Commit
•
ac20351
1
Parent(s):
da08614
Training in progress, epoch 1
Browse files- all_results.json +14 -14
- eval_results.json +9 -9
- model.safetensors +1 -1
- runs/Jan26_18-25-00_a63521f81d59/events.out.tfevents.1706296014.a63521f81d59.335.1 +3 -0
- runs/Jan26_18-25-00_a63521f81d59/events.out.tfevents.1706296016.a63521f81d59.335.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +464 -80
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
-
"total_flos":
|
| 12 |
-
"train_loss": 0.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 0.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9259882253994953,
|
| 4 |
+
"eval_f1": 0.9268755487412734,
|
| 5 |
+
"eval_loss": 0.32298851013183594,
|
| 6 |
+
"eval_precision": 0.9315188840219485,
|
| 7 |
+
"eval_recall": 0.9259882253994953,
|
| 8 |
+
"eval_runtime": 139.3443,
|
| 9 |
+
"eval_samples_per_second": 8.533,
|
| 10 |
+
"eval_steps_per_second": 2.139,
|
| 11 |
+
"total_flos": 1.104340029133824e+18,
|
| 12 |
+
"train_loss": 0.6521745291690099,
|
| 13 |
+
"train_runtime": 2345.9873,
|
| 14 |
+
"train_samples_per_second": 6.078,
|
| 15 |
+
"train_steps_per_second": 0.38
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9259882253994953,
|
| 4 |
+
"eval_f1": 0.9268755487412734,
|
| 5 |
+
"eval_loss": 0.32298851013183594,
|
| 6 |
+
"eval_precision": 0.9315188840219485,
|
| 7 |
+
"eval_recall": 0.9259882253994953,
|
| 8 |
+
"eval_runtime": 139.3443,
|
| 9 |
+
"eval_samples_per_second": 8.533,
|
| 10 |
+
"eval_steps_per_second": 2.139
|
| 11 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343248584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8981f97df48d97438799cc2f0d353f4b9d211e8e7990a6cb29d60a5fab8a8bb8
|
| 3 |
size 343248584
|
runs/Jan26_18-25-00_a63521f81d59/events.out.tfevents.1706296014.a63521f81d59.335.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5262c177ae39ab5bbc27921f4f94595568bd3f8da799633efbc1cabf5e26517f
|
| 3 |
+
size 560
|
runs/Jan26_18-25-00_a63521f81d59/events.out.tfevents.1706296016.a63521f81d59.335.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aefa926a9dcd28f31bca3b8cc85929599a971439ecc9cc23aa1adae6533a4de4
|
| 3 |
+
size 14800
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.104340029133824e+18,
|
| 4 |
+
"train_loss": 0.6521745291690099,
|
| 5 |
+
"train_runtime": 2345.9873,
|
| 6 |
+
"train_samples_per_second": 6.078,
|
| 7 |
+
"train_steps_per_second": 0.38
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,214 +1,598 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "enver/cat-sounds/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": 0.03,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.07,
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.1,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.13,
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss":
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.17,
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.2,
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss":
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.24,
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27,
|
| 55 |
-
"learning_rate": 4.
|
| 56 |
-
"loss":
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.3,
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss":
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.34,
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss":
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.37,
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss":
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.4,
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss":
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.44,
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss":
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.47,
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.5,
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss":
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.54,
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss":
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.57,
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss":
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.61,
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.64,
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.67,
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.71,
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.74,
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.77,
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.81,
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.84,
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.87,
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.91,
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.94,
|
| 175 |
-
"learning_rate": 3.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.98,
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 1.0,
|
| 187 |
-
"eval_accuracy": 0.
|
| 188 |
-
"eval_f1": 0.
|
| 189 |
-
"eval_loss": 0.
|
| 190 |
-
"eval_precision": 0.
|
| 191 |
-
"eval_recall": 0.
|
| 192 |
-
"eval_runtime":
|
| 193 |
-
"eval_samples_per_second":
|
| 194 |
-
"eval_steps_per_second":
|
| 195 |
"step": 297
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 1.
