Commit
•
3c52601
1
Parent(s):
36f2f81
🍻 cheers
Browse files
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.044844754857893646,
|
| 4 |
+
"eval_loss": 6.141994476318359,
|
| 5 |
+
"eval_runtime": 145.3561,
|
| 6 |
+
"eval_samples_per_second": 198.973,
|
| 7 |
+
"eval_steps_per_second": 24.877,
|
| 8 |
+
"train_loss": 6.8843976465667565,
|
| 9 |
+
"train_runtime": 17474.7904,
|
| 10 |
+
"train_samples_per_second": 66.203,
|
| 11 |
+
"train_steps_per_second": 2.069
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.044844754857893646,
|
| 4 |
+
"eval_loss": 6.141994476318359,
|
| 5 |
+
"eval_runtime": 145.3561,
|
| 6 |
+
"eval_samples_per_second": 198.973,
|
| 7 |
+
"eval_steps_per_second": 24.877
|
| 8 |
}
|
runs/May26_21-32-23_adrian-development/events.out.tfevents.1685147186.adrian-development.12758.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f296a6505dabbb69cdab57e4e6290bb23ab27b4ebb18b8eba00b1fd83c5de107
|
| 3 |
+
size 369
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"train_loss": 6.8843976465667565,
|
| 4 |
+
"train_runtime": 17474.7904,
|
| 5 |
+
"train_samples_per_second": 66.203,
|
| 6 |
+
"train_steps_per_second": 2.069
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,70 +1,565 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "Transformers/vit-base-clothing-leafs-example/checkpoint-
|
| 4 |
"epoch": 5.0,
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"learning_rate": 0.
|
| 13 |
-
"loss":
|
| 14 |
"step": 1000
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch":
|
| 18 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"learning_rate":
|
| 28 |
-
"loss":
|
| 29 |
"step": 2000
|
| 30 |
},
|
| 31 |
{
|
| 32 |
-
"epoch":
|
| 33 |
-
"eval_accuracy": 0.
|
| 34 |
-
"eval_loss":
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second":
|
| 38 |
"step": 2000
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss":
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
"step": 3000
|
| 54 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
{
|
| 56 |
"epoch": 5.0,
|
| 57 |
-
"step":
|
| 58 |
-
"total_flos": 9.
|
| 59 |
-
"train_loss":
|
| 60 |
-
"train_runtime":
|
| 61 |
-
"train_samples_per_second":
|
| 62 |
-
"train_steps_per_second":
|
| 63 |
}
|
| 64 |
],
|
| 65 |
-
"max_steps":
|
| 66 |
"num_train_epochs": 5,
|
| 67 |
-
"total_flos": 9.
|
| 68 |
"trial_name": null,
|
| 69 |
"trial_params": null
|
| 70 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 6.141994476318359,
|
| 3 |
+
"best_model_checkpoint": "Transformers/vit-base-clothing-leafs-example/checkpoint-36000",
|
| 4 |
"epoch": 5.0,
|
| 5 |
+
"global_step": 36155,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 0.0001944682616512239,
|
| 13 |
+
"loss": 8.6059,
|
| 14 |
"step": 1000
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"eval_accuracy": 0.0002420302883618007,
|
| 19 |
+
"eval_loss": 8.584440231323242,
|
| 20 |
+
"eval_runtime": 155.6325,
|
| 21 |
+
"eval_samples_per_second": 185.835,
|
| 22 |
+
"eval_steps_per_second": 23.234,
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.28,
|
| 27 |
+
"learning_rate": 0.0001889365233024478,
|
| 28 |
+
"loss": 8.5506,
|
| 29 |
"step": 2000
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 0.28,
|
| 33 |
+
"eval_accuracy": 0.00100269690892746,
|
| 34 |
