Commit
•
bf850b9
1
Parent(s):
94b54bb
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May24_14-32-58_9f79468a2253/events.out.tfevents.1716569752.9f79468a2253.25.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +505 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9341269841269841
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2564
|
| 36 |
+
- Accuracy: 0.9341
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.301428412334932e+19,
|
| 4 |
+
"train_loss": 0.2947656165036288,
|
| 5 |
+
"train_runtime": 8332.2574,
|
| 6 |
+
"train_samples_per_second": 21.1,
|
| 7 |
+
"train_steps_per_second": 0.66
|
| 8 |
+
}
|
runs/May24_14-32-58_9f79468a2253/events.out.tfevents.1716569752.9f79468a2253.25.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bea237aba744e8361f2e791bccf09a899c7e4b4c01cb77ff0e310eee7ee3452
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 1.301428412334932e+19,
|
| 4 |
+
"train_loss": 0.2947656165036288,
|
| 5 |
+
"train_runtime": 8332.2574,
|
| 6 |
+
"train_samples_per_second": 21.1,
|
| 7 |
+
"train_steps_per_second": 0.66
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.26930707693099976,
|
| 3 |
+
"best_model_checkpoint": "./convnext-tiny-1e-4/checkpoint-5500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"grad_norm": 17.60952377319336,
|
| 14 |
+
"learning_rate": 9.991845519630678e-05,
|
| 15 |
+
"loss": 1.9015,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36,
|
| 20 |
+
"grad_norm": 19.555858612060547,
|
| 21 |
+
"learning_rate": 9.967408676742751e-05,
|
| 22 |
+
"loss": 0.9352,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.55,
|
| 27 |
+
"grad_norm": 14.498743057250977,
|
| 28 |
+
"learning_rate": 9.926769179238466e-05,
|
| 29 |
+
"loss": 0.7326,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.73,
|
| 34 |
+
"grad_norm": 14.032439231872559,
|
| 35 |
+
"learning_rate": 9.870059584711668e-05,
|
| 36 |
+
"loss": 0.6518,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.91,
|
| 41 |
+
"grad_norm": 13.6815767288208,
|
| 42 |
+
"learning_rate": 9.797464868072488e-05,
|
| 43 |
+
"loss": 0.5828,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.8874751491053678,
|
| 49 |
+
"eval_loss": 0.4074288010597229,
|
| 50 |
+
"eval_runtime": 70.8056,
|
| 51 |
+
"eval_samples_per_second": 35.52,
|
| 52 |
+
"eval_steps_per_second": 1.116,
|
| 53 |
+
"step": 550
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.09,
|
| 57 |
+
"grad_norm": 23.21503448486328,
|
| 58 |
+
"learning_rate": 9.709221818197624e-05,
|
| 59 |
+
"loss": 0.5615,
|
| 60 |
+
"step": 600
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.27,
|
| 64 |
+
"grad_norm": 9.002695083618164,
|
| 65 |
+
"learning_rate": 9.60561826557425e-05,
|
| 66 |
+
"loss": 0.4534,
|
| 67 |
+
"step": 700
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.45,
|
| 71 |
+
"grad_norm": 20.327482223510742,
|
| 72 |
+
"learning_rate": 9.486992143456792e-05,
|
| 73 |
+
"loss": 0.4444,
|
| 74 |
+
"step": 800
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.64,
|
| 78 |
+
"grad_norm": 9.196972846984863,
|
| 79 |
+
"learning_rate": 9.353730385598887e-05,
|
| 80 |
+
"loss": 0.4863,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.82,
|
| 85 |
+
"grad_norm": 7.924983501434326,
|
| 86 |
+
"learning_rate": 9.206267664155907e-05,
|
| 87 |
+
"loss": 0.4324,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.0,
|
| 92 |
+
"grad_norm": 12.762895584106445,
|
| 93 |
+
"learning_rate": 9.045084971874738e-05,
|
| 94 |
+
"loss": 0.4404,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.0,
|
| 99 |
+
"eval_accuracy": 0.8811133200795228,
|
| 100 |
+
"eval_loss": 0.40930676460266113,
|
| 101 |
+
"eval_runtime": 68.8533,
|
| 102 |
+
"eval_samples_per_second": 36.527,
|
| 103 |
+
"eval_steps_per_second": 1.147,
|
| 104 |
+
"step": 1100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.18,
|
| 108 |
+
"grad_norm": 14.092179298400879,
|
| 109 |
+
"learning_rate": 8.870708053195413e-05,
