Model save
Browse files- README.md +70 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1208 -0
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Mistral-7B-Instruct-v0.2-mirage-mistral-sft-instruct
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Mistral-7B-Instruct-v0.2-mirage-mistral-sft-instruct
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2758
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 64
|
| 48 |
+
- total_eval_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.2844 | 0.2480 | 200 | 0.3115 |
|
| 59 |
+
| 0.2638 | 0.4960 | 400 | 0.2921 |
|
| 60 |
+
| 0.2596 | 0.7440 | 600 | 0.2790 |
|
| 61 |
+
| 0.2458 | 0.9919 | 800 | 0.2758 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- PEFT 0.7.1
|
| 67 |
+
- Transformers 4.41.2
|
| 68 |
+
- Pytorch 2.3.0+cu121
|
| 69 |
+
- Datasets 2.20.0
|
| 70 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b383e72d425a845a7746a389142436b34268870b6c9d8c29d7589538431c49f0
|
| 3 |
size 83946192
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9993800371977681,
|
| 3 |
+
"total_flos": 2.076935220048691e+16,
|
| 4 |
+
"train_loss": 0.28037568409153013,
|
| 5 |
+
"train_runtime": 38684.7769,
|
| 6 |
+
"train_samples": 51593,
|
| 7 |
+
"train_samples_per_second": 1.334,
|
| 8 |
+
"train_steps_per_second": 0.021
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9993800371977681,
|
| 3 |
+
"total_flos": 2.076935220048691e+16,
|
| 4 |
+
"train_loss": 0.28037568409153013,
|
| 5 |
+
"train_runtime": 38684.7769,
|
| 6 |
+
"train_samples": 51593,
|
| 7 |
+
"train_samples_per_second": 1.334,
|
| 8 |
+
"train_steps_per_second": 0.021
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9993800371977681,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 806,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0012399256044637321,
|
| 13 |
+
"grad_norm": 0.6019122951437104,
|
| 14 |
+
"learning_rate": 2.469135802469136e-06,
|
| 15 |
+
"loss": 0.4222,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006199628022318661,
|
| 20 |
+
"grad_norm": 1.5495790328852515,
|
| 21 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 22 |
+
"loss": 0.471,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012399256044637322,
|
| 27 |
+
"grad_norm": 0.9274998509045178,
|
| 28 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 29 |
+
"loss": 0.4844,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.018598884066955982,
|
| 34 |
+
"grad_norm": 0.4319451186674129,
|
| 35 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 36 |
+
"loss": 0.4111,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.024798512089274645,
|
| 41 |
+
"grad_norm": 0.5038186551413125,
|
| 42 |
+
"learning_rate": 4.938271604938271e-05,
|
| 43 |
+
"loss": 0.3561,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.030998140111593304,
|
| 48 |
+
"grad_norm": 0.44167588919852313,
|
| 49 |
+
"learning_rate": 6.17283950617284e-05,
|
| 50 |
+
"loss": 0.347,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.037197768133911964,
|
| 55 |
+
"grad_norm": 0.33451826071357504,
|
| 56 |
+
"learning_rate": 7.407407407407407e-05,
|
| 57 |
+
"loss": 0.3322,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04339739615623062,
|
| 62 |
+
"grad_norm": 0.34868148088717704,
|
| 63 |
+
"learning_rate": 8.641975308641975e-05,
|
| 64 |
+
"loss": 0.3399,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04959702417854929,
|
| 69 |
+
"grad_norm": 0.3356513986019191,
|
| 70 |
+
"learning_rate": 9.876543209876543e-05,
|
| 71 |
+
"loss": 0.3602,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05579665220086795,
|
| 76 |
+
"grad_norm": 0.37808175632129626,
|
| 77 |
+
"learning_rate": 0.00011111111111111112,
|
| 78 |
+
"loss": 0.321,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06199628022318661,
|
| 83 |
+
"grad_norm": 0.41761376999084465,
|
| 84 |
+
"learning_rate": 0.0001234567901234568,
|
| 85 |
+
"loss": 0.3504,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06819590824550527,
|
| 90 |
+
"grad_norm": 0.35639408007374757,
|
| 91 |
+
"learning_rate": 0.00013580246913580247,
|
| 92 |
+
"loss": 0.3108,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07439553626782393,
|
| 97 |
+
"grad_norm": 0.34681060518951073,
|
| 98 |
+
"learning_rate": 0.00014814814814814815,
|
| 99 |
+
"loss": 0.305,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08059516429014259,
|
| 104 |
+
"grad_norm": 0.29992433196050555,
|
| 105 |
+
"learning_rate": 0.00016049382716049385,
|
| 106 |
+
"loss": 0.3127,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08679479231246125,
|
| 111 |
+
"grad_norm": 0.37053951666137375,
|
| 112 |
+
"learning_rate": 0.0001728395061728395,
|
| 113 |
+
