End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +861 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: openthoughts2_0.3k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# openthoughts2_0.3k
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: openthoughts2_0.3k
|
|
|
|
| 16 |
|
| 17 |
# openthoughts2_0.3k
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts2_0.3k dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.30379746835443,
|
| 3 |
+
"total_flos": 5.164190805262336e+16,
|
| 4 |
+
"train_loss": 0.27243100587501484,
|
| 5 |
+
"train_runtime": 3122.1661,
|
| 6 |
+
"train_samples_per_second": 1.316,
|
| 7 |
+
"train_steps_per_second": 0.037
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 12.30379746835443,
|
| 3 |
+
"total_flos": 5.164190805262336e+16,
|
| 4 |
+
"train_loss": 0.27243100587501484,
|
| 5 |
+
"train_runtime": 3122.1661,
|
| 6 |
+
"train_samples_per_second": 1.316,
|
| 7 |
+
"train_steps_per_second": 0.037
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,861 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.30379746835443,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 117,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.10126582278481013,
|
| 13 |
+
"grad_norm": 6.072399482609559,
|
| 14 |
+
"learning_rate": 8.333333333333333e-07,
|
| 15 |
+
"loss": 0.9311,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.20253164556962025,
|
| 20 |
+
"grad_norm": 6.528417904864116,
|
| 21 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 22 |
+
"loss": 0.9497,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3037974683544304,
|
| 27 |
+
"grad_norm": 6.359051167500462,
|
| 28 |
+
"learning_rate": 2.5e-06,
|
| 29 |
+
"loss": 0.925,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4050632911392405,
|
| 34 |
+
"grad_norm": 5.565105862329674,
|
| 35 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 36 |
+
"loss": 0.844,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5063291139240507,
|
| 41 |
+
"grad_norm": 4.727785661318209,
|
| 42 |
+
"learning_rate": 4.166666666666667e-06,
|
| 43 |
+
"loss": 0.7805,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6075949367088608,
|
| 48 |
+
"grad_norm": 2.939782828489048,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7894,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7088607594936709,
|
| 55 |
+
"grad_norm": 2.4973979783489733,
|
| 56 |
+
"learning_rate": 5.833333333333334e-06,
|
| 57 |
+
"loss": 0.7919,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.810126582278481,
|
| 62 |
+
"grad_norm": 3.4573139987846306,
|
| 63 |
+
"learning_rate": 6.666666666666667e-06,
|
| 64 |
+
"loss": 0.6866,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9113924050632911,
|
| 69 |
+
"grad_norm": 3.6563089349469426,
|
| 70 |
+
"learning_rate": 7.500000000000001e-06,
|
| 71 |
+
"loss": 0.7305,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0506329113924051,
|
| 76 |
+
"grad_norm": 3.567454282033785,
|
| 77 |
+
"learning_rate": 8.333333333333334e-06,
|
| 78 |
+
"loss": 0.6779,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.1518987341772151,
|
| 83 |
+
"grad_norm": 4.098166086636336,
|
| 84 |
+
"learning_rate": 9.166666666666666e-06,
|
| 85 |
+
"loss": 0.6925,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.2531645569620253,
|
| 90 |
+
"grad_norm": 3.6049015574707237,
|
| 91 |
+
"learning_rate": 1e-05,
|
| 92 |
+
"loss": 0.638,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.3544303797468356,
|
| 97 |
+
"grad_norm": 2.649495808700651,
|
| 98 |
+
"learning_rate": 9.997762161417517e-06,
|
