Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep09_01-42-08_COE-CS-sv003/events.out.tfevents.1725846516.COE-CS-sv003.731003.0 +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_p0.1_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_p0.1_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: 0.3369
|
| 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 |
+
| 0.3403 | 1.0 | 1207 | 0.3369 |
|
| 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": 1.0,
|
| 3 |
+
"total_flos": 252668899491840.0,
|
| 4 |
+
"train_loss": 0.5252359404283411,
|
| 5 |
+
"train_runtime": 27071.2973,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.427,
|
| 8 |
+
"train_steps_per_second": 0.045
|
| 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_01-42-08_COE-CS-sv003/events.out.tfevents.1725846516.COE-CS-sv003.731003.0
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:f981c5b92e1b3880150fcf64f7a35df04dc7312b99770d2e89613e88ce05fa62
|
| 3 |
+
size 56823
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 252668899491840.0,
|
| 4 |
+
"train_loss": 0.5252359404283411,
|
| 5 |
+
"train_runtime": 27071.2973,
|
| 6 |
+
"train_samples": 98881,
|
| 7 |
+
"train_samples_per_second": 1.427,
|
| 8 |
+
"train_steps_per_second": 0.045
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1207,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0008285004142502071,
|
| 13 |
+
"grad_norm": 23.866117550094145,
|
| 14 |
+
"learning_rate": 8.264462809917357e-08,
|
| 15 |
+
"loss": 1.4163,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004142502071251036,
|
| 20 |
+
"grad_norm": 22.991207135218495,
|
| 21 |
+
"learning_rate": 4.132231404958678e-07,
|
| 22 |
+
"loss": 1.4008,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.008285004142502071,
|
| 27 |
+
"grad_norm": 8.161072224423009,
|
| 28 |
+
"learning_rate": 8.264462809917356e-07,
|
| 29 |
+
"loss": 1.3121,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012427506213753107,
|
| 34 |
+
"grad_norm": 10.651287293408194,
|
| 35 |
+
"learning_rate": 1.2396694214876035e-06,
|
| 36 |
+
"loss": 1.1732,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016570008285004142,
|
| 41 |
+
"grad_norm": 2.9695263532042517,
|
| 42 |
+
"learning_rate": 1.6528925619834712e-06,
|
| 43 |
+
"loss": 1.0137,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.020712510356255178,
|
| 48 |
+
"grad_norm": 3.0649608491168774,
|
| 49 |
+
"learning_rate": 2.066115702479339e-06,
|
| 50 |
+
"loss": 0.9608,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.024855012427506214,
|
| 55 |
+
"grad_norm": 2.4113702925470575,
|
| 56 |
+
"learning_rate": 2.479338842975207e-06,
|
| 57 |
+
"loss": 0.9263,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02899751449875725,
|
| 62 |
+
"grad_norm": 2.2764880745044525,
|
| 63 |
+
"learning_rate": 2.8925619834710743e-06,
|
| 64 |
+
"loss": 0.9069,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.033140016570008285,
|
| 69 |
+
"grad_norm": 2.307963331742189,
|
| 70 |
+
"learning_rate": 3.3057851239669424e-06,
|
| 71 |
+
"loss": 0.8949,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.037282518641259324,
|
| 76 |
+
"grad_norm": 2.290742694256339,
|
| 77 |
+
"learning_rate": 3.71900826446281e-06,
|
| 78 |
+
"loss": 0.8849,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.041425020712510356,
|
| 83 |
+
"grad_norm": 2.418716943098049,
|
| 84 |
+
"learning_rate": 4.132231404958678e-06,
|
| 85 |
+
"loss": 0.8662,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.045567522783761395,
|
| 90 |
+
"grad_norm": 2.256258952989886,
|
| 91 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 92 |
+
"loss": 0.8617,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04971002485501243,
|
| 97 |
+
"grad_norm": 2.3643676843983013,
|
| 98 |
+
"learning_rate": 4.958677685950414e-06,
|
| 99 |
+
"loss": 0.8434,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.053852526926263466,
|
| 104 |
+
"grad_norm": 2.51362497881208,
|
| 105 |
+
"learning_rate": 5.371900826446281e-06,
|
| 106 |
+
"loss": 0.8586,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0579950289975145,
|
| 111 |
+
"grad_norm": 2.409197722940547,
|
| 112 |
+
"learning_rate": 5.785123966942149e-06,
|
| 113 |
+
"loss": 0.8391,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06213753106876554,
|
| 118 |
+
"grad_norm": 2.504763734639035,
|
| 119 |
+
"learning_rate": 6.198347107438017e-06,
|
| 120 |
+
"loss": 0.8323,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06628003314001657,
|
| 125 |
+
"grad_norm": 2.342235286421664,
|
| 126 |
+
"learning_rate": 6.611570247933885e-06,
|
| 127 |
+
"loss": 0.8366,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07042253521126761,
|
| 132 |
+
"grad_norm": 2.601805905814255,
|
| 133 |
+
"learning_rate": 7.0247933884297525e-06,
|
| 134 |
+
"loss": 0.83,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07456503728251865,
|
| 139 |
+
"grad_norm": 2.4729528650877226,
|
| 140 |
+
"learning_rate": 7.43801652892562e-06,
|
| 141 |
+
"loss": 0.8193,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07870753935376967,
|
| 146 |
+
"grad_norm": 2.347978873060577,
|
| 147 |
+
"learning_rate": 7.851239669421489e-06,
|
| 148 |
+
"loss": 0.8108,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08285004142502071,
|
| 153 |
+
"grad_norm": 2.3865550609084005,
|
| 154 |
+
"learning_rate": 8.264462809917356e-06,
|
| 155 |
+
"loss": 0.8068,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.08699254349627175,
|
| 160 |
+
"grad_norm": 2.397866066956603,
|
| 161 |
+
"learning_rate": 8.677685950413224e-06,
|
| 162 |
+
"loss": 0.8146,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09113504556752279,
|
| 167 |
+
"grad_norm": 2.528140675905014,
|
| 168 |
+
"learning_rate": 9.090909090909091e-06,
|
| 169 |
+
"loss": 0.8014,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.09527754763877382,
|
| 174 |
+
"grad_norm": 2.5772809506040004,
|
| 175 |
+
"learning_rate": 9.50413223140496e-06,
|
| 176 |
+
"loss": 0.7929,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09942004971002485,
|
| 181 |
+
"grad_norm": 2.4698447608273226,
|
| 182 |
+
"learning_rate": 9.917355371900828e-06,
|
| 183 |
+
"loss": 0.7957,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1035625517812759,