"loss": 0.2985,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0929944203347799,
|
| 118 |
+
"grad_norm": 0.3241692211944496,
|
| 119 |
+
"learning_rate": 0.0001851851851851852,
|
| 120 |
+
"loss": 0.3187,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09919404835709858,
|
| 125 |
+
"grad_norm": 0.3336770081253457,
|
| 126 |
+
"learning_rate": 0.00019753086419753085,
|
| 127 |
+
"loss": 0.3013,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.10539367637941724,
|
| 132 |
+
"grad_norm": 0.340347188617851,
|
| 133 |
+
"learning_rate": 0.0001999849788616454,
|
| 134 |
+
"loss": 0.3127,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1115933044017359,
|
| 139 |
+
"grad_norm": 0.24966989402744666,
|
| 140 |
+
"learning_rate": 0.00019992396322115213,
|
| 141 |
+
"loss": 0.3132,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.11779293242405456,
|
| 146 |
+
"grad_norm": 0.36652120591883697,
|
| 147 |
+
"learning_rate": 0.00019981604287632102,
|
| 148 |
+
"loss": 0.2848,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.12399256044637322,
|
| 153 |
+
"grad_norm": 0.37152546200115255,
|
| 154 |
+
"learning_rate": 0.0001996612684853896,
|
| 155 |
+
"loss": 0.3074,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.13019218846869188,
|
| 160 |
+
"grad_norm": 0.37937877581455376,
|
| 161 |
+
"learning_rate": 0.00019945971270007043,
|
| 162 |
+
"loss": 0.2966,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.13639181649101054,
|
| 167 |
+
"grad_norm": 0.32819913975467047,
|
| 168 |
+
"learning_rate": 0.0001992114701314478,
|
| 169 |
+
"loss": 0.2973,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1425914445133292,
|
| 174 |
+
"grad_norm": 0.2497292935586131,
|
| 175 |
+
"learning_rate": 0.00019891665730556725,
|
| 176 |
+
"loss": 0.3072,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.14879107253564786,
|
| 181 |
+
"grad_norm": 0.3383083276284943,
|
| 182 |
+
"learning_rate": 0.0001985754126087376,
|
| 183 |
+
"loss": 0.2657,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.15499070055796652,
|
| 188 |
+
"grad_norm": 0.4050699278620848,
|
| 189 |
+
"learning_rate": 0.00019818789622257196,
|
| 190 |
+
"loss": 0.2882,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.16119032858028517,
|
| 195 |
+
"grad_norm": 0.3123213984265953,
|
| 196 |
+
"learning_rate": 0.0001977542900487977,
|
| 197 |
+
"loss": 0.2765,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.16738995660260383,
|
| 202 |
+
"grad_norm": 0.33824727842613916,
|
| 203 |
+
"learning_rate": 0.00019727479762387116,
|
| 204 |
+
"loss": 0.3042,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1735895846249225,
|
| 209 |
+
"grad_norm": 0.2424449276469738,
|
| 210 |
+
"learning_rate": 0.00019674964402343684,
|
| 211 |
+
"loss": 0.3264,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.17978921264724115,
|
| 216 |
+
"grad_norm": 0.3067543075934479,
|
| 217 |
+
"learning_rate": 0.00019617907575667602,
|
| 218 |
+
"loss": 0.2886,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1859888406695598,
|
| 223 |
+
"grad_norm": 0.362577361435356,
|
| 224 |
+
"learning_rate": 0.00019556336065059432,
|
| 225 |
+
"loss": 0.3086,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.1921884686918785,
|
| 230 |
+
"grad_norm": 0.3238274733762567,
|
| 231 |
+
"learning_rate": 0.00019490278772430256,
|
| 232 |
+
"loss": 0.2963,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.19838809671419716,
|
| 237 |
+
"grad_norm": 0.3597604834062663,
|
| 238 |
+
"learning_rate": 0.00019419766705335026,
|
| 239 |
+
"loss": 0.313,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.20458772473651582,
|
| 244 |
+
"grad_norm": 0.27740278103597305,
|
| 245 |
+
"learning_rate": 0.00019344832962417475,
|
| 246 |
+
"loss": 0.3236,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.21078735275883448,
|
| 251 |
+
"grad_norm": 0.31990061265265674,
|
| 252 |
+
"learning_rate": 0.00019265512717873498,
|
| 253 |
+
"loss": 0.2907,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.21698698078115314,
|
| 258 |
+
"grad_norm": 0.3521599467310119,
|
| 259 |
+
"learning_rate": 0.00019181843204940232,
|
| 260 |
+
"loss": 0.2933,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2231866088034718,
|
| 265 |
+
"grad_norm": 0.32261509567312185,
|
| 266 |
+
"learning_rate": 0.00019093863698418627,
|
| 267 |
+
"loss": 0.2852,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.22938623682579046,
|
| 272 |
+
"grad_norm": 0.29712733472005987,
|
| 273 |
+
"learning_rate": 0.00019001615496237712,
|
| 274 |
+
"loss": 0.2868,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.23558586484810912,
|
| 279 |
+
"grad_norm": 0.24705896150819331,
|