|
| 110 |
+
"loss": 0.3572,
|
| 111 |
+
"step": 1200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.36,
|
| 115 |
+
"grad_norm": 9.523673057556152,
|
| 116 |
+
"learning_rate": 8.683705689382024e-05,
|
| 117 |
+
"loss": 0.3574,
|
| 118 |
+
"step": 1300
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.55,
|
| 122 |
+
"grad_norm": 5.849709987640381,
|
| 123 |
+
"learning_rate": 8.484687843276469e-05,
|
| 124 |
+
"loss": 0.3547,
|
| 125 |
+
"step": 1400
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.73,
|
| 129 |
+
"grad_norm": 8.085291862487793,
|
| 130 |
+
"learning_rate": 8.274303669726426e-05,
|
| 131 |
+
"loss": 0.3713,
|
| 132 |
+
"step": 1500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.91,
|
| 136 |
+
"grad_norm": 7.404701232910156,
|
| 137 |
+
"learning_rate": 8.053239398177191e-05,
|
| 138 |
+
"loss": 0.3503,
|
| 139 |
+
"step": 1600
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 3.0,
|
| 143 |
+
"eval_accuracy": 0.9017892644135189,
|
| 144 |
+
"eval_loss": 0.33908799290657043,
|
| 145 |
+
"eval_runtime": 67.9125,
|
| 146 |
+
"eval_samples_per_second": 37.033,
|
| 147 |
+
"eval_steps_per_second": 1.163,
|
| 148 |
+
"step": 1650
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.09,
|
| 152 |
+
"grad_norm": 13.007326126098633,
|
| 153 |
+
"learning_rate": 7.822216094333847e-05,
|
| 154 |
+
"loss": 0.3168,
|
| 155 |
+
"step": 1700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.27,
|
| 159 |
+
"grad_norm": 10.012882232666016,
|
| 160 |
+
"learning_rate": 7.58198730819481e-05,
|
| 161 |
+
"loss": 0.2862,
|
| 162 |
+
"step": 1800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.45,
|
| 166 |
+
"grad_norm": 10.694050788879395,
|
| 167 |
+
"learning_rate": 7.333336616128369e-05,
|
| 168 |
+
"loss": 0.2627,
|
| 169 |
+
"step": 1900
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.64,
|
| 173 |
+
"grad_norm": 9.87967586517334,
|
| 174 |
+
"learning_rate": 7.077075065009433e-05,
|
| 175 |
+
"loss": 0.3063,
|
| 176 |
+
"step": 2000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.82,
|
| 180 |
+
"grad_norm": 10.754569053649902,
|
| 181 |
+
"learning_rate": 6.814038526753205e-05,
|
| 182 |
+
"loss": 0.2825,
|
| 183 |
+
"step": 2100
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.0,
|
| 187 |
+
"grad_norm": 9.205183029174805,
|
| 188 |
+
"learning_rate": 6.545084971874738e-05,
|
| 189 |
+
"loss": 0.2636,
|
| 190 |
+
"step": 2200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.0,
|
| 194 |
+
"eval_accuracy": 0.91610337972167,
|
| 195 |
+
"eval_loss": 0.307881236076355,
|
| 196 |
+
"eval_runtime": 67.843,
|
| 197 |
+
"eval_samples_per_second": 37.071,
|
| 198 |
+
"eval_steps_per_second": 1.164,
|
| 199 |
+
"step": 2200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.18,
|
| 203 |
+
"grad_norm": 13.164912223815918,
|
| 204 |
+
"learning_rate": 6.271091670967436e-05,
|
| 205 |
+
"loss": 0.2436,
|
| 206 |
+
"step": 2300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.36,
|
| 210 |
+
"grad_norm": 6.218183994293213,
|
| 211 |
+
"learning_rate": 5.992952333228728e-05,
|
| 212 |
+
"loss": 0.2253,
|
| 213 |
+
"step": 2400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.55,
|
| 217 |
+
"grad_norm": 13.5186128616333,
|
| 218 |
+
"learning_rate": 5.7115741913664264e-05,
|
| 219 |
+
"loss": 0.2223,
|
| 220 |
+
"step": 2500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.73,
|
| 224 |
+
"grad_norm": 15.335129737854004,
|
| 225 |
+
"learning_rate": 5.427875042394199e-05,
|
| 226 |
+
"loss": 0.2409,
|
| 227 |
+
"step": 2600
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.91,
|
| 231 |
+
"grad_norm": 4.0428643226623535,
|
| 232 |
+
"learning_rate": 5.142780253968481e-05,
|
| 233 |
+
"loss": 0.2217,
|
| 234 |
+
"step": 2700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.0,
|
| 238 |
+
"eval_accuracy": 0.9168986083499006,
|
| 239 |
+
"eval_loss": 0.30684027075767517,
|
| 240 |
+
"eval_runtime": 71.9472,