| 99 |
+
"loss": 0.5902,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.4556962025316456,
|
| 104 |
+
"grad_norm": 1.903448209503473,
|
| 105 |
+
"learning_rate": 9.991050648838676e-06,
|
| 106 |
+
"loss": 0.6156,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.5569620253164556,
|
| 111 |
+
"grad_norm": 2.3072830102920396,
|
| 112 |
+
"learning_rate": 9.979871469976197e-06,
|
| 113 |
+
"loss": 0.6304,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.6582278481012658,
|
| 118 |
+
"grad_norm": 2.5675698669272533,
|
| 119 |
+
"learning_rate": 9.964234631709188e-06,
|
| 120 |
+
"loss": 0.5867,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.759493670886076,
|
| 125 |
+
"grad_norm": 2.3369229527199322,
|
| 126 |
+
"learning_rate": 9.944154131125643e-06,
|
| 127 |
+
"loss": 0.5766,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.8607594936708862,
|
| 132 |
+
"grad_norm": 1.7502043484517904,
|
| 133 |
+
"learning_rate": 9.91964794299315e-06,
|
| 134 |
+
"loss": 0.6034,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.9620253164556962,
|
| 139 |
+
"grad_norm": 1.3842136352111996,
|
| 140 |
+
"learning_rate": 9.890738003669029e-06,
|
| 141 |
+
"loss": 0.6321,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.1012658227848102,
|
| 146 |
+
"grad_norm": 1.191500677161361,
|
| 147 |
+
"learning_rate": 9.857450191464337e-06,
|
| 148 |
+
"loss": 0.5439,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.2025316455696204,
|
| 153 |
+
"grad_norm": 1.4627345570631196,
|
| 154 |
+
"learning_rate": 9.819814303479268e-06,
|
| 155 |
+
"loss": 0.5128,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.3037974683544302,
|
| 160 |
+
"grad_norm": 1.3954713454302212,
|
| 161 |
+
"learning_rate": 9.777864028930705e-06,
|
| 162 |
+
"loss": 0.5064,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.4050632911392404,
|
| 167 |
+
"grad_norm": 1.149689960616138,
|
| 168 |
+
"learning_rate": 9.731636918995821e-06,
|
| 169 |
+
"loss": 0.5034,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.5063291139240507,
|
| 174 |
+
"grad_norm": 0.8646967455048312,
|
| 175 |
+
"learning_rate": 9.681174353198687e-06,
|
| 176 |
+
"loss": 0.4141,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.607594936708861,
|
| 181 |
+
"grad_norm": 1.211177188921121,
|
| 182 |
+
"learning_rate": 9.626521502369984e-06,
|
| 183 |
+
"loss": 0.4684,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.708860759493671,
|
| 188 |
+
"grad_norm": 1.114994524367215,
|
| 189 |
+
"learning_rate": 9.567727288213005e-06,
|
| 190 |
+
"loss": 0.4384,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.810126582278481,
|
| 195 |
+
"grad_norm": 1.1034819058451153,
|
| 196 |
+
"learning_rate": 9.504844339512096e-06,
|
| 197 |
+
"loss": 0.4866,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.911392405063291,
|
| 202 |
+
"grad_norm": 0.9561311333450966,
|
| 203 |
+
"learning_rate": 9.437928945022772e-06,
|
| 204 |
+
"loss": 0.4938,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.050632911392405,
|
| 209 |
+
"grad_norm": 0.9492493144685268,
|
| 210 |
+
"learning_rate": 9.36704100308565e-06,
|
| 211 |
+
"loss": 0.4079,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.151898734177215,
|
| 216 |
+
"grad_norm": 0.8460198523294045,
|
| 217 |
+
"learning_rate": 9.292243968009332e-06,
|
| 218 |
+
"loss": 0.3836,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.2531645569620253,
|
| 223 |
+
"grad_norm": 0.8448002700469955,
|
| 224 |
+
"learning_rate": 9.213604793270196e-06,
|
| 225 |
+
"loss": 0.4039,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.3544303797468356,
