End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +469 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: ML815_Baseline
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# ML815_Baseline
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: ML815_Baseline
|
|
|
|
| 16 |
|
| 17 |
# ML815_Baseline
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the AnghaBench-armv8-O2-native-clang-2percent dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995956328346138,
|
| 3 |
+
"total_flos": 2.6734690727624704e+17,
|
| 4 |
+
"train_loss": 0.053742153359076734,
|
| 5 |
+
"train_runtime": 8084.4069,
|
| 6 |
+
"train_samples_per_second": 2.447,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9995956328346138,
|
| 3 |
+
"total_flos": 2.6734690727624704e+17,
|
| 4 |
+
"train_loss": 0.053742153359076734,
|
| 5 |
+
"train_runtime": 8084.4069,
|
| 6 |
+
"train_samples_per_second": 2.447,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,469 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995956328346138,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 618,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016174686615446826,
|
| 13 |
+
"grad_norm": 6.084117889404297,
|
| 14 |
+
"learning_rate": 3.225806451612903e-06,
|
| 15 |
+
"loss": 0.7994,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03234937323089365,
|
| 20 |
+
"grad_norm": 2.019094467163086,
|
| 21 |
+
"learning_rate": 6.451612903225806e-06,
|
| 22 |
+
"loss": 0.339,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04852405984634048,
|
| 27 |
+
"grad_norm": 1.6682400703430176,
|
| 28 |
+
"learning_rate": 9.67741935483871e-06,
|
| 29 |
+
"loss": 0.1355,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0646987464617873,
|
| 34 |
+
"grad_norm": 0.7796459794044495,
|
| 35 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 36 |
+
"loss": 0.0864,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08087343307723413,
|
| 41 |
+
"grad_norm": 0.7346309423446655,
|
| 42 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 43 |
+
"loss": 0.0771,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09704811969268096,
|
| 48 |
+
"grad_norm": 0.5999702215194702,
|
| 49 |
+
"learning_rate": 1.935483870967742e-05,
|
| 50 |
+
"loss": 0.0616,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11322280630812778,
|
| 55 |
+
"grad_norm": 0.6098871231079102,
|
| 56 |
+
"learning_rate": 1.9989785286500294e-05,
|
| 57 |
+
"loss": 0.068,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1293974929235746,
|
| 62 |
+
"grad_norm": 0.6197764277458191,
|
| 63 |
+
"learning_rate": 1.994832377542755e-05,
|
| 64 |
+
"loss": 0.0532,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14557217953902143,
|
| 69 |
+
"grad_norm": 0.5199822783470154,
|
| 70 |
+
"learning_rate": 1.9875109281794828e-05,
|
| 71 |
+
"loss": 0.0531,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16174686615446826,
|
| 76 |
+
"grad_norm": 0.44315075874328613,
|
| 77 |
+
"learning_rate": 1.9770375491054264e-05,
|
| 78 |
+
"loss": 0.0543,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1779215527699151,
|
| 83 |
+
"grad_norm": 0.4719191789627075,
|
| 84 |
+
"learning_rate": 1.9634456691705705e-05,
|
| 85 |
+
"loss": 0.0506,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1940962393853619,
|
| 90 |
+
"grad_norm": 0.454826295375824,
|
| 91 |
+
"learning_rate": 1.9467786708317257e-05,
|
| 92 |
+
"loss": 0.0436,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21027092600080874,
|
| 97 |
+
"grad_norm": 0.5078369379043579,
