Model save
Browse files- README.md +69 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Sep29_14-41-10_5bc1778c8f32/events.out.tfevents.1727620913.5bc1778c8f32.69828.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +722 -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_classification-lora
|
| 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_classification-lora
|
| 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: 1.9203
|
| 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: 1
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 8
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 16
|
| 50 |
+
- total_eval_batch_size: 8
|
| 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 |
+
| 1.3004 | 0.9990 | 478 | 1.9203 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.13.0
|
| 66 |
+
- Transformers 4.45.1
|
| 67 |
+
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.1
|
| 69 |
+
- Tokenizers 0.20.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12859872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a4671c221c07d04c0ad389118eacc3ddb3fb12ca4c1b5c8baddc1a3b35b9cd
|
| 3 |
size 12859872
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9989550679205852,
|
| 3 |
+
"total_flos": 3.643767570437243e+17,
|
| 4 |
+
"train_loss": 4.360991338805674,
|
| 5 |
+
"train_runtime": 2613.4355,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 2.928,
|
| 8 |
+
"train_steps_per_second": 0.183
|
| 9 |
+
}
|
runs/Sep29_14-41-10_5bc1778c8f32/events.out.tfevents.1727620913.5bc1778c8f32.69828.0
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 sha256:18f39eb3af9251d4390c29c3194a7a99a0811394a82c893ef1da371e1e77eaef
|
| 3 |
+
size 27503
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9989550679205852,
|
| 3 |
+
"total_flos": 3.643767570437243e+17,
|
| 4 |
+
"train_loss": 4.360991338805674,
|
| 5 |
+
"train_runtime": 2613.4355,
|
| 6 |
+
"train_samples": 92634,
|
| 7 |
+
"train_samples_per_second": 2.928,
|
| 8 |
+
"train_steps_per_second": 0.183
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,722 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9989550679205852,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 478,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0020898641588296763,
|
| 13 |
+
"grad_norm": 216.79754638671875,
|
| 14 |
+
"learning_rate": 6.2499999999999995e-06,
|
| 15 |
+
"loss": 57.9838,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01044932079414838,
|
| 20 |
+
"grad_norm": 184.4412841796875,
|
| 21 |
+
"learning_rate": 3.125e-05,
|
| 22 |
+
"loss": 60.093,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02089864158829676,
|
| 27 |
+
"grad_norm": 107.91060638427734,
|
| 28 |
+
"learning_rate": 6.25e-05,
|
| 29 |
+
"loss": 48.3094,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03134796238244514,
|
| 34 |
+
"grad_norm": 17.1436710357666,
|
| 35 |
+
"learning_rate": 9.374999999999999e-05,
|
| 36 |
+
"loss": 33.2668,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04179728317659352,
|
| 41 |
+
"grad_norm": 12.335116386413574,
|
| 42 |
+
"learning_rate": 0.000125,
|
| 43 |
+
"loss": 27.698,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0522466039707419,
|
| 48 |
+
"grad_norm": 6.2943196296691895,
|
| 49 |
+
"learning_rate": 0.00015625,
|
| 50 |
+
"loss": 25.9692,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06269592476489028,
|
| 55 |
+
"grad_norm": 5.466517448425293,
|
| 56 |
+
"learning_rate": 0.00018749999999999998,
|
| 57 |
+
"loss": 25.2691,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07314524555903866,
|
| 62 |
+
"grad_norm": 9.744288444519043,
|
| 63 |
+
"learning_rate": 0.00021874999999999998,
|
| 64 |
+
