Commit
•
a582353
1
Parent(s):
dd92ecc
Training in progress, epoch 0
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.044444444444444,
|
| 3 |
+
"eval_accuracy": 0.7948717948717948,
|
| 4 |
+
"eval_loss": 1.3669681549072266,
|
| 5 |
+
"eval_runtime": 15.6538,
|
| 6 |
+
"eval_samples_per_second": 2.491,
|
| 7 |
+
"eval_steps_per_second": 1.278
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344940444
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55667667e8df224b0a3746476db020d4d0683a0b73de70a4e27a360671061ca8
|
| 3 |
size 344940444
|
runs/Apr24_19-09-46_e0d26c525230/events.out.tfevents.1713987155.e0d26c525230.685.1
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 sha256:65ebcd04e3a848ac21a1bfb722d5244d1f4939efb04338bce171ff036493ec5f
|
| 3 |
+
size 734
|
runs/Apr24_19-56-38_e0d26c525230/events.out.tfevents.1713988636.e0d26c525230.685.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2500dc365b725090a3a044884982aa61b6324b0ab2f5c3271f620d58ea0f6b07
|
| 3 |
+
size 6207
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.044444444444444,
|
| 3 |
+
"eval_accuracy": 0.7948717948717948,
|
| 4 |
+
"eval_loss": 1.3669681549072266,
|
| 5 |
+
"eval_runtime": 15.6538,
|
| 6 |
+
"eval_samples_per_second": 2.491,
|
| 7 |
+
"eval_steps_per_second": 1.278
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8333333333333334,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-ssbd-trim-yolo/checkpoint-344",
|
| 4 |
+
"epoch": 14.044444444444444,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 630,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.015873015873015872,
|
| 13 |
+
"grad_norm": 30.015491485595703,
|
| 14 |
+
"learning_rate": 7.936507936507936e-06,
|
| 15 |
+
"loss": 1.0764,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.031746031746031744,
|
| 20 |
+
"grad_norm": 22.576404571533203,
|
| 21 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 22 |
+
"loss": 1.1431,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.047619047619047616,
|
| 27 |
+
"grad_norm": 20.933401107788086,
|
| 28 |
+
"learning_rate": 2.380952380952381e-05,
|
| 29 |
+
"loss": 1.106,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06349206349206349,
|
| 34 |
+
"grad_norm": 10.277111053466797,
|
| 35 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 36 |
+
"loss": 0.9077,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06825396825396825,
|
| 41 |
+
"eval_accuracy": 0.5277777777777778,
|
| 42 |
+
"eval_loss": 1.1113542318344116,
|
| 43 |
+
"eval_runtime": 14.5432,
|
| 44 |
+
"eval_samples_per_second": 2.475,
|
| 45 |
+
"eval_steps_per_second": 1.238,
|
| 46 |
+
"step": 43
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.011111111111111,
|
| 50 |
+
"grad_norm": 15.602046012878418,
|
| 51 |
+
"learning_rate": 3.968253968253968e-05,
|
| 52 |
+
"loss": 1.2326,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.0269841269841269,
|
| 57 |
+
"grad_norm": 13.100045204162598,
|
| 58 |
+
"learning_rate": 4.761904761904762e-05,
|
| 59 |
+
"loss": 1.0985,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.042857142857143,
|
| 64 |
+
"grad_norm": 14.066707611083984,
|
| 65 |
+
"learning_rate": 4.938271604938271e-05,
|
| 66 |
+
"loss": 1.1182,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.0587301587301587,
|
| 71 |
+
"grad_norm": 12.698005676269531,
|
| 72 |
+
"learning_rate": 4.850088183421517e-05,
|
| 73 |
+
"loss": 1.0662,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0682539682539682,
|
| 78 |
+
"eval_accuracy": 0.25,
|
| 79 |
+
"eval_loss": 1.4397388696670532,
|
| 80 |
+
