|
| 722 |
+
"loss": 0.4544,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5482397205052405,
|
| 727 |
+
"grad_norm": 1.8925742071728788,
|
| 728 |
+
"learning_rate": 5.0281503230878304e-06,
|
| 729 |
+
"loss": 0.4503,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5536146197258801,
|
| 734 |
+
"grad_norm": 2.120435800008408,
|
| 735 |
+
"learning_rate": 4.934317455048005e-06,
|
| 736 |
+
"loss": 0.4432,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.5589895189465197,
|
| 741 |
+
"grad_norm": 2.078137912583167,
|
| 742 |
+
"learning_rate": 4.840507719694202e-06,
|
| 743 |
+
"loss": 0.4454,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5643644181671593,
|
| 748 |
+
"grad_norm": 1.8218423489133921,
|
| 749 |
+
"learning_rate": 4.746754155806437e-06,
|
| 750 |
+
"loss": 0.4353,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5697393173877989,
|
| 755 |
+
"grad_norm": 1.886033793318668,
|
| 756 |
+
"learning_rate": 4.6530897823817425e-06,
|
| 757 |
+
"loss": 0.4518,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5751142166084386,
|
| 762 |
+
"grad_norm": 1.837947070178225,
|
| 763 |
+
"learning_rate": 4.559547587005227e-06,
|
| 764 |
+
"loss": 0.4491,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.5804891158290783,
|
| 769 |
+
"grad_norm": 1.8242868271131116,
|
| 770 |
+
"learning_rate": 4.466160514232206e-06,
|
| 771 |
+
"loss": 0.4405,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.5858640150497179,
|
| 776 |
+
"grad_norm": 1.9410093391418528,
|
| 777 |
+
"learning_rate": 4.3729614539854815e-06,
|
| 778 |
+
"loss": 0.4323,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5912389142703575,
|
| 783 |
+
"grad_norm": 2.079990387721551,
|
| 784 |
+
"learning_rate": 4.279983229971863e-06,
|
| 785 |
+
"loss": 0.4347,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5966138134909971,
|
| 790 |
+
"grad_norm": 1.8661086060382346,
|
| 791 |
+
"learning_rate": 4.187258588122019e-06,
|
| 792 |
+
"loss": 0.4309,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6019887127116367,
|
| 797 |
+
"grad_norm": 1.9549179181995389,
|
| 798 |
+
"learning_rate": 4.094820185057701e-06,
|
| 799 |
+
"loss": 0.434,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6073636119322763,
|
| 804 |
+
"grad_norm": 1.9438750319747926,
|
| 805 |
+
"learning_rate": 4.002700576590441e-06,
|
| 806 |
+
"loss": 0.417,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6127385111529159,
|
| 811 |
+
"grad_norm": 1.86309458236793,
|
| 812 |
+
"learning_rate": 3.910932206255742e-06,
|
| 813 |
+
"loss": 0.4196,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6181134103735555,
|
| 818 |
+
"grad_norm": 1.931200769910855,
|
| 819 |
+
"learning_rate": 3.819547393886816e-06,
|
| 820 |
+
"loss": 0.4089,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6234883095941951,
|
| 825 |
+
"grad_norm": 1.9236481963943084,
|
| 826 |
+
"learning_rate": 3.7285783242318773e-06,
|
| 827 |
+
"loss": 0.4176,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6288632088148347,
|
| 832 |
+
"grad_norm": 1.987655423768294,
|
| 833 |
+
"learning_rate": 3.6380570356190346e-06,
|
| 834 |
+
"loss": 0.4111,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6342381080354743,
|
| 839 |
+
"grad_norm": 1.9140625569934329,
|
| 840 |
+
"learning_rate": 3.548015408672723e-06,
|
| 841 |
+
"loss": 0.4179,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6396130072561139,
|
| 846 |
+
"grad_norm": 1.914275720117943,
|
| 847 |
+
"learning_rate": 3.4584851550857007e-06,
|
| 848 |
+
"loss": 0.4101,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6449879064767535,
|
| 853 |