+
"eval_loss": 8.518888473510742,
|
| 35 |
+
"eval_runtime": 153.9354,
|
| 36 |
+
"eval_samples_per_second": 187.884,
|
| 37 |
+
"eval_steps_per_second": 23.49,
|
| 38 |
"step": 2000
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 0.00018341584843036926,
|
| 43 |
+
"loss": 8.4931,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.41,
|
| 48 |
+
"eval_accuracy": 0.0012101514418090035,
|
| 49 |
+
"eval_loss": 8.464128494262695,
|
| 50 |
+
"eval_runtime": 157.4956,
|
| 51 |
+
"eval_samples_per_second": 183.637,
|
| 52 |
+
"eval_steps_per_second": 22.959,
|
| 53 |
"step": 3000
|
| 54 |
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.55,
|
| 57 |
+
"learning_rate": 0.00017788411008159315,
|
| 58 |
+
"loss": 8.4223,
|
| 59 |
+
"step": 4000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.55,
|
| 63 |
+
"eval_accuracy": 0.0016250605075720905,
|
| 64 |
+
"eval_loss": 8.349540710449219,
|
| 65 |
+
"eval_runtime": 156.3508,
|
| 66 |
+
"eval_samples_per_second": 184.982,
|
| 67 |
+
"eval_steps_per_second": 23.127,
|
| 68 |
+
"step": 4000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.69,
|
| 72 |
+
"learning_rate": 0.00017235237173281705,
|
| 73 |
+
"loss": 8.3144,
|
| 74 |
+
"step": 5000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.69,
|
| 78 |
+
"eval_accuracy": 0.0020745453288154346,
|
| 79 |
+
"eval_loss": 8.255170822143555,
|
| 80 |
+
"eval_runtime": 157.1252,
|
| 81 |
+
"eval_samples_per_second": 184.07,
|
| 82 |
+
"eval_steps_per_second": 23.013,
|
| 83 |
+
"step": 5000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.83,
|
| 87 |
+
"learning_rate": 0.00016682063338404094,
|
| 88 |
+
"loss": 8.1936,
|
| 89 |
+
"step": 6000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.83,
|
| 93 |
+
"eval_accuracy": 0.0023511513726574926,
|
| 94 |
+
"eval_loss": 8.138504981994629,
|
| 95 |
+
"eval_runtime": 157.2716,
|
| 96 |
+
"eval_samples_per_second": 183.898,
|
| 97 |
+
"eval_steps_per_second": 22.992,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.97,
|
| 102 |
+
"learning_rate": 0.00016128889503526483,
|
| 103 |
+
"loss": 8.0638,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.97,
|
| 108 |
+
"eval_accuracy": 0.002835211949381094,
|
| 109 |
+
"eval_loss": 7.992447376251221,
|
| 110 |
+
"eval_runtime": 156.9147,
|
| 111 |
+
"eval_samples_per_second": 184.317,
|
| 112 |
+
"eval_steps_per_second": 23.044,
|
| 113 |
+
"step": 7000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.11,
|
| 117 |
+
"learning_rate": 0.00015575715668648873,
|
| 118 |
+
"loss": 7.8485,
|
| 119 |
+
"step": 8000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.11,
|
| 123 |
+
"eval_accuracy": 0.0036304543254270104,
|
| 124 |
+
"eval_loss": 7.836571216583252,
|
| 125 |
+
"eval_runtime": 155.7627,
|
| 126 |
+
"eval_samples_per_second": 185.68,
|
| 127 |
+
"eval_steps_per_second": 23.215,
|
| 128 |
+
"step": 8000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.24,
|
| 132 |
+
"learning_rate": 0.00015022541833771265,
|
| 133 |
+
"loss": 7.6933,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.24,
|
| 138 |
+
"eval_accuracy": 0.004494848212433442,
|
| 139 |
+
"eval_loss": 7.659491062164307,
|
| 140 |
+
"eval_runtime": 156.4028,
|
| 141 |
+
"eval_samples_per_second": 184.92,
|
| 142 |
+
"eval_steps_per_second": 23.12,