"eval_runtime": 14.9962,
|
| 81 |
+
"eval_samples_per_second": 2.401,
|
| 82 |
+
"eval_steps_per_second": 1.2,
|
| 83 |
+
"step": 86
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.0063492063492063,
|
| 87 |
+
"grad_norm": 8.443410873413086,
|
| 88 |
+
"learning_rate": 4.761904761904762e-05,
|
| 89 |
+
"loss": 1.1849,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.022222222222222,
|
| 94 |
+
"grad_norm": 29.700166702270508,
|
| 95 |
+
"learning_rate": 4.673721340388007e-05,
|
| 96 |
+
"loss": 0.8618,
|
| 97 |
+
"step": 100
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.038095238095238,
|
| 101 |
+
"grad_norm": 8.657772064208984,
|
| 102 |
+
"learning_rate": 4.585537918871252e-05,
|
| 103 |
+
"loss": 0.8981,
|
| 104 |
+
"step": 110
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0539682539682538,
|
| 108 |
+
"grad_norm": 14.876176834106445,
|
| 109 |
+
"learning_rate": 4.4973544973544974e-05,
|
| 110 |
+
"loss": 0.7166,
|
| 111 |
+
"step": 120
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0682539682539685,
|
| 115 |
+
"eval_accuracy": 0.5555555555555556,
|
| 116 |
+
"eval_loss": 1.1110920906066895,
|
| 117 |
+
"eval_runtime": 15.0737,
|
| 118 |
+
"eval_samples_per_second": 2.388,
|
| 119 |
+
"eval_steps_per_second": 1.194,
|
| 120 |
+
"step": 129
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.0015873015873016,
|
| 124 |
+
"grad_norm": 23.024181365966797,
|
| 125 |
+
"learning_rate": 4.409171075837743e-05,
|
| 126 |
+
"loss": 0.9402,
|
| 127 |
+
"step": 130
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.0174603174603174,
|
| 131 |
+
"grad_norm": 10.229450225830078,
|
| 132 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 133 |
+
"loss": 0.9261,
|
| 134 |
+
"step": 140
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.033333333333333,
|
| 138 |
+
"grad_norm": 0.9213091135025024,
|
| 139 |
+
"learning_rate": 4.232804232804233e-05,
|
| 140 |
+
"loss": 0.73,
|
| 141 |
+
"step": 150
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.049206349206349,
|
| 145 |
+
"grad_norm": 6.072920322418213,
|
| 146 |
+
"learning_rate": 4.144620811287478e-05,
|
| 147 |
+
"loss": 1.2687,
|
| 148 |
+
"step": 160
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.0650793650793653,
|
| 152 |
+
"grad_norm": 15.582525253295898,
|
| 153 |
+
"learning_rate": 4.056437389770723e-05,
|
| 154 |
+
"loss": 0.5385,
|
| 155 |
+
"step": 170
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.0682539682539685,
|
| 159 |
+
"eval_accuracy": 0.6111111111111112,
|
| 160 |
+
"eval_loss": 1.46772301197052,
|
| 161 |
+
"eval_runtime": 16.2266,
|
| 162 |
+
"eval_samples_per_second": 2.219,
|
| 163 |
+
"eval_steps_per_second": 1.109,
|
| 164 |
+
"step": 172
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.012698412698413,
|
| 168 |
+
"grad_norm": 0.8077548742294312,
|
| 169 |
+
"learning_rate": 3.968253968253968e-05,
|
| 170 |
+
"loss": 1.1557,
|
| 171 |
+
"step": 180
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.0285714285714285,
|
| 175 |
+
"grad_norm": 0.7511183619499207,
|
| 176 |
+
"learning_rate": 3.8800705467372136e-05,
|
| 177 |
+
"loss": 0.7099,
|
| 178 |
+
"step": 190
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.044444444444444,
|
| 182 |
+
"grad_norm": 5.223026752471924,
|
| 183 |
+
"learning_rate": 3.791887125220458e-05,
|
| 184 |
+
"loss": 0.5282,
|
| 185 |
+
"step": 200
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.06031746031746,
|
| 189 |
+
"grad_norm": 8.660394668579102,
|
| 190 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 191 |
+
"loss": 0.5025,
|
| 192 |