"loss": 23.7082,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08359456635318704,
|
| 69 |
+
"grad_norm": 19.27219581604004,
|
| 70 |
+
"learning_rate": 0.00025,
|
| 71 |
+
"loss": 21.3655,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09404388714733543,
|
| 76 |
+
"grad_norm": 41.77222442626953,
|
| 77 |
+
"learning_rate": 0.00028125,
|
| 78 |
+
"loss": 16.1707,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1044932079414838,
|
| 83 |
+
"grad_norm": 18.60293960571289,
|
| 84 |
+
"learning_rate": 0.0002999839868651235,
|
| 85 |
+
"loss": 8.0969,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.11494252873563218,
|
| 90 |
+
"grad_norm": 11.452897071838379,
|
| 91 |
+
"learning_rate": 0.00029980387835984494,
|
| 92 |
+
"loss": 4.1367,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12539184952978055,
|
| 97 |
+
"grad_norm": 8.422245979309082,
|
| 98 |
+
"learning_rate": 0.000299423886051382,
|
| 99 |
+
"loss": 3.1254,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.13584117032392895,
|
| 104 |
+
"grad_norm": 2.444629669189453,
|
| 105 |
+
"learning_rate": 0.0002988445169647103,
|
| 106 |
+
"loss": 2.4463,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.14629049111807732,
|
| 111 |
+
"grad_norm": 1.307098627090454,
|
| 112 |
+
"learning_rate": 0.0002980665441538907,
|
| 113 |
+
"loss": 2.1685,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.15673981191222572,
|
| 118 |
+
"grad_norm": 2.10964298248291,
|
| 119 |
+
"learning_rate": 0.0002970910056705806,
|
| 120 |
+
"loss": 2.0392,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1671891327063741,
|
| 125 |
+
"grad_norm": 1.1905853748321533,
|
| 126 |
+
"learning_rate": 0.0002959192031789579,
|
| 127 |
+
"loss": 1.9225,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.17763845350052246,
|
| 132 |
+
"grad_norm": 0.8916841745376587,
|
| 133 |
+
"learning_rate": 0.0002945527002189068,
|
| 134 |
+
"loss": 1.8422,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18808777429467086,
|
| 139 |
+
"grad_norm": 3.186051845550537,
|
| 140 |
+
"learning_rate": 0.00029299332011978107,
|
| 141 |
+
"loss": 1.748,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19853709508881923,
|
| 146 |
+
"grad_norm": 3.865817070007324,
|
| 147 |
+
"learning_rate": 0.00029124314356752967,
|
| 148 |
+
"loss": 1.7184,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2089864158829676,
|
| 153 |
+
"grad_norm": 2.8790738582611084,
|
| 154 |
+
"learning_rate": 0.0002893045058284311,
|
| 155 |
+
"loss": 1.6432,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.219435736677116,
|
| 160 |
+
"grad_norm": 1.6771491765975952,
|
| 161 |
+
"learning_rate": 0.00028717999363313967,
|
| 162 |
+
"loss": 1.6567,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.22988505747126436,
|
| 167 |
+
"grad_norm": 2.725285530090332,
|
| 168 |
+
"learning_rate": 0.00028487244172520246,
|
| 169 |
+
"loss": 1.6157,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.24033437826541273,
|
| 174 |
+
"grad_norm": 2.289280652999878,
|
| 175 |
+
"learning_rate": 0.0002823849290786517,
|
| 176 |
+
"loss": 1.6148,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2507836990595611,
|
| 181 |
+
"grad_norm": 2.0211188793182373,
|
| 182 |
+
"learning_rate": 0.0002797207747897198,
|
| 183 |
+
"loss": 1.5858,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2612330198537095,
|
| 188 |
+
"grad_norm": 2.0264103412628174,
|
| 189 |
+
"learning_rate": 0.00027688353364815834,
|
| 190 |
+
"loss": 1.5708,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2716823406478579,
|
| 195 |
+
"grad_norm": 0.9253348112106323,
|
| 196 |
+
"learning_rate": 0.0002738769913940706,
|
| 197 |
+