| 280 |
+
"learning_rate": 0.00018905141900069178,
|
| 281 |
+
"loss": 0.314,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.24178549287042778,
|
| 286 |
+
"grad_norm": 0.31936683972288543,
|
| 287 |
+
"learning_rate": 0.00018804488195001392,
|
| 288 |
+
"loss": 0.2696,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.24798512089274644,
|
| 293 |
+
"grad_norm": 0.32950608272624643,
|
| 294 |
+
"learning_rate": 0.00018699701628282407,
|
| 295 |
+
"loss": 0.2844,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.24798512089274644,
|
| 300 |
+
"eval_loss": 0.3114877939224243,
|
| 301 |
+
"eval_runtime": 1124.0065,
|
| 302 |
+
"eval_samples_per_second": 3.559,
|
| 303 |
+
"eval_steps_per_second": 0.111,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2541847489150651,
|
| 308 |
+
"grad_norm": 0.37057110121612846,
|
| 309 |
+
"learning_rate": 0.0001859083138714191,
|
| 310 |
+
"loss": 0.2852,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.26038437693738375,
|
| 315 |
+
"grad_norm": 0.2869667980293731,
|
| 316 |
+
"learning_rate": 0.0001847792857570255,
|
| 317 |
+
"loss": 0.2905,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.2665840049597024,
|
| 322 |
+
"grad_norm": 0.24148834606008088,
|
| 323 |
+
"learning_rate": 0.00018361046190991455,
|
| 324 |
+
"loss": 0.2841,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2727836329820211,
|
| 329 |
+
"grad_norm": 0.3669480816784026,
|
| 330 |
+
"learning_rate": 0.0001824023909806322,
|
| 331 |
+
"loss": 0.2745,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.27898326100433973,
|
| 336 |
+
"grad_norm": 0.3054046475344961,
|
| 337 |
+
"learning_rate": 0.00018115564004246023,
|
| 338 |
+
"loss": 0.2803,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2851828890266584,
|
| 343 |
+
"grad_norm": 0.3589718511823372,
|
| 344 |
+
"learning_rate": 0.00017987079432522996,
|
| 345 |
+
"loss": 0.2834,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.29138251704897705,
|
| 350 |
+
"grad_norm": 0.32815022889743933,
|
| 351 |
+
"learning_rate": 0.00017854845694061292,
|
| 352 |
+
"loss": 0.2956,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2975821450712957,
|
| 357 |
+
"grad_norm": 0.22811456346947673,
|
| 358 |
+
"learning_rate": 0.00017718924859901793,
|
| 359 |
+
"loss": 0.2992,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.30378177309361437,
|
| 364 |
+
"grad_norm": 0.3261921325400897,
|
| 365 |
+
"learning_rate": 0.00017579380731822712,
|
| 366 |
+
"loss": 0.2696,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.30998140111593303,
|
| 371 |
+
"grad_norm": 0.3265151909802919,
|
| 372 |
+
"learning_rate": 0.00017436278812390786,
|
| 373 |
+
"loss": 0.2762,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3161810291382517,
|
| 378 |
+
"grad_norm": 0.25119517956050147,
|
| 379 |
+
"learning_rate": 0.00017289686274214118,
|
| 380 |
+
"loss": 0.2758,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.32238065716057035,
|
| 385 |
+
"grad_norm": 0.30203405562074537,
|
| 386 |
+
"learning_rate": 0.00017139671928411072,
|
| 387 |
+
"loss": 0.2888,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.328580285182889,
|
| 392 |
+
"grad_norm": 0.231597052058556,
|
| 393 |
+
"learning_rate": 0.00016986306192310084,
|
| 394 |
+
"loss": 0.2994,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.33477991320520767,
|
| 399 |
+
"grad_norm": 0.3462354390170321,
|
| 400 |
+
"learning_rate": 0.00016829661056395474,
|
| 401 |
+
"loss": 0.273,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.34097954122752633,
|
| 406 |
+
"grad_norm": 0.3416446609085483,
|
| 407 |
+
"learning_rate": 0.00016669810050514827,
|
| 408 |
+
"loss": 0.2794,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.347179169249845,
|
| 413 |
+
"grad_norm": 0.3004081195597297,
|
| 414 |
+
"learning_rate": 0.00016506828209363796,
|
| 415 |
+
"loss": 0.2785,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.35337879727216365,
|
| 420 |
+
"grad_norm": 0.3372149956322208,
|
| 421 |
+
"learning_rate": 0.00016340792037264527,
|
| 422 |
+
"loss": 0.2924,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3595784252944823,
|
| 427 |
+
"grad_norm": 0.2773063250024901,
|
| 428 |
+
"learning_rate": 0.00016171779472254206,
|
| 429 |
+
"loss": 0.2824,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.36577805331680097,
|
| 434 |
+
"grad_norm": 0.29747563137485017,
|
| 435 |
+
"learning_rate": 0.0001599986984950065,
|
| 436 |
+
"loss": 0.2787,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.3719776813391196,
|
| 441 |
+
"grad_norm": 0.3237809552896745,
|
| 442 |
+
"learning_rate": 0.0001582514386406206,
|
| 443 |
+