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
}
|
| 206 |
],
|
| 207 |
"logging_steps": 10,
|
| 208 |
-
"max_steps":
|
| 209 |
-
"num_train_epochs":
|
| 210 |
"save_steps": 500,
|
| 211 |
-
"total_flos":
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
| 214 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9259882253994953,
|
| 3 |
+
"best_model_checkpoint": "enver/cat-sounds/checkpoint-891",
|
| 4 |
+
"epoch": 2.9974768713204374,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 891,
|
| 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 |
+
"learning_rate": 5.555555555555556e-06,
|
| 14 |
+
"loss": 2.3176,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 20 |
+
"loss": 2.2754,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 26 |
+
"loss": 2.2346,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 32 |
+
"loss": 2.1605,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.17,
|
| 37 |
+
"learning_rate": 2.777777777777778e-05,
|
| 38 |
+
"loss": 2.0691,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.2,
|
| 43 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 44 |
+
"loss": 1.9679,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.24,
|
| 49 |
+
"learning_rate": 3.888888888888889e-05,
|
| 50 |
+
"loss": 1.8312,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.27,
|
| 55 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 56 |
+
"loss": 1.6983,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.3,
|
| 61 |
+
"learning_rate": 5e-05,
|
| 62 |
+
"loss": 1.5913,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.34,
|
| 67 |
+
"learning_rate": 4.937578027465668e-05,
|
| 68 |
+
"loss": 1.4524,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.37,
|
| 73 |
+
"learning_rate": 4.875156054931336e-05,
|
| 74 |
+
"loss": 1.3422,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.4,
|
| 79 |
+
"learning_rate": 4.812734082397004e-05,
|
| 80 |
+
"loss": 1.1812,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.44,
|
| 85 |
+
"learning_rate": 4.750312109862672e-05,
|
| 86 |
+
"loss": 1.2109,
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.47,
|
| 91 |
+
"learning_rate": 4.6878901373283394e-05,
|
| 92 |
+
"loss": 1.1491,
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.5,
|
| 97 |
+
"learning_rate": 4.625468164794008e-05,
|
| 98 |
+
"loss": 1.0259,
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.54,
|
| 103 |
+
"learning_rate": 4.563046192259676e-05,
|
| 104 |
+
"loss": 1.002,
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.57,
|
| 109 |
+
"learning_rate": 4.500624219725343e-05,
|
| 110 |
+
"loss": 1.1162,
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.61,
|
| 115 |
+
"learning_rate": 4.438202247191011e-05,
|
| 116 |
+
"loss": 0.8804,
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.64,
|
| 121 |
+
"learning_rate": 4.37578027465668e-05,
|
| 122 |
+
"loss": 0.9022,
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.67,
|
| 127 |
+
"learning_rate": 4.313358302122347e-05,
|
| 128 |
+
"loss": 0.8509,
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.71,
|
| 133 |
+
"learning_rate": 4.250936329588015e-05,
|
| 134 |
+
"loss": 0.814,
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.74,
|
| 139 |
+
"learning_rate": 4.188514357053683e-05,
|
| 140 |
+
"loss": 0.8451,
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.77,
|
| 145 |
+
"learning_rate": 4.126092384519351e-05,
|
| 146 |
+
"loss": 0.9322,
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.81,
|
| 151 |
+
"learning_rate": 4.063670411985019e-05,
|
| 152 |
+
"loss": 0.7668,
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.84,
|
| 157 |
+
"learning_rate": 4.001248439450687e-05,
|
| 158 |
+
"loss": 0.8153,
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.87,
|
| 163 |
+
"learning_rate": 3.938826466916355e-05,
|
| 164 |
+
"loss": 0.7569,
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.91,
|
| 169 |
+
"learning_rate": 3.876404494382023e-05,
|