|
| 98 |
+
"learning_rate": 1.9270897516847406e-05,
|
| 99 |
+
"loss": 0.0421,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.22644561261625556,
|
| 104 |
+
"grad_norm": 0.3744693994522095,
|
| 105 |
+
"learning_rate": 1.9044417546688295e-05,
|
| 106 |
+
"loss": 0.047,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2426202992317024,
|
| 111 |
+
"grad_norm": 0.4639657139778137,
|
| 112 |
+
"learning_rate": 1.878906967484966e-05,
|
| 113 |
+
"loss": 0.0421,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2587949858471492,
|
| 118 |
+
"grad_norm": 0.4336051642894745,
|
| 119 |
+
"learning_rate": 1.8505668918685603e-05,
|
| 120 |
+
"loss": 0.0433,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.274969672462596,
|
| 125 |
+
"grad_norm": 0.5246915817260742,
|
| 126 |
+
"learning_rate": 1.8195119834528535e-05,
|
| 127 |
+
"loss": 0.0426,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29114435907804287,
|
| 132 |
+
"grad_norm": 0.3944627642631531,
|
| 133 |
+
"learning_rate": 1.7858413630533305e-05,
|
| 134 |
+
"loss": 0.0397,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.30731904569348967,
|
| 139 |
+
"grad_norm": 0.4689359664916992,
|
| 140 |
+
"learning_rate": 1.7496625002946702e-05,
|
| 141 |
+
"loss": 0.0418,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3234937323089365,
|
| 146 |
+
"grad_norm": 0.42653799057006836,
|
| 147 |
+
"learning_rate": 1.7110908705900322e-05,
|
| 148 |
+
"loss": 0.0322,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3396684189243833,
|
| 153 |
+
"grad_norm": 0.4104606807231903,
|
| 154 |
+
"learning_rate": 1.670249586567531e-05,
|
| 155 |
+
"loss": 0.0344,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3558431055398302,
|
| 160 |
+
"grad_norm": 0.3860621452331543,
|
| 161 |
+
"learning_rate": 1.627269005120304e-05,
|
| 162 |
+
"loss": 0.0329,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.37201779215527697,
|
| 167 |
+
"grad_norm": 0.4381610155105591,
|
| 168 |
+
"learning_rate": 1.5822863113343934e-05,
|
| 169 |
+
"loss": 0.034,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3881924787707238,
|
| 174 |
+
"grad_norm": 0.32563912868499756,
|
| 175 |
+
"learning_rate": 1.5354450806224553e-05,
|
| 176 |
+
"loss": 0.04,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4043671653861706,
|
| 181 |
+
"grad_norm": 0.21232913434505463,
|
| 182 |
+
"learning_rate": 1.48689482046087e-05,
|
| 183 |
+
"loss": 0.0335,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4205418520016175,
|
| 188 |
+
"grad_norm": 0.3260803818702698,
|
| 189 |
+
"learning_rate": 1.4367904931929422e-05,
|
| 190 |
+
"loss": 0.0316,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4367165386170643,
|
| 195 |
+
"grad_norm": 0.33327850699424744,
|
| 196 |
+
"learning_rate": 1.3852920214212966e-05,
|
| 197 |
+
"loss": 0.0329,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45289122523251113,
|
| 202 |
+
"grad_norm": 0.35602909326553345,
|
| 203 |
+
"learning_rate": 1.3325637775681561e-05,
|
| 204 |
+
"loss": 0.0337,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.46906591184795793,
|
| 209 |
+
"grad_norm": 0.40170156955718994,
|
| 210 |
+
"learning_rate": 1.2787740592327232e-05,
|
| 211 |
+
"loss": 0.0342,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4852405984634048,
|
| 216 |
+
"grad_norm": 0.32156628370285034,
|
| 217 |
+
"learning_rate": 1.2240945520202079e-05,
|
| 218 |
+
"loss": 0.0309,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5014152850788516,
|
| 223 |
+
