End of training
Browse files
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 5.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.967741935483871,
|
| 4 |
+
"eval_loss": 0.10572722554206848,
|
| 5 |
+
"eval_runtime": 28.4074,
|
| 6 |
+
"eval_samples_per_second": 5.456,
|
| 7 |
+
"eval_steps_per_second": 1.373
|
| 8 |
}
|
runs/May21_00-58-36_8696136f2511/events.out.tfevents.1716253831.8696136f2511.34.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7213fa081849d36717f407e41ac91154d061e3eabb23ad0c4d799a6006aa45ad
|
| 3 |
+
size 1057
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 5.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.967741935483871,
|
| 4 |
+
"eval_loss": 0.10572722554206848,
|
| 5 |
+
"eval_runtime": 28.4074,
|
| 6 |
+
"eval_samples_per_second": 5.456,
|
| 7 |
+
"eval_steps_per_second": 1.373
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,105 +1,360 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 3.
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"eval_accuracy": 0.
|
| 63 |
-
"eval_loss":
|
| 64 |
-
"eval_runtime": 13.
|
| 65 |
-
"eval_samples_per_second": 5.
|
| 66 |
-
"eval_steps_per_second": 1.
|
| 67 |
"step": 75
|
| 68 |
},
|
| 69 |
{
|
| 70 |
-
"epoch": 1.
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"train_samples_per_second": 1.942,
|
| 76 |
-
"train_steps_per_second": 0.486
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch": 1.
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"eval_steps_per_second": 1.329,
|
| 85 |
-
"step": 75
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 1.
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
|
| 94 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
}
|
| 96 |
],
|
| 97 |
"logging_steps": 10,
|
| 98 |
-
"max_steps":
|
| 99 |
"num_input_tokens_seen": 0,
|
| 100 |
"num_train_epochs": 9223372036854775807,
|
| 101 |
"save_steps": 500,
|
| 102 |
-
"total_flos":
|
| 103 |
"train_batch_size": 4,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-375",
|
| 4 |
+
"epoch": 4.2,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 375,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 14.895779609680176,
|
| 14 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 15 |
+
"loss": 1.3822,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 15.425480842590332,
|
| 21 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 22 |
+
"loss": 1.1621,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 11.494285583496094,
|
| 28 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 29 |
+
"loss": 1.0609,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 14.816349983215332,
|
| 35 |
+
"learning_rate": 4.9703264094955494e-05,
|
| 36 |
+
"loss": 0.8414,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 18.69601058959961,
|
| 42 |
+
"learning_rate": 4.821958456973294e-05,
|
| 43 |
+
"loss": 0.7904,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"grad_norm": 11.910196304321289,
|
| 49 |
+
"learning_rate": 4.673590504451038e-05,
|
| 50 |
+
"loss": 0.9924,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.19,
|
| 55 |
+
"grad_norm": 12.124129295349121,
|
| 56 |
+
"learning_rate": 4.525222551928784e-05,
|
| 57 |
+
"loss": 0.9101,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"eval_accuracy": 0.6285714285714286,
|
| 63 |
+
"eval_loss": 0.8777225017547607,
|
| 64 |
+
"eval_runtime": 13.2025,
|
| 65 |
+
"eval_samples_per_second": 5.302,
|
| 66 |
+
"eval_steps_per_second": 1.363,
|
| 67 |
"step": 75
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 1.01,
|
| 71 |
+
"grad_norm": 14.571742057800293,
|
| 72 |
+
"learning_rate": 4.3768545994065286e-05,
|
| 73 |
+
"loss": 0.5606,
|
| 74 |
+
"step": 80
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.04,
|
| 78 |
+
"grad_norm": 9.837146759033203,
|
| 79 |
+
"learning_rate": 4.228486646884273e-05,
|
| 80 |
+
"loss": 0.5213,
|
| 81 |
+
"step": 90
|
|
|
