End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +603 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: Qwen3-4B-Instruct_0910_LODO_gitlab_full
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Qwen3-4B-Instruct_0910_LODO_gitlab_full
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: Qwen3-4B-Instruct_0910_LODO_gitlab_full
|
|
|
|
| 16 |
|
| 17 |
# Qwen3-4B-Instruct_0910_LODO_gitlab_full
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the Policy_Traj_LODO_gitlab dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 33113178439680.0,
|
| 4 |
+
"train_loss": 0.042386234274015444,
|
| 5 |
+
"train_runtime": 4174.8779,
|
| 6 |
+
"train_samples_per_second": 24.521,
|
| 7 |
+
"train_steps_per_second": 0.192
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 33113178439680.0,
|
| 4 |
+
"train_loss": 0.042386234274015444,
|
| 5 |
+
"train_runtime": 4174.8779,
|
| 6 |
+
"train_samples_per_second": 24.521,
|
| 7 |
+
"train_steps_per_second": 0.192
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 801,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.03750586029067042,
|
| 14 |
+
"grad_norm": 34.85824610814536,
|
| 15 |
+
"learning_rate": 1.8e-05,
|
| 16 |
+
"loss": 0.3557,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.07501172058134084,
|
| 21 |
+
"grad_norm": 7.1481602122450285,
|
| 22 |
+
"learning_rate": 3.8e-05,
|
| 23 |
+
"loss": 0.1487,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.11251758087201125,
|
| 28 |
+
"grad_norm": 8.614036123620082,
|
| 29 |
+
"learning_rate": 4.999672209164081e-05,
|
| 30 |
+
"loss": 0.1396,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.15002344116268168,
|
| 35 |
+
"grad_norm": 10.10705100519714,
|
| 36 |
+
"learning_rate": 4.995985549356568e-05,
|
| 37 |
+
"loss": 0.0895,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1875293014533521,
|
| 42 |
+
"grad_norm": 5.6723632225651555,
|
| 43 |
+
"learning_rate": 4.988208552916535e-05,
|
| 44 |
+
"loss": 0.0733,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2250351617440225,
|
| 49 |
+
"grad_norm": 3.5917593429678067,
|
| 50 |
+
"learning_rate": 4.976353964522509e-05,
|
| 51 |
+
"loss": 0.2835,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.26254102203469293,
|
| 56 |
+
"grad_norm": 2.7853884780818023,
|
| 57 |
+
"learning_rate": 4.960441211072686e-05,
|
| 58 |
+
"loss": 0.0559,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.30004688232536336,
|
| 63 |
+
"grad_norm": 1.0618750438052633,
|
| 64 |
+
"learning_rate": 4.940496369848795e-05,
|
| 65 |
+
"loss": 0.0562,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.33755274261603374,
|
| 70 |
+
"grad_norm": 0.21567312878465145,
|
| 71 |
+
"learning_rate": 4.916552125781528e-05,
|
| 72 |
+
"loss": 0.0545,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3750586029067042,
|
| 77 |
+
"grad_norm": 6.591249771359263,
|
| 78 |
+
"learning_rate": 4.8886477178875826e-05,
|
| 79 |
+
"loss": 0.0665,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4125644631973746,
|
| 84 |
+
"grad_norm": 0.2514334496388468,
|
| 85 |
+
"learning_rate": 4.856828874966086e-05,
|
| 86 |
+
"loss": 0.0577,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.450070323488045,
|
| 91 |
+
"grad_norm": 2.19013548059961,
|
| 92 |
+
"learning_rate": 4.821147740659794e-05,
|
| 93 |
+
"loss": 0.0424,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4875761837787154,
|
| 98 |
+
"grad_norm": 1.8200457984558476,
|
| 99 |
+
"learning_rate": 4.781662788003851e-05,
|
| 100 |
+