"loss": 0.2821,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.37817730936143834,
|
| 448 |
+
"grad_norm": 0.29633580280256444,
|
| 449 |
+
"learning_rate": 0.00015647683533008455,
|
| 450 |
+
"loss": 0.2777,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.384376937383757,
|
| 455 |
+
"grad_norm": 0.3580023136614935,
|
| 456 |
+
"learning_rate": 0.00015467572156922503,
|
| 457 |
+
"loss": 0.2717,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.39057656540607566,
|
| 462 |
+
"grad_norm": 0.2483260531032943,
|
| 463 |
+
"learning_rate": 0.0001528489428079793,
|
| 464 |
+
"loss": 0.3054,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3967761934283943,
|
| 469 |
+
"grad_norm": 0.3058237506306256,
|
| 470 |
+
"learning_rate": 0.00015099735654353747,
|
| 471 |
+
"loss": 0.2724,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.402975821450713,
|
| 476 |
+
"grad_norm": 0.3309948471867418,
|
| 477 |
+
"learning_rate": 0.00014912183191782995,
|
| 478 |
+
"loss": 0.2607,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.40917544947303164,
|
| 483 |
+
"grad_norm": 0.3163723023278254,
|
| 484 |
+
"learning_rate": 0.00014722324930954885,
|
| 485 |
+
"loss": 0.2881,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4153750774953503,
|
| 490 |
+
"grad_norm": 0.30350103196436556,
|
| 491 |
+
"learning_rate": 0.0001453024999208946,
|
| 492 |
+
"loss": 0.2817,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.42157470551766896,
|
| 497 |
+
"grad_norm": 0.22626437910720568,
|
| 498 |
+
"learning_rate": 0.00014336048535924223,
|
| 499 |
+
"loss": 0.2838,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4277743335399876,
|
| 504 |
+
"grad_norm": 0.3445629260554824,
|
| 505 |
+
"learning_rate": 0.00014139811721392324,
|
| 506 |
+
"loss": 0.2552,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4339739615623063,
|
| 511 |
+
"grad_norm": 0.33697169212335193,
|
| 512 |
+
"learning_rate": 0.00013941631662832199,
|
| 513 |
+
"loss": 0.2738,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.44017358958462494,
|
| 518 |
+
"grad_norm": 0.27110424764249635,
|
| 519 |
+
"learning_rate": 0.00013741601386748728,
|
| 520 |
+
"loss": 0.2837,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4463732176069436,
|
| 525 |
+
"grad_norm": 0.3176558105393564,
|
| 526 |
+
"learning_rate": 0.00013539814788146235,
|
| 527 |
+
"loss": 0.277,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.45257284562926225,
|
| 532 |
+
"grad_norm": 0.21215927511567548,
|
| 533 |
+
"learning_rate": 0.00013336366586453783,
|
| 534 |
+
"loss": 0.2827,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4587724736515809,
|
| 539 |
+
"grad_norm": 0.31096775561405154,
|
| 540 |
+
"learning_rate": 0.0001313135228106353,
|
| 541 |
+
"loss": 0.2651,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4649721016738996,
|
| 546 |
+
"grad_norm": 0.31585451791739527,
|
| 547 |
+
"learning_rate": 0.0001292486810650289,
|
| 548 |
+
"loss": 0.2773,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.47117172969621823,
|
| 553 |
+
"grad_norm": 0.3080807025298427,
|
| 554 |
+
"learning_rate": 0.00012717010987261715,
|
| 555 |
+
"loss": 0.2873,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4773713577185369,
|
| 560 |
+
"grad_norm": 0.3591626086115439,
|
| 561 |
+
"learning_rate": 0.0001250787849229552,
|
| 562 |
+
"loss": 0.2827,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.48357098574085555,
|
| 567 |
+
"grad_norm": 0.25352609144718685,
|
| 568 |
+
"learning_rate": 0.00012297568789226238,
|
| 569 |
+
"loss": 0.2958,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4897706137631742,
|
| 574 |
+
"grad_norm": 0.30645533387883167,
|
| 575 |
+
"learning_rate": 0.00012086180598261956,
|
| 576 |
+
"loss": 0.2597,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.49597024178549287,
|
| 581 |
+
"grad_norm": 0.33773747309079233,
|
| 582 |
+
"learning_rate": 0.00011873813145857249,
|
| 583 |
+
"loss": 0.2638,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.49597024178549287,
|
| 588 |
+
"eval_loss": 0.29208001494407654,
|
| 589 |
+
"eval_runtime": 1119.5912,
|
| 590 |
+
"eval_samples_per_second": 3.573,
|
| 591 |
+
"eval_steps_per_second": 0.112,
|
| 592 |
+
"step": 400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5021698698078115,
|
| 596 |
+
"grad_norm": 0.3152505586487655,
|
| 597 |
+
"learning_rate": 0.00011660566118135894,
|
| 598 |
+
"loss": 0.2656,
|
| 599 |
+
"step": 405
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.5083694978301302,
|
| 603 |
+
"grad_norm": 0.29454612946664416,
|
| 604 |
+
"learning_rate": 0.00011446539614097813,
|
| 605 |
+
"loss": 0.27,
|
| 606 |
+
"step": 410