+
"step": 210
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.068253968253968,
|
| 196 |
+
"eval_accuracy": 0.6666666666666666,
|
| 197 |
+
"eval_loss": 1.3852248191833496,
|
| 198 |
+
"eval_runtime": 14.7477,
|
| 199 |
+
"eval_samples_per_second": 2.441,
|
| 200 |
+
"eval_steps_per_second": 1.221,
|
| 201 |
+
"step": 215
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.007936507936508,
|
| 205 |
+
"grad_norm": 0.08930220454931259,
|
| 206 |
+
"learning_rate": 3.615520282186949e-05,
|
| 207 |
+
"loss": 0.8413,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.023809523809524,
|
| 212 |
+
"grad_norm": 12.50485610961914,
|
| 213 |
+
"learning_rate": 3.527336860670194e-05,
|
| 214 |
+
"loss": 0.3356,
|
| 215 |
+
"step": 230
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.0396825396825395,
|
| 219 |
+
"grad_norm": 1.2022631168365479,
|
| 220 |
+
"learning_rate": 3.439153439153439e-05,
|
| 221 |
+
"loss": 0.5643,
|
| 222 |
+
"step": 240
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.055555555555555,
|
| 226 |
+
"grad_norm": 0.06211042404174805,
|
| 227 |
+
"learning_rate": 3.3509700176366844e-05,
|
| 228 |
+
"loss": 0.8695,
|
| 229 |
+
"step": 250
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.068253968253968,
|
| 233 |
+
"eval_accuracy": 0.8055555555555556,
|
| 234 |
+
"eval_loss": 0.8737678527832031,
|
| 235 |
+
"eval_runtime": 15.6375,
|
| 236 |
+
"eval_samples_per_second": 2.302,
|
| 237 |
+
"eval_steps_per_second": 1.151,
|
| 238 |
+
"step": 258
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 6.003174603174603,
|
| 242 |
+
"grad_norm": 0.12375453114509583,
|
| 243 |
+
"learning_rate": 3.262786596119929e-05,
|
| 244 |
+
"loss": 0.0653,
|
| 245 |
+
"step": 260
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 6.019047619047619,
|
| 249 |
+
"grad_norm": 316.117919921875,
|
| 250 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 251 |
+
"loss": 0.2375,
|
| 252 |
+
"step": 270
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.034920634920635,
|
| 256 |
+
"grad_norm": 248.5700225830078,
|
| 257 |
+
"learning_rate": 3.08641975308642e-05,
|
| 258 |
+
"loss": 0.7338,
|
| 259 |
+
"step": 280
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.050793650793651,
|
| 263 |
+
"grad_norm": 2.953540802001953,
|
| 264 |
+
"learning_rate": 2.998236331569665e-05,
|
| 265 |
+
"loss": 0.2325,
|
| 266 |
+
"step": 290
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.066666666666666,
|
| 270 |
+
"grad_norm": 0.8457281589508057,
|
| 271 |
+
"learning_rate": 2.91005291005291e-05,
|
| 272 |
+
"loss": 0.5152,
|
| 273 |
+
"step": 300
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.068253968253968,
|
| 277 |
+
"eval_accuracy": 0.6944444444444444,
|
| 278 |
+
"eval_loss": 1.6813074350357056,
|
| 279 |
+
"eval_runtime": 15.1352,
|
| 280 |
+
"eval_samples_per_second": 2.379,
|
| 281 |
+
"eval_steps_per_second": 1.189,
|
| 282 |
+
"step": 301
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.014285714285714,
|
| 286 |
+
"grad_norm": 0.029814492911100388,
|
| 287 |
+
"learning_rate": 2.8218694885361552e-05,
|
| 288 |
+
"loss": 0.4158,
|
| 289 |
+
"step": 310
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 7.03015873015873,
|
| 293 |
+
"grad_norm": 0.041262779384851456,
|
| 294 |
+
"learning_rate": 2.7336860670194003e-05,
|
| 295 |
+
"loss": 0.4212,
|
| 296 |
+
"step": 320
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.046031746031746,
|
| 300 |
+
"grad_norm": 107.87213134765625,
|
| 301 |
+
"learning_rate": 2.6455026455026456e-05,
|
| 302 |
+
"loss": 0.2547,
|