+
"grad_norm": 1.9920083731014693,
|
| 854 |
+
"learning_rate": 3.3694978064505258e-06,
|
| 855 |
+
"loss": 0.4096,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6503628056973931,
|
| 860 |
+
"grad_norm": 1.8555446650582728,
|
| 861 |
+
"learning_rate": 3.2810847031544703e-06,
|
| 862 |
+
"loss": 0.4134,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.6557377049180327,
|
| 867 |
+
"grad_norm": 1.847095213057005,
|
| 868 |
+
"learning_rate": 3.193276983341773e-06,
|
| 869 |
+
"loss": 0.4044,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6611126041386725,
|
| 874 |
+
"grad_norm": 1.8348823558923015,
|
| 875 |
+
"learning_rate": 3.10610557194712e-06,
|
| 876 |
+
"loss": 0.4081,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6664875033593121,
|
| 881 |
+
"grad_norm": 1.7814726492285784,
|
| 882 |
+
"learning_rate": 3.019601169804216e-06,
|
| 883 |
+
"loss": 0.4054,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6718624025799517,
|
| 888 |
+
"grad_norm": 1.9239354085532425,
|
| 889 |
+
"learning_rate": 2.9337942428332787e-06,
|
| 890 |
+
"loss": 0.4072,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.6772373018005913,
|
| 895 |
+
"grad_norm": 1.8174216015392752,
|
| 896 |
+
"learning_rate": 2.848715011311271e-06,
|
| 897 |
+
"loss": 0.3882,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6826122010212309,
|
| 902 |
+
"grad_norm": 1.8355921561483057,
|
| 903 |
+
"learning_rate": 2.764393439228643e-06,
|
| 904 |
+
"loss": 0.4032,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6879871002418705,
|
| 909 |
+
"grad_norm": 1.8428986241754186,
|
| 910 |
+
"learning_rate": 2.6808592237363364e-06,
|
| 911 |
+
"loss": 0.3938,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.6933619994625101,
|
| 916 |
+
"grad_norm": 1.930494807022806,
|
| 917 |
+
"learning_rate": 2.5981417846867753e-06,
|
| 918 |
+
"loss": 0.3827,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6987368986831497,
|
| 923 |
+
"grad_norm": 1.9965194348229882,
|
| 924 |
+
"learning_rate": 2.5162702542724924e-06,
|
| 925 |
+
"loss": 0.4025,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7041117979037893,
|
| 930 |
+
"grad_norm": 1.9343155927695501,
|
| 931 |
+
"learning_rate": 2.4352734667661073e-06,
|
| 932 |
+
"loss": 0.3931,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7094866971244289,
|
| 937 |
+
"grad_norm": 1.8913804765293543,
|
| 938 |
+
"learning_rate": 2.3551799483651894e-06,
|
| 939 |
+
"loss": 0.4008,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7148615963450685,
|
| 944 |
+
"grad_norm": 1.877731033002426,
|
| 945 |
+
"learning_rate": 2.2760179071456356e-06,
|
| 946 |
+
"loss": 0.3836,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7202364955657081,
|
| 951 |
+
"grad_norm": 2.271932216399522,
|
| 952 |
+
"learning_rate": 2.1978152231271077e-06,
|
| 953 |
+
"loss": 0.3899,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.7256113947863477,
|
| 958 |
+
"grad_norm": 1.8362601272256027,
|
| 959 |
+
"learning_rate": 2.120599438453968e-06,
|
| 960 |
+
"loss": 0.3935,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7309862940069873,
|
| 965 |
+
"grad_norm": 1.8391327367572157,
|
| 966 |
+
"learning_rate": 2.044397747695247e-06,
|
| 967 |
+
"loss": 0.39,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7363611932276269,
|
| 972 |
+
"grad_norm": 1.8672651878485813,
|
| 973 |
+
"learning_rate": 1.969236988267005e-06,
|
| 974 |
+
"loss": 0.3829,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7417360924482665,
|
| 979 |
+
"grad_norm": 1.8664855719301263,
|
| 980 |
+
"learning_rate": 1.8951436309804766e-06,
|
| 981 |
