Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- runs/Sep29_10-55-51_2fe66dad8940/events.out.tfevents.1727622043.2fe66dad8940.539.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +778 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-7b
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: gemma
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: gemma7b-gpt4o_100k_closedqa-k
|
| 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 |
+
# gemma7b-gpt4o_100k_closedqa-k
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.2841
|
| 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: 0.0003
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- total_eval_batch_size: 16
|
| 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 |
+
| 1.1207 | 0.9990 | 519 | 2.2841 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.1.dev0
|
| 66 |
+
- Transformers 4.45.1
|
| 67 |
+
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.20.0
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9990375360923965,
|
| 3 |
+
"total_flos": 7.912619964723364e+17,
|
| 4 |
+
"train_loss": 2.7495121248425316,
|
| 5 |
+
"train_runtime": 6850.0708,
|
| 6 |
+
"train_samples": 111440,
|
| 7 |
+
"train_samples_per_second": 2.426,
|
| 8 |
+
"train_steps_per_second": 0.076
|
| 9 |
+
}
|
runs/Sep29_10-55-51_2fe66dad8940/events.out.tfevents.1727622043.2fe66dad8940.539.0
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:b6558e5125370890894d48455f7718d5a10b3e0f4f2978c430c6939b42b5d86e
|
| 3 |
+
size 29150
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9990375360923965,
|
| 3 |
+
"total_flos": 7.912619964723364e+17,
|
| 4 |
+
"train_loss": 2.7495121248425316,
|
| 5 |
+
"train_runtime": 6850.0708,
|
| 6 |
+
"train_samples": 111440,
|
| 7 |
+
"train_samples_per_second": 2.426,
|
| 8 |
+
"train_steps_per_second": 0.076
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,778 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9990375360923965,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 519,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0019249278152069298,
|
| 13 |
+
"grad_norm": 166.78744506835938,
|
| 14 |
+
"learning_rate": 5.769230769230769e-06,
|
| 15 |
+
"loss": 32.2268,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009624639076034648,
|
| 20 |
+
"grad_norm": 132.89913940429688,
|
| 21 |
+
"learning_rate": 2.8846153846153845e-05,
|
| 22 |
+
"loss": 29.726,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.019249278152069296,
|
| 27 |
+
"grad_norm": 64.4798812866211,
|
| 28 |
+
"learning_rate": 5.769230769230769e-05,
|
| 29 |
+
"loss": 25.1178,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.028873917228103944,
|
| 34 |
+
"grad_norm": 12.633763313293457,
|
| 35 |
+
"learning_rate": 8.653846153846152e-05,
|
| 36 |
+
"loss": 19.6514,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03849855630413859,
|
| 41 |
+
"grad_norm": 9.107071876525879,
|
| 42 |
+
"learning_rate": 0.00011538461538461538,
|
| 43 |
+
"loss": 17.2219,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04812319538017324,
|
| 48 |
+
"grad_norm": 4.696881294250488,
|
| 49 |
+
"learning_rate": 0.00014423076923076922,
|
| 50 |
+
"loss": 15.4404,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05774783445620789,
|
| 55 |
+
"grad_norm": 3.118898868560791,
|
| 56 |
+
"learning_rate": 0.00017307692307692304,
|
| 57 |
+
"loss": 14.695,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06737247353224254,
|
| 62 |
+
"grad_norm": 4.403642654418945,
|
| 63 |
+
"learning_rate": 0.00020192307692307691,
|
| 64 |
+
"loss": 13.7845,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07699711260827719,
|
| 69 |
+
"grad_norm": 7.105109214782715,
|
| 70 |
+
"learning_rate": 0.00023076923076923076,
|
| 71 |
+
"loss": 12.8307,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08662175168431184,
|
| 76 |
+
"grad_norm": 16.107545852661133,
|
| 77 |
+
"learning_rate": 0.0002596153846153846,
|
