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 +667 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_qwen_epoch2
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_qwen_epoch2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6188
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_qwen_epoch2
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_qwen_epoch2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6188
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9971509971509973,
|
| 3 |
+
"eval_loss": 0.6187613010406494,
|
| 4 |
+
"eval_runtime": 443.5964,
|
| 5 |
+
"eval_samples_per_second": 26.653,
|
| 6 |
+
"eval_steps_per_second": 0.417,
|
| 7 |
+
"total_flos": 1836725450047488.0,
|
| 8 |
+
"train_loss": 0.6210468141999963,
|
| 9 |
+
"train_runtime": 47044.2331,
|
| 10 |
+
"train_samples_per_second": 9.549,
|
| 11 |
+
"train_steps_per_second": 0.019
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9971509971509973,
|
| 3 |
+
"eval_loss": 0.6187613010406494,
|
| 4 |
+
"eval_runtime": 443.5964,
|
| 5 |
+
"eval_samples_per_second": 26.653,
|
| 6 |
+
"eval_steps_per_second": 0.417
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9971509971509973,
|
| 3 |
+
"total_flos": 1836725450047488.0,
|
| 4 |
+
"train_loss": 0.6210468141999963,
|
| 5 |
+
"train_runtime": 47044.2331,
|
| 6 |
+
"train_samples_per_second": 9.549,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,667 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9971509971509973,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 876,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022792022792022793,
|
| 13 |
+
"grad_norm": 3.7423104091436783,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7531,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.045584045584045586,
|
| 20 |
+
"grad_norm": 0.804241817019037,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.699,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06837606837606838,
|
| 27 |
+
"grad_norm": 0.9152853396823092,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.679,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09116809116809117,
|
| 34 |
+
"grad_norm": 0.8622513053123825,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6792,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11396011396011396,
|
| 41 |
+
"grad_norm": 0.8036004831872618,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6753,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13675213675213677,
|
| 48 |
+
"grad_norm": 0.6816477255973206,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6551,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15954415954415954,
|
| 55 |
+
"grad_norm": 0.44513213813326225,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.652,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18233618233618235,
|
| 62 |
+
"grad_norm": 0.3742970630530666,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.655,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.20512820512820512,
|
| 69 |
+
"grad_norm": 0.3165130129136532,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6398,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.22792022792022792,
|
| 76 |
+
"grad_norm": 0.3042067201330251,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6411,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25071225071225073,
|
| 83 |
+
"grad_norm": 0.35376934688819983,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6324,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27350427350427353,
|
| 90 |
+
"grad_norm": 0.30824084149805553,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6407,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2962962962962963,
|
| 97 |
+
"grad_norm": 0.29372321657922484,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6416,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3190883190883191,
|
| 104 |
+
"grad_norm": 0.30117031377143266,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6438,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3418803418803419,
|
| 111 |
+
"grad_norm": 0.3067841663492602,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6363,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3646723646723647,
|
| 118 |
+
"grad_norm": 0.3116337699832478,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6414,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.38746438746438744,
|
| 125 |
+
"grad_norm": 0.3594095078967235,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6333,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.41025641025641024,
|
| 132 |
+
"grad_norm": 0.30116165319677957,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6388,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.43304843304843305,
|
| 139 |
+
"grad_norm": 0.3022545956449521,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6314,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.45584045584045585,
|
| 146 |
+
"grad_norm": 0.3069466305582857,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6394,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.47863247863247865,
|
| 153 |
+
"grad_norm": 0.30814435636491544,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6357,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5014245014245015,
|
| 160 |
+
"grad_norm": 0.3071303249181051,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6395,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5242165242165242,
|
| 167 |
+
"grad_norm": 0.32490357531744296,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.635,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5470085470085471,
|
| 174 |
+
"grad_norm": 0.29591883031381105,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6309,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5698005698005698,
|
| 181 |
+
"grad_norm": 0.33357471359245844,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6359,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5925925925925926,
|
| 188 |
+
"grad_norm": 0.2981284989408182,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.634,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6153846153846154,