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 1.07,
|
| 85 |
+
"grad_norm": 18.2418212890625,
|
| 86 |
+
"learning_rate": 4.080118694362018e-05,
|
| 87 |
+
"loss": 0.6293,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.09,
|
| 92 |
+
"grad_norm": 10.92044734954834,
|
| 93 |
+
"learning_rate": 3.9317507418397627e-05,
|
| 94 |
+
"loss": 0.6146,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.12,
|
| 99 |
+
"grad_norm": 10.466025352478027,
|
| 100 |
+
"learning_rate": 3.783382789317508e-05,
|
| 101 |
+
"loss": 0.5081,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.15,
|
| 106 |
+
"grad_norm": 34.30221176147461,
|
| 107 |
+
"learning_rate": 3.635014836795252e-05,
|
| 108 |
+
"loss": 0.4598,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.17,
|
| 113 |
+
"grad_norm": 2.5953423976898193,
|
| 114 |
+
"learning_rate": 3.4866468842729974e-05,
|
| 115 |
+
"loss": 0.5664,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.2,
|
| 120 |
+
"grad_norm": 2.9291703701019287,
|
| 121 |
+
"learning_rate": 3.338278931750742e-05,
|
| 122 |
+
"loss": 0.2332,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2,
|
| 127 |
+
"eval_accuracy": 0.8285714285714286,
|
| 128 |
+
"eval_loss": 0.3904847800731659,
|
| 129 |
+
"eval_runtime": 12.86,
|
| 130 |
+
"eval_samples_per_second": 5.443,
|
| 131 |
+
"eval_steps_per_second": 1.4,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.03,
|
| 136 |
+
"grad_norm": 11.46927261352539,
|
| 137 |
+
"learning_rate": 3.189910979228487e-05,
|
| 138 |
+
"loss": 0.2465,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.05,
|
| 143 |
+
"grad_norm": 1.3007924556732178,
|
| 144 |
+
"learning_rate": 3.0415430267062318e-05,
|
| 145 |
+
"loss": 0.5288,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.08,
|
| 150 |
+
"grad_norm": 30.475011825561523,
|
| 151 |
+
"learning_rate": 2.8931750741839762e-05,
|
| 152 |
+
"loss": 0.4022,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.11,
|
| 157 |
+
"grad_norm": 0.40067318081855774,
|
| 158 |
+
"learning_rate": 2.744807121661721e-05,
|
| 159 |
+
"loss": 0.3373,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.13,
|
| 164 |
+
"grad_norm": 6.692281723022461,
|
| 165 |
+
"learning_rate": 2.5964391691394662e-05,
|
| 166 |
+
"loss": 0.2017,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.16,
|
| 171 |
+
"grad_norm": 0.8030463457107544,
|
| 172 |
+
"learning_rate": 2.4480712166172106e-05,
|
| 173 |
+
"loss": 0.2078,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.19,
|
| 178 |
+
"grad_norm": 4.740080833435059,
|
| 179 |
+
"learning_rate": 2.2997032640949558e-05,
|
| 180 |
+
"loss": 0.1484,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.2,
|
| 185 |
+
"eval_accuracy": 0.9428571428571428,
|
| 186 |
+
"eval_loss": 0.2271830290555954,
|
| 187 |
+
"eval_runtime": 12.9105,
|
| 188 |
+
"eval_samples_per_second": 5.422,
|
| 189 |
+
"eval_steps_per_second": 1.394,
|
| 190 |
+
"step": 225
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.01,
|
| 194 |
+
"grad_norm": 12.664633750915527,
|
| 195 |
+
"learning_rate": 2.1513353115727002e-05,
|
| 196 |
+
"loss": 0.0884,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.04,
|
| 201 |
+
"grad_norm": 0.1440916657447815,
|
| 202 |
+
"learning_rate": 2.0029673590504454e-05,
|
| 203 |
+
"loss": 0.1236,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.07,
|
| 208 |
+
"grad_norm": 3.6163482666015625,
|
| 209 |
+
"learning_rate": 1.85459940652819e-05,
|
| 210 |
+
"loss": 0.3029,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.09,
|
| 215 |
+
"grad_norm": 0.2636096179485321,
|
| 216 |
+
"learning_rate": 1.706231454005935e-05,
|
| 217 |
+
"loss": 0.125,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.12,
|
| 222 |
+
"grad_norm": 12.344978332519531,
|
| 223 |
+
"learning_rate": 1.5578635014836794e-05,
|
| 224 |
+
"loss": 0.2013,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.15,
