End of training
Browse files- README.md +4 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +365 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama2
|
|
| 4 |
base_model: meta-llama/CodeLlama-7b-Instruct-hf
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: text-to-odrl-codellama.7b-v0
|
|
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# text-to-odrl-codellama.7b-v0
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/CodeLlama-7b-Instruct-hf
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: text-to-odrl-codellama.7b-v0
|
|
|
|
| 16 |
|
| 17 |
# text-to-odrl-codellama.7b-v0
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the text_to_odrl_train dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0923
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.09225524216890335,
|
| 4 |
+
"eval_runtime": 945.9721,
|
| 5 |
+
"eval_samples_per_second": 3.923,
|
| 6 |
+
"eval_steps_per_second": 1.962,
|
| 7 |
+
"total_flos": 2.4087255599087616e+17,
|
| 8 |
+
"train_loss": 0.11968068110531774,
|
| 9 |
+
"train_runtime": 7304.8453,
|
| 10 |
+
"train_samples_per_second": 1.016,
|
| 11 |
+
"train_steps_per_second": 0.064
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.09225524216890335,
|
| 4 |
+
"eval_runtime": 945.9721,
|
| 5 |
+
"eval_samples_per_second": 3.923,
|
| 6 |
+
"eval_steps_per_second": 1.962
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 2.4087255599087616e+17,
|
| 4 |
+
"train_loss": 0.11968068110531774,
|
| 5 |
+
"train_runtime": 7304.8453,
|
| 6 |
+
"train_samples_per_second": 1.016,
|
| 7 |
+
"train_steps_per_second": 0.064
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,365 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 464,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04310344827586207,
|
| 14 |
+
"grad_norm": 0.22970597445964813,
|
| 15 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 16 |
+
"loss": 0.5477,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08620689655172414,
|
| 21 |
+
"grad_norm": 0.24922381341457367,
|
| 22 |
+
"learning_rate": 4.99847706754774e-05,
|
| 23 |
+
"loss": 0.4192,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12931034482758622,
|
| 28 |
+
"grad_norm": 0.1861911565065384,
|
| 29 |
+
"learning_rate": 4.9863047384206835e-05,
|
| 30 |
+
"loss": 0.2814,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1724137931034483,
|
| 35 |
+
"grad_norm": 0.16707484424114227,
|
| 36 |
+
"learning_rate": 4.962019382530521e-05,
|
| 37 |
+
"loss": 0.2082,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21551724137931033,
|
| 42 |
+
"grad_norm": 0.17490606009960175,
|
| 43 |
+
"learning_rate": 4.925739315689991e-05,
|
| 44 |
+
"loss": 0.1599,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.25862068965517243,
|
| 49 |
+
"grad_norm": 0.16346780955791473,
|
| 50 |
+
"learning_rate": 4.877641290737884e-05,
|
| 51 |
+
"loss": 0.144,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3017241379310345,
|
| 56 |
+
"grad_norm": 0.16197219491004944,
|
| 57 |
+
"learning_rate": 4.817959636416969e-05,
|
| 58 |
+
"loss": 0.123,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3448275862068966,
|
| 63 |
+
"grad_norm": 0.1676415354013443,
|
| 64 |
+
"learning_rate": 4.7469851157479177e-05,
|
| 65 |
+
"loss": 0.1168,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3879310344827586,
|
| 70 |
+
"grad_norm": 0.14542680978775024,
|
| 71 |
+
"learning_rate": 4.665063509461097e-05,
|
| 72 |
+
"loss": 0.1112,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43103448275862066,
|
| 77 |
+
"grad_norm": 0.1882169097661972,
|
| 78 |
+
"learning_rate": 4.572593931387604e-05,
|
| 79 |
+
"loss": 0.1005,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.47413793103448276,
|
| 84 |
+
"grad_norm": 0.14488768577575684,
|
| 85 |
+
"learning_rate": 4.4700268840168045e-05,
|
| 86 |
+
"loss": 0.102,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5172413793103449,