|
| 195 |
+
"grad_norm": 0.3102186918626153,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6312,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6381766381766382,
|
| 202 |
+
"grad_norm": 0.32329286600519713,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.642,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6609686609686609,
|
| 209 |
+
"grad_norm": 0.3242832742998967,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6307,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6837606837606838,
|
| 216 |
+
"grad_norm": 0.29295198198920075,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6287,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7065527065527065,
|
| 223 |
+
"grad_norm": 0.29895032078931544,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6286,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7293447293447294,
|
| 230 |
+
"grad_norm": 0.3447337206328429,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6292,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7521367521367521,
|
| 237 |
+
"grad_norm": 0.30639369318166265,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6258,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7749287749287749,
|
| 244 |
+
"grad_norm": 0.32323869936115435,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6316,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7977207977207977,
|
| 251 |
+
"grad_norm": 0.33615968390765805,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.6387,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8205128205128205,
|
| 258 |
+
"grad_norm": 0.3134642477669063,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.6305,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8433048433048433,
|
| 265 |
+
"grad_norm": 0.32819600455604525,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.6242,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8660968660968661,
|
| 272 |
+
"grad_norm": 0.30983155185254496,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.6365,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8888888888888888,
|
| 279 |
+
"grad_norm": 0.3264724671732252,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.6351,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9116809116809117,
|
| 286 |
+
"grad_norm": 0.2944418898860399,
|
| 287 |
+
"learning_rate": 5e-06,
|
| 288 |
+
"loss": 0.6383,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9344729344729344,
|
| 293 |
+
"grad_norm": 0.2885387150113508,
|
| 294 |
+
"learning_rate": 5e-06,
|
| 295 |
+
"loss": 0.6345,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9572649572649573,
|
| 300 |
+
"grad_norm": 0.29703808786645514,
|
| 301 |
+
"learning_rate": 5e-06,
|
| 302 |
+
"loss": 0.6214,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.98005698005698,
|
| 307 |
+
"grad_norm": 0.3420563577044849,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.6345,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9982905982905983,
|
| 314 |
+
"eval_loss": 0.6251205205917358,
|
| 315 |
+
"eval_runtime": 442.0682,
|
| 316 |
+
"eval_samples_per_second": 26.745,
|
| 317 |
+
"eval_steps_per_second": 0.418,
|
| 318 |
+
"step": 438
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0034188034188034,
|
| 322 |
+
"grad_norm": 0.34625889399732096,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6472,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0262108262108263,
|
| 329 |
+
"grad_norm": 0.3281982864617852,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6017,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.049002849002849,
|
| 336 |
+
"grad_norm": 0.3141455005951138,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.5954,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.0717948717948718,
|
| 343 |
+
"grad_norm": 0.28996166460793643,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5962,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.0945868945868946,
|
| 350 |
+
"grad_norm": 0.3076841135262722,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6039,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1173789173789175,
|
| 357 |
+
"grad_norm": 0.3297318480619313,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6089,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.1401709401709401,
|
| 364 |
+
"grad_norm": 0.29043048157109264,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5988,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.162962962962963,
|
| 371 |
+
"grad_norm": 0.31369187178492997,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5966,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.1857549857549858,
|
| 378 |
+
"grad_norm": 0.295573169618973,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6023,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2085470085470085,
|
| 385 |
+
"grad_norm": 0.32173567699812744,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.5953,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2313390313390313,
|
| 392 |
+
"grad_norm": 0.28814724323263435,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6055,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.2541310541310542,
|
| 399 |
+
"grad_norm": 0.33914723903856536,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6022,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.2769230769230768,
|
| 406 |
+
"grad_norm": 0.2903868392469319,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6037,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.2997150997150997,
|
| 413 |
+
"grad_norm": 0.30247551693702623,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5977,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.3225071225071225,
|
| 420 |
+
"grad_norm": 0.269850218574931,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.5962,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.3452991452991454,
|
| 427 |
+
"grad_norm": 0.297302467684091,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5958,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.368091168091168,
|
| 434 |
+