|
| 188 |
+
"grad_norm": 2.4271647358481077,
|
| 189 |
+
"learning_rate": 9.999665269535307e-06,
|
| 190 |
+
"loss": 0.7947,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.10770505385252693,
|
| 195 |
+
"grad_norm": 2.399585162136438,
|
| 196 |
+
"learning_rate": 9.998305503833872e-06,
|
| 197 |
+
"loss": 0.7952,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11184755592377796,
|
| 202 |
+
"grad_norm": 2.356625988593114,
|
| 203 |
+
"learning_rate": 9.995900066492902e-06,
|
| 204 |
+
"loss": 0.7903,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.115990057995029,
|
| 209 |
+
"grad_norm": 2.3562051609533894,
|
| 210 |
+
"learning_rate": 9.992449460742464e-06,
|
| 211 |
+
"loss": 0.7855,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12013256006628004,
|
| 216 |
+
"grad_norm": 2.2315403444753925,
|
| 217 |
+
"learning_rate": 9.98795440846732e-06,
|
| 218 |
+
"loss": 0.7721,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12427506213753108,
|
| 223 |
+
"grad_norm": 2.3299296938897203,
|
| 224 |
+
"learning_rate": 9.982415850055902e-06,
|
| 225 |
+
"loss": 0.7733,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.12841756420878211,
|
| 230 |
+
"grad_norm": 2.176864153510824,
|
| 231 |
+
"learning_rate": 9.975834944203581e-06,
|
| 232 |
+
"loss": 0.7641,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13256006628003314,
|
| 237 |
+
"grad_norm": 2.189529036305693,
|
| 238 |
+
"learning_rate": 9.968213067670265e-06,
|
| 239 |
+
"loss": 0.7688,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.13670256835128416,
|
| 244 |
+
"grad_norm": 2.232386403924057,
|
| 245 |
+
"learning_rate": 9.959551814992364e-06,
|
| 246 |
+
"loss": 0.7458,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14084507042253522,
|
| 251 |
+
"grad_norm": 2.596315903481849,
|
| 252 |
+
"learning_rate": 9.949852998149217e-06,
|
| 253 |
+
"loss": 0.7621,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.14498757249378624,
|
| 258 |
+
"grad_norm": 2.2955324137983615,
|
| 259 |
+
"learning_rate": 9.939118646184007e-06,
|
| 260 |
+
"loss": 0.7456,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.1491300745650373,
|
| 265 |
+
"grad_norm": 2.5048442022915363,
|
| 266 |
+
"learning_rate": 9.927351004779275e-06,
|
| 267 |
+
"loss": 0.7536,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.15327257663628832,
|
| 272 |
+
"grad_norm": 2.373845911290789,
|
| 273 |
+
"learning_rate": 9.914552535787122e-06,
|
| 274 |
+
"loss": 0.7334,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15741507870753935,
|
| 279 |
+
"grad_norm": 2.490700611604481,
|
| 280 |
+
"learning_rate": 9.900725916714157e-06,
|
| 281 |
+
"loss": 0.7385,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1615575807787904,
|
| 286 |
+
"grad_norm": 2.4943108442217667,
|
| 287 |
+
"learning_rate": 9.885874040161373e-06,
|
| 288 |
+
"loss": 0.7226,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16570008285004142,
|
| 293 |
+
"grad_norm": 2.6495649004577753,
|
| 294 |
+
"learning_rate": 9.87000001321898e-06,
|
| 295 |
+
"loss": 0.7309,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.16984258492129245,
|
| 300 |
+
"grad_norm": 2.24352822185874,
|
| 301 |
+
"learning_rate": 9.853107156816393e-06,
|
| 302 |
+
"loss": 0.724,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.1739850869925435,
|
| 307 |
+
"grad_norm": 2.577647983056561,
|
| 308 |
+
"learning_rate": 9.835199005027477e-06,
|
| 309 |
+
"loss": 0.7137,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.17812758906379453,
|
| 314 |
+
"grad_norm": 2.4661359633344566,
|
| 315 |
+
"learning_rate": 9.816279304331202e-06,
|
| 316 |
+
"loss": 0.711,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18227009113504558,
|
| 321 |
+
"grad_norm": 2.3694444605967147,
|
| 322 |
+
"learning_rate": 9.79635201282785e-06,
|
| 323 |
+
"loss": 0.7101,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1864125932062966,
|
| 328 |
+
"grad_norm": 2.198135101539898,
|
| 329 |
+
"learning_rate": 9.775421299410977e-06,
|
| 330 |
+
"loss": 0.6933,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.19055509527754763,
|
| 335 |
+
"grad_norm": 2.3950158836366224,
|
| 336 |
+
"learning_rate": 9.753491542895237e-06,
|
| 337 |
+
"loss": 0.707,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.19469759734879868,
|
| 342 |
+
"grad_norm": 2.443771290836774,
|
| 343 |
+
"learning_rate": 9.730567331100333e-06,
|
| 344 |
+
"loss": 0.693,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1988400994200497,
|
| 349 |
+
"grad_norm": 2.69404610606291,
|
| 350 |
+
"learning_rate": 9.706653459891207e-06,
|
| 351 |
+
"loss": 0.6823,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.20298260149130073,
|
| 356 |
+
"grad_norm": 2.6424681261577265,
|
| 357 |
+
"learning_rate": 9.681754932174719e-06,
|
| 358 |
+
"loss": 0.6846,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2071251035625518,
|
| 363 |
+
"grad_norm": 2.3720791178993106,
|
| 364 |
+
"learning_rate": 9.655876956853025e-06,
|
| 365 |
+
"loss": 0.6829,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2112676056338028,
|
| 370 |
+
"grad_norm": 2.246578155524963,
|
| 371 |
+
"learning_rate": 9.629024947733836e-06,
|
| 372 |
+
"loss": 0.6802,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.21541010770505387,
|
| 377 |
+
"grad_norm": 2.532693053271893,
|
| 378 |
+
"learning_rate": 9.601204522397826e-06,
|
| 379 |
+
"loss": 0.6811,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2195526097763049,
|
| 384 |
+
"grad_norm": 2.3168391897960996,
|
| 385 |
+
"learning_rate": 9.572421501023403e-06,
|
| 386 |
+
"loss": 0.6737,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22369511184755592,
|
| 391 |
+
"grad_norm": 2.2740027059012102,
|
| 392 |
+
"learning_rate": 9.5426819051691e-06,
|
| 393 |
+
"loss": 0.6762,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.22783761391880697,
|
| 398 |
+
"grad_norm": 2.453598814349311,
|
| 399 |
+
"learning_rate": 9.511991956513828e-06,
|
| 400 |
+
"loss": 0.6689,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.231980115990058,
|
| 405 |
+
"grad_norm": 2.6061851377315857,
|
| 406 |
+
"learning_rate": 9.480358075555278e-06,
|
| 407 |
+