| 78 |
+
"loss": 10.7864,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.09624639076034648,
|
| 83 |
+
"grad_norm": 24.628265380859375,
|
| 84 |
+
"learning_rate": 0.00028846153846153843,
|
| 85 |
+
"loss": 7.478,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.10587102983638114,
|
| 90 |
+
"grad_norm": 8.615938186645508,
|
| 91 |
+
"learning_rate": 0.00029996945395293625,
|
| 92 |
+
"loss": 3.5198,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11549566891241578,
|
| 97 |
+
"grad_norm": 5.187551021575928,
|
| 98 |
+
"learning_rate": 0.0002997828287165724,
|
| 99 |
+
"loss": 2.5417,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.12512030798845045,
|
| 104 |
+
"grad_norm": 2.919438362121582,
|
| 105 |
+
"learning_rate": 0.00029942675913693153,
|
| 106 |
+
"loss": 2.0943,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1347449470644851,
|
| 111 |
+
"grad_norm": 1.5105671882629395,
|
| 112 |
+
"learning_rate": 0.0002989016480237121,
|
| 113 |
+
"loss": 1.8019,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.14436958614051973,
|
| 118 |
+
"grad_norm": 0.6488280892372131,
|
| 119 |
+
"learning_rate": 0.0002982080894176895,
|
| 120 |
+
"loss": 1.6616,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.15399422521655437,
|
| 125 |
+
"grad_norm": 1.0447803735733032,
|
| 126 |
+
"learning_rate": 0.0002973468679186978,
|
| 127 |
+
"loss": 1.5605,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.16361886429258904,
|
| 132 |
+
"grad_norm": 0.5504654049873352,
|
| 133 |
+
"learning_rate": 0.0002963189577980372,
|
| 134 |
+
"loss": 1.5028,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.17324350336862368,
|
| 139 |
+
"grad_norm": 0.7152052521705627,
|
| 140 |
+
"learning_rate": 0.0002951255218963139,
|
| 141 |
+
"loss": 1.4363,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.18286814244465832,
|
| 146 |
+
"grad_norm": 1.1773169040679932,
|
| 147 |
+
"learning_rate": 0.0002937679103079571,
|
| 148 |
+
"loss": 1.4284,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.19249278152069296,
|
| 153 |
+
"grad_norm": 0.908633828163147,
|
| 154 |
+
"learning_rate": 0.00029224765885390143,
|
| 155 |
+
"loss": 1.3772,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.20211742059672763,
|
| 160 |
+
"grad_norm": 0.9546915292739868,
|
| 161 |
+
"learning_rate": 0.0002905664873441643,
|
| 162 |
+
"loss": 1.3789,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.21174205967276227,
|
| 167 |
+
"grad_norm": 0.6474579572677612,
|
| 168 |
+
"learning_rate": 0.00028872629763228145,
|
| 169 |
+
"loss": 1.3446,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.22136669874879691,
|
| 174 |
+
"grad_norm": 0.6460303068161011,
|
| 175 |
+
"learning_rate": 0.0002867291714638035,
|
| 176 |
+
"loss": 1.3102,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.23099133782483156,
|
| 181 |
+
"grad_norm": 0.8272395730018616,
|
| 182 |
+
"learning_rate": 0.0002845773681212862,
|
| 183 |
+
"loss": 1.3315,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.24061597690086622,
|
| 188 |
+
"grad_norm": 1.1858478784561157,
|
| 189 |
+
"learning_rate": 0.00028227332186843884,
|
| 190 |
+
"loss": 1.3232,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2502406159769009,
|
| 195 |
+
"grad_norm": 1.020283579826355,
|
| 196 |
+
"learning_rate": 0.0002798196391963229,
|
| 197 |
+
"loss": 1.298,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2598652550529355,
|
| 202 |
+
"grad_norm": 1.3490053415298462,
|
| 203 |
+
"learning_rate": 0.0002772190958747147,
|
| 204 |
+
"loss": 1.3026,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2694898941289702,
|
| 209 |
+
"grad_norm": 1.1797901391983032,
|
| 210 |
+
"learning_rate": 0.00027447463381196973,
|
| 211 |
+
"loss": 1.2889,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2791145332050048,
|
| 216 |
+
"grad_norm": 1.916670799255371,
|
| 217 |
+
"learning_rate": 0.0002715893577269389,
|
| 218 |
+
