Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- runs/Aug31_20-00-12_COE-CS-sv003/events.out.tfevents.1725134679.COE-CS-sv003.3492139.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +645 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: feedback_p0.1_seed42_level2_rare
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# feedback_p0.1_seed42_level2_rare
|
| 20 |
+
|
| 21 |
+
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.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.9004
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 128
|
| 50 |
+
- total_eval_batch_size: 4
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 0.8811 | 0.9988 | 423 | 0.9004 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.11.1
|
| 66 |
+
- Transformers 4.43.4
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 2.19.1
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9988193624557261,
|
| 3 |
+
"total_flos": 1701364321222656.0,
|
| 4 |
+
"train_loss": 0.9762231091799184,
|
| 5 |
+
"train_runtime": 12298.1539,
|
| 6 |
+
"train_samples": 90047,
|
| 7 |
+
"train_samples_per_second": 4.405,
|
| 8 |
+
"train_steps_per_second": 0.034
|
| 9 |
+
}
|
runs/Aug31_20-00-12_COE-CS-sv003/events.out.tfevents.1725134679.COE-CS-sv003.3492139.0
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:ba6012582efbe7e93a643463abbb00d854187ef6082fc1a7b66cdd4997329fa7
|
| 3 |
+
size 23677
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9988193624557261,
|
| 3 |
+
"total_flos": 1701364321222656.0,
|
| 4 |
+
"train_loss": 0.9762231091799184,
|
| 5 |
+
"train_runtime": 12298.1539,
|
| 6 |
+
"train_samples": 90047,
|
| 7 |
+
"train_samples_per_second": 4.405,
|
| 8 |
+
"train_steps_per_second": 0.034
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9988193624557261,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 423,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0023612750885478157,
|
| 13 |
+
"grad_norm": 2.076144772146165,
|
| 14 |
+
"learning_rate": 2.3255813953488374e-07,
|
| 15 |
+
"loss": 1.5599,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.011806375442739079,
|
| 20 |
+
"grad_norm": 2.0790308307649474,
|
| 21 |
+
"learning_rate": 1.1627906976744188e-06,
|
| 22 |
+
"loss": 1.5677,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.023612750885478158,
|
| 27 |
+
"grad_norm": 2.0012552002239015,
|
| 28 |
+
"learning_rate": 2.3255813953488376e-06,
|
| 29 |
+
"loss": 1.5676,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03541912632821724,
|
| 34 |
+
"grad_norm": 1.8029125522774907,
|
| 35 |
+
"learning_rate": 3.4883720930232564e-06,
|
| 36 |
+
"loss": 1.5496,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.047225501770956316,
|
| 41 |
+
"grad_norm": 1.5366911813713426,
|
| 42 |
+
"learning_rate": 4.651162790697675e-06,
|
| 43 |
+
"loss": 1.5073,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0590318772136954,
|
| 48 |
+
"grad_norm": 1.15288952321188,
|
| 49 |
+
"learning_rate": 5.8139534883720935e-06,
|
| 50 |
+
"loss": 1.4721,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07083825265643448,
|
| 55 |
+
"grad_norm": 0.8788084960337258,
|
| 56 |
+
"learning_rate": 6.976744186046513e-06,
|
| 57 |
+
"loss": 1.4226,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08264462809917356,
|
| 62 |
+
"grad_norm": 0.7427556918141682,
|
| 63 |
+
"learning_rate": 8.139534883720931e-06,
|
| 64 |
+
"loss": 1.3826,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09445100354191263,
|
| 69 |
+
"grad_norm": 0.7304797066851969,
|
| 70 |
+
"learning_rate": 9.30232558139535e-06,
|
| 71 |
+
"loss": 1.3468,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10625737898465171,
|
| 76 |
+
"grad_norm": 0.7059242113707709,
|
| 77 |
+
"learning_rate": 9.999316524962347e-06,
|
| 78 |
+
"loss": 1.2972,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1180637544273908,
|
| 83 |
+
"grad_norm": 0.6583420607175058,
|
| 84 |
+
"learning_rate": 9.991629576543164e-06,