"loss": 0.6523,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.23612261806130902,
|
| 412 |
+
"grad_norm": 2.3350040791986517,
|
| 413 |
+
"learning_rate": 9.447786880266706e-06,
|
| 414 |
+
"loss": 0.6626,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.24026512013256007,
|
| 419 |
+
"grad_norm": 2.16738386427134,
|
| 420 |
+
"learning_rate": 9.414285184712432e-06,
|
| 421 |
+
"loss": 0.6526,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2444076222038111,
|
| 426 |
+
"grad_norm": 2.353502989995007,
|
| 427 |
+
"learning_rate": 9.37985999762229e-06,
|
| 428 |
+
"loss": 0.6503,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24855012427506215,
|
| 433 |
+
"grad_norm": 2.559615826375987,
|
| 434 |
+
"learning_rate": 9.344518520925377e-06,
|
| 435 |
+
"loss": 0.6409,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.2526926263463132,
|
| 440 |
+
"grad_norm": 2.2923285566494296,
|
| 441 |
+
"learning_rate": 9.308268148243355e-06,
|
| 442 |
+
"loss": 0.628,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.25683512841756423,
|
| 447 |
+
"grad_norm": 2.20361635294026,
|
| 448 |
+
"learning_rate": 9.271116463343692e-06,
|
| 449 |
+
"loss": 0.6401,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2609776304888152,
|
| 454 |
+
"grad_norm": 2.3077464669006966,
|
| 455 |
+
"learning_rate": 9.23307123855307e-06,
|
| 456 |
+
"loss": 0.6322,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.2651201325600663,
|
| 461 |
+
"grad_norm": 2.36438437607611,
|
| 462 |
+
"learning_rate": 9.194140433131397e-06,
|
| 463 |
+
"loss": 0.6122,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.26926263463131733,
|
| 468 |
+
"grad_norm": 2.3361508013893255,
|
| 469 |
+
"learning_rate": 9.154332191606671e-06,
|
| 470 |
+
"loss": 0.6279,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.27340513670256833,
|
| 475 |
+
"grad_norm": 2.3055892316817324,
|
| 476 |
+
"learning_rate": 9.113654842071114e-06,
|
| 477 |
+
"loss": 0.6136,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.2775476387738194,
|
| 482 |
+
"grad_norm": 2.150656102185965,
|
| 483 |
+
"learning_rate": 9.072116894438885e-06,
|
| 484 |
+
"loss": 0.6132,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.28169014084507044,
|
| 489 |
+
"grad_norm": 2.1980462175987707,
|
| 490 |
+
"learning_rate": 9.029727038665765e-06,
|
| 491 |
+
"loss": 0.6238,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.28583264291632143,
|
| 496 |
+
"grad_norm": 2.1777751804898915,
|
| 497 |
+
"learning_rate": 8.986494142931168e-06,
|
| 498 |
+
"loss": 0.6065,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.2899751449875725,
|
| 503 |
+
"grad_norm": 2.33402398930558,
|
| 504 |
+
"learning_rate": 8.94242725178288e-06,
|
| 505 |
+
"loss": 0.6107,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.29411764705882354,
|
| 510 |
+
"grad_norm": 2.2919553245717306,
|
| 511 |
+
"learning_rate": 8.89753558424488e-06,
|
| 512 |
+
"loss": 0.6065,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2982601491300746,
|
| 517 |
+
"grad_norm": 2.421470706741744,
|
| 518 |
+
"learning_rate": 8.851828531888692e-06,
|
| 519 |
+
"loss": 0.6123,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3024026512013256,
|
| 524 |
+
"grad_norm": 2.226227311801291,
|
| 525 |
+
"learning_rate": 8.805315656868587e-06,
|
| 526 |
+
"loss": 0.614,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.30654515327257664,
|
| 531 |
+
"grad_norm": 2.2094485446668233,
|
| 532 |
+
"learning_rate": 8.75800668992117e-06,
|
| 533 |
+
"loss": 0.5961,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3106876553438277,
|
| 538 |
+
"grad_norm": 2.172339243964824,
|
| 539 |
+
"learning_rate": 8.709911528329623e-06,
|
| 540 |
+
"loss": 0.5977,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3148301574150787,
|
| 545 |
+
"grad_norm": 2.202510437920946,
|
| 546 |
+
"learning_rate": 8.661040233853166e-06,
|
| 547 |
+
"loss": 0.5913,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.31897265948632975,
|
| 552 |
+
"grad_norm": 2.4240297905693535,
|
| 553 |
+
"learning_rate": 8.611403030622074e-06,
|
| 554 |
+
"loss": 0.5885,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3231151615575808,
|
| 559 |
+
"grad_norm": 2.3295900029200447,
|
| 560 |
+
"learning_rate": 8.561010302998734e-06,
|
| 561 |
+
"loss": 0.5754,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3272576636288318,
|
| 566 |
+
"grad_norm": 2.396863934008288,
|
| 567 |
+
"learning_rate": 8.509872593405189e-06,
|
| 568 |
+
"loss": 0.5852,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.33140016570008285,
|
| 573 |
+
"grad_norm": 2.292182476322964,
|
| 574 |
+
"learning_rate": 8.458000600117604e-06,
|
| 575 |
+
"loss": 0.5747,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3355426677713339,
|
| 580 |
+
"grad_norm": 2.317074544699955,
|
| 581 |
+
"learning_rate": 8.40540517502813e-06,
|
| 582 |
+
"loss": 0.5719,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3396851698425849,
|
| 587 |
+
"grad_norm": 2.1839364363051357,
|
| 588 |
+
"learning_rate": 8.35209732137463e-06,
|
| 589 |
+
"loss": 0.5718,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.34382767191383595,
|
| 594 |
+
"grad_norm": 2.252030122787996,
|
| 595 |
+
"learning_rate": 8.298088191438753e-06,
|
| 596 |
+
"loss": 0.5697,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.347970173985087,
|
| 601 |
+
"grad_norm": 2.1248298616099475,
|
| 602 |
+
"learning_rate": 8.243389084212808e-06,
|
| 603 |
+
"loss": 0.5523,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.352112676056338,
|
| 608 |
+
"grad_norm": 2.173293611964785,
|
| 609 |
+
"learning_rate": 8.188011443035962e-06,
|
| 610 |
+
"loss": 0.5447,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.35625517812758906,
|
| 615 |
+
"grad_norm": 2.1954256707470075,
|
| 616 |
+
"learning_rate": 8.131966853200226e-06,
|
| 617 |
+
"loss": 0.549,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.3603976801988401,
|
| 622 |
+
"grad_norm": 2.149878633517254,
|
| 623 |
+
"learning_rate": 8.075267039526764e-06,
|
| 624 |
+
"loss": 0.5499,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.36454018227009116,
|
| 629 |
+
"grad_norm": 2.4205240164300315,
|
| 630 |
+
"learning_rate": 8.017923863912989e-06,
|
| 631 |