|
| 230 |
+
"grad_norm": 0.9979909857423938,
|
| 231 |
+
"learning_rate": 9.131193871579975e-06,
|
| 232 |
+
"loss": 0.4142,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.4556962025316453,
|
| 237 |
+
"grad_norm": 1.008238173973131,
|
| 238 |
+
"learning_rate": 9.045084971874738e-06,
|
| 239 |
+
"loss": 0.2943,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.5569620253164556,
|
| 244 |
+
"grad_norm": 0.8117140188138161,
|
| 245 |
+
"learning_rate": 8.955355173281709e-06,
|
| 246 |
+
"loss": 0.3625,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.6582278481012658,
|
| 251 |
+
"grad_norm": 0.9323524575252192,
|
| 252 |
+
"learning_rate": 8.862084796122998e-06,
|
| 253 |
+
"loss": 0.3301,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.759493670886076,
|
| 258 |
+
"grad_norm": 0.7649027000661041,
|
| 259 |
+
"learning_rate": 8.765357330018056e-06,
|
| 260 |
+
"loss": 0.3401,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.8607594936708862,
|
| 265 |
+
"grad_norm": 0.812294103768114,
|
| 266 |
+
"learning_rate": 8.665259359149132e-06,
|
| 267 |
+
"loss": 0.3731,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.962025316455696,
|
| 272 |
+
"grad_norm": 0.8989937598022456,
|
| 273 |
+
"learning_rate": 8.561880484756726e-06,
|
| 274 |
+
"loss": 0.3556,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.10126582278481,
|
| 279 |
+
"grad_norm": 0.6739283815775967,
|
| 280 |
+
"learning_rate": 8.455313244934324e-06,
|
| 281 |
+
"loss": 0.3495,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.2025316455696204,
|
| 286 |
+
"grad_norm": 0.6998338778113444,
|
| 287 |
+
"learning_rate": 8.345653031794292e-06,
|
| 288 |
+
"loss": 0.2985,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.30379746835443,
|
| 293 |
+
"grad_norm": 0.7834404406433867,
|
| 294 |
+
"learning_rate": 8.232998006078998e-06,
|
| 295 |
+
"loss": 0.3125,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.405063291139241,
|
| 300 |
+
"grad_norm": 0.7507220560040153,
|
| 301 |
+
"learning_rate": 8.117449009293668e-06,
|
| 302 |
+
"loss": 0.2084,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.506329113924051,
|
| 307 |
+
"grad_norm": 0.8027498393678201,
|
| 308 |
+
"learning_rate": 7.99910947343957e-06,
|
| 309 |
+
"loss": 0.2719,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.6075949367088604,
|
| 314 |
+
"grad_norm": 0.6777632208321701,
|
| 315 |
+
"learning_rate": 7.87808532842837e-06,
|
| 316 |
+
"loss": 0.2179,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.708860759493671,
|
| 321 |
+
"grad_norm": 0.820932146824711,
|
| 322 |
+
"learning_rate": 7.754484907260513e-06,
|
| 323 |
+
"loss": 0.2132,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.810126582278481,
|
| 328 |
+
"grad_norm": 0.7671983330942551,
|
| 329 |
+
"learning_rate": 7.628418849052523e-06,
|
| 330 |
+
"loss": 0.2101,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.911392405063291,
|
| 335 |
+
"grad_norm": 0.6479792729844295,
|
| 336 |
+
"learning_rate": 7.500000000000001e-06,
|
| 337 |
+
"loss": 0.2558,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.050632911392405,
|
| 342 |
+
"grad_norm": 0.6997994303448063,
|
| 343 |
+
"learning_rate": 7.369343312364994e-06,
|
| 344 |
+
"loss": 0.2486,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 5.151898734177215,
|
| 349 |
+
"grad_norm": 0.600614946556084,
|
| 350 |
+
"learning_rate": 7.236565741578163e-06,
|
| 351 |
+
"loss": 0.1955,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 5.253164556962025,
|
| 356 |
+
"grad_norm": 0.6084873052924032,