|
| 143 |
+
"step": 9000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.38,
|
| 147 |
+
"learning_rate": 0.00014469367998893652,
|
| 148 |
+
"loss": 7.5808,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.38,
|
| 153 |
+
"eval_accuracy": 0.00615448447548579,
|
| 154 |
+
"eval_loss": 7.523160934448242,
|
| 155 |
+
"eval_runtime": 155.1944,
|
| 156 |
+
"eval_samples_per_second": 186.36,
|
| 157 |
+
"eval_steps_per_second": 23.3,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.52,
|
| 162 |
+
"learning_rate": 0.0001391674733785092,
|
| 163 |
+
"loss": 7.4352,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.52,
|
| 168 |
+
"eval_accuracy": 0.00701887836249222,
|
| 169 |
+
"eval_loss": 7.381638526916504,
|
| 170 |
+
"eval_runtime": 156.5342,
|
| 171 |
+
"eval_samples_per_second": 184.765,
|
| 172 |
+
"eval_steps_per_second": 23.1,
|
| 173 |
+
"step": 11000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.66,
|
| 177 |
+
"learning_rate": 0.0001336357350297331,
|
| 178 |
+
"loss": 7.3279,
|
| 179 |
+
"step": 12000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.66,
|
| 183 |
+
"eval_accuracy": 0.008436484337182767,
|
| 184 |
+
"eval_loss": 7.285288333892822,
|
| 185 |
+
"eval_runtime": 157.1769,
|
| 186 |
+
"eval_samples_per_second": 184.009,
|
| 187 |
+
"eval_steps_per_second": 23.006,
|
| 188 |
+
"step": 12000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.8,
|
| 192 |
+
"learning_rate": 0.000128103996680957,
|
| 193 |
+
"loss": 7.2141,
|
| 194 |
+
"step": 13000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.8,
|
| 198 |
+
"eval_accuracy": 0.010511029665998203,
|
| 199 |
+
"eval_loss": 7.1552510261535645,
|
| 200 |
+
"eval_runtime": 155.9751,
|
| 201 |
+
"eval_samples_per_second": 185.427,
|
| 202 |
+
"eval_steps_per_second": 23.183,
|
| 203 |
+
"step": 13000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.94,
|
| 207 |
+
"learning_rate": 0.0001225722583321809,
|
| 208 |
+
"loss": 7.151,
|
| 209 |
+
"step": 14000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.94,
|
| 213 |
+
"eval_accuracy": 0.011859484129728235,
|
| 214 |
+
"eval_loss": 7.085327625274658,
|
| 215 |
+
"eval_runtime": 156.2266,
|
| 216 |
+
"eval_samples_per_second": 185.129,
|
| 217 |
+
"eval_steps_per_second": 23.146,
|
| 218 |
+
"step": 14000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.07,
|
| 222 |
+
"learning_rate": 0.00011704605172175355,
|
| 223 |
+
"loss": 6.9695,
|
| 224 |
+
"step": 15000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.07,
|
| 228 |
+
"eval_accuracy": 0.013380817370859553,
|
| 229 |
+
"eval_loss": 7.008819103240967,
|
| 230 |
+
"eval_runtime": 155.749,
|
| 231 |
+
"eval_samples_per_second": 185.696,
|
| 232 |
+
"eval_steps_per_second": 23.217,
|
| 233 |
+
"step": 15000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.21,
|
| 237 |
+
"learning_rate": 0.00011151984511132624,
|
| 238 |
+
"loss": 6.8563,
|
| 239 |
+
"step": 16000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.21,
|
| 243 |
+
"eval_accuracy": 0.013934029458543669,
|
| 244 |
+
"eval_loss": 6.940927982330322,
|
| 245 |
+
"eval_runtime": 155.6806,
|
| 246 |
+
"eval_samples_per_second": 185.778,
|
| 247 |
+
"eval_steps_per_second": 23.227,
|
| 248 |
+
"step": 16000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.35,