+
"loss": 0.5575,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.36868268434134216,
|
| 636 |
+
"grad_norm": 2.0890174160238737,
|
| 637 |
+
"learning_rate": 7.959949322850994e-06,
|
| 638 |
+
"loss": 0.5453,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3728251864125932,
|
| 643 |
+
"grad_norm": 2.0946555310239887,
|
| 644 |
+
"learning_rate": 7.901355544917827e-06,
|
| 645 |
+
"loss": 0.5414,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.37696768848384427,
|
| 650 |
+
"grad_norm": 2.126619902644704,
|
| 651 |
+
"learning_rate": 7.842154788238124e-06,
|
| 652 |
+
"loss": 0.5495,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.38111019055509526,
|
| 657 |
+
"grad_norm": 2.2360988935530033,
|
| 658 |
+
"learning_rate": 7.782359437919644e-06,
|
| 659 |
+
"loss": 0.5438,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.3852526926263463,
|
| 664 |
+
"grad_norm": 2.1459033718890077,
|
| 665 |
+
"learning_rate": 7.721982003462255e-06,
|
| 666 |
+
"loss": 0.5353,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.38939519469759737,
|
| 671 |
+
"grad_norm": 2.283786387893568,
|
| 672 |
+
"learning_rate": 7.661035116140856e-06,
|
| 673 |
+
"loss": 0.5357,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.39353769676884837,
|
| 678 |
+
"grad_norm": 2.1816854698567,
|
| 679 |
+
"learning_rate": 7.599531526362873e-06,
|
| 680 |
+
"loss": 0.5449,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3976801988400994,
|
| 685 |
+
"grad_norm": 2.2069133172922255,
|
| 686 |
+
"learning_rate": 7.537484101000787e-06,
|
| 687 |
+
"loss": 0.526,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.40182270091135047,
|
| 692 |
+
"grad_norm": 2.118219362380726,
|
| 693 |
+
"learning_rate": 7.474905820700334e-06,
|
| 694 |
+
"loss": 0.534,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.40596520298260147,
|
| 699 |
+
"grad_norm": 2.264878177122059,
|
| 700 |
+
"learning_rate": 7.411809777164873e-06,
|
| 701 |
+
"loss": 0.5165,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4101077050538525,
|
| 706 |
+
"grad_norm": 2.1705389482990363,
|
| 707 |
+
"learning_rate": 7.3482091704165405e-06,
|
| 708 |
+
"loss": 0.5245,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4142502071251036,
|
| 713 |
+
"grad_norm": 2.2941159685489336,
|
| 714 |
+
"learning_rate": 7.284117306034733e-06,
|
| 715 |
+
"loss": 0.5103,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4183927091963546,
|
| 720 |
+
"grad_norm": 2.2324713585602254,
|
| 721 |
+
"learning_rate": 7.219547592372512e-06,
|
| 722 |
+
"loss": 0.5214,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.4225352112676056,
|
| 727 |
+
"grad_norm": 2.2391139429721236,
|
| 728 |
+
"learning_rate": 7.15451353775151e-06,
|
| 729 |
+
"loss": 0.5195,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4266777133388567,
|
| 734 |
+
"grad_norm": 2.2449960646697513,
|
| 735 |
+
"learning_rate": 7.089028747635908e-06,
|
| 736 |
+
"loss": 0.4994,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.43082021541010773,
|
| 741 |
+
"grad_norm": 2.4452540985802687,
|
| 742 |
+
"learning_rate": 7.023106921786118e-06,
|
| 743 |
+
"loss": 0.5079,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.43496271748135873,
|
| 748 |
+
"grad_norm": 2.1476468599114065,
|
| 749 |
+
"learning_rate": 6.956761851392706e-06,
|
| 750 |
+
"loss": 0.5122,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.4391052195526098,
|
| 755 |
+
"grad_norm": 2.216754671617839,
|
| 756 |
+
"learning_rate": 6.890007416191209e-06,
|
| 757 |
+
"loss": 0.508,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.44324772162386084,
|
| 762 |
+
"grad_norm": 2.0655580498022537,
|
| 763 |
+
"learning_rate": 6.822857581558423e-06,
|
| 764 |
+
"loss": 0.5005,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.44739022369511183,
|
| 769 |
+
"grad_norm": 2.1974636316633975,
|
| 770 |
+
"learning_rate": 6.7553263955907755e-06,
|
| 771 |
+
"loss": 0.4997,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.4515327257663629,
|
| 776 |
+
"grad_norm": 2.3612483703811127,
|
| 777 |
+
"learning_rate": 6.687427986165379e-06,
|
| 778 |
+
"loss": 0.4912,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.45567522783761394,
|
| 783 |
+
"grad_norm": 2.1051086338026055,
|
| 784 |
+
"learning_rate": 6.6191765579844205e-06,
|
| 785 |
+
"loss": 0.4958,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.45981772990886494,
|
| 790 |
+
"grad_norm": 2.1903547319110013,
|
| 791 |
+
"learning_rate": 6.550586389603451e-06,
|
| 792 |
+
"loss": 0.4876,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.463960231980116,
|
| 797 |
+
"grad_norm": 2.2727306239643523,
|
| 798 |
+
"learning_rate": 6.481671830444243e-06,
|
| 799 |
+
"loss": 0.4843,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.46810273405136704,
|
| 804 |
+
"grad_norm": 2.111227587642084,
|
| 805 |
+
"learning_rate": 6.412447297792818e-06,
|
| 806 |
+
"loss": 0.4716,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.47224523612261804,
|
| 811 |
+
"grad_norm": 2.205352360925359,
|
| 812 |
+
"learning_rate": 6.3429272737832726e-06,
|
| 813 |
+
"loss": 0.4784,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.4763877381938691,
|
| 818 |
+
"grad_norm": 2.16751009903555,
|
| 819 |
+
"learning_rate": 6.273126302368037e-06,
|
| 820 |
+
"loss": 0.487,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.48053024026512015,
|
| 825 |
+
"grad_norm": 2.1849501403147404,
|
| 826 |
+
"learning_rate": 6.203058986275207e-06,
|
| 827 |
+
"loss": 0.4727,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.48467274233637114,
|
| 832 |
+
"grad_norm": 2.2295368151988284,
|
| 833 |
+
"learning_rate": 6.132739983953579e-06,
|
| 834 |
+
"loss": 0.4687,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.4888152444076222,
|
| 839 |
+
"grad_norm": 2.101227396044922,
|
| 840 |
+
"learning_rate": 6.062184006506027e-06,
|
| 841 |
+
"loss": 0.4775,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.49295774647887325,
|
| 846 |
+
"grad_norm": 2.248193658880927,
|
| 847 |
+
"learning_rate": 5.991405814611855e-06,
|
| 848 |
+
"loss": 0.4665,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.4971002485501243,
|
| 853 |
+
"grad_norm": 2.2704834915264662,
|
| 854 |
+