|
| 357 |
+
"learning_rate": 7.101786141547829e-06,
|
| 358 |
+
"loss": 0.186,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.3544303797468356,
|
| 363 |
+
"grad_norm": 0.6760586464049322,
|
| 364 |
+
"learning_rate": 6.965125158269619e-06,
|
| 365 |
+
"loss": 0.2063,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.455696202531645,
|
| 370 |
+
"grad_norm": 0.8388676036575262,
|
| 371 |
+
"learning_rate": 6.8267051218319766e-06,
|
| 372 |
+
"loss": 0.1844,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 5.556962025316456,
|
| 377 |
+
"grad_norm": 0.6648670967418823,
|
| 378 |
+
"learning_rate": 6.686649936914151e-06,
|
| 379 |
+
"loss": 0.2212,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.658227848101266,
|
| 384 |
+
"grad_norm": 0.6913807985993646,
|
| 385 |
+
"learning_rate": 6.545084971874738e-06,
|
| 386 |
+
"loss": 0.2044,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.759493670886076,
|
| 391 |
+
"grad_norm": 0.7410214359703502,
|
| 392 |
+
"learning_rate": 6.402136946530014e-06,
|
| 393 |
+
"loss": 0.158,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.860759493670886,
|
| 398 |
+
"grad_norm": 0.7098765043481983,
|
| 399 |
+
"learning_rate": 6.257933818722544e-06,
|
| 400 |
+
"loss": 0.2431,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.962025316455696,
|
| 405 |
+
"grad_norm": 0.5721423832787186,
|
| 406 |
+
"learning_rate": 6.112604669781572e-06,
|
| 407 |
+
"loss": 0.2224,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 6.10126582278481,
|
| 412 |
+
"grad_norm": 0.5970589230104892,
|
| 413 |
+
"learning_rate": 5.9662795889777666e-06,
|
| 414 |
+
"loss": 0.1807,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 6.2025316455696204,
|
| 419 |
+
"grad_norm": 0.5675637702182478,
|
| 420 |
+
"learning_rate": 5.819089557075689e-06,
|
| 421 |
+
"loss": 0.1659,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.30379746835443,
|
| 426 |
+
"grad_norm": 0.569833648680632,
|
| 427 |
+
"learning_rate": 5.671166329088278e-06,
|
| 428 |
+
"loss": 0.1562,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 6.405063291139241,
|
| 433 |
+
"grad_norm": 0.7751449220394955,
|
| 434 |
+
"learning_rate": 5.522642316338268e-06,
|
| 435 |
+
"loss": 0.0946,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 6.506329113924051,
|
| 440 |
+
"grad_norm": 0.748937902790741,
|
| 441 |
+
"learning_rate": 5.373650467932122e-06,
|
| 442 |
+
"loss": 0.1981,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.6075949367088604,
|
| 447 |
+
"grad_norm": 0.6309090190435733,
|
| 448 |
+
"learning_rate": 5.224324151752575e-06,
|
| 449 |
+
"loss": 0.1124,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.708860759493671,
|
| 454 |
+
"grad_norm": 0.6274934004644721,
|
| 455 |
+
"learning_rate": 5.074797035076319e-06,
|
| 456 |
+
"loss": 0.1542,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.810126582278481,
|
| 461 |
+
"grad_norm": 0.6001914889775909,
|
| 462 |
+
"learning_rate": 4.9252029649236835e-06,
|
| 463 |
+
"loss": 0.1885,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.911392405063291,
|
| 468 |
+
"grad_norm": 0.6404055666945739,
|
| 469 |
+
"learning_rate": 4.775675848247427e-06,
|
| 470 |
+
"loss": 0.129,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.050632911392405,
|
| 475 |
+
"grad_norm": 0.5952620582885074,
|
| 476 |
+
"learning_rate": 4.626349532067879e-06,
|
| 477 |
+
"loss": 0.0944,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.151898734177215,
|
| 482 |
+
"grad_norm": 0.46524834102802404,
|
| 483 |
+
"learning_rate": 4.477357683661734e-06,
|