|
| 252 |
+
"learning_rate": 0.00010598810676255014,
|
| 253 |
+
"loss": 6.8019,
|
| 254 |
+
"step": 17000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.35,
|
| 258 |
+
"eval_accuracy": 0.01583569600995782,
|
| 259 |
+
"eval_loss": 6.863400936126709,
|
| 260 |
+
"eval_runtime": 156.1188,
|
| 261 |
+
"eval_samples_per_second": 185.256,
|
| 262 |
+
"eval_steps_per_second": 23.162,
|
| 263 |
+
"step": 17000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.49,
|
| 267 |
+
"learning_rate": 0.00010045636841377403,
|
| 268 |
+
"loss": 6.7372,
|
| 269 |
+
"step": 18000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.49,
|
| 273 |
+
"eval_accuracy": 0.017495332273010165,
|
| 274 |
+
"eval_loss": 6.800116539001465,
|
| 275 |
+
"eval_runtime": 156.6848,
|
| 276 |
+
"eval_samples_per_second": 184.587,
|
| 277 |
+
"eval_steps_per_second": 23.078,
|
| 278 |
+
"step": 18000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.63,
|
| 282 |
+
"learning_rate": 9.492463006499794e-05,
|
| 283 |
+
"loss": 6.6903,
|
| 284 |
+
"step": 19000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.63,
|
| 288 |
+
"eval_accuracy": 0.019120392780582255,
|
| 289 |
+
"eval_loss": 6.7322998046875,
|
| 290 |
+
"eval_runtime": 156.774,
|
| 291 |
+
"eval_samples_per_second": 184.482,
|
| 292 |
+
"eval_steps_per_second": 23.065,
|
| 293 |
+
"step": 19000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.77,
|
| 297 |
+
"learning_rate": 8.93984234545706e-05,
|
| 298 |
+
"loss": 6.6482,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.77,
|
| 303 |
+
"eval_accuracy": 0.020710877532674088,
|
| 304 |
+
"eval_loss": 6.66375732421875,
|
| 305 |
+
"eval_runtime": 156.4579,
|
| 306 |
+
"eval_samples_per_second": 184.855,
|
| 307 |
+
"eval_steps_per_second": 23.112,
|
| 308 |
+
"step": 20000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.9,
|
| 312 |
+
"learning_rate": 8.38666851057945e-05,
|
| 313 |
+
"loss": 6.5669,
|
| 314 |
+
"step": 21000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.9,
|
| 318 |
+
"eval_accuracy": 0.023891847036857754,
|
| 319 |
+
"eval_loss": 6.609040260314941,
|
| 320 |
+
"eval_runtime": 155.2279,
|
| 321 |
+
"eval_samples_per_second": 186.32,
|
| 322 |
+
"eval_steps_per_second": 23.295,
|
| 323 |
+
"step": 21000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.04,
|
| 327 |
+
"learning_rate": 7.834047849536717e-05,
|
| 328 |
+
"loss": 6.4484,
|
| 329 |
+
"step": 22000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.04,
|
| 333 |
+
"eval_accuracy": 0.023995574303298527,
|
| 334 |
+
"eval_loss": 6.544083595275879,
|
| 335 |
+
"eval_runtime": 155.967,
|
| 336 |
+
"eval_samples_per_second": 185.437,
|
| 337 |
+
"eval_steps_per_second": 23.184,
|
| 338 |
+
"step": 22000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.18,
|
| 342 |
+
"learning_rate": 7.281427188493984e-05,
|
| 343 |
+
"loss": 6.2568,
|
| 344 |
+
"step": 23000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.18,
|
| 348 |
+
"eval_accuracy": 0.02734942258488348,
|
| 349 |
+
"eval_loss": 6.501514911651611,
|
| 350 |
+
"eval_runtime": 156.6432,
|
| 351 |
+
"eval_samples_per_second": 184.636,
|
| 352 |
+
"eval_steps_per_second": 23.084,
|
| 353 |
+
"step": 23000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.32,
|