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.5145691258524488,
|
| 610 |
+
"grad_norm": 0.1892793890960918,
|
| 611 |
+
"learning_rate": 0.0001123183409863219,
|
| 612 |
+
"loss": 0.2978,
|
| 613 |
+
"step": 415
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.5207687538747675,
|
| 617 |
+
"grad_norm": 0.3335006508167189,
|
| 618 |
+
"learning_rate": 0.00011016550355358872,
|
| 619 |
+
"loss": 0.2538,
|
| 620 |
+
"step": 420
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.5269683818970862,
|
| 624 |
+
"grad_norm": 0.32122639513136675,
|
| 625 |
+
"learning_rate": 0.00010800789439320128,
|
| 626 |
+
"loss": 0.2778,
|
| 627 |
+
"step": 425
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.5331680099194048,
|
| 631 |
+
"grad_norm": 0.2771952164280048,
|
| 632 |
+
"learning_rate": 0.00010584652629545011,
|
| 633 |
+
"loss": 0.2634,
|
| 634 |
+
"step": 430
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5393676379417235,
|
| 638 |
+
"grad_norm": 0.34208078840367095,
|
| 639 |
+
"learning_rate": 0.0001036824138150859,
|
| 640 |
+
"loss": 0.2759,
|
| 641 |
+
"step": 435
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.5455672659640421,
|
| 645 |
+
"grad_norm": 0.21374327433641943,
|
| 646 |
+
"learning_rate": 0.00010151657279508336,
|
| 647 |
+
"loss": 0.2818,
|
| 648 |
+
"step": 440
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.5517668939863608,
|
| 652 |
+
"grad_norm": 0.28462533877594465,
|
| 653 |
+
"learning_rate": 9.935001988980061e-05,
|
| 654 |
+
"loss": 0.2661,
|
| 655 |
+
"step": 445
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.5579665220086795,
|
| 659 |
+
"grad_norm": 0.3047348276188714,
|
| 660 |
+
"learning_rate": 9.718377208775744e-05,
|
| 661 |
+
"loss": 0.2677,
|
| 662 |
+
"step": 450
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.5641661500309981,
|
| 666 |
+
"grad_norm": 0.30754878782389855,
|
| 667 |
+
"learning_rate": 9.50188462342571e-05,
|
| 668 |
+
"loss": 0.2614,
|
| 669 |
+
"step": 455
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.5703657780533168,
|
| 673 |
+
"grad_norm": 0.31116409658881644,
|
| 674 |
+
"learning_rate": 9.285625855407484e-05,
|
| 675 |
+
"loss": 0.2673,
|
| 676 |
+
"step": 460
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.5765654060756354,
|
| 680 |
+
"grad_norm": 0.2651806274866606,
|
| 681 |
+
"learning_rate": 9.069702417443821e-05,
|
| 682 |
+
"loss": 0.2869,
|
| 683 |
+
"step": 465
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.5827650340979541,
|
| 687 |
+
"grad_norm": 0.2909752165016893,
|
| 688 |
+
"learning_rate": 8.854215664852206e-05,
|
| 689 |
+
"loss": 0.2669,
|
| 690 |
+
"step": 470
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.5889646621202728,
|
| 694 |
+
"grad_norm": 0.30706363315844515,
|
| 695 |
+
"learning_rate": 8.63926674796829e-05,
|
| 696 |
+
"loss": 0.2674,
|
| 697 |
+
"step": 475
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5951642901425914,
|
| 701 |
+
"grad_norm": 0.30444202963242784,
|
| 702 |
+
"learning_rate": 8.424956564665508e-05,
|
| 703 |
+
"loss": 0.2802,
|
| 704 |
+
"step": 480
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.6013639181649101,
|
| 708 |
+
"grad_norm": 0.2789382860436405,
|
| 709 |
+
"learning_rate": 8.211385712993218e-05,
|
| 710 |
+
"loss": 0.2545,
|
| 711 |
+
"step": 485
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.6075635461872287,
|
| 715 |
+
"grad_norm": 0.23185325685334424,
|
| 716 |
+
"learning_rate": 7.998654443955586e-05,
|
| 717 |
+
"loss": 0.266,
|
| 718 |
+
"step": 490
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.6137631742095474,
|
| 722 |
+
"grad_norm": 0.3567624100649805,
|
| 723 |
+
"learning_rate": 7.786862614453355e-05,
|
| 724 |
+
"loss": 0.2665,
|
| 725 |
+
"step": 495
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.6199628022318661,
|
| 729 |
+
"grad_norm": 0.31757337819796233,
|
| 730 |
+
"learning_rate": 7.576109640410633e-05,
|
| 731 |
+
"loss": 0.2692,
|
| 732 |
+
"step": 500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.6261624302541847,
|
| 736 |
+
"grad_norm": 0.26049216875661646,
|
| 737 |
+
"learning_rate": 7.366494450108659e-05,
|
| 738 |
+
"loss": 0.253,
|
| 739 |
+
"step": 505
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.6323620582765034,
|
| 743 |
+
"grad_norm": 0.3279613920140163,
|
| 744 |
+
"learning_rate": 7.158115437748468e-05,
|
| 745 |
+
"loss": 0.2664,
|
| 746 |
+
"step": 510
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.638561686298822,
|
| 750 |
+
"grad_norm": 0.24958219949066954,
|
| 751 |
+
"learning_rate": 6.951070417264277e-05,
|
| 752 |
+
"loss": 0.282,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.6447613143211407,
|
| 757 |
+