"grad_norm": 0.24567893147468567,
|
| 224 |
+
"learning_rate": 1.1686997815570473e-05,
|
| 225 |
+
"loss": 0.0273,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5175899716942984,
|
| 230 |
+
"grad_norm": 0.31566041707992554,
|
| 231 |
+
"learning_rate": 1.112766556441367e-05,
|
| 232 |
+
"loss": 0.0342,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5337646583097453,
|
| 237 |
+
"grad_norm": 0.26993805170059204,
|
| 238 |
+
"learning_rate": 1.05647340390667e-05,
|
| 239 |
+
"loss": 0.0307,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.549939344925192,
|
| 244 |
+
"grad_norm": 0.25027933716773987,
|
| 245 |
+
"learning_rate": 1e-05,
|
| 246 |
+
"loss": 0.0283,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5661140315406389,
|
| 251 |
+
"grad_norm": 0.29696565866470337,
|
| 252 |
+
"learning_rate": 9.435265960933304e-06,
|
| 253 |
+
"loss": 0.0327,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5822887181560857,
|
| 258 |
+
"grad_norm": 0.21952570974826813,
|
| 259 |
+
"learning_rate": 8.872334435586333e-06,
|
| 260 |
+
"loss": 0.024,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5984634047715326,
|
| 265 |
+
"grad_norm": 0.36718422174453735,
|
| 266 |
+
"learning_rate": 8.313002184429529e-06,
|
| 267 |
+
"loss": 0.027,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6146380913869793,
|
| 272 |
+
"grad_norm": 0.34000155329704285,
|
| 273 |
+
"learning_rate": 7.759054479797924e-06,
|
| 274 |
+
"loss": 0.0286,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6308127780024262,
|
| 279 |
+
"grad_norm": 0.35067811608314514,
|
| 280 |
+
"learning_rate": 7.2122594076727705e-06,
|
| 281 |
+
"loss": 0.0251,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.646987464617873,
|
| 286 |
+
"grad_norm": 0.22097982466220856,
|
| 287 |
+
"learning_rate": 6.6743622243184405e-06,
|
| 288 |
+
"loss": 0.0237,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6631621512333199,
|
| 293 |
+
"grad_norm": 0.23619405925273895,
|
| 294 |
+
"learning_rate": 6.147079785787038e-06,
|
| 295 |
+
"loss": 0.0277,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6793368378487666,
|
| 300 |
+
"grad_norm": 0.24173900485038757,
|
| 301 |
+
"learning_rate": 5.6320950680705826e-06,
|
| 302 |
+
"loss": 0.0295,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6955115244642135,
|
| 307 |
+
"grad_norm": 0.31293392181396484,
|
| 308 |
+
"learning_rate": 5.131051795391302e-06,
|
| 309 |
+
"loss": 0.0264,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7116862110796603,
|
| 314 |
+
"grad_norm": 0.2306731641292572,
|
| 315 |
+
"learning_rate": 4.645549193775452e-06,
|
| 316 |
+
"loss": 0.0271,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7278608976951072,
|
| 321 |
+
"grad_norm": 0.2935221195220947,
|
| 322 |
+
"learning_rate": 4.177136886656067e-06,
|
| 323 |
+
"loss": 0.0222,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7440355843105539,
|
| 328 |
+
"grad_norm": 0.22359654307365417,
|
| 329 |
+
"learning_rate": 3.727309948796963e-06,
|
| 330 |
+
"loss": 0.0255,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7602102709260008,
|
| 335 |
+
"grad_norm": 0.17210273444652557,
|
| 336 |
+
"learning_rate": 3.2975041343246937e-06,
|
| 337 |
+
"loss": 0.0273,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7763849575414477,
|
| 342 |
+
"grad_norm": 0.2949126660823822,
|
| 343 |
+
"learning_rate": 2.8890912940996784e-06,
|
| 344 |
+
"loss": 0.0258,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7925596441568945,
|
| 349 |
+