| 484 |
+
"loss": 0.1655,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.253164556962025,
|
| 489 |
+
"grad_norm": 0.4457965027456963,
|
| 490 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 491 |
+
"loss": 0.081,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.3544303797468356,
|
| 496 |
+
"grad_norm": 0.47788652166072815,
|
| 497 |
+
"learning_rate": 4.180910442924312e-06,
|
| 498 |
+
"loss": 0.1226,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.455696202531645,
|
| 503 |
+
"grad_norm": 0.6252950270769206,
|
| 504 |
+
"learning_rate": 4.033720411022235e-06,
|
| 505 |
+
"loss": 0.1305,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.556962025316456,
|
| 510 |
+
"grad_norm": 0.579503825540115,
|
| 511 |
+
"learning_rate": 3.887395330218429e-06,
|
| 512 |
+
"loss": 0.1636,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.658227848101266,
|
| 517 |
+
"grad_norm": 0.5243943559327514,
|
| 518 |
+
"learning_rate": 3.7420661812774577e-06,
|
| 519 |
+
"loss": 0.1118,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.759493670886076,
|
| 524 |
+
"grad_norm": 0.5152657410146392,
|
| 525 |
+
"learning_rate": 3.5978630534699873e-06,
|
| 526 |
+
"loss": 0.1123,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.860759493670886,
|
| 531 |
+
"grad_norm": 0.7529963904638194,
|
| 532 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 533 |
+
"loss": 0.0736,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.962025316455696,
|
| 538 |
+
"grad_norm": 0.5641636199364488,
|
| 539 |
+
"learning_rate": 3.3133500630858507e-06,
|
| 540 |
+
"loss": 0.0975,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.10126582278481,
|
| 545 |
+
"grad_norm": 0.5480619305002655,
|
| 546 |
+
"learning_rate": 3.173294878168025e-06,
|
| 547 |
+
"loss": 0.0823,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 8.20253164556962,
|
| 552 |
+
"grad_norm": 0.45454040006743707,
|
| 553 |
+
"learning_rate": 3.0348748417303826e-06,
|
| 554 |
+
"loss": 0.0993,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 8.30379746835443,
|
| 559 |
+
"grad_norm": 0.4707710283401514,
|
| 560 |
+
"learning_rate": 2.8982138584521734e-06,
|
| 561 |
+
"loss": 0.134,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 8.405063291139241,
|
| 566 |
+
"grad_norm": 0.46013119087249,
|
| 567 |
+
"learning_rate": 2.7634342584218364e-06,
|
| 568 |
+
"loss": 0.1124,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.50632911392405,
|
| 573 |
+
"grad_norm": 0.3674000562058081,
|
| 574 |
+
"learning_rate": 2.6306566876350072e-06,
|
| 575 |
+
"loss": 0.068,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 8.60759493670886,
|
| 580 |
+
"grad_norm": 0.5680967440483309,
|
| 581 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 582 |
+
"loss": 0.1122,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 8.708860759493671,
|
| 587 |
+
"grad_norm": 0.40616358293863153,
|
| 588 |
+
"learning_rate": 2.371581150947476e-06,
|
| 589 |
+
"loss": 0.0526,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.810126582278482,
|
| 594 |
+
"grad_norm": 0.5359486096542745,
|
| 595 |
+
"learning_rate": 2.245515092739488e-06,
|
| 596 |
+
"loss": 0.0801,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.91139240506329,
|
| 601 |
+
"grad_norm": 0.5997640716920127,
|
| 602 |
+
"learning_rate": 2.1219146715716332e-06,
|
| 603 |
+
"loss": 0.097,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 9.050632911392405,
|
| 608 |
+
"grad_norm": 0.37092137107517437,
|
| 609 |
+
"learning_rate": 2.0008905265604316e-06,
|
| 610 |
+
