End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +745 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: oh_v1.3_camel_math_x8
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh_v1.3_camel_math_x8
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6987
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: oh_v1.3_camel_math_x8
|
|
|
|
| 16 |
|
| 17 |
# oh_v1.3_camel_math_x8
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v1.3_camel_math_x8 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6987
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6986876726150513,
|
| 4 |
+
"eval_runtime": 341.5155,
|
| 5 |
+
"eval_samples_per_second": 25.642,
|
| 6 |
+
"eval_steps_per_second": 0.401,
|
| 7 |
+
"total_flos": 1632951934648320.0,
|
| 8 |
+
"train_loss": 0.6751218311603253,
|
| 9 |
+
"train_runtime": 57099.1896,
|
| 10 |
+
"train_samples_per_second": 8.741,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6986876726150513,
|
| 4 |
+
"eval_runtime": 341.5155,
|
| 5 |
+
"eval_samples_per_second": 25.642,
|
| 6 |
+
"eval_steps_per_second": 0.401
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1632951934648320.0,
|
| 4 |
+
"train_loss": 0.6751218311603253,
|
| 5 |
+
"train_runtime": 57099.1896,
|
| 6 |
+
"train_samples_per_second": 8.741,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 975,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03076923076923077,
|
| 13 |
+
"grad_norm": 2.3324186560475026,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.9796,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06153846153846154,
|
| 20 |
+
"grad_norm": 1.0624345768919523,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.8629,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09230769230769231,
|
| 27 |
+
"grad_norm": 1.0856708355070386,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.8232,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12307692307692308,
|
| 34 |
+
"grad_norm": 1.3950701294784864,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.8034,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15384615384615385,
|
| 41 |
+
"grad_norm": 0.9965613643303693,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7826,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18461538461538463,
|
| 48 |
+
"grad_norm": 0.835067800401052,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7723,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2153846153846154,
|
| 55 |
+
"grad_norm": 0.781647957469068,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.767,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24615384615384617,
|
| 62 |
+
"grad_norm": 1.1712549789017386,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7559,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.27692307692307694,
|
| 69 |
+
"grad_norm": 1.0092940618549995,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7469,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3076923076923077,
|
| 76 |
+
"grad_norm": 0.5624307958541879,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.7414,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3384615384615385,
|
| 83 |
+
"grad_norm": 0.5739018842323079,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.7402,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.36923076923076925,
|
| 90 |
+
"grad_norm": 0.5881069634317425,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.7409,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4,
|
| 97 |
+
"grad_norm": 0.7381656504744467,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.7376,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4307692307692308,
|
| 104 |
+
"grad_norm": 0.5677544829127201,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.7298,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.46153846153846156,
|
| 111 |
+
"grad_norm": 0.7988060295240222,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.734,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.49230769230769234,
|
| 118 |
+
"grad_norm": 0.6718712556340437,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.7301,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5230769230769231,
|
| 125 |
+
"grad_norm": 0.6738769041614976,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.7316,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5538461538461539,
|
| 132 |
+
"grad_norm": 0.5838925373137313,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.7253,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5846153846153846,
|
| 139 |
+
"grad_norm": 0.6725428665358475,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.7241,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6153846153846154,
|
| 146 |
+
"grad_norm": 0.5603996763654583,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.7228,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6461538461538462,
|
| 153 |
+
"grad_norm": 0.7449029762390439,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.7204,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.676923076923077,
|
| 160 |
+
"grad_norm": 0.5236476916978245,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.717,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7076923076923077,
|
| 167 |
+
"grad_norm": 0.6865974040573393,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.7134,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7384615384615385,
|
| 174 |
+
"grad_norm": 0.6717184095724111,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.7159,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7692307692307693,
|
| 181 |
+
"grad_norm": 0.8235556500295945,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.711,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8,
|
| 188 |
+
"grad_norm": 0.5131501040264781,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.7165,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8307692307692308,
|
| 195 |
+
"grad_norm": 0.5193918430229191,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.7055,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8615384615384616,
|
| 202 |
+
"grad_norm": 0.5456897002979056,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.711,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8923076923076924,
|
| 209 |
+
"grad_norm": 0.5750072559309753,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.7084,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9230769230769231,
|
| 216 |
+
"grad_norm": 0.6116232515773206,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.7128,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9538461538461539,
|
| 223 |
+