"learning_rate": 5.920420215438794e-06,
|
| 855 |
+
"loss": 0.4789,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5012427506213754,
|
| 860 |
+
"grad_norm": 2.32381879564274,
|
| 861 |
+
"learning_rate": 5.849242059545259e-06,
|
| 862 |
+
"loss": 0.4697,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5053852526926264,
|
| 867 |
+
"grad_norm": 2.2576290726260373,
|
| 868 |
+
"learning_rate": 5.777886237773542e-06,
|
| 869 |
+
"loss": 0.4593,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5095277547638773,
|
| 874 |
+
"grad_norm": 2.135648372066762,
|
| 875 |
+
"learning_rate": 5.706367678134562e-06,
|
| 876 |
+
"loss": 0.4668,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5136702568351285,
|
| 881 |
+
"grad_norm": 2.07573918775664,
|
| 882 |
+
"learning_rate": 5.634701342684852e-06,
|
| 883 |
+
"loss": 0.4632,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5178127589063795,
|
| 888 |
+
"grad_norm": 2.1248245211465244,
|
| 889 |
+
"learning_rate": 5.562902224396416e-06,
|
| 890 |
+
"loss": 0.4595,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5219552609776305,
|
| 895 |
+
"grad_norm": 2.130098034424365,
|
| 896 |
+
"learning_rate": 5.49098534402012e-06,
|
| 897 |
+
"loss": 0.4598,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5260977630488816,
|
| 902 |
+
"grad_norm": 2.334633169152005,
|
| 903 |
+
"learning_rate": 5.418965746943281e-06,
|
| 904 |
+
"loss": 0.4559,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5302402651201326,
|
| 909 |
+
"grad_norm": 2.1778621060776193,
|
| 910 |
+
"learning_rate": 5.34685850004208e-06,
|
| 911 |
+
"loss": 0.4513,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5343827671913836,
|
| 916 |
+
"grad_norm": 2.168236740017704,
|
| 917 |
+
"learning_rate": 5.2746786885295034e-06,
|
| 918 |
+
"loss": 0.4556,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5385252692626347,
|
| 923 |
+
"grad_norm": 1.993317342719062,
|
| 924 |
+
"learning_rate": 5.2024414127994325e-06,
|
| 925 |
+
"loss": 0.4462,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.5426677713338857,
|
| 930 |
+
"grad_norm": 2.126792629247378,
|
| 931 |
+
"learning_rate": 5.13016178526756e-06,
|
| 932 |
+
"loss": 0.4365,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5468102734051367,
|
| 937 |
+
"grad_norm": 2.1107942879381727,
|
| 938 |
+
"learning_rate": 5.057854927209804e-06,
|
| 939 |
+
"loss": 0.4434,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.5509527754763878,
|
| 944 |
+
"grad_norm": 2.1123391684515815,
|
| 945 |
+
"learning_rate": 4.985535965598843e-06,
|
| 946 |
+
"loss": 0.4489,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.5550952775476388,
|
| 951 |
+
"grad_norm": 2.20383507837916,
|
| 952 |
+
"learning_rate": 4.913220029939491e-06,
|
| 953 |
+
"loss": 0.4426,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.5592377796188898,
|
| 958 |
+
"grad_norm": 2.024690328428114,
|
| 959 |
+
"learning_rate": 4.840922249103506e-06,
|
| 960 |
+
"loss": 0.4372,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.5633802816901409,
|
| 965 |
+
"grad_norm": 2.1658026493211713,
|
| 966 |
+
"learning_rate": 4.7686577481645745e-06,
|
| 967 |
+
"loss": 0.4344,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.5675227837613919,
|
| 972 |
+
"grad_norm": 2.130458226840472,
|
| 973 |
+
"learning_rate": 4.696441645234042e-06,
|
| 974 |
+
"loss": 0.4423,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.5716652858326429,
|
| 979 |
+
"grad_norm": 2.130335330283906,
|
| 980 |
+
"learning_rate": 4.624289048298147e-06,
|
| 981 |
+
"loss": 0.4324,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.575807787903894,
|
| 986 |
+
"grad_norm": 2.0262507094150077,
|
| 987 |
+
"learning_rate": 4.55221505205734e-06,
|
| 988 |
+
"loss": 0.4338,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.579950289975145,
|
| 993 |
+
"grad_norm": 2.0666888969605277,
|
| 994 |
+
"learning_rate": 4.480234734768393e-06,
|
| 995 |
+
"loss": 0.4286,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.584092792046396,
|
| 1000 |
+
"grad_norm": 2.0542477917888453,
|
| 1001 |
+
"learning_rate": 4.408363155089952e-06,
|
| 1002 |
+
"loss": 0.4307,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.5882352941176471,
|
| 1007 |
+
"grad_norm": 2.1776472324502327,
|
| 1008 |
+
"learning_rate": 4.3366153489321855e-06,
|
| 1009 |
+
"loss": 0.4344,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.5923777961888981,
|
| 1014 |
+
"grad_norm": 2.0982654105842475,
|
| 1015 |
+
"learning_rate": 4.265006326311199e-06,
|
| 1016 |
+
"loss": 0.418,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.5965202982601492,
|
| 1021 |
+
"grad_norm": 2.0399148247049363,
|
| 1022 |
+
"learning_rate": 4.1935510682088545e-06,
|
| 1023 |
+
"loss": 0.422,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6006628003314002,
|
| 1028 |
+
"grad_norm": 2.132392353626558,
|
| 1029 |
+
"learning_rate": 4.122264523438668e-06,
|
| 1030 |
+
"loss": 0.4122,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6048053024026512,
|
| 1035 |
+
"grad_norm": 2.0436310042803094,
|
| 1036 |
+
"learning_rate": 4.051161605518453e-06,
|
| 1037 |
+
"loss": 0.4233,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6089478044739023,
|
| 1042 |
+
"grad_norm": 2.0217278892738504,
|
| 1043 |
+
"learning_rate": 3.980257189550316e-06,
|
| 1044 |
+
"loss": 0.4226,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6130903065451533,
|
| 1049 |
+
"grad_norm": 1.8834806774575015,
|
| 1050 |
+
"learning_rate": 3.909566109108727e-06,
|
| 1051 |
+
"loss": 0.411,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6172328086164043,
|
| 1056 |
+
"grad_norm": 2.158825355814557,
|
| 1057 |
+
"learning_rate": 3.839103153137247e-06,
|
| 1058 |
+
"loss": 0.4175,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6213753106876554,
|
| 1063 |
+
"grad_norm": 2.1656769542527363,
|
| 1064 |
+
"learning_rate": 3.768883062854598e-06,
|
| 1065 |
+
"loss": 0.4178,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6255178127589064,
|
| 1070 |
+
"grad_norm": 2.028679198499099,
|
| 1071 |
+
"learning_rate": 3.6989205286707398e-06,
|
| 1072 |
+
"loss": 0.4169,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.6296603148301574,
|
| 1077 |