|
| 85 |
+
"loss": 1.2514,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12987012987012986,
|
| 90 |
+
"grad_norm": 0.7052267168168249,
|
| 91 |
+
"learning_rate": 9.975414512725058e-06,
|
| 92 |
+
"loss": 1.2064,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14167650531286896,
|
| 97 |
+
"grad_norm": 0.7953507814585752,
|
| 98 |
+
"learning_rate": 9.95069903667256e-06,
|
| 99 |
+
"loss": 1.141,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15348288075560804,
|
| 104 |
+
"grad_norm": 0.7040999205365234,
|
| 105 |
+
"learning_rate": 9.917525374361913e-06,
|
| 106 |
+
"loss": 1.0903,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1652892561983471,
|
| 111 |
+
"grad_norm": 0.49774178618410275,
|
| 112 |
+
"learning_rate": 9.8759502024387e-06,
|
| 113 |
+
"loss": 1.0358,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1770956316410862,
|
| 118 |
+
"grad_norm": 0.3979506170145657,
|
| 119 |
+
"learning_rate": 9.826044551386743e-06,
|
| 120 |
+
"loss": 1.0108,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.18890200708382526,
|
| 125 |
+
"grad_norm": 0.3592564248086942,
|
| 126 |
+
"learning_rate": 9.767893684173722e-06,
|
| 127 |
+
"loss": 0.9903,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.20070838252656434,
|
| 132 |
+
"grad_norm": 0.3100433480431281,
|
| 133 |
+
"learning_rate": 9.701596950580807e-06,
|
| 134 |
+
"loss": 0.9802,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.21251475796930341,
|
| 139 |
+
"grad_norm": 0.29254652561679195,
|
| 140 |
+
"learning_rate": 9.627267617465243e-06,
|
| 141 |
+
"loss": 0.9727,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2243211334120425,
|
| 146 |
+
"grad_norm": 0.28591179700225494,
|
| 147 |
+
"learning_rate": 9.545032675245814e-06,
|
| 148 |
+
"loss": 0.9649,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2361275088547816,
|
| 153 |
+
"grad_norm": 0.25951903429965284,
|
| 154 |
+
"learning_rate": 9.45503262094184e-06,
|
| 155 |
+
"loss": 0.9475,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24793388429752067,
|
| 160 |
+
"grad_norm": 0.2563158359962438,
|
| 161 |
+
"learning_rate": 9.357421218136387e-06,
|
| 162 |
+
"loss": 0.9512,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2597402597402597,
|
| 167 |
+
"grad_norm": 0.2314934921504106,
|
| 168 |
+
"learning_rate": 9.252365234273754e-06,
|
| 169 |
+
"loss": 0.9315,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2715466351829988,
|
| 174 |
+
"grad_norm": 0.22648204221178658,
|
| 175 |
+
"learning_rate": 9.140044155740102e-06,
|
| 176 |
+
"loss": 0.9331,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2833530106257379,
|
| 181 |
+
"grad_norm": 0.22855760026108562,
|
| 182 |
+
"learning_rate": 9.02064988121396e-06,
|
| 183 |
+
"loss": 0.9281,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.29515938606847697,
|
| 188 |
+
"grad_norm": 0.23051819672441418,
|
| 189 |
+
"learning_rate": 8.894386393810563e-06,
|
| 190 |
+
"loss": 0.9244,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3069657615112161,
|
| 195 |
+
"grad_norm": 0.21787273370263488,
|
| 196 |
+
"learning_rate": 8.761469412580126e-06,
|
| 197 |
+
"loss": 0.922,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3187721369539551,
|
| 202 |
+
"grad_norm": 0.22368732408818312,
|
| 203 |
+
"learning_rate": 8.622126023955446e-06,
|
| 204 |
+
"loss": 0.9278,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3305785123966942,
|
| 209 |
+
"grad_norm": 0.2199630006396667,
|
| 210 |
+
"learning_rate": 8.476594293778561e-06,
|
| 211 |
+
"loss": 0.9166,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.34238488783943327,
|
| 216 |
+
"grad_norm": 0.22565816759515664,
|
| 217 |
+
"learning_rate": 8.325122860569241e-06,
|
| 218 |
+
"loss": 0.9165,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3541912632821724,
|
| 223 |
+
"grad_norm": 0.21761891023596566,
|
| 224 |
+
"learning_rate": 8.167970510730254e-06,
|
| 225 |
+