"loss": 0.0435,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.5250820440693859,
|
| 105 |
+
"grad_norm": 1.788433839164408,
|
| 106 |
+
"learning_rate": 4.738438723602154e-05,
|
| 107 |
+
"loss": 0.0459,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5625879043600562,
|
| 112 |
+
"grad_norm": 3.4278131423512943,
|
| 113 |
+
"learning_rate": 4.69154638158837e-05,
|
| 114 |
+
"loss": 0.0416,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6000937646507267,
|
| 119 |
+
"grad_norm": 0.26651980565241046,
|
| 120 |
+
"learning_rate": 4.641062607545347e-05,
|
| 121 |
+
"loss": 0.0422,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.6375996249413971,
|
| 126 |
+
"grad_norm": 1.6317479332317566,
|
| 127 |
+
"learning_rate": 4.587070132573178e-05,
|
| 128 |
+
"loss": 0.0388,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6751054852320675,
|
| 133 |
+
"grad_norm": 1.6520649014609303,
|
| 134 |
+
"learning_rate": 4.529657437712276e-05,
|
| 135 |
+
"loss": 0.0334,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.712611345522738,
|
| 140 |
+
"grad_norm": 0.15277860741515586,
|
| 141 |
+
"learning_rate": 4.4689186089436366e-05,
|
| 142 |
+
"loss": 0.0412,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.7501172058134083,
|
| 147 |
+
"grad_norm": 0.9030791837609309,
|
| 148 |
+
"learning_rate": 4.404953183003916e-05,
|
| 149 |
+
"loss": 0.036,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7876230661040787,
|
| 154 |
+
"grad_norm": 1.9866732218980805,
|
| 155 |
+
"learning_rate": 4.337865984268001e-05,
|
| 156 |
+
"loss": 0.0393,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.8251289263947492,
|
| 161 |
+
"grad_norm": 0.23596674543489504,
|
| 162 |
+
"learning_rate": 4.267766952966369e-05,
|
| 163 |
+
"loss": 0.0385,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8626347866854196,
|
| 168 |
+
"grad_norm": 2.7613828112655905,
|
| 169 |
+
"learning_rate": 4.194770965018758e-05,
|
| 170 |
+
"loss": 0.0411,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.90014064697609,
|
| 175 |
+
"grad_norm": 0.9440762280964653,
|
| 176 |
+
"learning_rate": 4.118997643779401e-05,
|
| 177 |
+
"loss": 0.0346,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.9376465072667605,
|
| 182 |
+
"grad_norm": 0.41009567832530625,
|
| 183 |
+
"learning_rate": 4.0405711640023186e-05,
|
| 184 |
+
"loss": 0.0344,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9751523675574308,
|
| 189 |
+
"grad_norm": 0.32482405462507263,
|
| 190 |
+
"learning_rate": 3.9596200483479385e-05,
|
| 191 |
+
"loss": 0.0324,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.0112517580872011,
|
| 196 |
+
"grad_norm": 0.806991725526476,
|
| 197 |
+
"learning_rate": 3.876276956764509e-05,
|
| 198 |
+
"loss": 0.0346,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.0487576183778715,
|
| 203 |
+
"grad_norm": 1.1338976875621802,
|
| 204 |
+
"learning_rate": 3.7906784690894645e-05,
|
| 205 |
+
"loss": 0.0424,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.086263478668542,
|
| 210 |
+
"grad_norm": 1.500478633231241,
|
| 211 |
+
"learning_rate": 3.702964861227013e-05,
|
| 212 |
+
"loss": 0.0346,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.1237693389592125,
|
| 217 |
+
"grad_norm": 1.4409676013917596,
|
| 218 |
+
"learning_rate": 3.613279875268731e-05,
|
| 219 |
+
"loss": 0.0354,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.1612751992498829,
|
| 224 |
+
"grad_norm": 0.2422476126318276,
|
| 225 |
+
"learning_rate": 3.521770483933891e-05,
|
| 226 |
+
"loss": 0.034,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.1987810595405533,