| 303 |
+
"step": 330
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.061904761904762,
|
| 307 |
+
"grad_norm": 0.03740064427256584,
|
| 308 |
+
"learning_rate": 2.5573192239858906e-05,
|
| 309 |
+
"loss": 0.1175,
|
| 310 |
+
"step": 340
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 7.068253968253968,
|
| 314 |
+
"eval_accuracy": 0.8333333333333334,
|
| 315 |
+
"eval_loss": 1.226004719734192,
|
| 316 |
+
"eval_runtime": 15.2787,
|
| 317 |
+
"eval_samples_per_second": 2.356,
|
| 318 |
+
"eval_steps_per_second": 1.178,
|
| 319 |
+
"step": 344
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 8.00952380952381,
|
| 323 |
+
"grad_norm": 0.02109268307685852,
|
| 324 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 325 |
+
"loss": 0.0097,
|
| 326 |
+
"step": 350
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.025396825396825,
|
| 330 |
+
"grad_norm": 0.08379709720611572,
|
| 331 |
+
"learning_rate": 2.380952380952381e-05,
|
| 332 |
+
"loss": 0.0013,
|
| 333 |
+
"step": 360
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 8.041269841269841,
|
| 337 |
+
"grad_norm": 1.6022357940673828,
|
| 338 |
+
"learning_rate": 2.292768959435626e-05,
|
| 339 |
+
"loss": 0.3725,
|
| 340 |
+
"step": 370
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.057142857142857,
|
| 344 |
+
"grad_norm": 74.2785415649414,
|
| 345 |
+
"learning_rate": 2.2045855379188714e-05,
|
| 346 |
+
"loss": 0.5459,
|
| 347 |
+
"step": 380
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 8.068253968253968,
|
| 351 |
+
"eval_accuracy": 0.75,
|
| 352 |
+
"eval_loss": 1.5197035074234009,
|
| 353 |
+
"eval_runtime": 15.1279,
|
| 354 |
+
"eval_samples_per_second": 2.38,
|
| 355 |
+
"eval_steps_per_second": 1.19,
|
| 356 |
+
"step": 387
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 9.004761904761905,
|
| 360 |
+
"grad_norm": 0.024311769753694534,
|
| 361 |
+
"learning_rate": 2.1164021164021164e-05,
|
| 362 |
+
"loss": 0.2267,
|
| 363 |
+
"step": 390
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 9.02063492063492,
|
| 367 |
+
"grad_norm": 0.052084945142269135,
|
| 368 |
+
"learning_rate": 2.0282186948853614e-05,
|
| 369 |
+
"loss": 0.3809,
|
| 370 |
+
"step": 400
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 9.036507936507936,
|
| 374 |
+
"grad_norm": 88.70760345458984,
|
| 375 |
+
"learning_rate": 1.9400352733686068e-05,
|
| 376 |
+
"loss": 0.0571,
|
| 377 |
+
"step": 410
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 9.052380952380952,
|
| 381 |
+
"grad_norm": 0.028513841331005096,
|
| 382 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 383 |
+
"loss": 0.0024,
|
| 384 |
+
"step": 420
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.068253968253968,
|
| 388 |
+
"grad_norm": 378.1549072265625,
|
| 389 |
+
"learning_rate": 1.763668430335097e-05,
|
| 390 |
+
"loss": 0.0563,
|
| 391 |
+
"step": 430
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 9.068253968253968,
|
| 395 |
+
"eval_accuracy": 0.7222222222222222,
|
| 396 |
+
"eval_loss": 1.8295029401779175,
|
| 397 |
+
"eval_runtime": 15.283,
|
| 398 |
+
"eval_samples_per_second": 2.356,
|
| 399 |
+
"eval_steps_per_second": 1.178,
|
| 400 |
+
"step": 430
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 10.015873015873016,
|
| 404 |
+
"grad_norm": 0.03957889601588249,
|
| 405 |
+
"learning_rate": 1.6754850088183422e-05,
|
| 406 |
+
"loss": 0.0009,
|
| 407 |
+
"step": 440
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 10.031746031746032,
|
| 411 |
+
"grad_norm": 0.02481396682560444,
|
| 412 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 413 |