|
| 91 |
+
"grad_norm": 0.15230809152126312,
|
| 92 |
+
"learning_rate": 4.357862063693486e-05,
|
| 93 |
+
"loss": 0.103,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5603448275862069,
|
| 98 |
+
"grad_norm": 0.13396801054477692,
|
| 99 |
+
"learning_rate": 4.2366459261474933e-05,
|
| 100 |
+
"loss": 0.1035,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.603448275862069,
|
| 105 |
+
"grad_norm": 0.1350702941417694,
|
| 106 |
+
"learning_rate": 4.1069690242163484e-05,
|
| 107 |
+
"loss": 0.0995,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.646551724137931,
|
| 112 |
+
"grad_norm": 0.1560034453868866,
|
| 113 |
+
"learning_rate": 3.969463130731183e-05,
|
| 114 |
+
"loss": 0.0979,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6896551724137931,
|
| 119 |
+
"grad_norm": 0.13901282846927643,
|
| 120 |
+
"learning_rate": 3.824798160583012e-05,
|
| 121 |
+
"loss": 0.0947,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7327586206896551,
|
| 126 |
+
"grad_norm": 0.18362534046173096,
|
| 127 |
+
"learning_rate": 3.673678906964727e-05,
|
| 128 |
+
"loss": 0.0969,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7758620689655172,
|
| 133 |
+
"grad_norm": 0.17652247846126556,
|
| 134 |
+
"learning_rate": 3.516841607689501e-05,
|
| 135 |
+
"loss": 0.0905,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.8189655172413793,
|
| 140 |
+
"grad_norm": 0.1358911544084549,
|
| 141 |
+
"learning_rate": 3.355050358314172e-05,
|
| 142 |
+
"loss": 0.0925,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8620689655172413,
|
| 147 |
+
"grad_norm": 0.1052212044596672,
|
| 148 |
+
"learning_rate": 3.1890933895424976e-05,
|
| 149 |
+
"loss": 0.0953,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.9051724137931034,
|
| 154 |
+
"grad_norm": 0.13334128260612488,
|
| 155 |
+
"learning_rate": 3.0197792270443982e-05,
|
| 156 |
+
"loss": 0.0886,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.9482758620689655,
|
| 161 |
+
"grad_norm": 0.12180697172880173,
|
| 162 |
+
"learning_rate": 2.8479327524001636e-05,
|
| 163 |
+
"loss": 0.0914,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9913793103448276,
|
| 168 |
+
"grad_norm": 0.1343410611152649,
|
| 169 |
+
"learning_rate": 2.674391184360313e-05,
|
| 170 |
+
"loss": 0.0887,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0344827586206897,
|
| 175 |
+
"grad_norm": 0.13129718601703644,
|
| 176 |
+
"learning_rate": 2.5e-05,
|
| 177 |
+
"loss": 0.0993,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.0775862068965518,
|
| 182 |
+
"grad_norm": 0.12985403835773468,
|
| 183 |
+
"learning_rate": 2.3256088156396868e-05,
|
| 184 |
+
"loss": 0.0925,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.1206896551724137,
|
| 189 |
+
"grad_norm": 0.10140767693519592,
|
| 190 |
+
"learning_rate": 2.1520672475998373e-05,
|
| 191 |
+
"loss": 0.086,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.1637931034482758,
|
| 196 |
+
"grad_norm": 0.10552043467760086,
|
| 197 |
+
"learning_rate": 1.980220772955602e-05,
|
| 198 |
+
"loss": 0.0885,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.206896551724138,
|
| 203 |
+
"grad_norm": 0.17615962028503418,
|
| 204 |
+
"learning_rate": 1.8109066104575023e-05,
|
| 205 |
+
"loss": 0.0935,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.25,
|
| 210 |
+
"grad_norm": 0.16146473586559296,
|
| 211 |
+
"learning_rate": 1.6449496416858284e-05,
|
| 212 |
+
"loss": 0.089,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.293103448275862,
|
| 217 |
+
"grad_norm": 0.11695656925439835,
|
| 218 |
+
"learning_rate": 1.4831583923104999e-05,
|
| 219 |
+
"loss": 0.0934,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.3362068965517242,
|
| 224 |
+
"grad_norm": 0.13488854467868805,
|
| 225 |
+
"learning_rate": 1.3263210930352737e-05,
|
| 226 |
+
"loss": 0.0902,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.3793103448275863,
|
| 231 |
+