"loss": 0.9131,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3659976387249115,
|
| 230 |
+
"grad_norm": 0.23528529266527912,
|
| 231 |
+
"learning_rate": 8.005405736415127e-06,
|
| 232 |
+
"loss": 0.9145,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3778040141676505,
|
| 237 |
+
"grad_norm": 0.22111746390221937,
|
| 238 |
+
"learning_rate": 7.837706276813819e-06,
|
| 239 |
+
"loss": 0.915,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.38961038961038963,
|
| 244 |
+
"grad_norm": 0.2332103421059307,
|
| 245 |
+
"learning_rate": 7.66515864363997e-06,
|
| 246 |
+
"loss": 0.9102,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4014167650531287,
|
| 251 |
+
"grad_norm": 0.22080523814797284,
|
| 252 |
+
"learning_rate": 7.488057631630438e-06,
|
| 253 |
+
"loss": 0.9116,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4132231404958678,
|
| 258 |
+
"grad_norm": 0.23897773985208756,
|
| 259 |
+
"learning_rate": 7.30670581489344e-06,
|
| 260 |
+
"loss": 0.9076,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.42502951593860683,
|
| 265 |
+
"grad_norm": 0.2305609921175672,
|
| 266 |
+
"learning_rate": 7.121413029965769e-06,
|
| 267 |
+
"loss": 0.9042,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.43683589138134593,
|
| 272 |
+
"grad_norm": 0.2223301452294143,
|
| 273 |
+
"learning_rate": 6.932495846462262e-06,
|
| 274 |
+
"loss": 0.9007,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.448642266824085,
|
| 279 |
+
"grad_norm": 0.23329590047699517,
|
| 280 |
+
"learning_rate": 6.7402770262219234e-06,
|
| 281 |
+
"loss": 0.9066,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4604486422668241,
|
| 286 |
+
"grad_norm": 0.23446529786527753,
|
| 287 |
+
"learning_rate": 6.545084971874738e-06,
|
| 288 |
+
"loss": 0.8984,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4722550177095632,
|
| 293 |
+
"grad_norm": 0.22441297879630748,
|
| 294 |
+
"learning_rate": 6.34725316577129e-06,
|
| 295 |
+
"loss": 0.896,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.48406139315230223,
|
| 300 |
+
"grad_norm": 0.230862157896832,
|
| 301 |
+
"learning_rate": 6.147119600233758e-06,
|
| 302 |
+
"loss": 0.9031,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.49586776859504134,
|
| 307 |
+
"grad_norm": 0.22741396830189342,
|
| 308 |
+
"learning_rate": 5.945026200101702e-06,
|
| 309 |
+
"loss": 0.8975,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5076741440377804,
|
| 314 |
+
"grad_norm": 0.22303706899043335,
|
| 315 |
+
"learning_rate": 5.74131823855921e-06,
|
| 316 |
+
"loss": 0.8954,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5194805194805194,
|
| 321 |
+
"grad_norm": 0.22759645992430375,
|
| 322 |
+
"learning_rate": 5.53634374724146e-06,
|
| 323 |
+
"loss": 0.8953,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5312868949232585,
|
| 328 |
+
"grad_norm": 0.23319235277649508,
|
| 329 |
+
"learning_rate": 5.3304529216284974e-06,
|
| 330 |
+
"loss": 0.8961,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5430932703659976,
|
| 335 |
+
"grad_norm": 0.23100654509118668,
|
| 336 |
+
"learning_rate": 5.123997522742151e-06,
|
| 337 |
+
"loss": 0.8916,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5548996458087367,
|
| 342 |
+
"grad_norm": 0.23540273074706297,
|
| 343 |
+
"learning_rate": 4.917330276168208e-06,
|
| 344 |
+
"loss": 0.8903,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5667060212514758,
|
| 349 |
+
"grad_norm": 0.23627549294885386,
|
| 350 |
+
"learning_rate": 4.710804269430681e-06,
|
| 351 |
+
"loss": 0.8918,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5785123966942148,
|
| 356 |
+
"grad_norm": 0.23485084433644773,
|
| 357 |
+
"learning_rate": 4.504772348747687e-06,
|
| 358 |
+
"loss": 0.8898,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5903187721369539,
|
| 363 |
+
"grad_norm": 0.2312799347377704,
|
| 364 |
+
"learning_rate": 4.299586516199611e-06,
|
| 365 |
+
"loss": 0.8868,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.602125147579693,