+
"loss": 0.3826,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7471109916689062,
|
| 986 |
+
"grad_norm": 1.8648482987681003,
|
| 987 |
+
"learning_rate": 1.8221437707193424e-06,
|
| 988 |
+
"loss": 0.3796,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.7524858908895459,
|
| 993 |
+
"grad_norm": 1.8823945570583507,
|
| 994 |
+
"learning_rate": 1.7502631172493878e-06,
|
| 995 |
+
"loss": 0.3784,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7578607901101855,
|
| 1000 |
+
"grad_norm": 1.8429277019145163,
|
| 1001 |
+
"learning_rate": 1.6795269861638041e-06,
|
| 1002 |
+
"loss": 0.3808,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7632356893308251,
|
| 1007 |
+
"grad_norm": 1.8821109309531021,
|
| 1008 |
+
"learning_rate": 1.6099602899673083e-06,
|
| 1009 |
+
"loss": 0.3752,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7686105885514647,
|
| 1014 |
+
"grad_norm": 1.8044029771514785,
|
| 1015 |
+
"learning_rate": 1.5415875293022181e-06,
|
| 1016 |
+
"loss": 0.3631,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.7739854877721043,
|
| 1021 |
+
"grad_norm": 1.8714319214476052,
|
| 1022 |
+
"learning_rate": 1.4744327843196043e-06,
|
| 1023 |
+
"loss": 0.3722,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7793603869927439,
|
| 1028 |
+
"grad_norm": 1.8005842812695019,
|
| 1029 |
+
"learning_rate": 1.4085197061985022e-06,
|
| 1030 |
+
"loss": 0.3764,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7847352862133835,
|
| 1035 |
+
"grad_norm": 1.9498199256183426,
|
| 1036 |
+
"learning_rate": 1.3438715088162403e-06,
|
| 1037 |
+
"loss": 0.3717,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.7901101854340231,
|
| 1042 |
+
"grad_norm": 1.7622641111168549,
|
| 1043 |
+
"learning_rate": 1.280510960572745e-06,
|
| 1044 |
+
"loss": 0.3726,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7954850846546627,
|
| 1049 |
+
"grad_norm": 1.859176007788758,
|
| 1050 |
+
"learning_rate": 1.2184603763717684e-06,
|
| 1051 |
+
"loss": 0.3581,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8008599838753023,
|
| 1056 |
+
"grad_norm": 1.8187680407734916,
|
| 1057 |
+
"learning_rate": 1.1577416097618138e-06,
|
| 1058 |
+
"loss": 0.361,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8062348830959419,
|
| 1063 |
+
"grad_norm": 1.8234490317185335,
|
| 1064 |
+
"learning_rate": 1.0983760452395415e-06,
|
| 1065 |
+
"loss": 0.3629,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.8116097823165815,
|
| 1070 |
+
"grad_norm": 1.7846174067763332,
|
| 1071 |
+
"learning_rate": 1.040384590718399e-06,
|
| 1072 |
+
"loss": 0.3603,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8169846815372211,
|
| 1077 |
+
"grad_norm": 1.9539954235141312,
|
| 1078 |
+
"learning_rate": 9.837876701650606e-07,
|
| 1079 |
+
"loss": 0.3604,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8223595807578608,
|
| 1084 |
+
"grad_norm": 1.829814154109719,
|
| 1085 |
+
"learning_rate": 9.286052164063369e-07,
|
| 1086 |
+
"loss": 0.361,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8277344799785004,
|
| 1091 |
+
"grad_norm": 1.7589374129255484,
|
| 1092 |
+
"learning_rate": 8.748566641090433e-07,
|
| 1093 |
+
"loss": 0.3598,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.83310937919914,
|
| 1098 |
+
"grad_norm": 1.8087859749367046,
|
| 1099 |
+
"learning_rate": 8.225609429353187e-07,
|
| 1100 |
+
"loss": 0.3575,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8384842784197797,
|
| 1105 |
+
"grad_norm": 1.659093947160247,
|
| 1106 |
+
"learning_rate": 7.717364708758024e-07,
|
| 1107 |
+