+
"grad_norm": 2.0638901993850087,
|
| 1078 |
+
"learning_rate": 3.6292301871135425e-06,
|
| 1079 |
+
"loss": 0.4074,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6338028169014085,
|
| 1084 |
+
"grad_norm": 2.1149502198751344,
|
| 1085 |
+
"learning_rate": 3.55982661776676e-06,
|
| 1086 |
+
"loss": 0.4126,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6379453189726595,
|
| 1091 |
+
"grad_norm": 2.242329346685076,
|
| 1092 |
+
"learning_rate": 3.4907243402199013e-06,
|
| 1093 |
+
"loss": 0.4165,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.6420878210439105,
|
| 1098 |
+
"grad_norm": 2.1066940525003326,
|
| 1099 |
+
"learning_rate": 3.4219378110306523e-06,
|
| 1100 |
+
"loss": 0.3997,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6462303231151616,
|
| 1105 |
+
"grad_norm": 2.169707690258044,
|
| 1106 |
+
"learning_rate": 3.353481420700495e-06,
|
| 1107 |
+
"loss": 0.4104,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.6503728251864126,
|
| 1112 |
+
"grad_norm": 2.098473714909255,
|
| 1113 |
+
"learning_rate": 3.285369490664133e-06,
|
| 1114 |
+
"loss": 0.3956,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.6545153272576636,
|
| 1119 |
+
"grad_norm": 2.1657310992501295,
|
| 1120 |
+
"learning_rate": 3.2176162702933816e-06,
|
| 1121 |
+
"loss": 0.4135,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.6586578293289147,
|
| 1126 |
+
"grad_norm": 2.1452143463915307,
|
| 1127 |
+
"learning_rate": 3.150235933916115e-06,
|
| 1128 |
+
"loss": 0.3934,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.6628003314001657,
|
| 1133 |
+
"grad_norm": 2.052594101769282,
|
| 1134 |
+
"learning_rate": 3.0832425778509235e-06,
|
| 1135 |
+
"loss": 0.3979,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.6669428334714167,
|
| 1140 |
+
"grad_norm": 2.0098945834829824,
|
| 1141 |
+
"learning_rate": 3.0166502174581012e-06,
|
| 1142 |
+
"loss": 0.3967,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.6710853355426678,
|
| 1147 |
+
"grad_norm": 2.042954604946958,
|
| 1148 |
+
"learning_rate": 2.950472784207544e-06,
|
| 1149 |
+
"loss": 0.3945,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.6752278376139188,
|
| 1154 |
+
"grad_norm": 2.0032403215865506,
|
| 1155 |
+
"learning_rate": 2.8847241227642255e-06,
|
| 1156 |
+
"loss": 0.3967,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.6793703396851698,
|
| 1161 |
+
"grad_norm": 2.1221545047500214,
|
| 1162 |
+
"learning_rate": 2.819417988091814e-06,
|
| 1163 |
+
"loss": 0.3868,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.6835128417564209,
|
| 1168 |
+
"grad_norm": 2.130884956811238,
|
| 1169 |
+
"learning_rate": 2.754568042575061e-06,
|
| 1170 |
+
"loss": 0.3922,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.6876553438276719,
|
| 1175 |
+
"grad_norm": 1.9774695256683483,
|
| 1176 |
+
"learning_rate": 2.6901878531615677e-06,
|
| 1177 |
+
"loss": 0.3901,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.6917978458989229,
|
| 1182 |
+
"grad_norm": 2.1120886925275055,
|
| 1183 |
+
"learning_rate": 2.6262908885235046e-06,
|
| 1184 |
+
"loss": 0.3941,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.695940347970174,
|
| 1189 |
+
"grad_norm": 2.045887267583242,
|
| 1190 |
+
"learning_rate": 2.5628905162398797e-06,
|
| 1191 |
+
"loss": 0.3959,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.700082850041425,
|
| 1196 |
+
"grad_norm": 1.8783748619115133,
|
| 1197 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 1198 |
+
"loss": 0.3806,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.704225352112676,
|
| 1203 |
+
"grad_norm": 2.08098731426819,
|
| 1204 |
+
"learning_rate": 2.4376324968286154e-06,
|
| 1205 |
+
"loss": 0.387,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7083678541839271,
|
| 1210 |
+
"grad_norm": 2.1586747995562705,
|
| 1211 |
+
"learning_rate": 2.375801054333409e-06,
|
| 1212 |
+
"loss": 0.3729,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7125103562551781,
|
| 1217 |
+
"grad_norm": 2.0279143582578616,
|
| 1218 |
+
"learning_rate": 2.3145186079753685e-06,
|
| 1219 |
+
"loss": 0.3758,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7166528583264291,
|
| 1224 |
+
"grad_norm": 2.2429697814696854,
|
| 1225 |
+
"learning_rate": 2.253797978362617e-06,
|
| 1226 |
+
"loss": 0.3786,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7207953603976802,
|
| 1231 |
+
"grad_norm": 2.0360034426541556,
|
| 1232 |
+
"learning_rate": 2.193651868568285e-06,
|
| 1233 |
+
"loss": 0.377,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7249378624689312,
|
| 1238 |
+
"grad_norm": 1.9725681488817448,
|
| 1239 |
+
"learning_rate": 2.1340928614729445e-06,
|
| 1240 |
+
"loss": 0.3721,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7290803645401823,
|
| 1245 |
+
"grad_norm": 2.103021145158836,
|
| 1246 |
+
"learning_rate": 2.075133417132223e-06,
|
| 1247 |
+
"loss": 0.3719,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.7332228666114333,
|
| 1252 |
+
"grad_norm": 2.092900322935167,
|
| 1253 |
+
"learning_rate": 2.016785870170079e-06,
|
| 1254 |
+
"loss": 0.3714,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.7373653686826843,
|
| 1259 |
+
"grad_norm": 2.0906479452415336,
|
| 1260 |
+
"learning_rate": 1.9590624271983406e-06,
|
| 1261 |
+
"loss": 0.3749,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.7415078707539354,
|
| 1266 |
+
"grad_norm": 2.096208214143563,
|
| 1267 |
+
"learning_rate": 1.9019751642630252e-06,
|
| 1268 |
+
"loss": 0.37,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.7456503728251864,
|
| 1273 |
+
"grad_norm": 2.0164719015170656,
|
| 1274 |
+
"learning_rate": 1.8455360243179537e-06,
|
| 1275 |
+
"loss": 0.3724,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.7497928748964374,
|
| 1280 |
+
"grad_norm": 1.9827943207162666,
|
| 1281 |
+
"learning_rate": 1.7897568147262323e-06,
|
| 1282 |
+
"loss": 0.3747,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.7539353769676885,
|
| 1287 |
+
"grad_norm": 1.9263424969881737,
|
| 1288 |
+
"learning_rate": 1.7346492047900897e-06,
|
| 1289 |
+
"loss": 0.3635,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.7580778790389395,
|
| 1294 |
+
"grad_norm": 2.2195829689186106,
|
| 1295 |
+