|
| 241 |
+
"eval_samples_per_second": 34.956,
|
| 242 |
+
"eval_steps_per_second": 1.098,
|
| 243 |
+
"step": 2750
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.09,
|
| 247 |
+
"grad_norm": 8.145292282104492,
|
| 248 |
+
"learning_rate": 4.85721974603152e-05,
|
| 249 |
+
"loss": 0.2155,
|
| 250 |
+
"step": 2800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 5.27,
|
| 254 |
+
"grad_norm": 17.054922103881836,
|
| 255 |
+
"learning_rate": 4.5721249576058027e-05,
|
| 256 |
+
"loss": 0.193,
|
| 257 |
+
"step": 2900
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.45,
|
| 261 |
+
"grad_norm": 5.592764377593994,
|
| 262 |
+
"learning_rate": 4.288425808633575e-05,
|
| 263 |
+
"loss": 0.1827,
|
| 264 |
+
"step": 3000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.64,
|
| 268 |
+
"grad_norm": 3.9595816135406494,
|
| 269 |
+
"learning_rate": 4.007047666771274e-05,
|
| 270 |
+
"loss": 0.1662,
|
| 271 |
+
"step": 3100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.82,
|
| 275 |
+
"grad_norm": 7.078103542327881,
|
| 276 |
+
"learning_rate": 3.728908329032567e-05,
|
| 277 |
+
"loss": 0.1985,
|
| 278 |
+
"step": 3200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.0,
|
| 282 |
+
"grad_norm": 20.20966339111328,
|
| 283 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 284 |
+
"loss": 0.2024,
|
| 285 |
+
"step": 3300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.0,
|
| 289 |
+
"eval_accuracy": 0.9284294234592445,
|
| 290 |
+
"eval_loss": 0.283940851688385,
|
| 291 |
+
"eval_runtime": 69.4245,
|
| 292 |
+
"eval_samples_per_second": 36.226,
|
| 293 |
+
"eval_steps_per_second": 1.138,
|
| 294 |
+
"step": 3300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.18,
|
| 298 |
+
"grad_norm": 6.057071208953857,
|
| 299 |
+
"learning_rate": 3.1859614732467954e-05,
|
| 300 |
+
"loss": 0.1643,
|
| 301 |
+
"step": 3400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.36,
|
| 305 |
+
"grad_norm": 10.104562759399414,
|
| 306 |
+
"learning_rate": 2.9229249349905684e-05,
|
| 307 |
+
"loss": 0.1492,
|
| 308 |
+
"step": 3500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.55,
|
| 312 |
+
"grad_norm": 4.825140476226807,
|
| 313 |
+
"learning_rate": 2.6666633838716314e-05,
|
| 314 |
+
"loss": 0.1509,
|
| 315 |
+
"step": 3600
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.73,
|
| 319 |
+
"grad_norm": 5.883378505706787,
|
| 320 |
+
"learning_rate": 2.418012691805191e-05,
|
| 321 |
+
"loss": 0.1371,
|
| 322 |
+
"step": 3700
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.91,
|
| 326 |
+
"grad_norm": 11.501364707946777,
|
| 327 |
+
"learning_rate": 2.1777839056661554e-05,
|
| 328 |
+
"loss": 0.1565,
|
| 329 |
+
"step": 3800
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 7.0,
|
| 333 |
+
"eval_accuracy": 0.9324055666003976,
|
| 334 |
+
"eval_loss": 0.2781141400337219,
|
| 335 |
+
"eval_runtime": 70.6162,
|
| 336 |
+
"eval_samples_per_second": 35.615,
|
| 337 |
+
"eval_steps_per_second": 1.119,
|
| 338 |
+
"step": 3850
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.09,
|
| 342 |
+
"grad_norm": 7.272291660308838,
|
| 343 |
+
"learning_rate": 1.946760601822809e-05,
|
| 344 |
+
"loss": 0.1158,
|
| 345 |
+
"step": 3900
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.27,
|
| 349 |
+
"grad_norm": 10.176920890808105,
|
| 350 |
+
"learning_rate": 1.725696330273575e-05,
|
| 351 |
+
"loss": 0.1342,
|
| 352 |
+
"step": 4000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.45,
|
| 356 |
+
"grad_norm": 10.327248573303223,
|
| 357 |
+
"learning_rate": 1.5153121567235335e-05,
|
| 358 |
+
"loss": 0.1261,
|
| 359 |
+
"step": 4100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.64,
|
| 363 |
+
"grad_norm": 10.916594505310059,
|
| 364 |
+
"learning_rate": 1.3162943106179749e-05,
|
| 365 |
+
"loss": 0.1336,
|
| 366 |
+
"step": 4200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.82,
|
| 370 |
+
"grad_norm": 15.206429481506348,
|
| 371 |