| 170 |
+
"loss": 0.8009,
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.94,
|
| 175 |
+
"learning_rate": 3.813982521847691e-05,
|
| 176 |
+
"loss": 0.6789,
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.98,
|
| 181 |
+
"learning_rate": 3.751560549313358e-05,
|
| 182 |
+
"loss": 0.6474,
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 1.0,
|
| 187 |
+
"eval_accuracy": 0.8359966358284272,
|
| 188 |
+
"eval_f1": 0.8379685951133469,
|
| 189 |
+
"eval_loss": 0.6715514659881592,
|
| 190 |
+
"eval_precision": 0.8527444218731524,
|
| 191 |
+
"eval_recall": 0.8359966358284272,
|
| 192 |
+
"eval_runtime": 138.4497,
|
| 193 |
+
"eval_samples_per_second": 8.588,
|
| 194 |
+
"eval_steps_per_second": 2.152,
|
| 195 |
"step": 297
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.01,
|
| 199 |
+
"learning_rate": 3.689138576779027e-05,
|
| 200 |
+
"loss": 0.7577,
|
| 201 |
+
"step": 300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.04,
|
| 205 |
+
"learning_rate": 3.626716604244694e-05,
|
| 206 |
+
"loss": 0.5251,
|
| 207 |
+
"step": 310
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.08,
|
| 211 |
+
"learning_rate": 3.564294631710362e-05,
|
| 212 |
+
"loss": 0.6098,
|
| 213 |
+
"step": 320
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.11,
|
| 217 |
+
"learning_rate": 3.5018726591760305e-05,
|
| 218 |
+
"loss": 0.5334,
|
| 219 |
+
"step": 330
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.14,
|
| 223 |
+
"learning_rate": 3.439450686641698e-05,
|
| 224 |
+
"loss": 0.5506,
|
| 225 |
+
"step": 340
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.18,
|
| 229 |
+
"learning_rate": 3.377028714107366e-05,
|
| 230 |
+
"loss": 0.6034,
|
| 231 |
+
"step": 350
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.21,
|
| 235 |
+
"learning_rate": 3.314606741573034e-05,
|
| 236 |
+
"loss": 0.4747,
|
| 237 |
+
"step": 360
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.24,
|
| 241 |
+
"learning_rate": 3.252184769038702e-05,
|
| 242 |
+
"loss": 0.5192,
|
| 243 |
+
"step": 370
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.28,
|
| 247 |
+
"learning_rate": 3.1897627965043697e-05,
|
| 248 |
+
"loss": 0.4885,
|
| 249 |
+
"step": 380
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.31,
|
| 253 |
+
"learning_rate": 3.1273408239700376e-05,
|
| 254 |
+
"loss": 0.5599,
|
| 255 |
+
"step": 390
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.35,
|
| 259 |
+
"learning_rate": 3.0649188514357056e-05,
|
| 260 |
+
"loss": 0.5168,
|
| 261 |
+
"step": 400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.38,
|
| 265 |
+
"learning_rate": 3.0024968789013735e-05,
|
| 266 |
+
"loss": 0.4305,
|
| 267 |
+
"step": 410
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.41,
|
| 271 |
+
"learning_rate": 2.940074906367041e-05,
|
| 272 |
+
"loss": 0.4534,
|
| 273 |
+
"step": 420
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.45,
|
| 277 |
+
"learning_rate": 2.877652933832709e-05,
|
| 278 |
+
"loss": 0.5032,
|
| 279 |
+
"step": 430
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.48,
|
| 283 |
+
"learning_rate": 2.8152309612983774e-05,
|
| 284 |
+
"loss": 0.4587,
|
| 285 |
+
"step": 440
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.51,
|
| 289 |
+
"learning_rate": 2.752808988764045e-05,
|
| 290 |
+
"loss": 0.4103,
|
| 291 |
+
"step": 450
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.55,
|
| 295 |
+
"learning_rate": 2.690387016229713e-05,
|
| 296 |
+
"loss": 0.3474,
|
| 297 |
+
"step": 460
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.58,
|
| 301 |
+
"learning_rate": 2.6279650436953806e-05,
|
| 302 |
+
"loss": 0.4218,
|
| 303 |
+
"step": 470
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.61,
|
| 307 |
+
"learning_rate": 2.565543071161049e-05,
|
| 308 |
+
"loss": 0.3609,
|
| 309 |
+
"step": 480
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.65,
|
| 313 |
+
"learning_rate": 2.503121098626717e-05,
|
| 314 |
+
"loss": 0.3032,
|
| 315 |
+