"loss": 1.2773,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.28873917228103946,
|
| 223 |
+
"grad_norm": 0.5742417573928833,
|
| 224 |
+
"learning_rate": 0.0002685665316367035,
|
| 225 |
+
"loss": 1.2937,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2983638113570741,
|
| 230 |
+
"grad_norm": 0.6991013884544373,
|
| 231 |
+
"learning_rate": 0.0002654095751641007,
|
| 232 |
+
"loss": 1.2667,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.30798845043310874,
|
| 237 |
+
"grad_norm": 1.23212468624115,
|
| 238 |
+
"learning_rate": 0.00026212205966921786,
|
| 239 |
+
"loss": 1.2571,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3176130895091434,
|
| 244 |
+
"grad_norm": 0.8666950464248657,
|
| 245 |
+
"learning_rate": 0.0002587077042092314,
|
| 246 |
+
"loss": 1.2649,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3272377285851781,
|
| 251 |
+
"grad_norm": 0.945165753364563,
|
| 252 |
+
"learning_rate": 0.00025517037133116085,
|
| 253 |
+
"loss": 1.2262,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3368623676612127,
|
| 258 |
+
"grad_norm": 0.9452968835830688,
|
| 259 |
+
"learning_rate": 0.0002515140627022976,
|
| 260 |
+
"loss": 1.2332,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.34648700673724736,
|
| 265 |
+
"grad_norm": 0.7168753743171692,
|
| 266 |
+
"learning_rate": 0.00024774291458325127,
|
| 267 |
+
"loss": 1.2303,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.35611164581328203,
|
| 272 |
+
"grad_norm": 1.55524742603302,
|
| 273 |
+
"learning_rate": 0.00024386119314873578,
|
| 274 |
+
"loss": 1.2258,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.36573628488931664,
|
| 279 |
+
"grad_norm": 0.549445629119873,
|
| 280 |
+
"learning_rate": 0.00023987328966138704,
|
| 281 |
+
"loss": 1.2098,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3753609239653513,
|
| 286 |
+
"grad_norm": 0.6080393195152283,
|
| 287 |
+
"learning_rate": 0.00023578371550407354,
|
| 288 |
+
"loss": 1.2385,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3849855630413859,
|
| 293 |
+
"grad_norm": 2.411741256713867,
|
| 294 |
+
"learning_rate": 0.0002315970970763186,
|
| 295 |
+
"loss": 1.2144,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3946102021174206,
|
| 300 |
+
"grad_norm": 1.1420116424560547,
|
| 301 |
+
"learning_rate": 0.00022731817056060802,
|
| 302 |
+
"loss": 1.1943,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.40423484119345526,
|
| 307 |
+
"grad_norm": 1.1481698751449585,
|
| 308 |
+
"learning_rate": 0.00022295177656450404,
|
| 309 |
+
"loss": 1.2004,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4138594802694899,
|
| 314 |
+
"grad_norm": 3.898259401321411,
|
| 315 |
+
"learning_rate": 0.00021850285464462677,
|
| 316 |
+
"loss": 1.2195,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.42348411934552455,
|
| 321 |
+
"grad_norm": 0.6957814693450928,
|
| 322 |
+
"learning_rate": 0.0002139764377186976,
|
| 323 |
+
"loss": 1.2159,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4331087584215592,
|
| 328 |
+
"grad_norm": 0.9523270726203918,
|
| 329 |
+
"learning_rate": 0.00020937764637196638,
|
| 330 |
+
"loss": 1.186,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.44273339749759383,
|
| 335 |
+
"grad_norm": 1.081147313117981,
|
| 336 |
+
"learning_rate": 0.00020471168306446336,
|
| 337 |
+
"loss": 1.2156,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4523580365736285,
|
| 342 |
+
"grad_norm": 2.2060320377349854,
|
| 343 |
+
"learning_rate": 0.0001999838262456287,
|
| 344 |
+
"loss": 1.1998,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4619826756496631,
|
| 349 |
+
"grad_norm": 1.1269886493682861,
|
| 350 |
+
"learning_rate": 0.0001951994243829781,
|
| 351 |
+
"loss": 1.2017,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4716073147256978,
|
| 356 |
+
"grad_norm": 1.608312964439392,
|
| 357 |
+
"learning_rate": 0.00019036388991155846,
|
| 358 |
+