|
| 229 |
+
"grad_norm": 18.149120330810547,
|
| 230 |
+
"learning_rate": 1.4094955489614246e-05,
|
| 231 |
+
"loss": 0.085,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.17,
|
| 236 |
+
"grad_norm": 2.8482699394226074,
|
| 237 |
+
"learning_rate": 1.2611275964391692e-05,
|
| 238 |
+
"loss": 0.112,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.2,
|
| 243 |
+
"grad_norm": 0.20341695845127106,
|
| 244 |
+
"learning_rate": 1.112759643916914e-05,
|
| 245 |
+
"loss": 0.0183,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.2,
|
| 250 |
+
"eval_accuracy": 0.9857142857142858,
|
| 251 |
+
"eval_loss": 0.06157089024782181,
|
| 252 |
+
"eval_runtime": 13.0386,
|
| 253 |
+
"eval_samples_per_second": 5.369,
|
| 254 |
+
"eval_steps_per_second": 1.381,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.03,
|
| 259 |
+
"grad_norm": 32.8179817199707,
|
| 260 |
+
"learning_rate": 9.643916913946588e-06,
|
| 261 |
+
"loss": 0.0328,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.05,
|
| 266 |
+
"grad_norm": 0.15981259942054749,
|
| 267 |
+
"learning_rate": 8.160237388724036e-06,
|
| 268 |
+
"loss": 0.0132,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.08,
|
| 273 |
+
"grad_norm": 16.473556518554688,
|
| 274 |
+
"learning_rate": 6.676557863501484e-06,
|
| 275 |
+
"loss": 0.0534,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.11,
|
| 280 |
+
"grad_norm": 0.11358954757452011,
|
| 281 |
+
"learning_rate": 5.192878338278932e-06,
|
| 282 |
+
"loss": 0.0142,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.13,
|
| 287 |
+
"grad_norm": 0.09973251819610596,
|
| 288 |
+
"learning_rate": 3.7091988130563796e-06,
|
| 289 |
+
"loss": 0.0977,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.16,
|
| 294 |
+
"grad_norm": 1.2808237075805664,
|
| 295 |
+
"learning_rate": 2.225519287833828e-06,
|
| 296 |
+
"loss": 0.011,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.19,
|
| 301 |
+
"grad_norm": 0.34775447845458984,
|
| 302 |
+
"learning_rate": 7.41839762611276e-07,
|
| 303 |
+
"loss": 0.0393,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.2,
|
| 308 |
+
"eval_accuracy": 1.0,
|
| 309 |
+
"eval_loss": 0.03910655900835991,
|
| 310 |
+
"eval_runtime": 13.2105,
|
| 311 |
+
"eval_samples_per_second": 5.299,
|
| 312 |
+
"eval_steps_per_second": 1.363,
|
| 313 |
+
"step": 375
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.2,
|
| 317 |
+
"step": 375,
|
| 318 |
+
"total_flos": 1.86923023515648e+18,
|
| 319 |
+
"train_loss": 0.39019181327025093,
|
| 320 |
+
"train_runtime": 577.3468,
|
| 321 |
+
"train_samples_per_second": 2.598,
|
| 322 |
+
"train_steps_per_second": 0.65
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.2,
|
| 326 |
+
"eval_accuracy": 0.967741935483871,
|
| 327 |
+
"eval_loss": 0.10572722554206848,
|
| 328 |
+
"eval_runtime": 28.9857,
|
| 329 |
+
"eval_samples_per_second": 5.347,
|
| 330 |
+
"eval_steps_per_second": 1.345,
|
| 331 |
+
"step": 375
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.2,
|
| 335 |
+
"eval_accuracy": 0.967741935483871,
|
| 336 |
+
"eval_loss": 0.10572721064090729,
|
| 337 |
+
"eval_runtime": 28.3051,
|
| 338 |
+
"eval_samples_per_second": 5.476,
|
| 339 |
+
"eval_steps_per_second": 1.378,
|
| 340 |
+
"step": 375
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.2,
|
| 344 |
+
"eval_accuracy": 0.967741935483871,
|
| 345 |
+
"eval_loss": 0.10572722554206848,
|
| 346 |
+
"eval_runtime": 28.4074,
|
| 347 |
+
"eval_samples_per_second": 5.456,
|
| 348 |
+
"eval_steps_per_second": 1.373,
|
| 349 |
+
"step": 375
|
| 350 |
}
|
| 351 |
],
|
| 352 |
"logging_steps": 10,
|
| 353 |
+
"max_steps": 375,
|
| 354 |
"num_input_tokens_seen": 0,
|
| 355 |
"num_train_epochs": 9223372036854775807,
|
| 356 |
"save_steps": 500,
|
| 357 |
+
"total_flos": 1.86923023515648e+18,
|
| 358 |
"train_batch_size": 4,
|
| 359 |
"trial_name": null,
|
| 360 |
"trial_params": null
|