"grad_norm": 0.5681793375147939,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.7086,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9846153846153847,
|
| 230 |
+
"grad_norm": 0.6343675909171526,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.7104,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0,
|
| 237 |
+
"eval_loss": 0.7103046774864197,
|
| 238 |
+
"eval_runtime": 341.5784,
|
| 239 |
+
"eval_samples_per_second": 25.637,
|
| 240 |
+
"eval_steps_per_second": 0.401,
|
| 241 |
+
"step": 325
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0153846153846153,
|
| 245 |
+
"grad_norm": 0.7692870192954333,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.6897,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0461538461538462,
|
| 252 |
+
"grad_norm": 0.5505626206403108,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.6636,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0769230769230769,
|
| 259 |
+
"grad_norm": 0.5824910302345806,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.665,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1076923076923078,
|
| 266 |
+
"grad_norm": 0.6417795632315966,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.664,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1384615384615384,
|
| 273 |
+
"grad_norm": 0.6909469669994084,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.6634,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1692307692307693,
|
| 280 |
+
"grad_norm": 0.5616732809499269,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6653,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.2,
|
| 287 |
+
"grad_norm": 0.567347803253029,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6605,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2307692307692308,
|
| 294 |
+
"grad_norm": 0.6020788318645328,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6649,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2615384615384615,
|
| 301 |
+
"grad_norm": 0.6247830402384781,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6662,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2923076923076924,
|
| 308 |
+
"grad_norm": 0.7223035560412274,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6631,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.323076923076923,
|
| 315 |
+
"grad_norm": 0.7277266215407076,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6596,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.353846153846154,
|
| 322 |
+
"grad_norm": 0.5531058222331595,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6659,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3846153846153846,
|
| 329 |
+
"grad_norm": 0.7560378640801586,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6654,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4153846153846155,
|
| 336 |
+
"grad_norm": 0.6002650702602214,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6602,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4461538461538461,
|
| 343 |
+
"grad_norm": 0.5446217104790005,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6633,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.476923076923077,
|
| 350 |
+
"grad_norm": 0.6427854645725265,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6606,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5076923076923077,
|
| 357 |
+
"grad_norm": 0.5777163615379136,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6619,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5384615384615383,
|
| 364 |
+
"grad_norm": 0.5645927733372786,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.6613,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5692307692307692,
|
| 371 |
+
"grad_norm": 0.5877237236567665,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6666,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6,
|
| 378 |
+
"grad_norm": 0.7318508117188922,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6657,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6307692307692307,
|
| 385 |
+
"grad_norm": 0.5337461204074161,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6678,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6615384615384614,
|
| 392 |
+
"grad_norm": 0.6743103368990547,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6593,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6923076923076923,
|
| 399 |
+
"grad_norm": 0.7414434681428989,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6575,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.7230769230769232,
|
| 406 |
+
"grad_norm": 0.8444136346063817,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6631,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7538461538461538,
|
| 413 |
+
"grad_norm": 0.5509955001744837,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6592,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7846153846153845,
|
| 420 |
+
"grad_norm": 0.6630480503790037,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6594,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8153846153846154,
|
| 427 |
+
"grad_norm": 0.5120012670268558,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6568,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.8461538461538463,
|
| 434 |
+
"grad_norm": 0.5752130113945352,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6599,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.876923076923077,
|
| 441 |
+
"grad_norm": 0.5835189539855182,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6591,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9076923076923076,
|
| 448 |
+
"grad_norm": 0.5603728195599548,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6629,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9384615384615385,
|
| 455 |
+
"grad_norm": 0.6856529088244573,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6586,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9692307692307693,
|
| 462 |
+
"grad_norm": 0.5160023610012462,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6603,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.0,
|
| 469 |
+
"grad_norm": 0.6268329172925445,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.658,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.0,
|
| 476 |
+
"eval_loss": 0.6978012323379517,
|
| 477 |
+
"eval_runtime": 343.0061,
|
| 478 |
+
"eval_samples_per_second": 25.53,
|
| 479 |
+
"eval_steps_per_second": 0.399,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.0307692307692307,
|
| 484 |
+
"grad_norm": 0.7968437785991972,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.6088,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.0615384615384613,