|
| 370 |
+
"grad_norm": 0.23487979871660336,
|
| 371 |
+
"learning_rate": 4.0955973283394525e-06,
|
| 372 |
+
"loss": 0.8921,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6139315230224321,
|
| 377 |
+
"grad_norm": 0.2428635988467086,
|
| 378 |
+
"learning_rate": 3.893153297272829e-06,
|
| 379 |
+
"loss": 0.8892,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6257378984651711,
|
| 384 |
+
"grad_norm": 0.2406791935486902,
|
| 385 |
+
"learning_rate": 3.6926002952309015e-06,
|
| 386 |
+
"loss": 0.8894,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6375442739079102,
|
| 391 |
+
"grad_norm": 0.2347436699395759,
|
| 392 |
+
"learning_rate": 3.4942809636534637e-06,
|
| 393 |
+
"loss": 0.8907,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6493506493506493,
|
| 398 |
+
"grad_norm": 0.2314236794179229,
|
| 399 |
+
"learning_rate": 3.298534127791785e-06,
|
| 400 |
+
"loss": 0.8888,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6611570247933884,
|
| 405 |
+
"grad_norm": 0.23772858526107482,
|
| 406 |
+
"learning_rate": 3.105694217831361e-06,
|
| 407 |
+
"loss": 0.8925,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6729634002361276,
|
| 412 |
+
"grad_norm": 0.23577518827246635,
|
| 413 |
+
"learning_rate": 2.9160906975235493e-06,
|
| 414 |
+
"loss": 0.8843,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6847697756788665,
|
| 419 |
+
"grad_norm": 0.23875169965661389,
|
| 420 |
+
"learning_rate": 2.7300475013022666e-06,
|
| 421 |
+
"loss": 0.8855,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6965761511216056,
|
| 426 |
+
"grad_norm": 0.25946575212692286,
|
| 427 |
+
"learning_rate": 2.5478824808474613e-06,
|
| 428 |
+
"loss": 0.8812,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7083825265643447,
|
| 433 |
+
"grad_norm": 0.23981241529026295,
|
| 434 |
+
"learning_rate": 2.3699068620408305e-06,
|
| 435 |
+
"loss": 0.8911,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7201889020070839,
|
| 440 |
+
"grad_norm": 0.2426716970278435,
|
| 441 |
+
"learning_rate": 2.1964247132416373e-06,
|
| 442 |
+
"loss": 0.8846,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.731995277449823,
|
| 447 |
+
"grad_norm": 0.24628962220884432,
|
| 448 |
+
"learning_rate": 2.027732425791011e-06,
|
| 449 |
+
"loss": 0.8837,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.743801652892562,
|
| 454 |
+
"grad_norm": 0.2343357474000064,
|
| 455 |
+
"learning_rate": 1.864118207632315e-06,
|
| 456 |
+
"loss": 0.8829,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.755608028335301,
|
| 461 |
+
"grad_norm": 0.24636516414618967,
|
| 462 |
+
"learning_rate": 1.7058615909127102e-06,
|
| 463 |
+
"loss": 0.888,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7674144037780402,
|
| 468 |
+
"grad_norm": 0.2413404480858812,
|
| 469 |
+
"learning_rate": 1.5532329544071712e-06,
|
| 470 |
+
"loss": 0.8814,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7792207792207793,
|
| 475 |
+
"grad_norm": 0.24045371457493014,
|
| 476 |
+
"learning_rate": 1.406493061580881e-06,
|
| 477 |
+
"loss": 0.8923,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7910271546635183,
|
| 482 |
+
"grad_norm": 0.2428515672773077,
|
| 483 |
+
"learning_rate": 1.2658926150792321e-06,
|
| 484 |
+
"loss": 0.8857,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8028335301062574,
|
| 489 |
+
"grad_norm": 0.2449761845744851,
|
| 490 |
+
"learning_rate": 1.1316718284065536e-06,
|
| 491 |
+
"loss": 0.879,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8146399055489965,
|
| 496 |
+
"grad_norm": 0.2448836327125855,
|
| 497 |
+
"learning_rate": 1.0040600155253766e-06,
|
| 498 |
+
"loss": 0.886,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8264462809917356,
|
| 503 |
+
"grad_norm": 0.2595973551731746,
|
| 504 |
+
"learning_rate": 8.832751990773714e-07,
|
| 505 |
+
"loss": 0.8801,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8382526564344747,
|
| 510 |