"learning_rate": 1.6802247233095914e-06,
|
| 1296 |
+
"loss": 0.3667,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.7622203811101905,
|
| 1301 |
+
"grad_norm": 2.0103741607119185,
|
| 1302 |
+
"learning_rate": 1.626494756170765e-06,
|
| 1303 |
+
"loss": 0.3692,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.7663628831814416,
|
| 1308 |
+
"grad_norm": 2.1097047260728963,
|
| 1309 |
+
"learning_rate": 1.5734705439636017e-06,
|
| 1310 |
+
"loss": 0.365,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.7705053852526926,
|
| 1315 |
+
"grad_norm": 2.036839326608303,
|
| 1316 |
+
"learning_rate": 1.5211631796304721e-06,
|
| 1317 |
+
"loss": 0.3648,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.7746478873239436,
|
| 1322 |
+
"grad_norm": 1.9414201763962056,
|
| 1323 |
+
"learning_rate": 1.46958360614543e-06,
|
| 1324 |
+
"loss": 0.3656,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.7787903893951947,
|
| 1329 |
+
"grad_norm": 2.047677571212274,
|
| 1330 |
+
"learning_rate": 1.4187426142248723e-06,
|
| 1331 |
+
"loss": 0.3542,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.7829328914664457,
|
| 1336 |
+
"grad_norm": 2.06103898039325,
|
| 1337 |
+
"learning_rate": 1.3686508400700787e-06,
|
| 1338 |
+
"loss": 0.3646,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.7870753935376967,
|
| 1343 |
+
"grad_norm": 2.0587768499958394,
|
| 1344 |
+
"learning_rate": 1.3193187631420462e-06,
|
| 1345 |
+
"loss": 0.3579,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.7912178956089478,
|
| 1350 |
+
"grad_norm": 1.9792392112511976,
|
| 1351 |
+
"learning_rate": 1.2707567039691505e-06,
|
| 1352 |
+
"loss": 0.3607,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.7953603976801988,
|
| 1357 |
+
"grad_norm": 1.9865516347697185,
|
| 1358 |
+
"learning_rate": 1.222974821988024e-06,
|
| 1359 |
+
"loss": 0.3588,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.7995028997514498,
|
| 1364 |
+
"grad_norm": 2.0887989420586055,
|
| 1365 |
+
"learning_rate": 1.1759831134181504e-06,
|
| 1366 |
+
"loss": 0.3604,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8036454018227009,
|
| 1371 |
+
"grad_norm": 2.1350401974441575,
|
| 1372 |
+
"learning_rate": 1.1297914091706086e-06,
|
| 1373 |
+
"loss": 0.3578,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8077879038939519,
|
| 1378 |
+
"grad_norm": 2.0023054097994417,
|
| 1379 |
+
"learning_rate": 1.0844093727913868e-06,
|
| 1380 |
+
"loss": 0.352,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8119304059652029,
|
| 1385 |
+
"grad_norm": 2.006501689438896,
|
| 1386 |
+
"learning_rate": 1.039846498439727e-06,
|
| 1387 |
+
"loss": 0.3508,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.816072908036454,
|
| 1392 |
+
"grad_norm": 2.1675559938665017,
|
| 1393 |
+
"learning_rate": 9.961121089018933e-07,
|
| 1394 |
+
"loss": 0.3513,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.820215410107705,
|
| 1399 |
+
"grad_norm": 1.9789546403226348,
|
| 1400 |
+
"learning_rate": 9.532153536407923e-07,
|
| 1401 |
+
"loss": 0.3548,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.824357912178956,
|
| 1406 |
+
"grad_norm": 2.2136680684771215,
|
| 1407 |
+
"learning_rate": 9.111652068818621e-07,
|
| 1408 |
+
"loss": 0.3515,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8285004142502072,
|
| 1413 |
+
"grad_norm": 2.0985287351131183,
|
| 1414 |
+
"learning_rate": 8.699704657356195e-07,
|
| 1415 |
+
"loss": 0.3494,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.8326429163214581,
|
| 1420 |
+
"grad_norm": 2.03602744057189,
|
| 1421 |
+
"learning_rate": 8.296397483572515e-07,
|
| 1422 |
+
"loss": 0.3502,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.8367854183927091,
|
| 1427 |
+
"grad_norm": 1.9529410237196838,
|
| 1428 |
+
"learning_rate": 7.901814921436624e-07,
|
| 1429 |
+
"loss": 0.3412,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.8409279204639603,
|
| 1434 |
+
"grad_norm": 2.056866748380538,
|
| 1435 |
+
"learning_rate": 7.516039519683105e-07,
|
| 1436 |
+
"loss": 0.3451,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.8450704225352113,
|
| 1441 |
+
"grad_norm": 2.1162292783700596,
|
| 1442 |
+
"learning_rate": 7.139151984542636e-07,
|
| 1443 |
+
"loss": 0.346,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.8492129246064622,
|
| 1448 |
+
"grad_norm": 2.199566140011582,
|
| 1449 |
+
"learning_rate": 6.771231162857722e-07,
|
| 1450 |
+
"loss": 0.3503,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.8533554266777134,
|
| 1455 |
+
"grad_norm": 2.071853569310024,
|
| 1456 |
+
"learning_rate": 6.412354025587509e-07,
|
| 1457 |
+
"loss": 0.3394,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.8574979287489644,
|
| 1462 |
+
"grad_norm": 1.9821516702262831,
|
| 1463 |
+
"learning_rate": 6.062595651705111e-07,
|
| 1464 |
+
"loss": 0.3599,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.8616404308202155,
|
| 1469 |
+
"grad_norm": 2.03084885183303,
|
| 1470 |
+
"learning_rate": 5.722029212490666e-07,
|
| 1471 |
+
"loss": 0.3473,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.8657829328914665,
|
| 1476 |
+
"grad_norm": 1.9891381030542377,
|
| 1477 |
+
"learning_rate": 5.390725956223531e-07,
|
| 1478 |
+
"loss": 0.3399,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8699254349627175,
|
| 1483 |
+
"grad_norm": 1.996858017795371,
|
| 1484 |
+
"learning_rate": 5.068755193276798e-07,
|
| 1485 |
+
"loss": 0.3438,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.8740679370339686,
|
| 1490 |
+
"grad_norm": 2.0102978075746436,
|
| 1491 |
+
"learning_rate": 4.756184281617121e-07,
|
| 1492 |
+
"loss": 0.3596,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.8782104391052196,
|
| 1497 |
+
"grad_norm": 2.096782816191255,
|
| 1498 |
+
"learning_rate": 4.4530786127131575e-07,
|
| 1499 |
+
"loss": 0.3426,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.8823529411764706,
|
| 1504 |
+
"grad_norm": 2.041538694858829,
|
| 1505 |
+
"learning_rate": 4.159501597855287e-07,
|
| 1506 |
+
"loss": 0.3469,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.8864954432477217,
|
| 1511 |
+
"grad_norm": 2.050624816044249,
|
| 1512 |
+
"learning_rate": 3.8755146548896784e-07,
|
| 1513 |
+