|
| 231 |
+
"grad_norm": 1.5840918548478307,
|
| 232 |
+
"learning_rate": 3.4285866497155414e-05,
|
| 233 |
+
"loss": 0.0459,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.2362869198312236,
|
| 238 |
+
"grad_norm": 0.37403459055017013,
|
| 239 |
+
"learning_rate": 3.333881079127052e-05,
|
| 240 |
+
"loss": 0.0292,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.273792780121894,
|
| 245 |
+
"grad_norm": 0.7618214390592176,
|
| 246 |
+
"learning_rate": 3.2378089724518465e-05,
|
| 247 |
+
"loss": 0.0279,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.3112986404125644,
|
| 252 |
+
"grad_norm": 0.6779062975577348,
|
| 253 |
+
"learning_rate": 3.1405277694064305e-05,
|
| 254 |
+
"loss": 0.0317,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.3488045007032348,
|
| 259 |
+
"grad_norm": 0.6053365729294653,
|
| 260 |
+
"learning_rate": 3.0421968911335196e-05,
|
| 261 |
+
"loss": 0.0332,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.3863103609939054,
|
| 266 |
+
"grad_norm": 0.5023346538140172,
|
| 267 |
+
"learning_rate": 2.9429774789480575e-05,
|
| 268 |
+
"loss": 0.0258,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.4238162212845757,
|
| 273 |
+
"grad_norm": 0.1512518290372575,
|
| 274 |
+
"learning_rate": 2.843032130264289e-05,
|
| 275 |
+
"loss": 0.0254,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.4613220815752461,
|
| 280 |
+
"grad_norm": 0.4256415803778755,
|
| 281 |
+
"learning_rate": 2.7425246321366203e-05,
|
| 282 |
+
"loss": 0.0289,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.4988279418659165,
|
| 287 |
+
"grad_norm": 2.0526292381935587,
|
| 288 |
+
"learning_rate": 2.6416196928509408e-05,
|
| 289 |
+
"loss": 0.0293,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.5363338021565869,
|
| 294 |
+
"grad_norm": 2.199901935419105,
|
| 295 |
+
"learning_rate": 2.540482672006254e-05,
|
| 296 |
+
"loss": 0.0324,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.5738396624472575,
|
| 301 |
+
"grad_norm": 0.6587554924832156,
|
| 302 |
+
"learning_rate": 2.4392793095289677e-05,
|
| 303 |
+
"loss": 0.0318,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.6113455227379276,
|
| 308 |
+
"grad_norm": 0.11953774619854174,
|
| 309 |
+
"learning_rate": 2.338175454063911e-05,
|
| 310 |
+
"loss": 0.027,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.6488513830285982,
|
| 315 |
+
"grad_norm": 1.8366328720607281,
|
| 316 |
+
"learning_rate": 2.2373367911871904e-05,
|
| 317 |
+
"loss": 0.0271,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.6863572433192686,
|
| 322 |
+
"grad_norm": 0.16134023570988165,
|
| 323 |
+
"learning_rate": 2.136928571886275e-05,
|
| 324 |
+
"loss": 0.0309,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.723863103609939,
|
| 329 |
+
"grad_norm": 0.5782347760396018,
|
| 330 |
+
"learning_rate": 2.03711534175227e-05,
|
| 331 |
+
"loss": 0.0276,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.7613689639006096,
|
| 336 |
+
"grad_norm": 0.7600638604790938,
|
| 337 |
+
"learning_rate": 1.9380606713281775e-05,
|
| 338 |
+
"loss": 0.0284,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.7988748241912798,
|
| 343 |
+
"grad_norm": 0.28905055512217726,
|
| 344 |
+
"learning_rate": 1.8399268880550174e-05,
|
| 345 |
+
"loss": 0.0289,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.8363806844819504,
|
| 350 |
+
"grad_norm": 0.47269674339106393,
|
| 351 |
+
"learning_rate": 1.7428748102551237e-05,
|
| 352 |
+
"loss": 0.0254,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.8738865447726207,