"grad_norm": 0.3076230934858842,
|
| 758 |
+
"learning_rate": 6.745456576409227e-05,
|
| 759 |
+
"loss": 0.2541,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.6509609423434594,
|
| 764 |
+
"grad_norm": 0.3039043398796431,
|
| 765 |
+
"learning_rate": 6.541370431135072e-05,
|
| 766 |
+
"loss": 0.2648,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.657160570365778,
|
| 771 |
+
"grad_norm": 0.2823892989212078,
|
| 772 |
+
"learning_rate": 6.338907780287197e-05,
|
| 773 |
+
"loss": 0.2628,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.6633601983880967,
|
| 778 |
+
"grad_norm": 0.336100443174608,
|
| 779 |
+
"learning_rate": 6.138163660636284e-05,
|
| 780 |
+
"loss": 0.2609,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.6695598264104153,
|
| 785 |
+
"grad_norm": 0.22183756693967047,
|
| 786 |
+
"learning_rate": 5.9392323022676454e-05,
|
| 787 |
+
"loss": 0.2679,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.675759454432734,
|
| 792 |
+
"grad_norm": 0.30501277104459634,
|
| 793 |
+
"learning_rate": 5.7422070843492734e-05,
|
| 794 |
+
"loss": 0.2551,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.6819590824550527,
|
| 799 |
+
"grad_norm": 0.35227300737647005,
|
| 800 |
+
"learning_rate": 5.547180491299279e-05,
|
| 801 |
+
"loss": 0.2715,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.6881587104773713,
|
| 806 |
+
"grad_norm": 0.2645763624948684,
|
| 807 |
+
"learning_rate": 5.35424406937333e-05,
|
| 808 |
+
"loss": 0.2633,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.69435833849969,
|
| 813 |
+
"grad_norm": 0.2707425078158492,
|
| 814 |
+
"learning_rate": 5.163488383692499e-05,
|
| 815 |
+
"loss": 0.2677,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.7005579665220086,
|
| 820 |
+
"grad_norm": 0.24608132828527818,
|
| 821 |
+
"learning_rate": 4.975002975731613e-05,
|
| 822 |
+
"loss": 0.2763,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.7067575945443273,
|
| 827 |
+
"grad_norm": 0.2726783082526773,
|
| 828 |
+
"learning_rate": 4.78887632128814e-05,
|
| 829 |
+
"loss": 0.2428,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.712957222566646,
|
| 834 |
+
"grad_norm": 0.2981132504685635,
|
| 835 |
+
"learning_rate": 4.6051957889513e-05,
|
| 836 |
+
"loss": 0.2608,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.7191568505889646,
|
| 841 |
+
"grad_norm": 0.28491523081281545,
|
| 842 |
+
"learning_rate": 4.4240475990909106e-05,
|
| 843 |
+
"loss": 0.2569,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.7253564786112833,
|
| 848 |
+
"grad_norm": 0.3291243871750603,
|
| 849 |
+
"learning_rate": 4.24551678338518e-05,
|
| 850 |
+
"loss": 0.2612,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.7315561066336019,
|
| 855 |
+
"grad_norm": 0.2259584584201018,
|
| 856 |
+
"learning_rate": 4.069687144906532e-05,
|
| 857 |
+
"loss": 0.2696,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.7377557346559206,
|
| 862 |
+
"grad_norm": 0.330497624658356,
|
| 863 |
+
"learning_rate": 3.8966412187840804e-05,
|
| 864 |
+
"loss": 0.2478,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.7439553626782393,
|
| 869 |
+
"grad_norm": 0.2741703824563164,
|
| 870 |
+
"learning_rate": 3.726460233461339e-05,
|
| 871 |
+
"loss": 0.2596,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.7439553626782393,
|
| 876 |
+
"eval_loss": 0.2790033519268036,
|
| 877 |
+
"eval_runtime": 1119.6634,
|
| 878 |
+
"eval_samples_per_second": 3.573,
|
| 879 |
+
"eval_steps_per_second": 0.112,
|
| 880 |
+
"step": 600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.750154990700558,
|
| 884 |
+
"grad_norm": 0.25878146862151746,
|
| 885 |
+
"learning_rate": 3.5592240725672476e-05,
|
| 886 |
+
"loss": 0.2631,
|
| 887 |
+
"step": 605
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.7563546187228767,
|
| 891 |
+
"grad_norm": 0.30340990736911533,
|
| 892 |
+
"learning_rate": 3.395011237418494e-05,
|
| 893 |
+
"loss": 0.2649,
|
| 894 |
+
"step": 610
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.7625542467451953,
|
| 898 |
+
"grad_norm": 0.21196981539625306,
|
| 899 |
+
"learning_rate": 3.2338988101706726e-05,
|
| 900 |
+
"loss": 0.2519,
|
| 901 |
+
"step": 615
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.768753874767514,
|
| 905 |
+
"grad_norm": 0.2881373960219632,
|
| 906 |
+
"learning_rate": 3.075962417635634e-05,
|
| 907 |
+
"loss": 0.2371,
|
| 908 |
+
"step": 620
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.7749535027898327,
|
| 912 |
+
"grad_norm": 0.31620268309069777,
|
| 913 |
+
"learning_rate": 2.9212761957819347e-05,
|
| 914 |
+
"loss": 0.2726,
|
| 915 |
+
"step": 625
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.7811531308121513,