"loss": 1.1873,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.48123195380173245,
|
| 363 |
+
"grad_norm": 1.0753167867660522,
|
| 364 |
+
"learning_rate": 0.0001854826931110403,
|
| 365 |
+
"loss": 1.1984,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.49085659287776706,
|
| 370 |
+
"grad_norm": 1.3986575603485107,
|
| 371 |
+
"learning_rate": 0.0001805613559173714,
|
| 372 |
+
"loss": 1.181,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5004812319538018,
|
| 377 |
+
"grad_norm": 0.47483909130096436,
|
| 378 |
+
"learning_rate": 0.0001756054456759944,
|
| 379 |
+
"loss": 1.173,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5101058710298364,
|
| 384 |
+
"grad_norm": 0.8258511424064636,
|
| 385 |
+
"learning_rate": 0.00017062056884369325,
|
| 386 |
+
"loss": 1.1736,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.519730510105871,
|
| 391 |
+
"grad_norm": 0.7987772822380066,
|
| 392 |
+
"learning_rate": 0.0001656123646461951,
|
| 393 |
+
"loss": 1.1616,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5293551491819056,
|
| 398 |
+
"grad_norm": 0.7245559692382812,
|
| 399 |
+
"learning_rate": 0.00016058649869870098,
|
| 400 |
+
"loss": 1.1846,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5389797882579404,
|
| 405 |
+
"grad_norm": 1.228034496307373,
|
| 406 |
+
"learning_rate": 0.00015554865659656367,
|
| 407 |
+
"loss": 1.165,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.548604427333975,
|
| 412 |
+
"grad_norm": 0.8788666725158691,
|
| 413 |
+
"learning_rate": 0.00015050453748336224,
|
| 414 |
+
"loss": 1.1707,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5582290664100096,
|
| 419 |
+
"grad_norm": 0.7828085422515869,
|
| 420 |
+
"learning_rate": 0.00014545984760365,
|
| 421 |
+
"loss": 1.1609,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5678537054860443,
|
| 426 |
+
"grad_norm": 0.7824317216873169,
|
| 427 |
+
"learning_rate": 0.00014042029384766938,
|
| 428 |
+
"loss": 1.1656,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.5774783445620789,
|
| 433 |
+
"grad_norm": 0.9950030446052551,
|
| 434 |
+
"learning_rate": 0.00013539157729533678,
|
| 435 |
+
"loss": 1.1626,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5871029836381135,
|
| 440 |
+
"grad_norm": 1.1628440618515015,
|
| 441 |
+
"learning_rate": 0.00013037938676679957,
|
| 442 |
+
"loss": 1.1633,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5967276227141483,
|
| 447 |
+
"grad_norm": 0.7875819802284241,
|
| 448 |
+
"learning_rate": 0.00012538939238686286,
|
| 449 |
+
"loss": 1.1721,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6063522617901829,
|
| 454 |
+
"grad_norm": 1.3848762512207031,
|
| 455 |
+
"learning_rate": 0.0001204272391705654,
|
| 456 |
+
"loss": 1.1667,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6159769008662175,
|
| 461 |
+
"grad_norm": 0.8932669162750244,
|
| 462 |
+
"learning_rate": 0.00011549854063716169,
|
| 463 |
+
"loss": 1.1761,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6256015399422522,
|
| 468 |
+
"grad_norm": 0.7711289525032043,
|
| 469 |
+
"learning_rate": 0.00011060887245973355,
|
| 470 |
+
"loss": 1.1694,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6352261790182868,
|
| 475 |
+
"grad_norm": 2.6940572261810303,
|
| 476 |
+
"learning_rate": 0.00010576376615761647,
|
| 477 |
+
"loss": 1.1535,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6448508180943214,
|
| 482 |
+
"grad_norm": 0.9238442778587341,
|
| 483 |
+
"learning_rate": 0.00010096870283877523,
|
| 484 |
+
"loss": 1.1737,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6544754571703562,
|
| 489 |
+
"grad_norm": 1.135506510734558,
|
| 490 |
+
"learning_rate": 9.62291069992085e-05,
|
| 491 |
+
"loss": 1.1513,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6641000962463908,
|
| 496 |
+
"grad_norm": 0.5180495381355286,
|
| 497 |
+
"learning_rate": 9.155034038639637e-05,
|
| 498 |
+
"loss": 1.1538,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6737247353224254,