+
"loss": 0.2516,
|
| 414 |
+
"step": 450
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.047619047619047,
|
| 418 |
+
"grad_norm": 0.0098341079428792,
|
| 419 |
+
"learning_rate": 1.4991181657848324e-05,
|
| 420 |
+
"loss": 0.0012,
|
| 421 |
+
"step": 460
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 10.063492063492063,
|
| 425 |
+
"grad_norm": 0.011684373952448368,
|
| 426 |
+
"learning_rate": 1.4109347442680776e-05,
|
| 427 |
+
"loss": 0.2366,
|
| 428 |
+
"step": 470
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 10.068253968253968,
|
| 432 |
+
"eval_accuracy": 0.7777777777777778,
|
| 433 |
+
"eval_loss": 1.277262806892395,
|
| 434 |
+
"eval_runtime": 15.161,
|
| 435 |
+
"eval_samples_per_second": 2.375,
|
| 436 |
+
"eval_steps_per_second": 1.187,
|
| 437 |
+
"step": 473
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 11.011111111111111,
|
| 441 |
+
"grad_norm": 0.07974599301815033,
|
| 442 |
+
"learning_rate": 1.3227513227513228e-05,
|
| 443 |
+
"loss": 0.2535,
|
| 444 |
+
"step": 480
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 11.026984126984127,
|
| 448 |
+
"grad_norm": 0.012509225867688656,
|
| 449 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 450 |
+
"loss": 0.0955,
|
| 451 |
+
"step": 490
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 11.042857142857143,
|
| 455 |
+
"grad_norm": 0.019364865496754646,
|
| 456 |
+
"learning_rate": 1.146384479717813e-05,
|
| 457 |
+
"loss": 0.3646,
|
| 458 |
+
"step": 500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 11.058730158730159,
|
| 462 |
+
"grad_norm": 0.011683164164423943,
|
| 463 |
+
"learning_rate": 1.0582010582010582e-05,
|
| 464 |
+
"loss": 0.0009,
|
| 465 |
+
"step": 510
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 11.068253968253968,
|
| 469 |
+
"eval_accuracy": 0.7777777777777778,
|
| 470 |
+
"eval_loss": 1.4972862005233765,
|
| 471 |
+
"eval_runtime": 15.1317,
|
| 472 |
+
"eval_samples_per_second": 2.379,
|
| 473 |
+
"eval_steps_per_second": 1.19,
|
| 474 |
+
"step": 516
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 12.006349206349206,
|
| 478 |
+
"grad_norm": 0.06486235558986664,
|
| 479 |
+
"learning_rate": 9.700176366843034e-06,
|
| 480 |
+
"loss": 0.0008,
|
| 481 |
+
"step": 520
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 12.022222222222222,
|
| 485 |
+
"grad_norm": 0.014630606397986412,
|
| 486 |
+
"learning_rate": 8.818342151675484e-06,
|
| 487 |
+
"loss": 0.0007,
|
| 488 |
+
"step": 530
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 12.038095238095238,
|
| 492 |
+
"grad_norm": 0.011189568787813187,
|
| 493 |
+
"learning_rate": 7.936507936507936e-06,
|
| 494 |
+
"loss": 0.0007,
|
| 495 |
+
"step": 540
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 12.053968253968254,
|
| 499 |
+
"grad_norm": 249.22251892089844,
|
| 500 |
+
"learning_rate": 7.054673721340388e-06,
|
| 501 |
+
"loss": 0.143,
|
| 502 |
+
"step": 550
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 12.068253968253968,
|
| 506 |
+
"eval_accuracy": 0.7777777777777778,
|
| 507 |
+
"eval_loss": 1.5192021131515503,
|
| 508 |
+
"eval_runtime": 12.5425,
|
| 509 |
+
"eval_samples_per_second": 2.87,
|
| 510 |
+
"eval_steps_per_second": 1.435,
|
| 511 |
+
"step": 559
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 13.001587301587302,
|
| 515 |
+
"grad_norm": 0.01595219597220421,
|
| 516 |
+
"learning_rate": 6.172839506172839e-06,
|
| 517 |
+
"loss": 0.5178,
|
| 518 |
+
"step": 560
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 13.017460317460317,
|
| 522 |