"loss": 0.0745,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 9.151898734177216,
|
| 615 |
+
"grad_norm": 0.3980635601259192,
|
| 616 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 617 |
+
"loss": 0.1041,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 9.253164556962025,
|
| 622 |
+
"grad_norm": 0.3493171887225538,
|
| 623 |
+
"learning_rate": 1.7670019939210025e-06,
|
| 624 |
+
"loss": 0.0496,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 9.354430379746836,
|
| 629 |
+
"grad_norm": 0.3961182297025844,
|
| 630 |
+
"learning_rate": 1.6543469682057105e-06,
|
| 631 |
+
"loss": 0.0799,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 9.455696202531646,
|
| 636 |
+
"grad_norm": 0.44892699199272074,
|
| 637 |
+
"learning_rate": 1.544686755065677e-06,
|
| 638 |
+
"loss": 0.0679,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 9.556962025316455,
|
| 643 |
+
"grad_norm": 0.37258247045248516,
|
| 644 |
+
"learning_rate": 1.438119515243277e-06,
|
| 645 |
+
"loss": 0.1011,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 9.658227848101266,
|
| 650 |
+
"grad_norm": 0.35513862758990106,
|
| 651 |
+
"learning_rate": 1.3347406408508695e-06,
|
| 652 |
+
"loss": 0.0986,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 9.759493670886076,
|
| 657 |
+
"grad_norm": 0.37845306175190563,
|
| 658 |
+
"learning_rate": 1.234642669981946e-06,
|
| 659 |
+
"loss": 0.0913,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.860759493670885,
|
| 664 |
+
"grad_norm": 0.5739039401971411,
|
| 665 |
+
"learning_rate": 1.137915203877003e-06,
|
| 666 |
+
"loss": 0.0863,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 9.962025316455696,
|
| 671 |
+
"grad_norm": 0.33694694531512864,
|
| 672 |
+
"learning_rate": 1.044644826718295e-06,
|
| 673 |
+
"loss": 0.0587,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 10.10126582278481,
|
| 678 |
+
"grad_norm": 0.2582014853110333,
|
| 679 |
+
"learning_rate": 9.549150281252633e-07,
|
| 680 |
+
"loss": 0.0528,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 10.20253164556962,
|
| 685 |
+
"grad_norm": 0.32586737636444013,
|
| 686 |
+
"learning_rate": 8.688061284200266e-07,
|
| 687 |
+
"loss": 0.1201,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 10.30379746835443,
|
| 692 |
+
"grad_norm": 0.49581423067659225,
|
| 693 |
+
"learning_rate": 7.863952067298042e-07,
|
| 694 |
+
"loss": 0.0666,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 10.405063291139241,
|
| 699 |
+
"grad_norm": 0.372463197361783,
|
| 700 |
+
"learning_rate": 7.077560319906696e-07,
|
| 701 |
+
"loss": 0.0978,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 10.50632911392405,
|
| 706 |
+
"grad_norm": 0.2895426112826978,
|
| 707 |
+
"learning_rate": 6.329589969143518e-07,
|
| 708 |
+
"loss": 0.0864,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 10.60759493670886,
|
| 713 |
+
"grad_norm": 0.3486582961664102,
|
| 714 |
+
"learning_rate": 5.620710549772295e-07,
|
| 715 |
+
"loss": 0.0594,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 10.708860759493671,
|
| 720 |
+
"grad_norm": 0.3073636680406654,
|
| 721 |
+
"learning_rate": 4.951556604879049e-07,
|
| 722 |
+
"loss": 0.0587,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 10.810126582278482,
|
| 727 |
+
"grad_norm": 0.29519395152960587,
|
| 728 |
+
"learning_rate": 4.322727117869951e-07,
|
| 729 |
+
"loss": 0.0576,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 10.91139240506329,
|
| 734 |
+
"grad_norm": 0.3034747099522094,
|
| 735 |
+
"learning_rate": 3.734784976300165e-07,
|
| 736 |
+
"loss": 0.0953,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 11.050632911392405,