"grad_norm": 0.14104993641376495,
|
| 232 |
+
"learning_rate": 1.175201839416988e-05,
|
| 233 |
+
"loss": 0.0915,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.4224137931034484,
|
| 238 |
+
"grad_norm": 0.11073966324329376,
|
| 239 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 240 |
+
"loss": 0.0904,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.4655172413793103,
|
| 245 |
+
"grad_norm": 0.12246192991733551,
|
| 246 |
+
"learning_rate": 8.930309757836517e-06,
|
| 247 |
+
"loss": 0.086,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.5086206896551724,
|
| 252 |
+
"grad_norm": 0.11951974779367447,
|
| 253 |
+
"learning_rate": 7.633540738525066e-06,
|
| 254 |
+
"loss": 0.0883,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.5517241379310345,
|
| 259 |
+
"grad_norm": 0.11673244833946228,
|
| 260 |
+
"learning_rate": 6.421379363065142e-06,
|
| 261 |
+
"loss": 0.0868,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.5948275862068966,
|
| 266 |
+
"grad_norm": 0.11525051295757294,
|
| 267 |
+
"learning_rate": 5.299731159831953e-06,
|
| 268 |
+
"loss": 0.0889,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.6379310344827587,
|
| 273 |
+
"grad_norm": 0.16884970664978027,
|
| 274 |
+
"learning_rate": 4.274060686123959e-06,
|
| 275 |
+
"loss": 0.0905,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.6810344827586206,
|
| 280 |
+
"grad_norm": 0.12776394188404083,
|
| 281 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 282 |
+
"loss": 0.0905,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.7241379310344827,
|
| 287 |
+
"grad_norm": 0.13251963257789612,
|
| 288 |
+
"learning_rate": 2.5301488425208296e-06,
|
| 289 |
+
"loss": 0.0862,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.7672413793103448,
|
| 294 |
+
"grad_norm": 0.14248506724834442,
|
| 295 |
+
"learning_rate": 1.8204036358303173e-06,
|
| 296 |
+
"loss": 0.09,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.8103448275862069,
|
| 301 |
+
"grad_norm": 0.10634557157754898,
|
| 302 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 303 |
+
"loss": 0.0839,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.853448275862069,
|
| 308 |
+
"grad_norm": 0.12421922385692596,
|
| 309 |
+
"learning_rate": 7.426068431000882e-07,
|
| 310 |
+
"loss": 0.088,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.896551724137931,
|
| 315 |
+
"grad_norm": 0.12003956735134125,
|
| 316 |
+
"learning_rate": 3.7980617469479953e-07,
|
| 317 |
+
"loss": 0.0932,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.9396551724137931,
|
| 322 |
+
"grad_norm": 0.10775435715913773,
|
| 323 |
+
"learning_rate": 1.3695261579316777e-07,
|
| 324 |
+
"loss": 0.0842,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.9827586206896552,
|
| 329 |
+
"grad_norm": 0.13052473962306976,
|
| 330 |
+
"learning_rate": 1.522932452260595e-08,
|
| 331 |
+
"loss": 0.0894,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.0,
|
| 336 |
+
"step": 464,
|
| 337 |
+
"total_flos": 2.4087255599087616e+17,
|
| 338 |
+
"train_loss": 0.11968068110531774,
|
| 339 |
+
"train_runtime": 7304.8453,
|
| 340 |
+
"train_samples_per_second": 1.016,
|
| 341 |
+
"train_steps_per_second": 0.064
|
| 342 |
+
}
|
| 343 |
+
],
|
| 344 |
+
"logging_steps": 10,
|
| 345 |
+
"max_steps": 464,
|
| 346 |
+
"num_input_tokens_seen": 0,
|
| 347 |
+
"num_train_epochs": 2,
|
| 348 |
+
"save_steps": 100,
|
| 349 |
+
"stateful_callbacks": {
|
| 350 |
+
"TrainerControl": {
|
| 351 |
+
"args": {
|
| 352 |
+
"should_epoch_stop": false,
|
| 353 |
+
"should_evaluate": false,
|
| 354 |
+
"should_log": false,
|
| 355 |
+
"should_save": true,
|
| 356 |
+
"should_training_stop": true
|
| 357 |
+
},
|
| 358 |
+
"attributes": {}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"total_flos": 2.4087255599087616e+17,
|
| 362 |
+
"train_batch_size": 4,
|
| 363 |
+
"trial_name": null,
|
| 364 |
+
"trial_params": null
|
| 365 |
+
}
|