| 357 |
+
"learning_rate": 6.728253353616373e-05,
|
| 358 |
+
"loss": 6.2452,
|
| 359 |
+
"step": 24000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.32,
|
| 363 |
+
"eval_accuracy": 0.030426664822626376,
|
| 364 |
+
"eval_loss": 6.458929061889648,
|
| 365 |
+
"eval_runtime": 156.5343,
|
| 366 |
+
"eval_samples_per_second": 184.765,
|
| 367 |
+
"eval_steps_per_second": 23.1,
|
| 368 |
+
"step": 24000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.46,
|
| 372 |
+
"learning_rate": 6.175632692573642e-05,
|
| 373 |
+
"loss": 6.2002,
|
| 374 |
+
"step": 25000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.46,
|
| 378 |
+
"eval_accuracy": 0.031049028421271004,
|
| 379 |
+
"eval_loss": 6.431183815002441,
|
| 380 |
+
"eval_runtime": 156.3543,
|
| 381 |
+
"eval_samples_per_second": 184.977,
|
| 382 |
+
"eval_steps_per_second": 23.127,
|
| 383 |
+
"step": 25000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.6,
|
| 387 |
+
"learning_rate": 5.622458857696031e-05,
|
| 388 |
+
"loss": 6.1699,
|
| 389 |
+
"step": 26000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.6,
|
| 393 |
+
"eval_accuracy": 0.03194799806375769,
|
| 394 |
+
"eval_loss": 6.372282981872559,
|
| 395 |
+
"eval_runtime": 156.6121,
|
| 396 |
+
"eval_samples_per_second": 184.673,
|
| 397 |
+
"eval_steps_per_second": 23.089,
|
| 398 |
+
"step": 26000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.73,
|
| 402 |
+
"learning_rate": 5.0692850228184205e-05,
|
| 403 |
+
"loss": 6.1284,
|
| 404 |
+
"step": 27000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.73,
|
| 408 |
+
"eval_accuracy": 0.03429914943641518,
|
| 409 |
+
"eval_loss": 6.332355976104736,
|
| 410 |
+
"eval_runtime": 156.1088,
|
| 411 |
+
"eval_samples_per_second": 185.268,
|
| 412 |
+
"eval_steps_per_second": 23.163,
|
| 413 |
+
"step": 27000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.87,
|
| 417 |
+
"learning_rate": 4.516664361775688e-05,
|
| 418 |
+
"loss": 6.1186,
|
| 419 |
+
"step": 28000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.87,
|
| 423 |
+
"eval_accuracy": 0.034956088790540074,
|
| 424 |
+
"eval_loss": 6.3029093742370605,
|
| 425 |
+
"eval_runtime": 154.5904,
|
| 426 |
+
"eval_samples_per_second": 187.088,
|
| 427 |
+
"eval_steps_per_second": 23.391,
|
| 428 |
+
"step": 28000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.01,
|
| 432 |
+
"learning_rate": 3.963490526898078e-05,
|
| 433 |
+
"loss": 6.0611,
|
| 434 |
+
"step": 29000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.01,
|
| 438 |
+
"eval_accuracy": 0.03810248253924348,
|
| 439 |
+
"eval_loss": 6.272293567657471,
|
| 440 |
+
"eval_runtime": 156.0431,
|
| 441 |
+
"eval_samples_per_second": 185.346,
|
| 442 |
+
"eval_steps_per_second": 23.173,
|
| 443 |
+
"step": 29000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.15,
|
| 447 |
+
"learning_rate": 3.410316692020468e-05,
|
| 448 |
+
"loss": 5.7883,
|
| 449 |
+
"step": 30000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.15,
|
| 453 |
+
"eval_accuracy": 0.03827536131664477,
|
| 454 |
+
"eval_loss": 6.252718925476074,
|
| 455 |
+
"eval_runtime": 145.8769,
|
| 456 |
+
"eval_samples_per_second": 198.263,
|
| 457 |
+
"eval_steps_per_second": 24.788,
|
| 458 |
+
"step": 30000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.29,