|
| 919 |
+
"grad_norm": 0.2675293914015534,
|
| 920 |
+
"learning_rate": 2.7699127549351456e-05,
|
| 921 |
+
"loss": 0.2723,
|
| 922 |
+
"step": 630
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.78735275883447,
|
| 926 |
+
"grad_norm": 0.3208257587309821,
|
| 927 |
+
"learning_rate": 2.6219431456942535e-05,
|
| 928 |
+
"loss": 0.2662,
|
| 929 |
+
"step": 635
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.7935523868567886,
|
| 933 |
+
"grad_norm": 0.20931592628778878,
|
| 934 |
+
"learning_rate": 2.4774368255802483e-05,
|
| 935 |
+
"loss": 0.2662,
|
| 936 |
+
"step": 640
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.7997520148791073,
|
| 940 |
+
"grad_norm": 0.2722392147736918,
|
| 941 |
+
"learning_rate": 2.3364616264324722e-05,
|
| 942 |
+
"loss": 0.2528,
|
| 943 |
+
"step": 645
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.805951642901426,
|
| 947 |
+
"grad_norm": 0.29854156869280446,
|
| 948 |
+
"learning_rate": 2.199083722568095e-05,
|
| 949 |
+
"loss": 0.2612,
|
| 950 |
+
"step": 650
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.8121512709237446,
|
| 954 |
+
"grad_norm": 0.2760187147243271,
|
| 955 |
+
"learning_rate": 2.065367599719621e-05,
|
| 956 |
+
"loss": 0.2646,
|
| 957 |
+
"step": 655
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.8183508989460633,
|
| 961 |
+
"grad_norm": 0.29187099026880386,
|
| 962 |
+
"learning_rate": 1.93537602476504e-05,
|
| 963 |
+
"loss": 0.2574,
|
| 964 |
+
"step": 660
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.8245505269683819,
|
| 968 |
+
"grad_norm": 0.21386029056799546,
|
| 969 |
+
"learning_rate": 1.809170016264794e-05,
|
| 970 |
+
"loss": 0.2563,
|
| 971 |
+
"step": 665
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.8307501549907006,
|
| 975 |
+
"grad_norm": 0.2823252915248677,
|
| 976 |
+
"learning_rate": 1.686808815819435e-05,
|
| 977 |
+
"loss": 0.2669,
|
| 978 |
+
"step": 670
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.8369497830130193,
|
| 982 |
+
"grad_norm": 0.33535005943488133,
|
| 983 |
+
"learning_rate": 1.568349860261369e-05,
|
| 984 |
+
"loss": 0.2507,
|
| 985 |
+
"step": 675
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.8431494110353379,
|
| 989 |
+
"grad_norm": 0.29068903551261105,
|
| 990 |
+
"learning_rate": 1.4538487546937952e-05,
|
| 991 |
+
"loss": 0.2679,
|
| 992 |
+
"step": 680
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.8493490390576566,
|
| 996 |
+
"grad_norm": 0.31428561712386854,
|
| 997 |
+
"learning_rate": 1.3433592463894373e-05,
|
| 998 |
+
"loss": 0.256,
|
| 999 |
+
"step": 685
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.8555486670799752,
|
| 1003 |
+
"grad_norm": 0.2492283063735335,
|
| 1004 |
+
"learning_rate": 1.2369331995613665e-05,
|
| 1005 |
+
"loss": 0.2701,
|
| 1006 |
+
"step": 690
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.8617482951022939,
|
| 1010 |
+
"grad_norm": 0.29516035417057684,
|
| 1011 |
+
"learning_rate": 1.1346205710177304e-05,
|
| 1012 |
+
"loss": 0.2317,
|
| 1013 |
+
"step": 695
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.8679479231246126,
|
| 1017 |
+
"grad_norm": 0.34660496611894304,
|
| 1018 |
+
"learning_rate": 1.0364693867118424e-05,
|
| 1019 |
+
"loss": 0.2581,
|
| 1020 |
+
"step": 700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.8741475511469312,
|
| 1024 |
+
"grad_norm": 0.27935452297059005,
|
| 1025 |
+
"learning_rate": 9.425257191985859e-06,
|
| 1026 |
+
"loss": 0.2501,
|
| 1027 |
+
"step": 705
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.8803471791692499,
|
| 1031 |
+
"grad_norm": 0.2975961434950699,
|
| 1032 |
+
"learning_rate": 8.528336660077974e-06,
|
| 1033 |
+
"loss": 0.2598,
|
| 1034 |
+
"step": 710
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.8865468071915685,
|
| 1038 |
+
"grad_norm": 0.21801979336484165,
|
| 1039 |
+
"learning_rate": 7.674353289446945e-06,
|
| 1040 |
+
"loss": 0.2662,
|
| 1041 |
+
"step": 715
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.8927464352138872,
|
| 1045 |
+
"grad_norm": 0.34419068158586147,
|
| 1046 |
+
"learning_rate": 6.863707943271325e-06,
|
| 1047 |
+
"loss": 0.235,
|
| 1048 |
+
"step": 720
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.8989460632362059,
|
| 1052 |
+
"grad_norm": 0.3428004067461644,
|
| 1053 |
+
"learning_rate": 6.096781141689223e-06,
|
| 1054 |
+
"loss": 0.2548,
|
| 1055 |
+
"step": 725
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.9051456912585245,
|
| 1059 |
+
"grad_norm": 0.25288813676576166,
|
| 1060 |
+
"learning_rate": 5.373932883180655e-06,
|
| 1061 |
+
"loss": 0.248,
|
| 1062 |
+
"step": 730
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.9113453192808432,