|
| 503 |
+
"grad_norm": 0.5448501706123352,
|
| 504 |
+
"learning_rate": 8.693769593373337e-05,
|
| 505 |
+
"loss": 1.1342,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6833493743984601,
|
| 510 |
+
"grad_norm": 0.47162362933158875,
|
| 511 |
+
"learning_rate": 8.239639177280888e-05,
|
| 512 |
+
"loss": 1.1429,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6929740134744947,
|
| 517 |
+
"grad_norm": 0.599886417388916,
|
| 518 |
+
"learning_rate": 7.793156533030761e-05,
|
| 519 |
+
"loss": 1.1604,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7025986525505293,
|
| 524 |
+
"grad_norm": 0.5403456687927246,
|
| 525 |
+
"learning_rate": 7.354826751620954e-05,
|
| 526 |
+
"loss": 1.1378,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7122232916265641,
|
| 531 |
+
"grad_norm": 0.8314358592033386,
|
| 532 |
+
"learning_rate": 6.925145700986301e-05,
|
| 533 |
+
"loss": 1.1433,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7218479307025987,
|
| 538 |
+
"grad_norm": 1.6931346654891968,
|
| 539 |
+
"learning_rate": 6.504599465039542e-05,
|
| 540 |
+
"loss": 1.1502,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7314725697786333,
|
| 545 |
+
"grad_norm": 0.534213125705719,
|
| 546 |
+
"learning_rate": 6.093663793780725e-05,
|
| 547 |
+
"loss": 1.1438,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7410972088546679,
|
| 552 |
+
"grad_norm": 0.9398422837257385,
|
| 553 |
+
"learning_rate": 5.692803565096988e-05,
|
| 554 |
+
"loss": 1.1542,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7507218479307026,
|
| 559 |
+
"grad_norm": 1.0625075101852417,
|
| 560 |
+
"learning_rate": 5.302472258861687e-05,
|
| 561 |
+
"loss": 1.1346,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7603464870067372,
|
| 566 |
+
"grad_norm": 0.48856019973754883,
|
| 567 |
+
"learning_rate": 4.923111443927615e-05,
|
| 568 |
+
"loss": 1.1385,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7699711260827719,
|
| 573 |
+
"grad_norm": 0.4903761148452759,
|
| 574 |
+
"learning_rate": 4.5551502785948405e-05,
|
| 575 |
+
"loss": 1.1556,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7795957651588066,
|
| 580 |
+
"grad_norm": 0.6831708550453186,
|
| 581 |
+
"learning_rate": 4.199005025118158e-05,
|
| 582 |
+
"loss": 1.1529,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7892204042348412,
|
| 587 |
+
"grad_norm": 0.4595310688018799,
|
| 588 |
+
"learning_rate": 3.855078578803424e-05,
|
| 589 |
+
"loss": 1.1267,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.7988450433108758,
|
| 594 |
+
"grad_norm": 0.652646005153656,
|
| 595 |
+
"learning_rate": 3.5237600122254437e-05,
|
| 596 |
+
"loss": 1.1412,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.8084696823869105,
|
| 601 |
+
"grad_norm": 0.6624627113342285,
|
| 602 |
+
"learning_rate": 3.2054241350831046e-05,
|
| 603 |
+
"loss": 1.1323,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8180943214629451,
|
| 608 |
+
"grad_norm": 0.4390796720981598,
|
| 609 |
+
"learning_rate": 2.9004310701895837e-05,
|
| 610 |
+
"loss": 1.13,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8277189605389798,
|
| 615 |
+
"grad_norm": 0.9988071918487549,
|
| 616 |
+
"learning_rate": 2.6091258460773862e-05,
|
| 617 |
+
"loss": 1.1343,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8373435996150145,
|
| 622 |
+
"grad_norm": 0.481611430644989,
|
| 623 |
+
"learning_rate": 2.3318380066789787e-05,
|
| 624 |
+
"loss": 1.1217,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8469682386910491,
|
| 629 |
+
"grad_norm": 0.49289077520370483,
|
| 630 |
+
"learning_rate": 2.0688812385247176e-05,
|
| 631 |
+
"loss": 1.1299,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8565928777670837,
|
| 636 |
+
"grad_norm": 0.5225491523742676,
|
| 637 |
+
"learning_rate": 1.8205530158796505e-05,
|
| 638 |
+
"loss": 1.119,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8662175168431184,
|
| 643 |
+