"loss": 1.5481,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.28213166144200624,
|
| 202 |
+
"grad_norm": 3.3143184185028076,
|
| 203 |
+
"learning_rate": 0.00027070515966658604,
|
| 204 |
+
"loss": 1.5535,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.29258098223615464,
|
| 209 |
+
"grad_norm": 4.024845600128174,
|
| 210 |
+
"learning_rate": 0.0002673722706511174,
|
| 211 |
+
"loss": 1.5542,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.30303030303030304,
|
| 216 |
+
"grad_norm": 3.718261241912842,
|
| 217 |
+
"learning_rate": 0.00026388277143234146,
|
| 218 |
+
"loss": 1.5507,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.31347962382445144,
|
| 223 |
+
"grad_norm": 1.9526076316833496,
|
| 224 |
+
"learning_rate": 0.0002602413180604401,
|
| 225 |
+
"loss": 1.5251,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3239289446185998,
|
| 230 |
+
"grad_norm": 1.5725075006484985,
|
| 231 |
+
"learning_rate": 0.00025645276933851667,
|
| 232 |
+
"loss": 1.4937,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3343782654127482,
|
| 237 |
+
"grad_norm": 4.266882419586182,
|
| 238 |
+
"learning_rate": 0.00025252218033947993,
|
| 239 |
+
"loss": 1.4944,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3448275862068966,
|
| 244 |
+
"grad_norm": 2.6647915840148926,
|
| 245 |
+
"learning_rate": 0.0002484547956610429,
|
| 246 |
+
"loss": 1.4798,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3552769070010449,
|
| 251 |
+
"grad_norm": 2.0770153999328613,
|
| 252 |
+
"learning_rate": 0.0002442560424278399,
|
| 253 |
+
"loss": 1.4708,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3657262277951933,
|
| 258 |
+
"grad_norm": 1.8132774829864502,
|
| 259 |
+
"learning_rate": 0.00023993152304999582,
|
| 260 |
+
"loss": 1.4554,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3761755485893417,
|
| 265 |
+
"grad_norm": 1.9493850469589233,
|
| 266 |
+
"learning_rate": 0.00023548700774781242,
|
| 267 |
+
"loss": 1.485,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.38662486938349006,
|
| 272 |
+
"grad_norm": 3.6726951599121094,
|
| 273 |
+
"learning_rate": 0.00023092842685254442,
|
| 274 |
+
"loss": 1.4584,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.39707419017763845,
|
| 279 |
+
"grad_norm": 2.253319501876831,
|
| 280 |
+
"learning_rate": 0.00022626186289353913,
|
| 281 |
+
"loss": 1.4569,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.40752351097178685,
|
| 286 |
+
"grad_norm": 3.336820125579834,
|
| 287 |
+
"learning_rate": 0.00022149354248229784,
|
| 288 |
+
"loss": 1.4334,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4179728317659352,
|
| 293 |
+
"grad_norm": 3.0895018577575684,
|
| 294 |
+
"learning_rate": 0.0002166298280042877,
|
| 295 |
+
"loss": 1.4203,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4284221525600836,
|
| 300 |
+
"grad_norm": 1.8486225605010986,
|
| 301 |
+
"learning_rate": 0.00021167720912959004,
|
| 302 |
+
"loss": 1.414,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.438871473354232,
|
| 307 |
+
"grad_norm": 0.7216203808784485,
|
| 308 |
+
"learning_rate": 0.00020664229415371266,
|
| 309 |
+
"loss": 1.3897,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.44932079414838033,
|
| 314 |
+
"grad_norm": 2.909454107284546,
|
| 315 |
+
"learning_rate": 0.0002015318011801192,
|
| 316 |
+
"loss": 1.3713,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.45977011494252873,
|
| 321 |
+
"grad_norm": 1.5531753301620483,
|
| 322 |
+
"learning_rate": 0.0001963525491562421,
|
| 323 |
+
"loss": 1.4055,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4702194357366771,
|
| 328 |
+
"grad_norm": 4.848015308380127,
|
| 329 |
+
"learning_rate": 0.00019111144877493873,
|