"grad_norm": 0.1924426257610321,
|
| 350 |
+
"learning_rate": 2.5033749970533015e-06,
|
| 351 |
+
"loss": 0.0287,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8087343307723412,
|
| 356 |
+
"grad_norm": 0.2463998794555664,
|
| 357 |
+
"learning_rate": 2.1415863694666973e-06,
|
| 358 |
+
"loss": 0.0255,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8249090173877881,
|
| 363 |
+
"grad_norm": 0.33545950055122375,
|
| 364 |
+
"learning_rate": 1.8048801654714687e-06,
|
| 365 |
+
"loss": 0.0259,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.841083704003235,
|
| 370 |
+
"grad_norm": 0.2482132911682129,
|
| 371 |
+
"learning_rate": 1.4943310813144006e-06,
|
| 372 |
+
"loss": 0.0228,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8572583906186818,
|
| 377 |
+
"grad_norm": 0.3056134581565857,
|
| 378 |
+
"learning_rate": 1.2109303251503434e-06,
|
| 379 |
+
"loss": 0.0272,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8734330772341286,
|
| 384 |
+
"grad_norm": 0.2144118696451187,
|
| 385 |
+
"learning_rate": 9.555824533117064e-07,
|
| 386 |
+
"loss": 0.0227,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8896077638495754,
|
| 391 |
+
"grad_norm": 0.38680920004844666,
|
| 392 |
+
"learning_rate": 7.291024831525961e-07,
|
| 393 |
+
"loss": 0.022,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9057824504650223,
|
| 398 |
+
"grad_norm": 0.3151616156101227,
|
| 399 |
+
"learning_rate": 5.322132916827483e-07,
|
| 400 |
+
"loss": 0.0252,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9219571370804691,
|
| 405 |
+
"grad_norm": 0.20920976996421814,
|
| 406 |
+
"learning_rate": 3.6554330829429716e-07,
|
| 407 |
+
"loss": 0.0223,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9381318236959159,
|
| 412 |
+
"grad_norm": 0.18968930840492249,
|
| 413 |
+
"learning_rate": 2.2962450894573606e-07,
|
| 414 |
+
"loss": 0.0219,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9543065103113627,
|
| 419 |
+
"grad_norm": 0.27189257740974426,
|
| 420 |
+
"learning_rate": 1.2489071820517394e-07,
|
| 421 |
+
"loss": 0.0264,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.9704811969268096,
|
| 426 |
+
"grad_norm": 0.3213247060775757,
|
| 427 |
+
"learning_rate": 5.1676224572452246e-08,
|
| 428 |
+
"loss": 0.0262,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9866558835422564,
|
| 433 |
+
"grad_norm": 0.25112277269363403,
|
| 434 |
+
"learning_rate": 1.0214713499706596e-08,
|
| 435 |
+
"loss": 0.0224,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9995956328346138,
|
| 440 |
+
"step": 618,
|
| 441 |
+
"total_flos": 2.6734690727624704e+17,
|
| 442 |
+
"train_loss": 0.053742153359076734,
|
| 443 |
+
"train_runtime": 8084.4069,
|
| 444 |
+
"train_samples_per_second": 2.447,
|
| 445 |
+
"train_steps_per_second": 0.076
|
| 446 |
+
}
|
| 447 |
+
],
|
| 448 |
+
"logging_steps": 10,
|
| 449 |
+
"max_steps": 618,
|
| 450 |
+
"num_input_tokens_seen": 0,
|
| 451 |
+
"num_train_epochs": 1,
|
| 452 |
+
"save_steps": 100,
|
| 453 |
+
"stateful_callbacks": {
|
| 454 |
+
"TrainerControl": {
|
| 455 |
+
"args": {
|
| 456 |
+
"should_epoch_stop": false,
|
| 457 |
+
"should_evaluate": false,
|
| 458 |
+
"should_log": false,
|
| 459 |
+
"should_save": true,
|
| 460 |
+
"should_training_stop": true
|
| 461 |
+
},
|
| 462 |
+
"attributes": {}
|
| 463 |
+
}
|
| 464 |
+
},
|
| 465 |
+
"total_flos": 2.6734690727624704e+17,
|
| 466 |
+
"train_batch_size": 1,
|
| 467 |
+
"trial_name": null,
|
| 468 |
+
"trial_params": null
|
| 469 |
+
}
|
training_loss.png
ADDED
|