"loss": 0.357,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8438591776404193,
|
| 1112 |
+
"grad_norm": 1.7512154153875217,
|
| 1113 |
+
"learning_rate": 7.224011477630166e-07,
|
| 1114 |
+
"loss": 0.3556,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8492340768610589,
|
| 1119 |
+
"grad_norm": 1.721279609127408,
|
| 1120 |
+
"learning_rate": 6.745723489672412e-07,
|
| 1121 |
+
"loss": 0.3597,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8546089760816985,
|
| 1126 |
+
"grad_norm": 1.933232116242709,
|
| 1127 |
+
"learning_rate": 6.282669192770896e-07,
|
| 1128 |
+
"loss": 0.3583,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8599838753023381,
|
| 1133 |
+
"grad_norm": 1.807730857907691,
|
| 1134 |
+
"learning_rate": 5.83501166966956e-07,
|
| 1135 |
+
"loss": 0.3524,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.8653587745229777,
|
| 1140 |
+
"grad_norm": 1.7853591098408064,
|
| 1141 |
+
"learning_rate": 5.402908580534233e-07,
|
| 1142 |
+
"loss": 0.3623,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8707336737436173,
|
| 1147 |
+
"grad_norm": 1.706116308384166,
|
| 1148 |
+
"learning_rate": 4.986512107426283e-07,
|
| 1149 |
+
"loss": 0.3485,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8761085729642569,
|
| 1154 |
+
"grad_norm": 1.8110038058348839,
|
| 1155 |
+
"learning_rate": 4.5859689007058896e-07,
|
| 1156 |
+
"loss": 0.3517,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8814834721848965,
|
| 1161 |
+
"grad_norm": 1.74966735612597,
|
| 1162 |
+
"learning_rate": 4.2014200273832406e-07,
|
| 1163 |
+
"loss": 0.3461,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8868583714055361,
|
| 1168 |
+
"grad_norm": 1.887649690807963,
|
| 1169 |
+
"learning_rate": 3.8330009214363197e-07,
|
| 1170 |
+
"loss": 0.3509,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8922332706261757,
|
| 1175 |
+
"grad_norm": 1.7866587101491602,
|
| 1176 |
+
"learning_rate": 3.4808413361125004e-07,
|
| 1177 |
+
"loss": 0.3479,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8976081698468154,
|
| 1182 |
+
"grad_norm": 1.851631043751454,
|
| 1183 |
+
"learning_rate": 3.1450652982307815e-07,
|
| 1184 |
+
"loss": 0.3502,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.902983069067455,
|
| 1189 |
+
"grad_norm": 1.8437354756226652,
|
| 1190 |
+
"learning_rate": 2.8257910645009935e-07,
|
| 1191 |
+
"loss": 0.3475,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9083579682880946,
|
| 1196 |
+
"grad_norm": 1.690251790769186,
|
| 1197 |
+
"learning_rate": 2.523131079874963e-07,
|
| 1198 |
+
"loss": 0.3581,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9137328675087342,
|
| 1203 |
+
"grad_norm": 1.8644738435275017,
|
| 1204 |
+
"learning_rate": 2.2371919379446495e-07,
|
| 1205 |
+
"loss": 0.356,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9191077667293738,
|
| 1210 |
+
"grad_norm": 1.703645616104732,
|
| 1211 |
+
"learning_rate": 1.9680743434010385e-07,
|
| 1212 |
+
"loss": 0.3431,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9244826659500134,
|
| 1217 |
+
"grad_norm": 1.7632832319721445,
|
| 1218 |
+
"learning_rate": 1.7158730765669817e-07,
|
| 1219 |
+
"loss": 0.3527,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9298575651706531,
|
| 1224 |
+
"grad_norm": 1.778411516430386,
|
| 1225 |
+
"learning_rate": 1.480676960016636e-07,
|
| 1226 |
+
"loss": 0.3527,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.9352324643912927,
|
| 1231 |
+
"grad_norm": 1.7461766662441864,
|
| 1232 |
+
"learning_rate": 1.2625688272930925e-07,
|
| 1233 |
+
"loss": 0.3459,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9406073636119323,
|
| 1238 |