| 330 |
+
"loss": 1.435,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.48066875653082547,
|
| 335 |
+
"grad_norm": 4.833097457885742,
|
| 336 |
+
"learning_rate": 0.00018581549325353126,
|
| 337 |
+
"loss": 1.417,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.49111807732497387,
|
| 342 |
+
"grad_norm": 1.415703296661377,
|
| 343 |
+
"learning_rate": 0.00018047174900273435,
|
| 344 |
+
"loss": 1.4449,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5015673981191222,
|
| 349 |
+
"grad_norm": 0.9621894359588623,
|
| 350 |
+
"learning_rate": 0.00017508734619791966,
|
| 351 |
+
"loss": 1.3907,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5120167189132706,
|
| 356 |
+
"grad_norm": 2.091428279876709,
|
| 357 |
+
"learning_rate": 0.0001696694692653004,
|
| 358 |
+
"loss": 1.3581,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.522466039707419,
|
| 363 |
+
"grad_norm": 1.3531287908554077,
|
| 364 |
+
"learning_rate": 0.00016422534729572738,
|
| 365 |
+
"loss": 1.3717,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5329153605015674,
|
| 370 |
+
"grad_norm": 1.8569897413253784,
|
| 371 |
+
"learning_rate": 0.0001587622443988899,
|
| 372 |
+
"loss": 1.3811,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5433646812957158,
|
| 377 |
+
"grad_norm": 4.248292446136475,
|
| 378 |
+
"learning_rate": 0.0001532874500107902,
|
| 379 |
+
"loss": 1.3797,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5538140020898642,
|
| 384 |
+
"grad_norm": 2.5460174083709717,
|
| 385 |
+
"learning_rate": 0.0001478082691674256,
|
| 386 |
+
"loss": 1.3576,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5642633228840125,
|
| 391 |
+
"grad_norm": 1.3485275506973267,
|
| 392 |
+
"learning_rate": 0.00014233201275765494,
|
| 393 |
+
"loss": 1.383,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5747126436781609,
|
| 398 |
+
"grad_norm": 1.1686965227127075,
|
| 399 |
+
"learning_rate": 0.00013686598776825563,
|
| 400 |
+
"loss": 1.3715,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5851619644723093,
|
| 405 |
+
"grad_norm": 1.8593087196350098,
|
| 406 |
+
"learning_rate": 0.0001314174875341878,
|
| 407 |
+
"loss": 1.3671,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5956112852664577,
|
| 412 |
+
"grad_norm": 1.5989689826965332,
|
| 413 |
+
"learning_rate": 0.0001259937820070732,
|
| 414 |
+
"loss": 1.3379,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6060606060606061,
|
| 419 |
+
"grad_norm": 3.129467248916626,
|
| 420 |
+
"learning_rate": 0.00012060210805487529,
|
| 421 |
+
"loss": 1.3436,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6165099268547545,
|
| 426 |
+
"grad_norm": 1.071311593055725,
|
| 427 |
+
"learning_rate": 0.00011524965980572284,
|
| 428 |
+
"loss": 1.3711,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6269592476489029,
|
| 433 |
+
"grad_norm": 2.8161048889160156,
|
| 434 |
+
"learning_rate": 0.00010994357904876106,
|
| 435 |
+
"loss": 1.3242,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6374085684430512,
|
| 440 |
+
"grad_norm": 0.9445050954818726,
|
| 441 |
+
"learning_rate": 0.00010469094570483928,
|
| 442 |
+
"loss": 1.3217,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6478578892371996,
|
| 447 |
+
"grad_norm": 1.53034508228302,
|
| 448 |
+
"learning_rate": 9.949876837974944e-05,
|
| 449 |
+
"loss": 1.314,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.658307210031348,
|
| 454 |
+
"grad_norm": 1.8168761730194092,
|
| 455 |
+
"learning_rate": 9.437397501262026e-05,
|
| 456 |
+
"loss": 1.3365,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6687565308254964,
|
| 461 |
+
"grad_norm": 1.4955302476882935,
|
| 462 |
+
"learning_rate": 8.932340363194595e-05,