|
| 491 |
+
"grad_norm": 1.1539294867806145,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.6083,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.0923076923076924,
|
| 498 |
+
"grad_norm": 0.9623521768346174,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.6149,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.123076923076923,
|
| 505 |
+
"grad_norm": 0.6040507943945268,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.6164,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.1538461538461537,
|
| 512 |
+
"grad_norm": 0.5851170034060879,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.6115,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.184615384615385,
|
| 519 |
+
"grad_norm": 0.600096702685487,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.6153,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2153846153846155,
|
| 526 |
+
"grad_norm": 0.5589523777176305,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.6133,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.246153846153846,
|
| 533 |
+
"grad_norm": 0.5907169270955183,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.6131,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.276923076923077,
|
| 540 |
+
"grad_norm": 0.6628827223280479,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.6159,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.3076923076923075,
|
| 547 |
+
"grad_norm": 0.6215774766516785,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.6149,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.3384615384615386,
|
| 554 |
+
"grad_norm": 0.6649815302458084,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.6132,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3692307692307693,
|
| 561 |
+
"grad_norm": 0.699779615122456,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.6128,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.4,
|
| 568 |
+
"grad_norm": 0.546711048417698,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.6164,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.430769230769231,
|
| 575 |
+
"grad_norm": 0.6327118907910535,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.623,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.4615384615384617,
|
| 582 |
+
"grad_norm": 0.5174866030508046,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.6166,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.4923076923076923,
|
| 589 |
+
"grad_norm": 0.5497949972140503,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.615,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.523076923076923,
|
| 596 |
+
"grad_norm": 0.5993580492245987,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.614,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.5538461538461537,
|
| 603 |
+
"grad_norm": 0.6442768713339674,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.6222,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.5846153846153848,
|
| 610 |
+
"grad_norm": 0.6428843121497717,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.617,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.6153846153846154,
|
| 617 |
+
"grad_norm": 0.6117392354746288,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.62,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.646153846153846,
|
| 624 |
+
"grad_norm": 0.7180295224765794,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.619,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.676923076923077,
|
| 631 |
+
"grad_norm": 0.6501140616713876,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.6164,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.707692307692308,
|
| 638 |
+
"grad_norm": 0.5412288061836285,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.6218,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.7384615384615385,
|
| 645 |
+
"grad_norm": 0.7302614499001912,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.6176,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.769230769230769,
|
| 652 |
+
"grad_norm": 0.6661401784715161,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.6217,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.8,
|
| 659 |
+
"grad_norm": 0.7263597509162613,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.6154,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.830769230769231,
|
| 666 |
+
"grad_norm": 0.7506085991128838,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.6189,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.8615384615384616,
|
| 673 |
+
"grad_norm": 0.5917421117589724,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.6211,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.8923076923076922,
|
| 680 |
+
"grad_norm": 0.5306708247183923,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.6175,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.9230769230769234,
|
| 687 |
+
"grad_norm": 0.6648394376559398,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.6222,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.953846153846154,
|
| 694 |
+
"grad_norm": 0.5459019838181679,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.6174,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.9846153846153847,
|
| 701 |
+
"grad_norm": 0.6951553333219783,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.6176,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.0,
|
| 708 |
+
"eval_loss": 0.6986876726150513,
|
| 709 |
+
"eval_runtime": 342.0684,
|
| 710 |
+
"eval_samples_per_second": 25.6,
|
| 711 |
+
"eval_steps_per_second": 0.401,
|
| 712 |
+
"step": 975
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.0,
|
| 716 |
+
"step": 975,
|
| 717 |
+
"total_flos": 1632951934648320.0,
|
| 718 |
+
"train_loss": 0.6751218311603253,
|
| 719 |
+
"train_runtime": 57099.1896,
|
| 720 |
+
"train_samples_per_second": 8.741,
|
| 721 |
+
"train_steps_per_second": 0.017
|
| 722 |
+
}
|
| 723 |
+
],
|
| 724 |
+
"logging_steps": 10,
|
| 725 |
+
"max_steps": 975,
|
| 726 |
+
"num_input_tokens_seen": 0,
|
| 727 |
+
"num_train_epochs": 3,
|
| 728 |
+
"save_steps": 500,
|
| 729 |
+
"stateful_callbacks": {
|
| 730 |
+
"TrainerControl": {
|
| 731 |
+
"args": {
|
| 732 |
+
"should_epoch_stop": false,
|
| 733 |
+
"should_evaluate": false,
|
| 734 |
+
"should_log": false,
|
| 735 |
+
"should_save": true,
|
| 736 |
+
"should_training_stop": true
|
| 737 |
+
},
|
| 738 |
+
"attributes": {}
|
| 739 |
+
}
|
| 740 |
+
},
|
| 741 |
+
"total_flos": 1632951934648320.0,
|
| 742 |
+
"train_batch_size": 8,
|
| 743 |
+
"trial_name": null,
|
| 744 |
+
"trial_params": null
|
| 745 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|