"loss": 0.3453,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.8906379453189727,
|
| 1518 |
+
"grad_norm": 2.134183615956234,
|
| 1519 |
+
"learning_rate": 3.6011771953693044e-07,
|
| 1520 |
+
"loss": 0.3383,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.8947804473902237,
|
| 1525 |
+
"grad_norm": 2.0340883063292456,
|
| 1526 |
+
"learning_rate": 3.336546612124758e-07,
|
| 1527 |
+
"loss": 0.3394,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.8989229494614748,
|
| 1532 |
+
"grad_norm": 2.142834891831593,
|
| 1533 |
+
"learning_rate": 3.081678267257404e-07,
|
| 1534 |
+
"loss": 0.3377,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.9030654515327258,
|
| 1539 |
+
"grad_norm": 2.1312482485517608,
|
| 1540 |
+
"learning_rate": 2.836625480557265e-07,
|
| 1541 |
+
"loss": 0.3347,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.9072079536039768,
|
| 1546 |
+
"grad_norm": 2.076260403631579,
|
| 1547 |
+
"learning_rate": 2.601439518348331e-07,
|
| 1548 |
+
"loss": 0.3408,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.9113504556752279,
|
| 1553 |
+
"grad_norm": 2.063238043755945,
|
| 1554 |
+
"learning_rate": 2.376169582763288e-07,
|
| 1555 |
+
"loss": 0.347,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.9154929577464789,
|
| 1560 |
+
"grad_norm": 2.045149868081977,
|
| 1561 |
+
"learning_rate": 2.1608628014502364e-07,
|
| 1562 |
+
"loss": 0.338,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.9196354598177299,
|
| 1567 |
+
"grad_norm": 2.0728146587926535,
|
| 1568 |
+
"learning_rate": 1.955564217713335e-07,
|
| 1569 |
+
"loss": 0.3385,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.923777961888981,
|
| 1574 |
+
"grad_norm": 1.980028386143511,
|
| 1575 |
+
"learning_rate": 1.7603167810894662e-07,
|
| 1576 |
+
"loss": 0.3397,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.927920463960232,
|
| 1581 |
+
"grad_norm": 2.040384287235922,
|
| 1582 |
+
"learning_rate": 1.5751613383630128e-07,
|
| 1583 |
+
"loss": 0.337,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.932062966031483,
|
| 1588 |
+
"grad_norm": 2.0668331131661337,
|
| 1589 |
+
"learning_rate": 1.4001366250204762e-07,
|
| 1590 |
+
"loss": 0.3432,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9362054681027341,
|
| 1595 |
+
"grad_norm": 2.1215696014539636,
|
| 1596 |
+
"learning_rate": 1.235279257146804e-07,
|
| 1597 |
+
"loss": 0.348,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.9403479701739851,
|
| 1602 |
+
"grad_norm": 2.0968064514077187,
|
| 1603 |
+
"learning_rate": 1.080623723765134e-07,
|
| 1604 |
+
"loss": 0.3351,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.9444904722452361,
|
| 1609 |
+
"grad_norm": 2.0386634215167305,
|
| 1610 |
+
"learning_rate": 9.362023796215036e-08,
|
| 1611 |
+
"loss": 0.335,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.9486329743164872,
|
| 1616 |
+
"grad_norm": 2.081961716266303,
|
| 1617 |
+
"learning_rate": 8.020454384160437e-08,
|
| 1618 |
+
"loss": 0.345,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.9527754763877382,
|
| 1623 |
+
"grad_norm": 2.0627875473620443,
|
| 1624 |
+
"learning_rate": 6.78180966482156e-08,
|
| 1625 |
+
"loss": 0.3367,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.9569179784589892,
|
| 1630 |
+
"grad_norm": 2.0611893408248587,
|
| 1631 |
+
"learning_rate": 5.646348769148491e-08,
|
| 1632 |
+
"loss": 0.3388,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.9610604805302403,
|
| 1637 |
+
"grad_norm": 2.1119589491438315,
|
| 1638 |
+
"learning_rate": 4.6143092414961396e-08,
|
| 1639 |
+
"loss": 0.3406,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.9652029826014913,
|
| 1644 |
+
"grad_norm": 2.0229820894857866,
|
| 1645 |
+
"learning_rate": 3.685906989928656e-08,
|
| 1646 |
+
"loss": 0.3446,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.9693454846727423,
|
| 1651 |
+
"grad_norm": 1.9950176331137996,
|
| 1652 |
+
"learning_rate": 2.861336241050061e-08,
|
| 1653 |
+
"loss": 0.3361,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.9734879867439934,
|
| 1658 |
+
"grad_norm": 2.051002382020688,
|
| 1659 |
+
"learning_rate": 2.1407694993714755e-08,
|
| 1660 |
+
"loss": 0.3352,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.9776304888152444,
|
| 1665 |
+
"grad_norm": 2.0952467848619967,
|
| 1666 |
+
"learning_rate": 1.5243575112218744e-08,
|
| 1667 |
+
"loss": 0.3278,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.9817729908864954,
|
| 1672 |
+
"grad_norm": 2.1473598929894164,
|
| 1673 |
+
"learning_rate": 1.0122292332114814e-08,
|
| 1674 |
+
"loss": 0.3386,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.9859154929577465,
|
| 1679 |
+
"grad_norm": 2.027802609236831,
|
| 1680 |
+
"learning_rate": 6.044918052531268e-09,
|
| 1681 |
+
"loss": 0.3429,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.9900579950289975,
|
| 1686 |
+
"grad_norm": 2.088880428637403,
|
| 1687 |
+
"learning_rate": 3.0123052814812203e-09,
|
| 1688 |
+
"loss": 0.3452,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.9942004971002486,
|
| 1693 |
+
"grad_norm": 2.1283431853256705,
|
| 1694 |
+
"learning_rate": 1.025088457409229e-09,
|
| 1695 |
+
"loss": 0.3321,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.9983429991714996,
|
| 1700 |
+
"grad_norm": 1.953227804218852,
|
| 1701 |
+
"learning_rate": 8.368331646302353e-11,
|
| 1702 |
+
"loss": 0.3403,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.0,
|
| 1707 |
+
"eval_loss": 0.33688703179359436,
|
| 1708 |
+
"eval_runtime": 1.1942,
|
| 1709 |
+
"eval_samples_per_second": 2.512,
|
| 1710 |
+
"eval_steps_per_second": 0.837,
|
| 1711 |
+
"step": 1207
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.0,
|
| 1715 |
+
"step": 1207,
|
| 1716 |
+
"total_flos": 252668899491840.0,
|
| 1717 |
+
"train_loss": 0.5252359404283411,
|
| 1718 |
+
"train_runtime": 27071.2973,
|
| 1719 |
+
"train_samples_per_second": 1.427,
|
| 1720 |
+
"train_steps_per_second": 0.045
|
| 1721 |
+
}
|
| 1722 |
+
],
|
| 1723 |
+
"logging_steps": 5,
|
| 1724 |
+
"max_steps": 1207,
|
| 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": 252668899491840.0,
|
| 1741 |
+
"train_batch_size": 2,
|
| 1742 |
+
"trial_name": null,
|
| 1743 |
+
"trial_params": null
|
| 1744 |
+
}
|