"grad_norm": 0.3510894377240081,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6015,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.390883190883191,
|
| 441 |
+
"grad_norm": 0.3251341988125297,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6015,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4136752136752135,
|
| 448 |
+
"grad_norm": 0.2909407195521434,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6041,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.4364672364672364,
|
| 455 |
+
"grad_norm": 0.31809945732936756,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6021,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.4592592592592593,
|
| 462 |
+
"grad_norm": 0.308053494784738,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.597,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.4820512820512821,
|
| 469 |
+
"grad_norm": 0.29613688364727164,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5949,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.504843304843305,
|
| 476 |
+
"grad_norm": 0.2899379408613246,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.5946,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.5276353276353276,
|
| 483 |
+
"grad_norm": 0.3137945273300998,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.6022,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.5504273504273505,
|
| 490 |
+
"grad_norm": 0.2724494831447769,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.5908,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.573219373219373,
|
| 497 |
+
"grad_norm": 0.32140838815196376,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.5947,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.596011396011396,
|
| 504 |
+
"grad_norm": 0.2848716261938471,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.6102,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.6188034188034188,
|
| 511 |
+
"grad_norm": 0.3068892037035822,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.5973,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.6415954415954417,
|
| 518 |
+
"grad_norm": 0.2913053429545111,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.6019,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.6643874643874645,
|
| 525 |
+
"grad_norm": 0.32543222896562873,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.595,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.6871794871794872,
|
| 532 |
+
"grad_norm": 0.326218112009388,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.5961,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.7099715099715098,
|
| 539 |
+
"grad_norm": 0.3003624805192447,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.5935,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.7327635327635327,
|
| 546 |
+
"grad_norm": 0.31631458744002094,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.5974,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.7555555555555555,
|
| 553 |
+
"grad_norm": 0.2957884880110632,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.5938,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.7783475783475784,
|
| 560 |
+
"grad_norm": 0.30827577948493284,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.6009,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.8011396011396013,
|
| 567 |
+
"grad_norm": 0.29302997826431615,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.5985,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.823931623931624,
|
| 574 |
+
"grad_norm": 0.31044034277936555,
|
| 575 |
+
"learning_rate": 5e-06,
|
| 576 |
+
"loss": 0.5853,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.8467236467236468,
|
| 581 |
+
"grad_norm": 0.3167005866324159,
|
| 582 |
+
"learning_rate": 5e-06,
|
| 583 |
+
"loss": 0.5932,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.8695156695156694,
|
| 588 |
+
"grad_norm": 0.30381283586000696,
|
| 589 |
+
"learning_rate": 5e-06,
|
| 590 |
+
"loss": 0.5909,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.8923076923076922,
|
| 595 |
+
"grad_norm": 0.3231388546230539,
|
| 596 |
+
"learning_rate": 5e-06,
|
| 597 |
+
"loss": 0.5947,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.915099715099715,
|
| 602 |
+
"grad_norm": 0.31619140661356115,
|
| 603 |
+
"learning_rate": 5e-06,
|
| 604 |
+
"loss": 0.5992,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.937891737891738,
|
| 609 |
+
"grad_norm": 0.3008849085639024,
|
| 610 |
+
"learning_rate": 5e-06,
|
| 611 |
+
"loss": 0.5973,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.9606837606837608,
|
| 616 |
+
"grad_norm": 0.3110240663396626,
|
| 617 |
+
"learning_rate": 5e-06,
|
| 618 |
+
"loss": 0.5986,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.9834757834757835,
|
| 623 |
+
"grad_norm": 0.3538843685145682,
|
| 624 |
+
"learning_rate": 5e-06,
|
| 625 |
+
"loss": 0.5961,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.9971509971509973,
|
| 630 |
+
"eval_loss": 0.6187613010406494,
|
| 631 |
+
"eval_runtime": 442.0084,
|
| 632 |
+
"eval_samples_per_second": 26.748,
|
| 633 |
+
"eval_steps_per_second": 0.419,
|
| 634 |
+
"step": 876
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.9971509971509973,
|
| 638 |
+
"step": 876,
|
| 639 |
+
"total_flos": 1836725450047488.0,
|
| 640 |
+
"train_loss": 0.6210468141999963,
|
| 641 |
+
"train_runtime": 47044.2331,
|
| 642 |
+
"train_samples_per_second": 9.549,
|
| 643 |
+
"train_steps_per_second": 0.019
|
| 644 |
+
}
|
| 645 |
+
],
|
| 646 |
+
"logging_steps": 10,
|
| 647 |
+
"max_steps": 876,
|
| 648 |
+
"num_input_tokens_seen": 0,
|
| 649 |
+
"num_train_epochs": 2,
|
| 650 |
+
"save_steps": 500,
|
| 651 |
+
"stateful_callbacks": {
|
| 652 |
+
"TrainerControl": {
|
| 653 |
+
"args": {
|
| 654 |
+
"should_epoch_stop": false,
|
| 655 |
+
"should_evaluate": false,
|
| 656 |
+
"should_log": false,
|
| 657 |
+
"should_save": true,
|
| 658 |
+
"should_training_stop": true
|
| 659 |
+
},
|
| 660 |
+
"attributes": {}
|
| 661 |
+
}
|
| 662 |
+
},
|
| 663 |
+
"total_flos": 1836725450047488.0,
|
| 664 |
+
"train_batch_size": 8,
|
| 665 |
+
"trial_name": null,
|
| 666 |
+
"trial_params": null
|
| 667 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|