+
"grad_norm": 0.24085877723696658,
|
| 511 |
+
"learning_rate": 7.695237378953224e-07,
|
| 512 |
+
"loss": 0.8806,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8500590318772137,
|
| 517 |
+
"grad_norm": 0.2349888174416922,
|
| 518 |
+
"learning_rate": 6.629999744425236e-07,
|
| 519 |
+
"loss": 0.8865,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8618654073199528,
|
| 524 |
+
"grad_norm": 0.24734359411286833,
|
| 525 |
+
"learning_rate": 5.63885902781941e-07,
|
| 526 |
+
"loss": 0.8809,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8736717827626919,
|
| 531 |
+
"grad_norm": 0.2435441647058269,
|
| 532 |
+
"learning_rate": 4.723508576424063e-07,
|
| 533 |
+
"loss": 0.8826,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.885478158205431,
|
| 538 |
+
"grad_norm": 0.2368020124120789,
|
| 539 |
+
"learning_rate": 3.885512251130763e-07,
|
| 540 |
+
"loss": 0.8814,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.89728453364817,
|
| 545 |
+
"grad_norm": 0.23667153372023703,
|
| 546 |
+
"learning_rate": 3.126301754604233e-07,
|
| 547 |
+
"loss": 0.8823,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9090909090909091,
|
| 552 |
+
"grad_norm": 0.24294708476602403,
|
| 553 |
+
"learning_rate": 2.447174185242324e-07,
|
| 554 |
+
"loss": 0.8786,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9208972845336482,
|
| 559 |
+
"grad_norm": 0.23800996974296137,
|
| 560 |
+
"learning_rate": 1.849289821105199e-07,
|
| 561 |
+
"loss": 0.8842,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9327036599763873,
|
| 566 |
+
"grad_norm": 0.24960725926029678,
|
| 567 |
+
"learning_rate": 1.333670137599713e-07,
|
| 568 |
+
"loss": 0.8834,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9445100354191264,
|
| 573 |
+
"grad_norm": 0.24379096892390517,
|
| 574 |
+
"learning_rate": 9.011960623058202e-08,
|
| 575 |
+
"loss": 0.8858,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9563164108618654,
|
| 580 |
+
"grad_norm": 0.24062301713355164,
|
| 581 |
+
"learning_rate": 5.526064699265754e-08,
|
| 582 |
+
"loss": 0.8868,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9681227863046045,
|
| 587 |
+
"grad_norm": 0.26366446784110714,
|
| 588 |
+
"learning_rate": 2.884969199331178e-08,
|
| 589 |
+
"loss": 0.8864,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9799291617473436,
|
| 594 |
+
"grad_norm": 0.23577798452928722,
|
| 595 |
+
"learning_rate": 1.0931863906127327e-08,
|
| 596 |
+
"loss": 0.879,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9917355371900827,
|
| 601 |
+
"grad_norm": 0.24385817474356447,
|
| 602 |
+
"learning_rate": 1.53777503982655e-09,
|
| 603 |
+
"loss": 0.8811,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9988193624557261,
|
| 608 |
+
"eval_loss": 0.9003931283950806,
|
| 609 |
+
"eval_runtime": 2.2828,
|
| 610 |
+
"eval_samples_per_second": 2.19,
|
| 611 |
+
"eval_steps_per_second": 0.876,
|
| 612 |
+
"step": 423
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9988193624557261,
|
| 616 |
+
"step": 423,
|
| 617 |
+
"total_flos": 1701364321222656.0,
|
| 618 |
+
"train_loss": 0.9762231091799184,
|
| 619 |
+
"train_runtime": 12298.1539,
|
| 620 |
+
"train_samples_per_second": 4.405,
|
| 621 |
+
"train_steps_per_second": 0.034
|
| 622 |
+
}
|
| 623 |
+
],
|
| 624 |
+
"logging_steps": 5,
|
| 625 |
+
"max_steps": 423,
|
| 626 |
+
"num_input_tokens_seen": 0,
|
| 627 |
+
"num_train_epochs": 1,
|
| 628 |
+
"save_steps": 100,
|
| 629 |
+
"stateful_callbacks": {
|
| 630 |
+
"TrainerControl": {
|
| 631 |
+
"args": {
|
| 632 |
+
"should_epoch_stop": false,
|
| 633 |
+
"should_evaluate": false,
|
| 634 |
+
"should_log": false,
|
| 635 |
+
"should_save": true,
|
| 636 |
+
"should_training_stop": true
|
| 637 |
+
},
|
| 638 |
+
"attributes": {}
|
| 639 |
+
}
|
| 640 |
+
},
|
| 641 |
+
"total_flos": 1701364321222656.0,
|
| 642 |
+
"train_batch_size": 16,
|
| 643 |
+
"trial_name": null,
|
| 644 |
+
"trial_params": null
|
| 645 |
+
}
|