|
| 463 |
+
"loss": 1.3154,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6792058516196448,
|
| 468 |
+
"grad_norm": 1.2552021741867065,
|
| 469 |
+
"learning_rate": 8.435379323158218e-05,
|
| 470 |
+
"loss": 1.3366,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6896551724137931,
|
| 475 |
+
"grad_norm": 2.914289712905884,
|
| 476 |
+
"learning_rate": 7.947177477888472e-05,
|
| 477 |
+
"loss": 1.3233,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7001044932079414,
|
| 482 |
+
"grad_norm": 1.3406000137329102,
|
| 483 |
+
"learning_rate": 7.46838623669881e-05,
|
| 484 |
+
"loss": 1.3264,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7105538140020898,
|
| 489 |
+
"grad_norm": 0.9025297164916992,
|
| 490 |
+
"learning_rate": 6.999644452302975e-05,
|
| 491 |
+
"loss": 1.3197,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7210031347962382,
|
| 496 |
+
"grad_norm": 1.2824598550796509,
|
| 497 |
+
"learning_rate": 6.541577568391758e-05,
|
| 498 |
+
"loss": 1.3201,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7314524555903866,
|
| 503 |
+
"grad_norm": 0.9296241998672485,
|
| 504 |
+
"learning_rate": 6.0947967851014405e-05,
|
| 505 |
+
"loss": 1.3097,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.741901776384535,
|
| 510 |
+
"grad_norm": 0.8738858699798584,
|
| 511 |
+
"learning_rate": 5.659898243487463e-05,
|
| 512 |
+
"loss": 1.3044,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7523510971786834,
|
| 517 |
+
"grad_norm": 1.8482000827789307,
|
| 518 |
+
"learning_rate": 5.237462230091467e-05,
|
| 519 |
+
"loss": 1.3108,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7628004179728317,
|
| 524 |
+
"grad_norm": 2.537909746170044,
|
| 525 |
+
"learning_rate": 4.8280524026630565e-05,
|
| 526 |
+
"loss": 1.3164,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7732497387669801,
|
| 531 |
+
"grad_norm": 1.3068586587905884,
|
| 532 |
+
"learning_rate": 4.432215038069449e-05,
|
| 533 |
+
"loss": 1.2782,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.7836990595611285,
|
| 538 |
+
"grad_norm": 1.3742858171463013,
|
| 539 |
+
"learning_rate": 4.0504783033964645e-05,
|
| 540 |
+
"loss": 1.3179,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7941483803552769,
|
| 545 |
+
"grad_norm": 1.2923156023025513,
|
| 546 |
+
"learning_rate": 3.6833515512134606e-05,
|
| 547 |
+
"loss": 1.2904,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8045977011494253,
|
| 552 |
+
"grad_norm": 0.7867398262023926,
|
| 553 |
+
"learning_rate": 3.331324639942526e-05,
|
| 554 |
+
"loss": 1.3029,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8150470219435737,
|
| 559 |
+
"grad_norm": 1.1442195177078247,
|
| 560 |
+
"learning_rate": 2.9948672802388135e-05,
|
| 561 |
+
"loss": 1.3069,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8254963427377221,
|
| 566 |
+
"grad_norm": 1.4821033477783203,
|
| 567 |
+
"learning_rate": 2.67442840825406e-05,
|
| 568 |
+
"loss": 1.3177,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8359456635318704,
|
| 573 |
+
"grad_norm": 0.9633380770683289,
|
| 574 |
+
"learning_rate": 2.3704355866196373e-05,
|
| 575 |
+
"loss": 1.3249,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8463949843260188,
|
| 580 |
+
"grad_norm": 1.2908155918121338,
|
| 581 |
+
"learning_rate": 2.083294433948324e-05,
|
| 582 |
+
"loss": 1.3449,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8568443051201672,
|
| 587 |
+
"grad_norm": 1.1834619045257568,
|
| 588 |
+
"learning_rate": 1.813388083616068e-05,
|
| 589 |
+
"loss": 1.3086,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8672936259143156,
|
| 594 |
+
"grad_norm": 1.1399352550506592,
|
| 595 |
+