"step": 490
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.68,
|
| 319 |
+
"learning_rate": 2.4406991260923848e-05,
|
| 320 |
+
"loss": 0.4611,
|
| 321 |
+
"step": 500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.72,
|
| 325 |
+
"learning_rate": 2.3782771535580524e-05,
|
| 326 |
+
"loss": 0.4433,
|
| 327 |
+
"step": 510
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.75,
|
| 331 |
+
"learning_rate": 2.3158551810237207e-05,
|
| 332 |
+
"loss": 0.4522,
|
| 333 |
+
"step": 520
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.78,
|
| 337 |
+
"learning_rate": 2.2534332084893883e-05,
|
| 338 |
+
"loss": 0.4488,
|
| 339 |
+
"step": 530
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.82,
|
| 343 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 344 |
+
"loss": 0.4003,
|
| 345 |
+
"step": 540
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.85,
|
| 349 |
+
"learning_rate": 2.1285892634207243e-05,
|
| 350 |
+
"loss": 0.3832,
|
| 351 |
+
"step": 550
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.88,
|
| 355 |
+
"learning_rate": 2.0661672908863922e-05,
|
| 356 |
+
"loss": 0.2996,
|
| 357 |
+
"step": 560
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.92,
|
| 361 |
+
"learning_rate": 2.00374531835206e-05,
|
| 362 |
+
"loss": 0.3441,
|
| 363 |
+
"step": 570
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.95,
|
| 367 |
+
"learning_rate": 1.9413233458177278e-05,
|
| 368 |
+
"loss": 0.3271,
|
| 369 |
+
"step": 580
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.98,
|
| 373 |
+
"learning_rate": 1.8789013732833958e-05,
|
| 374 |
+
"loss": 0.413,
|
| 375 |
+
"step": 590
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.0,
|
| 379 |
+
"eval_accuracy": 0.8999158957106812,
|
| 380 |
+
"eval_f1": 0.9013231777661141,
|
| 381 |
+
"eval_loss": 0.42947980761528015,
|
| 382 |
+
"eval_precision": 0.9097523236239999,
|
| 383 |
+
"eval_recall": 0.8999158957106812,
|
| 384 |
+
"eval_runtime": 138.7049,
|
| 385 |
+
"eval_samples_per_second": 8.572,
|
| 386 |
+
"eval_steps_per_second": 2.148,
|
| 387 |
+
"step": 594
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.02,
|
| 391 |
+
"learning_rate": 1.8164794007490637e-05,
|
| 392 |
+
"loss": 0.3428,
|
| 393 |
+
"step": 600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.05,
|
| 397 |
+
"learning_rate": 1.7540574282147317e-05,
|
| 398 |
+
"loss": 0.2994,
|
| 399 |
+
"step": 610
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.09,
|
| 403 |
+
"learning_rate": 1.6916354556803996e-05,
|
| 404 |
+
"loss": 0.2385,
|
| 405 |
+
"step": 620
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.12,
|
| 409 |
+
"learning_rate": 1.6292134831460676e-05,
|
| 410 |
+
"loss": 0.3453,
|
| 411 |
+
"step": 630
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.15,
|
| 415 |
+
"learning_rate": 1.5667915106117352e-05,
|
| 416 |
+
"loss": 0.3042,
|
| 417 |
+
"step": 640
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.19,
|
| 421 |
+
"learning_rate": 1.5043695380774033e-05,
|
| 422 |
+
"loss": 0.2582,
|
| 423 |
+
"step": 650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.22,
|
| 427 |
+
"learning_rate": 1.4419475655430711e-05,
|
| 428 |
+
"loss": 0.2912,
|
| 429 |
+
"step": 660
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.25,
|
| 433 |
+
"learning_rate": 1.3795255930087393e-05,
|
| 434 |
+
"loss": 0.2173,
|
| 435 |
+
"step": 670
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.29,
|
| 439 |
+
"learning_rate": 1.3171036204744069e-05,
|
| 440 |
+
"loss": 0.2286,
|
| 441 |
+
"step": 680
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.32,
|
| 445 |
+
"learning_rate": 1.254681647940075e-05,
|
| 446 |
+
"loss": 0.2235,
|
| 447 |
+
"step": 690
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.35,
|
| 451 |
+
"learning_rate": 1.192259675405743e-05,
|
| 452 |
+
"loss": 0.238,
|
| 453 |
+
"step": 700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.39,
|
| 457 |
+
"learning_rate": 1.1298377028714107e-05,