|
| 357 |
+
"grad_norm": 0.1126048083243114,
|
| 358 |
+
"learning_rate": 1.6470634835885097e-05,
|
| 359 |
+
"loss": 0.0329,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.9113924050632911,
|
| 364 |
+
"grad_norm": 0.4869034202302143,
|
| 365 |
+
"learning_rate": 1.552649920414233e-05,
|
| 366 |
+
"loss": 0.0294,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.9488982653539617,
|
| 371 |
+
"grad_norm": 0.1048044631528693,
|
| 372 |
+
"learning_rate": 1.4597888424838518e-05,
|
| 373 |
+
"loss": 0.03,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.9864041256446319,
|
| 378 |
+
"grad_norm": 0.257084202132171,
|
| 379 |
+
"learning_rate": 1.368632427388653e-05,
|
| 380 |
+
"loss": 0.0263,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.0225035161744023,
|
| 385 |
+
"grad_norm": 0.41612935348774654,
|
| 386 |
+
"learning_rate": 1.2793300591761742e-05,
|
| 387 |
+
"loss": 0.0255,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.060009376465073,
|
| 392 |
+
"grad_norm": 0.1472784892712205,
|
| 393 |
+
"learning_rate": 1.1920280835446748e-05,
|
| 394 |
+
"loss": 0.019,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.097515236755743,
|
| 399 |
+
"grad_norm": 0.7021607086288816,
|
| 400 |
+
"learning_rate": 1.1068695680167664e-05,
|
| 401 |
+
"loss": 0.0259,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.1350210970464136,
|
| 406 |
+
"grad_norm": 1.0121270104703033,
|
| 407 |
+
"learning_rate": 1.0239940674851941e-05,
|
| 408 |
+
"loss": 0.0228,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.172526957337084,
|
| 413 |
+
"grad_norm": 0.8364824257153406,
|
| 414 |
+
"learning_rate": 9.43537395515003e-06,
|
| 415 |
+
"loss": 0.0233,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.2100328176277544,
|
| 420 |
+
"grad_norm": 0.29831710959245356,
|
| 421 |
+
"learning_rate": 8.656314017768693e-06,
|
| 422 |
+
"loss": 0.0213,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.247538677918425,
|
| 427 |
+
"grad_norm": 0.21598369420228658,
|
| 428 |
+
"learning_rate": 7.904037559763162e-06,
|
| 429 |
+
"loss": 0.0228,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.285044538209095,
|
| 434 |
+
"grad_norm": 0.5662760774283471,
|
| 435 |
+
"learning_rate": 7.179777386329276e-06,
|
| 436 |
+
"loss": 0.0184,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.3225503984997657,
|
| 441 |
+
"grad_norm": 0.10841392927498035,
|
| 442 |
+
"learning_rate": 6.484720390524007e-06,
|
| 443 |
+
"loss": 0.0223,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.360056258790436,
|
| 448 |
+
"grad_norm": 0.2351999089031456,
|
| 449 |
+
"learning_rate": 5.820005608225346e-06,
|
| 450 |
+
"loss": 0.0221,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.3975621190811065,
|
| 455 |
+
"grad_norm": 0.27088765350399413,
|
| 456 |
+
"learning_rate": 5.186722351518822e-06,
|
| 457 |
+
"loss": 0.0276,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.4350679793717767,
|
| 462 |
+
"grad_norm": 0.08323548651396794,
|
| 463 |
+
"learning_rate": 4.585908423569724e-06,
|
| 464 |
+
"loss": 0.0209,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.4725738396624473,
|
| 469 |
+
"grad_norm": 0.21245905268041415,
|
| 470 |
+
"learning_rate": 4.0185484179064425e-06,
|
| 471 |
+
"loss": 0.0233,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.510079699953118,
|
| 476 |
+
"grad_norm": 0.5537577775149638,
|
| 477 |
+
"learning_rate": 3.4855721049018688e-06,
|
| 478 |
+
"loss": 0.0229,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.547585560243788,