"grad_norm": 0.5030360817909241,
|
| 644 |
+
"learning_rate": 1.587134264220778e-05,
|
| 645 |
+
"loss": 1.1305,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.875842155919153,
|
| 650 |
+
"grad_norm": 0.4824385643005371,
|
| 651 |
+
"learning_rate": 1.3688890424353726e-05,
|
| 652 |
+
"loss": 1.1192,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8854667949951877,
|
| 657 |
+
"grad_norm": 0.5466002821922302,
|
| 658 |
+
"learning_rate": 1.1660642440999196e-05,
|
| 659 |
+
"loss": 1.1396,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.8950914340712224,
|
| 664 |
+
"grad_norm": 0.5023711323738098,
|
| 665 |
+
"learning_rate": 9.788893181776297e-06,
|
| 666 |
+
"loss": 1.1369,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.904716073147257,
|
| 671 |
+
"grad_norm": 0.4702525734901428,
|
| 672 |
+
"learning_rate": 8.07576009450408e-06,
|
| 673 |
+
"loss": 1.1296,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9143407122232916,
|
| 678 |
+
"grad_norm": 0.47570234537124634,
|
| 679 |
+
"learning_rate": 6.5231811897903714e-06,
|
| 680 |
+
"loss": 1.1365,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9239653512993262,
|
| 685 |
+
"grad_norm": 0.4453733265399933,
|
| 686 |
+
"learning_rate": 5.13291284862452e-06,
|
| 687 |
+
"loss": 1.1219,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.933589990375361,
|
| 692 |
+
"grad_norm": 0.4282439053058624,
|
| 693 |
+
"learning_rate": 3.906527835442064e-06,
|
| 694 |
+
"loss": 1.1193,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9432146294513956,
|
| 699 |
+
"grad_norm": 0.4609365165233612,
|
| 700 |
+
"learning_rate": 2.8454135189082684e-06,
|
| 701 |
+
"loss": 1.145,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9528392685274302,
|
| 706 |
+
"grad_norm": 0.46295586228370667,
|
| 707 |
+
"learning_rate": 1.950770302434157e-06,
|
| 708 |
+
"loss": 1.1418,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9624639076034649,
|
| 713 |
+
"grad_norm": 0.4474254250526428,
|
| 714 |
+
"learning_rate": 1.223610266200009e-06,
|
| 715 |
+
"loss": 1.1285,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9720885466794995,
|
| 720 |
+
"grad_norm": 0.5148175358772278,
|
| 721 |
+
"learning_rate": 6.647560222224957e-07,
|
| 722 |
+
"loss": 1.1177,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9817131857555341,
|
| 727 |
+
"grad_norm": 0.4380834400653839,
|
| 728 |
+
"learning_rate": 2.748397837611105e-07,
|
| 729 |
+
"loss": 1.14,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9913378248315688,
|
| 734 |
+
"grad_norm": 0.5519540309906006,
|
| 735 |
+
"learning_rate": 5.430265011625579e-08,
|
| 736 |
+
"loss": 1.1207,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.9990375360923965,
|
| 741 |
+
"eval_loss": 2.2841131687164307,
|
| 742 |
+
"eval_runtime": 1.3512,
|
| 743 |
+
"eval_samples_per_second": 4.441,
|
| 744 |
+
"eval_steps_per_second": 0.74,
|
| 745 |
+
"step": 519
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9990375360923965,
|
| 749 |
+
"step": 519,
|
| 750 |
+
"total_flos": 7.912619964723364e+17,
|
| 751 |
+
"train_loss": 2.7495121248425316,
|
| 752 |
+
"train_runtime": 6850.0708,
|
| 753 |
+
"train_samples_per_second": 2.426,
|
| 754 |
+
"train_steps_per_second": 0.076
|
| 755 |
+
}
|
| 756 |
+
],
|
| 757 |
+
"logging_steps": 5,
|
| 758 |
+
"max_steps": 519,
|
| 759 |
+
"num_input_tokens_seen": 0,
|
| 760 |
+
"num_train_epochs": 1,
|
| 761 |
+
"save_steps": 100,
|
| 762 |
+
"stateful_callbacks": {
|
| 763 |
+
"TrainerControl": {
|
| 764 |
+
"args": {
|
| 765 |
+
"should_epoch_stop": false,
|
| 766 |
+
"should_evaluate": false,
|
| 767 |
+
"should_log": false,
|
| 768 |
+
"should_save": true,
|
| 769 |
+
"should_training_stop": true
|
| 770 |
+
},
|
| 771 |
+
"attributes": {}
|
| 772 |
+
}
|
| 773 |
+
},
|
| 774 |
+
"total_flos": 7.912619964723364e+17,
|
| 775 |
+
"train_batch_size": 4,
|
| 776 |
+
"trial_name": null,
|
| 777 |
+
"trial_params": null
|
| 778 |
+
}
|