|
| 458 |
+
"loss": 0.2113,
|
| 459 |
+
"step": 710
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.42,
|
| 463 |
+
"learning_rate": 1.0674157303370787e-05,
|
| 464 |
+
"loss": 0.2061,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.46,
|
| 469 |
+
"learning_rate": 1.0049937578027465e-05,
|
| 470 |
+
"loss": 0.1937,
|
| 471 |
+
"step": 730
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.49,
|
| 475 |
+
"learning_rate": 9.425717852684144e-06,
|
| 476 |
+
"loss": 0.1994,
|
| 477 |
+
"step": 740
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.52,
|
| 481 |
+
"learning_rate": 8.801498127340826e-06,
|
| 482 |
+
"loss": 0.2239,
|
| 483 |
+
"step": 750
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.56,
|
| 487 |
+
"learning_rate": 8.177278401997504e-06,
|
| 488 |
+
"loss": 0.2161,
|
| 489 |
+
"step": 760
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.59,
|
| 493 |
+
"learning_rate": 7.553058676654183e-06,
|
| 494 |
+
"loss": 0.2486,
|
| 495 |
+
"step": 770
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.62,
|
| 499 |
+
"learning_rate": 6.928838951310862e-06,
|
| 500 |
+
"loss": 0.2777,
|
| 501 |
+
"step": 780
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.66,
|
| 505 |
+
"learning_rate": 6.304619225967541e-06,
|
| 506 |
+
"loss": 0.1885,
|
| 507 |
+
"step": 790
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.69,
|
| 511 |
+
"learning_rate": 5.68039950062422e-06,
|
| 512 |
+
"loss": 0.1919,
|
| 513 |
+
"step": 800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.72,
|
| 517 |
+
"learning_rate": 5.056179775280899e-06,
|
| 518 |
+
"loss": 0.2593,
|
| 519 |
+
"step": 810
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.76,
|
| 523 |
+
"learning_rate": 4.431960049937578e-06,
|
| 524 |
+
"loss": 0.224,
|
| 525 |
+
"step": 820
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.79,
|
| 529 |
+
"learning_rate": 3.8077403245942577e-06,
|
| 530 |
+
"loss": 0.2105,
|
| 531 |
+
"step": 830
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.83,
|
| 535 |
+
"learning_rate": 3.1835205992509364e-06,
|
| 536 |
+
"loss": 0.1998,
|
| 537 |
+
"step": 840
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.86,
|
| 541 |
+
"learning_rate": 2.5593008739076156e-06,
|
| 542 |
+
"loss": 0.154,
|
| 543 |
+
"step": 850
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.89,
|
| 547 |
+
"learning_rate": 1.9350811485642947e-06,
|
| 548 |
+
"loss": 0.2342,
|
| 549 |
+
"step": 860
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.93,
|
| 553 |
+
"learning_rate": 1.310861423220974e-06,
|
| 554 |
+
"loss": 0.1484,
|
| 555 |
+
"step": 870
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.96,
|
| 559 |
+
"learning_rate": 6.86641697877653e-07,
|
| 560 |
+
"loss": 0.1661,
|
| 561 |
+
"step": 880
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.99,
|
| 565 |
+
"learning_rate": 6.242197253433209e-08,
|
| 566 |
+
"loss": 0.2144,
|
| 567 |
+
"step": 890
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.0,
|
| 571 |
+
"eval_accuracy": 0.9259882253994953,
|
| 572 |
+
"eval_f1": 0.9268755487412734,
|
| 573 |
+
"eval_loss": 0.32298851013183594,
|
| 574 |
+
"eval_precision": 0.9315188840219485,
|
| 575 |
+
"eval_recall": 0.9259882253994953,
|
| 576 |
+
"eval_runtime": 141.4553,
|
| 577 |
+
"eval_samples_per_second": 8.405,
|
| 578 |
+
"eval_steps_per_second": 2.107,
|
| 579 |
+
"step": 891
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.0,
|
| 583 |
+
"step": 891,
|
| 584 |
+
"total_flos": 1.104340029133824e+18,
|
| 585 |
+
"train_loss": 0.6521745291690099,
|
| 586 |
+
"train_runtime": 2345.9873,
|
| 587 |
+
"train_samples_per_second": 6.078,
|
| 588 |
+
"train_steps_per_second": 0.38
|
| 589 |
}
|
| 590 |
],
|
| 591 |
"logging_steps": 10,
|
| 592 |
+
"max_steps": 891,
|
| 593 |
+
"num_train_epochs": 3,
|
| 594 |
"save_steps": 500,
|
| 595 |
+
"total_flos": 1.104340029133824e+18,
|
| 596 |
"trial_name": null,
|
| 597 |
"trial_params": null
|
| 598 |
}
|