|
| 483 |
+
"grad_norm": 0.7847967042002256,
|
| 484 |
+
"learning_rate": 2.98785290809723e-06,
|
| 485 |
+
"loss": 0.0253,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.5850914205344586,
|
| 490 |
+
"grad_norm": 0.507105447694394,
|
| 491 |
+
"learning_rate": 2.52620647286512e-06,
|
| 492 |
+
"loss": 0.0206,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.6225972808251288,
|
| 497 |
+
"grad_norm": 0.24719979538798334,
|
| 498 |
+
"learning_rate": 2.101389329757478e-06,
|
| 499 |
+
"loss": 0.0172,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.6601031411157994,
|
| 504 |
+
"grad_norm": 0.481232043094042,
|
| 505 |
+
"learning_rate": 1.7140976547289438e-06,
|
| 506 |
+
"loss": 0.0197,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.6976090014064695,
|
| 511 |
+
"grad_norm": 0.525987532669796,
|
| 512 |
+
"learning_rate": 1.3649661282672476e-06,
|
| 513 |
+
"loss": 0.0202,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.73511486169714,
|
| 518 |
+
"grad_norm": 0.12411824566724937,
|
| 519 |
+
"learning_rate": 1.0545668953003241e-06,
|
| 520 |
+
"loss": 0.0215,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.7726207219878107,
|
| 525 |
+
"grad_norm": 0.2216514712018457,
|
| 526 |
+
"learning_rate": 7.834086275845587e-07,
|
| 527 |
+
"loss": 0.0182,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.810126582278481,
|
| 532 |
+
"grad_norm": 0.220985617144204,
|
| 533 |
+
"learning_rate": 5.519356901107358e-07,
|
| 534 |
+
"loss": 0.0244,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.8476324425691515,
|
| 539 |
+
"grad_norm": 0.34207273950972444,
|
| 540 |
+
"learning_rate": 3.605274128937464e-07,
|
| 541 |
+
"loss": 0.0233,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.885138302859822,
|
| 546 |
+
"grad_norm": 0.11697799335786845,
|
| 547 |
+
"learning_rate": 2.094974693393731e-07,
|
| 548 |
+
"loss": 0.019,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.9226441631504922,
|
| 553 |
+
"grad_norm": 0.3157831029546487,
|
| 554 |
+
"learning_rate": 9.90933622069562e-08,
|
| 555 |
+
"loss": 0.0177,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.960150023441163,
|
| 560 |
+
"grad_norm": 0.16740144227166562,
|
| 561 |
+
"learning_rate": 2.9496018010233274e-08,
|
| 562 |
+
"loss": 0.022,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.997655883731833,
|
| 567 |
+
"grad_norm": 0.33884453903018824,
|
| 568 |
+
"learning_rate": 8.194905210923143e-10,
|
| 569 |
+
"loss": 0.0232,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 3.0,
|
| 574 |
+
"step": 801,
|
| 575 |
+
"total_flos": 33113178439680.0,
|
| 576 |
+
"train_loss": 0.042386234274015444,
|
| 577 |
+
"train_runtime": 4174.8779,
|
| 578 |
+
"train_samples_per_second": 24.521,
|
| 579 |
+
"train_steps_per_second": 0.192
|
| 580 |
+
}
|
| 581 |
+
],
|
| 582 |
+
"logging_steps": 10,
|
| 583 |
+
"max_steps": 801,
|
| 584 |
+
"num_input_tokens_seen": 0,
|
| 585 |
+
"num_train_epochs": 3,
|
| 586 |
+
"save_steps": 100,
|
| 587 |
+
"stateful_callbacks": {
|
| 588 |
+
"TrainerControl": {
|
| 589 |
+
"args": {
|
| 590 |
+
"should_epoch_stop": false,
|
| 591 |
+
"should_evaluate": false,
|
| 592 |
+
"should_log": false,
|
| 593 |
+
"should_save": true,
|
| 594 |
+
"should_training_stop": true
|
| 595 |
+
},
|
| 596 |
+
"attributes": {}
|
| 597 |
+
}
|
| 598 |
+
},
|
| 599 |
+
"total_flos": 33113178439680.0,
|
| 600 |
+
"train_batch_size": 4,
|
| 601 |
+
"trial_name": null,
|
| 602 |
+
"trial_params": null
|
| 603 |
+
}
|
training_loss.png
ADDED
|