+
"grad_norm": 0.036659013479948044,
|
| 523 |
+
"learning_rate": 5.291005291005291e-06,
|
| 524 |
+
"loss": 0.0018,
|
| 525 |
+
"step": 570
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 13.033333333333333,
|
| 529 |
+
"grad_norm": 196.40771484375,
|
| 530 |
+
"learning_rate": 4.409171075837742e-06,
|
| 531 |
+
"loss": 0.0321,
|
| 532 |
+
"step": 580
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 13.049206349206349,
|
| 536 |
+
"grad_norm": 0.029025763273239136,
|
| 537 |
+
"learning_rate": 3.527336860670194e-06,
|
| 538 |
+
"loss": 0.2369,
|
| 539 |
+
"step": 590
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 13.065079365079365,
|
| 543 |
+
"grad_norm": 1.3874189853668213,
|
| 544 |
+
"learning_rate": 2.6455026455026455e-06,
|
| 545 |
+
"loss": 0.0016,
|
| 546 |
+
"step": 600
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 13.068253968253968,
|
| 550 |
+
"eval_accuracy": 0.7222222222222222,
|
| 551 |
+
"eval_loss": 1.863442301750183,
|
| 552 |
+
"eval_runtime": 12.833,
|
| 553 |
+
"eval_samples_per_second": 2.805,
|
| 554 |
+
"eval_steps_per_second": 1.403,
|
| 555 |
+
"step": 602
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 14.012698412698413,
|
| 559 |
+
"grad_norm": 0.008897276595234871,
|
| 560 |
+
"learning_rate": 1.763668430335097e-06,
|
| 561 |
+
"loss": 0.0009,
|
| 562 |
+
"step": 610
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 14.028571428571428,
|
| 566 |
+
"grad_norm": 0.016890566796064377,
|
| 567 |
+
"learning_rate": 8.818342151675485e-07,
|
| 568 |
+
"loss": 0.0915,
|
| 569 |
+
"step": 620
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 14.044444444444444,
|
| 573 |
+
"grad_norm": 0.010226339101791382,
|
| 574 |
+
"learning_rate": 0.0,
|
| 575 |
+
"loss": 0.0185,
|
| 576 |
+
"step": 630
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 14.044444444444444,
|
| 580 |
+
"eval_accuracy": 0.7222222222222222,
|
| 581 |
+
"eval_loss": 1.8942972421646118,
|
| 582 |
+
"eval_runtime": 13.2569,
|
| 583 |
+
"eval_samples_per_second": 2.716,
|
| 584 |
+
"eval_steps_per_second": 1.358,
|
| 585 |
+
"step": 630
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 14.044444444444444,
|
| 589 |
+
"step": 630,
|
| 590 |
+
"total_flos": 1.5526103247553167e+18,
|
| 591 |
+
"train_loss": 0.4637793370005157,
|
| 592 |
+
"train_runtime": 1134.0988,
|
| 593 |
+
"train_samples_per_second": 1.111,
|
| 594 |
+
"train_steps_per_second": 0.556
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.044444444444444,
|
| 598 |
+
"eval_accuracy": 0.7948717948717948,
|
| 599 |
+
"eval_loss": 1.3669681549072266,
|
| 600 |
+
"eval_runtime": 16.5385,
|
| 601 |
+
"eval_samples_per_second": 2.358,
|
| 602 |
+
"eval_steps_per_second": 1.209,
|
| 603 |
+
"step": 630
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 14.044444444444444,
|
| 607 |
+
"eval_accuracy": 0.7948717948717948,
|
| 608 |
+
"eval_loss": 1.3669681549072266,
|
| 609 |
+
"eval_runtime": 15.6538,
|
| 610 |
+
"eval_samples_per_second": 2.491,
|
| 611 |
+
"eval_steps_per_second": 1.278,
|
| 612 |
+
"step": 630
|
| 613 |
+
}
|
| 614 |
+
],
|
| 615 |
+
"logging_steps": 10,
|
| 616 |
+
"max_steps": 630,
|
| 617 |
+
"num_input_tokens_seen": 0,
|
| 618 |
+
"num_train_epochs": 9223372036854775807,
|
| 619 |
+
"save_steps": 500,
|
| 620 |
+
"total_flos": 1.5526103247553167e+18,
|
| 621 |
+
"train_batch_size": 2,
|
| 622 |
+
"trial_name": null,
|
| 623 |
+
"trial_params": null
|
| 624 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684b691e14f4b7b649a6119f7f58e6e04c7625ce4f12c09dc593cfac0494bde8
|
| 3 |
size 5048
|