|
| 741 |
+
"grad_norm": 0.2529407827790441,
|
| 742 |
+
"learning_rate": 3.18825646801314e-07,
|
| 743 |
+
"loss": 0.057,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 11.151898734177216,
|
| 748 |
+
"grad_norm": 0.24273949649378235,
|
| 749 |
+
"learning_rate": 2.6836308100417874e-07,
|
| 750 |
+
"loss": 0.044,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 11.253164556962025,
|
| 755 |
+
"grad_norm": 0.30954761916571744,
|
| 756 |
+
"learning_rate": 2.2213597106929608e-07,
|
| 757 |
+
"loss": 0.0728,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 11.354430379746836,
|
| 762 |
+
"grad_norm": 0.24811277009407764,
|
| 763 |
+
"learning_rate": 1.801856965207338e-07,
|
| 764 |
+
"loss": 0.0428,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 11.455696202531646,
|
| 769 |
+
"grad_norm": 0.2989757408965876,
|
| 770 |
+
"learning_rate": 1.4254980853566248e-07,
|
| 771 |
+
"loss": 0.086,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 11.556962025316455,
|
| 776 |
+
"grad_norm": 0.22257702361173523,
|
| 777 |
+
"learning_rate": 1.0926199633097156e-07,
|
| 778 |
+
"loss": 0.0697,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 11.658227848101266,
|
| 783 |
+
"grad_norm": 0.3009281789737169,
|
| 784 |
+
"learning_rate": 8.035205700685167e-08,
|
| 785 |
+
"loss": 0.0781,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 11.759493670886076,
|
| 790 |
+
"grad_norm": 0.2429827327502092,
|
| 791 |
+
"learning_rate": 5.584586887435739e-08,
|
| 792 |
+
"loss": 0.0407,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 11.860759493670885,
|
| 797 |
+
"grad_norm": 0.2924882374183564,
|
| 798 |
+
"learning_rate": 3.576536829081323e-08,
|
| 799 |
+
"loss": 0.09,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 11.962025316455696,
|
| 804 |
+
"grad_norm": 0.28205168547697096,
|
| 805 |
+
"learning_rate": 2.012853002380466e-08,
|
| 806 |
+
"loss": 0.0965,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 12.10126582278481,
|
| 811 |
+
"grad_norm": 0.2936201996849507,
|
| 812 |
+
"learning_rate": 8.949351161324227e-09,
|
| 813 |
+
"loss": 0.0866,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 12.20253164556962,
|
| 818 |
+
"grad_norm": 0.2535203420104844,
|
| 819 |
+
"learning_rate": 2.237838582483387e-09,
|
| 820 |
+
"loss": 0.0495,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 12.30379746835443,
|
| 825 |
+
"grad_norm": 0.2866817448867829,
|
| 826 |
+
"learning_rate": 0.0,
|
| 827 |
+
"loss": 0.071,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 12.30379746835443,
|
| 832 |
+
"step": 117,
|
| 833 |
+
"total_flos": 5.164190805262336e+16,
|
| 834 |
+
"train_loss": 0.27243100587501484,
|
| 835 |
+
"train_runtime": 3122.1661,
|
| 836 |
+
"train_samples_per_second": 1.316,
|
| 837 |
+
"train_steps_per_second": 0.037
|
| 838 |
+
}
|
| 839 |
+
],
|
| 840 |
+
"logging_steps": 1,
|
| 841 |
+
"max_steps": 117,
|
| 842 |
+
"num_input_tokens_seen": 0,
|
| 843 |
+
"num_train_epochs": 13,
|
| 844 |
+
"save_steps": 500,
|
| 845 |
+
"stateful_callbacks": {
|
| 846 |
+
"TrainerControl": {
|
| 847 |
+
"args": {
|
| 848 |
+
"should_epoch_stop": false,
|
| 849 |
+
"should_evaluate": false,
|
| 850 |
+
"should_log": false,
|
| 851 |
+
"should_save": true,
|
| 852 |
+
"should_training_stop": true
|
| 853 |
+
},
|
| 854 |
+
"attributes": {}
|
| 855 |
+
}
|
| 856 |
+
},
|
| 857 |
+
"total_flos": 5.164190805262336e+16,
|
| 858 |
+
"train_batch_size": 1,
|
| 859 |
+
"trial_name": null,
|
| 860 |
+
"trial_params": null
|
| 861 |
+
}
|
training_loss.png
ADDED
|