+
"learning_rate": 1.1292919468045877e-05,
|
| 372 |
+
"loss": 0.1363,
|
| 373 |
+
"step": 4300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 0.1916830986738205,
|
| 378 |
+
"learning_rate": 9.549150281252633e-06,
|
| 379 |
+
"loss": 0.1203,
|
| 380 |
+
"step": 4400
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_accuracy": 0.9387673956262426,
|
| 385 |
+
"eval_loss": 0.27075594663619995,
|
| 386 |
+
"eval_runtime": 70.5293,
|
| 387 |
+
"eval_samples_per_second": 35.659,
|
| 388 |
+
"eval_steps_per_second": 1.12,
|
| 389 |
+
"step": 4400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 8.18,
|
| 393 |
+
"grad_norm": 10.416373252868652,
|
| 394 |
+
"learning_rate": 7.937323358440935e-06,
|
| 395 |
+
"loss": 0.1245,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.36,
|
| 400 |
+
"grad_norm": 9.158769607543945,
|
| 401 |
+
"learning_rate": 6.462696144011149e-06,
|
| 402 |
+
"loss": 0.1151,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 8.55,
|
| 407 |
+
"grad_norm": 9.09100341796875,
|
| 408 |
+
"learning_rate": 5.13007856543209e-06,
|
| 409 |
+
"loss": 0.1037,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.73,
|
| 414 |
+
"grad_norm": 2.6982064247131348,
|
| 415 |
+
"learning_rate": 3.9438173442575e-06,
|
| 416 |
+
"loss": 0.1193,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.91,
|
| 421 |
+
"grad_norm": 7.2986931800842285,
|
| 422 |
+
"learning_rate": 2.9077818180237693e-06,
|
| 423 |
+
"loss": 0.1281,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.0,
|
| 428 |
+
"eval_accuracy": 0.9363817097415507,
|
| 429 |
+
"eval_loss": 0.2707272469997406,
|
| 430 |
+
"eval_runtime": 69.913,
|
| 431 |
+
"eval_samples_per_second": 35.973,
|
| 432 |
+
"eval_steps_per_second": 1.13,
|
| 433 |
+
"step": 4950
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 9.09,
|
| 437 |
+
"grad_norm": 4.659209251403809,
|
| 438 |
+
"learning_rate": 2.0253513192751373e-06,
|
| 439 |
+
"loss": 0.1022,
|
| 440 |
+
"step": 5000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.27,
|
| 444 |
+
"grad_norm": 9.605278015136719,
|
| 445 |
+
"learning_rate": 1.2994041528833266e-06,
|
| 446 |
+
"loss": 0.1073,
|
| 447 |
+
"step": 5100
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.45,
|
| 451 |
+
"grad_norm": 9.004630088806152,
|
| 452 |
+
"learning_rate": 7.323082076153509e-07,
|
| 453 |
+
"loss": 0.0928,
|
| 454 |
+
"step": 5200
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 9.64,
|
| 458 |
+
"grad_norm": 9.619388580322266,
|
| 459 |
+
"learning_rate": 3.2591323257248893e-07,
|
| 460 |
+
"loss": 0.1171,
|
| 461 |
+
"step": 5300
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 9.82,
|
| 465 |
+
"grad_norm": 11.248806953430176,
|
| 466 |
+
"learning_rate": 8.15448036932176e-08,
|
| 467 |
+
"loss": 0.1334,
|
| 468 |
+
"step": 5400
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 10.0,
|
| 472 |
+
"grad_norm": 18.464763641357422,
|
| 473 |
+
"learning_rate": 0.0,
|
| 474 |
+
"loss": 0.1014,
|
| 475 |
+
"step": 5500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 10.0,
|
| 479 |
+
"eval_accuracy": 0.9379721669980119,
|
| 480 |
+
"eval_loss": 0.26930707693099976,
|
| 481 |
+
"eval_runtime": 69.9231,
|
| 482 |
+
"eval_samples_per_second": 35.968,
|
| 483 |
+
"eval_steps_per_second": 1.13,
|
| 484 |
+
"step": 5500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.0,
|
| 488 |
+
"step": 5500,
|
| 489 |
+
"total_flos": 1.301428412334932e+19,
|
| 490 |
+
"train_loss": 0.2947656165036288,
|
| 491 |
+
"train_runtime": 8332.2574,
|
| 492 |
+
"train_samples_per_second": 21.1,
|
| 493 |
+
"train_steps_per_second": 0.66
|
| 494 |
+
}
|
| 495 |
+
],
|
| 496 |
+
"logging_steps": 100,
|
| 497 |
+
"max_steps": 5500,
|
| 498 |
+
"num_input_tokens_seen": 0,
|
| 499 |
+
"num_train_epochs": 10,
|
| 500 |
+
"save_steps": 500,
|
| 501 |
+
"total_flos": 1.301428412334932e+19,
|
| 502 |
+
"train_batch_size": 32,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|