|
| 1066 |
+
"grad_norm": 0.279501011714134,
|
| 1067 |
+
"learning_rate": 4.695502475582814e-06,
|
| 1068 |
+
"loss": 0.2486,
|
| 1069 |
+
"step": 735
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.9175449473031618,
|
| 1073 |
+
"grad_norm": 0.2244165751957654,
|
| 1074 |
+
"learning_rate": 4.0618083768177e-06,
|
| 1075 |
+
"loss": 0.2594,
|
| 1076 |
+
"step": 740
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.9237445753254805,
|
| 1080 |
+
"grad_norm": 0.30028321537895275,
|
| 1081 |
+
"learning_rate": 3.4731480454065825e-06,
|
| 1082 |
+
"loss": 0.243,
|
| 1083 |
+
"step": 745
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.9299442033477991,
|
| 1087 |
+
"grad_norm": 0.34186025440033796,
|
| 1088 |
+
"learning_rate": 2.92979780084196e-06,
|
| 1089 |
+
"loss": 0.2454,
|
| 1090 |
+
"step": 750
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.9361438313701178,
|
| 1094 |
+
"grad_norm": 0.27131508037063784,
|
| 1095 |
+
"learning_rate": 2.4320126938819023e-06,
|
| 1096 |
+
"loss": 0.2464,
|
| 1097 |
+
"step": 755
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.9423434593924365,
|
| 1101 |
+
"grad_norm": 0.30864982789113204,
|
| 1102 |
+
"learning_rate": 1.980026386828371e-06,
|
| 1103 |
+
"loss": 0.2577,
|
| 1104 |
+
"step": 760
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.9485430874147551,
|
| 1108 |
+
"grad_norm": 0.22799699963033782,
|
| 1109 |
+
"learning_rate": 1.5740510438451371e-06,
|
| 1110 |
+
"loss": 0.2658,
|
| 1111 |
+
"step": 765
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.9547427154370738,
|
| 1115 |
+
"grad_norm": 0.2796812629005932,
|
| 1116 |
+
"learning_rate": 1.214277231367078e-06,
|
| 1117 |
+
"loss": 0.2615,
|
| 1118 |
+
"step": 770
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.9609423434593924,
|
| 1122 |
+
"grad_norm": 0.2906770373909308,
|
| 1123 |
+
"learning_rate": 9.008738286475749e-07,
|
| 1124 |
+
"loss": 0.2557,
|
| 1125 |
+
"step": 775
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.9671419714817111,
|
| 1129 |
+
"grad_norm": 0.30664325433457473,
|
| 1130 |
+
"learning_rate": 6.339879484858924e-07,
|
| 1131 |
+
"loss": 0.2485,
|
| 1132 |
+
"step": 780
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.9733415995040298,
|
| 1136 |
+
"grad_norm": 0.3437865129781069,
|
| 1137 |
+
"learning_rate": 4.1374486817183924e-07,
|
| 1138 |
+
"loss": 0.2514,
|
| 1139 |
+
"step": 785
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.9795412275263484,
|
| 1143 |
+
"grad_norm": 0.2189635610441498,
|
| 1144 |
+
"learning_rate": 2.402479706801741e-07,
|
| 1145 |
+
"loss": 0.2845,
|
| 1146 |
+
"step": 790
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.9857408555486671,
|
| 1150 |
+
"grad_norm": 0.30929816396563364,
|
| 1151 |
+
"learning_rate": 1.1357869614212479e-07,
|
| 1152 |
+
"loss": 0.2564,
|
| 1153 |
+
"step": 795
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.9919404835709857,
|
| 1157 |
+
"grad_norm": 0.31984749573339155,
|
| 1158 |
+
"learning_rate": 3.379650361716724e-08,
|
| 1159 |
+
"loss": 0.2458,
|
| 1160 |
+
"step": 800
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.9919404835709857,
|
| 1164 |
+
"eval_loss": 0.2757934629917145,
|
| 1165 |
+
"eval_runtime": 1122.4404,
|
| 1166 |
+
"eval_samples_per_second": 3.564,
|
| 1167 |
+
"eval_steps_per_second": 0.111,
|
| 1168 |
+
"step": 800
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.9981401115933044,
|
| 1172 |
+
"grad_norm": 0.28178798746795625,
|
| 1173 |
+
"learning_rate": 9.388431826629073e-10,
|
| 1174 |
+
"loss": 0.2537,
|
| 1175 |
+
"step": 805
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.9993800371977681,
|
| 1179 |
+
"step": 806,
|
| 1180 |
+
"total_flos": 2.076935220048691e+16,
|
| 1181 |
+
"train_loss": 0.28037568409153013,
|
| 1182 |
+
"train_runtime": 38684.7769,
|
| 1183 |
+
"train_samples_per_second": 1.334,
|
| 1184 |
+
"train_steps_per_second": 0.021
|
| 1185 |
+
}
|
| 1186 |
+
],
|
| 1187 |
+
"logging_steps": 5,
|
| 1188 |
+
"max_steps": 806,
|
| 1189 |
+
"num_input_tokens_seen": 0,
|
| 1190 |
+
"num_train_epochs": 1,
|
| 1191 |
+
"save_steps": 200,
|
| 1192 |
+
"stateful_callbacks": {
|
| 1193 |
+
"TrainerControl": {
|
| 1194 |
+
"args": {
|
| 1195 |
+
"should_epoch_stop": false,
|
| 1196 |
+
"should_evaluate": false,
|
| 1197 |
+
"should_log": false,
|
| 1198 |
+
"should_save": true,
|
| 1199 |
+
"should_training_stop": false
|
| 1200 |
+
},
|
| 1201 |
+
"attributes": {}
|
| 1202 |
+
}
|
| 1203 |
+
},
|
| 1204 |
+
"total_flos": 2.076935220048691e+16,
|
| 1205 |
+
"train_batch_size": 8,
|
| 1206 |
+
"trial_name": null,
|
| 1207 |
+
"trial_params": null
|
| 1208 |
+
}
|