"learning_rate": 1.5610766725458834e-05,
|
| 596 |
+
"loss": 1.315,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.877742946708464,
|
| 601 |
+
"grad_norm": 1.2300066947937012,
|
| 602 |
+
"learning_rate": 1.326696860675981e-05,
|
| 603 |
+
"loss": 1.2894,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.8881922675026124,
|
| 608 |
+
"grad_norm": 0.9975532293319702,
|
| 609 |
+
"learning_rate": 1.1105613817532976e-05,
|
| 610 |
+
"loss": 1.2953,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.8986415882967607,
|
| 615 |
+
"grad_norm": 0.9357336163520813,
|
| 616 |
+
"learning_rate": 9.129586260518634e-06,
|
| 617 |
+
"loss": 1.3159,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9090909090909091,
|
| 622 |
+
"grad_norm": 0.7603440880775452,
|
| 623 |
+
"learning_rate": 7.34152255572697e-06,
|
| 624 |
+
"loss": 1.2897,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.9195402298850575,
|
| 629 |
+
"grad_norm": 0.8711851835250854,
|
| 630 |
+
"learning_rate": 5.743808522387544e-06,
|
| 631 |
+
"loss": 1.275,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9299895506792059,
|
| 636 |
+
"grad_norm": 0.9144044518470764,
|
| 637 |
+
"learning_rate": 4.33857599554282e-06,
|
| 638 |
+
"loss": 1.328,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9404388714733543,
|
| 643 |
+
"grad_norm": 0.862479567527771,
|
| 644 |
+
"learning_rate": 3.1276999815337544e-06,
|
| 645 |
+
"loss": 1.2879,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9508881922675027,
|
| 650 |
+
"grad_norm": 0.7352892756462097,
|
| 651 |
+
"learning_rate": 2.1127961561727193e-06,
|
| 652 |
+
"loss": 1.2873,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9613375130616509,
|
| 657 |
+
"grad_norm": 2.582821846008301,
|
| 658 |
+
"learning_rate": 1.2952187089419642e-06,
|
| 659 |
+
"loss": 1.3191,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.9717868338557993,
|
| 664 |
+
"grad_norm": 0.7060139179229736,
|
| 665 |
+
"learning_rate": 6.760585360942872e-07,
|
| 666 |
+
"loss": 1.3047,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.9822361546499477,
|
| 671 |
+
"grad_norm": 0.8089200258255005,
|
| 672 |
+
"learning_rate": 2.5614178506644934e-07,
|
| 673 |
+
"loss": 1.2743,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9926854754440961,
|
| 678 |
+
"grad_norm": 1.2739328145980835,
|
| 679 |
+
"learning_rate": 3.6028752148081766e-08,
|
| 680 |
+
"loss": 1.3004,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9989550679205852,
|
| 685 |
+
"eval_loss": 1.9203195571899414,
|
| 686 |
+
"eval_runtime": 0.8302,
|
| 687 |
+
"eval_samples_per_second": 2.409,
|
| 688 |
+
"eval_steps_per_second": 1.205,
|
| 689 |
+
"step": 478
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9989550679205852,
|
| 693 |
+
"step": 478,
|
| 694 |
+
"total_flos": 3.643767570437243e+17,
|
| 695 |
+
"train_loss": 4.360991338805674,
|
| 696 |
+
"train_runtime": 2613.4355,
|
| 697 |
+
"train_samples_per_second": 2.928,
|
| 698 |
+
"train_steps_per_second": 0.183
|
| 699 |
+
}
|
| 700 |
+
],
|
| 701 |
+
"logging_steps": 5,
|
| 702 |
+
"max_steps": 478,
|
| 703 |
+
"num_input_tokens_seen": 0,
|
| 704 |
+
"num_train_epochs": 1,
|
| 705 |
+
"save_steps": 100,
|
| 706 |
+
"stateful_callbacks": {
|
| 707 |
+
"TrainerControl": {
|
| 708 |
+
"args": {
|
| 709 |
+
"should_epoch_stop": false,
|
| 710 |
+
"should_evaluate": false,
|
| 711 |
+
"should_log": false,
|
| 712 |
+
"should_save": true,
|
| 713 |
+
"should_training_stop": true
|
| 714 |
+
},
|
| 715 |
+
"attributes": {}
|
| 716 |
+
}
|
| 717 |
+
},
|
| 718 |
+
"total_flos": 3.643767570437243e+17,
|
| 719 |
+
"train_batch_size": 1,
|
| 720 |
+
"trial_name": null,
|
| 721 |
+
"trial_params": null
|
| 722 |
+
}
|