+
"grad_norm": 1.7323066734927444,
|
| 1239 |
+
"learning_rate": 1.0616254937352966e-07,
|
| 1240 |
+
"loss": 0.3484,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9459822628325719,
|
| 1245 |
+
"grad_norm": 1.7917085698996813,
|
| 1246 |
+
"learning_rate": 8.779177294245044e-08,
|
| 1247 |
+
"loss": 0.3545,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9513571620532115,
|
| 1252 |
+
"grad_norm": 1.8063043505678373,
|
| 1253 |
+
"learning_rate": 7.115102342598101e-08,
|
| 1254 |
+
"loss": 0.3463,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9567320612738511,
|
| 1259 |
+
"grad_norm": 1.7402924935517343,
|
| 1260 |
+
"learning_rate": 5.6246161517158336e-08,
|
| 1261 |
+
"loss": 0.3443,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.9621069604944907,
|
| 1266 |
+
"grad_norm": 1.7772873395565845,
|
| 1267 |
+
"learning_rate": 4.308243654806643e-08,
|
| 1268 |
+
"loss": 0.3421,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.9674818597151303,
|
| 1273 |
+
"grad_norm": 1.7288228417548714,
|
| 1274 |
+
"learning_rate": 3.166448464108629e-08,
|
| 1275 |
+
"loss": 0.3493,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.97285675893577,
|
| 1280 |
+
"grad_norm": 1.7547077783156886,
|
| 1281 |
+
"learning_rate": 2.1996327076096446e-08,
|
| 1282 |
+
"loss": 0.3504,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9782316581564096,
|
| 1287 |
+
"grad_norm": 1.8190476476140809,
|
| 1288 |
+
"learning_rate": 1.4081368874226398e-08,
|
| 1289 |
+
"loss": 0.3463,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.9836065573770492,
|
| 1294 |
+
"grad_norm": 1.66337852034001,
|
| 1295 |
+
"learning_rate": 7.922397598642551e-09,
|
| 1296 |
+
"loss": 0.3459,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.9889814565976888,
|
| 1301 |
+
"grad_norm": 1.7288826649004094,
|
| 1302 |
+
"learning_rate": 3.5215823727974274e-09,
|
| 1303 |
+
"loss": 0.3501,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.9943563558183284,
|
| 1308 |
+
"grad_norm": 1.7197053184297024,
|
| 1309 |
+
"learning_rate": 8.804731164901991e-10,
|
| 1310 |
+
"loss": 0.3516,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.999731255038968,
|
| 1315 |
+
"grad_norm": 1.7184366358056455,
|
| 1316 |
+
"learning_rate": 0.0,
|
| 1317 |
+
"loss": 0.3536,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.999731255038968,
|
| 1322 |
+
"eval_loss": 0.27914658188819885,
|
| 1323 |
+
"eval_runtime": 1.1884,
|
| 1324 |
+
"eval_samples_per_second": 1.683,
|
| 1325 |
+
"eval_steps_per_second": 0.841,
|
| 1326 |
+
"step": 930
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.999731255038968,
|
| 1330 |
+
"step": 930,
|
| 1331 |
+
"total_flos": 194670734868480.0,
|
| 1332 |
+
"train_loss": 0.5080837889384198,
|
| 1333 |
+
"train_runtime": 21164.3008,
|
| 1334 |
+
"train_samples_per_second": 1.406,
|
| 1335 |
+
"train_steps_per_second": 0.044
|
| 1336 |
+
}
|
| 1337 |
+
],
|
| 1338 |
+
"logging_steps": 5,
|
| 1339 |
+
"max_steps": 930,
|
| 1340 |
+
"num_input_tokens_seen": 0,
|
| 1341 |
+
"num_train_epochs": 1,
|
| 1342 |
+
"save_steps": 100,
|
| 1343 |
+
"stateful_callbacks": {
|
| 1344 |
+
"TrainerControl": {
|
| 1345 |
+
"args": {
|
| 1346 |
+
"should_epoch_stop": false,
|
| 1347 |
+
"should_evaluate": false,
|
| 1348 |
+
"should_log": false,
|
| 1349 |
+
"should_save": true,
|
| 1350 |
+
"should_training_stop": true
|
| 1351 |
+
},
|
| 1352 |
+
"attributes": {}
|
| 1353 |
+
}
|
| 1354 |
+
},
|
| 1355 |
+
"total_flos": 194670734868480.0,
|
| 1356 |
+
"train_batch_size": 2,
|
| 1357 |
+
"trial_name": null,
|
| 1358 |
+
"trial_params": null
|
| 1359 |
+
}
|