|
| 462 |
+
"learning_rate": 2.8576960309777352e-05,
|
| 463 |
+
"loss": 5.7684,
|
| 464 |
+
"step": 31000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.29,
|
| 468 |
+
"eval_accuracy": 0.03924348247009197,
|
| 469 |
+
"eval_loss": 6.218559741973877,
|
| 470 |
+
"eval_runtime": 146.1199,
|
| 471 |
+
"eval_samples_per_second": 197.933,
|
| 472 |
+
"eval_steps_per_second": 24.747,
|
| 473 |
+
"step": 31000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.43,
|
| 477 |
+
"learning_rate": 2.3045221961001246e-05,
|
| 478 |
+
"loss": 5.7701,
|
| 479 |
+
"step": 32000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.43,
|
| 483 |
+
"eval_accuracy": 0.04031533088997995,
|
| 484 |
+
"eval_loss": 6.203105926513672,
|
| 485 |
+
"eval_runtime": 145.5537,
|
| 486 |
+
"eval_samples_per_second": 198.703,
|
| 487 |
+
"eval_steps_per_second": 24.843,
|
| 488 |
+
"step": 32000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.56,
|
| 492 |
+
"learning_rate": 1.751901535057392e-05,
|
| 493 |
+
"loss": 5.7473,
|
| 494 |
+
"step": 33000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.56,
|
| 498 |
+
"eval_accuracy": 0.04304681557292027,
|
| 499 |
+
"eval_loss": 6.177652359008789,
|
| 500 |
+
"eval_runtime": 145.7844,
|
| 501 |
+
"eval_samples_per_second": 198.389,
|
| 502 |
+
"eval_steps_per_second": 24.804,
|
| 503 |
+
"step": 33000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.7,
|
| 507 |
+
"learning_rate": 1.1987277001797816e-05,
|
| 508 |
+
"loss": 5.735,
|
| 509 |
+
"step": 34000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.7,
|
| 513 |
+
"eval_accuracy": 0.044187815503768754,
|
| 514 |
+
"eval_loss": 6.163440704345703,
|
| 515 |
+
"eval_runtime": 146.1075,
|
| 516 |
+
"eval_samples_per_second": 197.95,
|
| 517 |
+
"eval_steps_per_second": 24.749,
|
| 518 |
+
"step": 34000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.84,
|
| 522 |
+
"learning_rate": 6.455538653021713e-06,
|
| 523 |
+
"loss": 5.7324,
|
| 524 |
+
"step": 35000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.84,
|
| 528 |
+
"eval_accuracy": 0.04429154277020953,
|
| 529 |
+
"eval_loss": 6.149352073669434,
|
| 530 |
+
"eval_runtime": 145.8359,
|
| 531 |
+
"eval_samples_per_second": 198.319,
|
| 532 |
+
"eval_steps_per_second": 24.795,
|
| 533 |
+
"step": 35000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.98,
|
| 537 |
+
"learning_rate": 9.238003042456093e-07,
|
| 538 |
+
"loss": 5.6949,
|
| 539 |
+
"step": 36000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.98,
|
| 543 |
+
"eval_accuracy": 0.044844754857893646,
|
| 544 |
+
"eval_loss": 6.141994476318359,
|
| 545 |
+
"eval_runtime": 145.8687,
|
| 546 |
+
"eval_samples_per_second": 198.274,
|
| 547 |
+
"eval_steps_per_second": 24.789,
|
| 548 |
+
"step": 36000
|
| 549 |
+
},
|
| 550 |
{
|
| 551 |
"epoch": 5.0,
|
| 552 |
+
"step": 36155,
|
| 553 |
+
"total_flos": 9.416417849072317e+19,
|
| 554 |
+
"train_loss": 6.8843976465667565,
|
| 555 |
+
"train_runtime": 17474.7904,
|
| 556 |
+
"train_samples_per_second": 66.203,
|
| 557 |
+
"train_steps_per_second": 2.069
|
| 558 |
}
|
| 559 |
],
|
| 560 |
+
"max_steps": 36155,
|
| 561 |
"num_train_epochs": 5,
|
| 562 |
+
"total_flos": 9.416417849072317e+19,
|
| 563 |
"trial_name": null,
|
| 564 |
"trial_params": null
|
| 565 |
}
|