End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan21_00-03-14_feec14bb91f4/events.out.tfevents.1737419950.feec14bb91f4.14041.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +567 -0
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss:
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8423
|
| 22 |
+
- Accuracy: 0.75
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 41.869565217391305,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.842289388179779,
|
| 5 |
+
"eval_runtime": 1.5112,
|
| 6 |
+
"eval_samples_per_second": 34.41,
|
| 7 |
+
"eval_steps_per_second": 1.323,
|
| 8 |
+
"total_flos": 2.8899664857724355e+18,
|
| 9 |
+
"train_loss": 2.0296274548485167,
|
| 10 |
+
"train_runtime": 2115.3253,
|
| 11 |
+
"train_samples_per_second": 14.474,
|
| 12 |
+
"train_steps_per_second": 0.099
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 41.869565217391305,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.842289388179779,
|
| 5 |
+
"eval_runtime": 1.5112,
|
| 6 |
+
"eval_samples_per_second": 34.41,
|
| 7 |
+
"eval_steps_per_second": 1.323
|
| 8 |
+
}
|
runs/Jan21_00-03-14_feec14bb91f4/events.out.tfevents.1737419950.feec14bb91f4.14041.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f82675f2094806a6af5de6fea4cc6c4052d716668a34962ddffbb287d6f3c58
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 41.869565217391305,
|
| 3 |
+
"total_flos": 2.8899664857724355e+18,
|
| 4 |
+
"train_loss": 2.0296274548485167,
|
| 5 |
+
"train_runtime": 2115.3253,
|
| 6 |
+
"train_samples_per_second": 14.474,
|
| 7 |
+
"train_steps_per_second": 0.099
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.75,
|
| 3 |
+
"best_model_checkpoint": "swinv2-base-patch4-window8-256-dmae-humeda-DAV15/checkpoint-80",
|
| 4 |
+
"epoch": 41.869565217391305,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 210,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8695652173913043,
|
| 13 |
+
"eval_accuracy": 0.3076923076923077,
|
| 14 |
+
"eval_loss": 1.5972468852996826,
|
| 15 |
+
"eval_runtime": 1.8054,
|
| 16 |
+
"eval_samples_per_second": 28.802,
|
| 17 |
+
"eval_steps_per_second": 1.108,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.8695652173913042,
|
| 22 |
+
"grad_norm": 10.893352508544922,
|
| 23 |
+
"learning_rate": 9.523809523809525e-06,
|
| 24 |
+
"loss": 6.7562,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.8695652173913042,
|
| 29 |
+
"eval_accuracy": 0.3076923076923077,
|
| 30 |
+
"eval_loss": 1.5356961488723755,
|
| 31 |
+
"eval_runtime": 1.4107,
|
| 32 |
+
"eval_samples_per_second": 36.861,
|
| 33 |
+
"eval_steps_per_second": 1.418,
|
| 34 |
+
"step": 10
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.869565217391304,
|
| 38 |
+
"eval_accuracy": 0.40384615384615385,
|
| 39 |
+
"eval_loss": 1.4953821897506714,
|
| 40 |
+
"eval_runtime": 1.4409,
|
| 41 |
+
"eval_samples_per_second": 36.088,
|
| 42 |
+
"eval_steps_per_second": 1.388,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.869565217391304,
|
| 47 |
+
"grad_norm": 9.43877124786377,
|
| 48 |
+
"learning_rate": 1.904761904761905e-05,
|
| 49 |
+
"loss": 6.2842,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.869565217391304,
|
| 54 |
+
"eval_accuracy": 0.34615384615384615,
|
| 55 |
+
"eval_loss": 1.461243987083435,
|
| 56 |
+
"eval_runtime": 1.6776,
|
| 57 |
+
"eval_samples_per_second": 30.997,
|
| 58 |
+
"eval_steps_per_second": 1.192,
|
| 59 |
+
"step": 20
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.869565217391305,
|
| 63 |
+
"eval_accuracy": 0.3269230769230769,
|
| 64 |
+
"eval_loss": 1.387509822845459,
|
| 65 |
+
"eval_runtime": 1.4405,
|
| 66 |
+
"eval_samples_per_second": 36.1,
|
| 67 |
+
"eval_steps_per_second": 1.388,
|
| 68 |
+
"step": 25
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.869565217391305,
|
| 72 |
+
"grad_norm": 13.647711753845215,
|
| 73 |
+
"learning_rate": 1.9888308262251286e-05,
|
| 74 |
+
"loss": 4.9858,
|
| 75 |
+
"step": 30
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.869565217391305,
|
| 79 |
+
"eval_accuracy": 0.34615384615384615,
|
| 80 |
+
"eval_loss": 1.3369739055633545,
|
| 81 |
+
"eval_runtime": 1.4598,
|
| 82 |
+
"eval_samples_per_second": 35.622,
|
| 83 |
+
"eval_steps_per_second": 1.37,
|
| 84 |
+
"step": 30
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.869565217391305,
|
| 88 |
+
"eval_accuracy": 0.4423076923076923,
|
| 89 |
+
"eval_loss": 1.2739052772521973,
|
| 90 |
+
"eval_runtime": 1.8216,
|
| 91 |
+
"eval_samples_per_second": 28.546,
|
| 92 |
+
"eval_steps_per_second": 1.098,
|
| 93 |
+
"step": 35
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.869565217391305,
|
| 97 |
+
"grad_norm": 18.52330207824707,
|
| 98 |
+
"learning_rate": 1.9505415489478293e-05,
|
| 99 |
+
"loss": 3.5596,
|
| 100 |
+
"step": 40
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 7.869565217391305,
|
| 104 |
+
"eval_accuracy": 0.4807692307692308,
|
| 105 |
+
"eval_loss": 1.1773827075958252,
|
| 106 |
+
"eval_runtime": 1.4754,
|
| 107 |
+
"eval_samples_per_second": 35.244,
|
| 108 |
+
"eval_steps_per_second": 1.356,
|
| 109 |
+
"step": 40
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 8.869565217391305,
|
| 113 |
+
"eval_accuracy": 0.4807692307692308,
|
| 114 |
+
"eval_loss": 1.121440052986145,
|
| 115 |
+
"eval_runtime": 1.4488,
|
| 116 |
+
"eval_samples_per_second": 35.893,
|
| 117 |
+
"eval_steps_per_second": 1.38,
|
| 118 |
+
"step": 45
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 9.869565217391305,
|
| 122 |
+
"grad_norm": 18.99748420715332,
|
| 123 |
+
"learning_rate": 1.8860495104301346e-05,
|
| 124 |
+
"loss": 2.6814,
|
| 125 |
+
"step": 50
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 9.869565217391305,
|
| 129 |
+
"eval_accuracy": 0.5192307692307693,
|
| 130 |
+
"eval_loss": 1.0998505353927612,
|
| 131 |
+
"eval_runtime": 1.5002,
|
| 132 |
+
"eval_samples_per_second": 34.663,
|
| 133 |
+
"eval_steps_per_second": 1.333,
|
| 134 |
+
"step": 50
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.869565217391305,
|
| 138 |
+
"eval_accuracy": 0.46153846153846156,
|
| 139 |
+
"eval_loss": 1.1773051023483276,
|
| 140 |
+
"eval_runtime": 1.8237,
|
| 141 |
+
"eval_samples_per_second": 28.513,
|
| 142 |
+
"eval_steps_per_second": 1.097,
|
| 143 |
+
"step": 55
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 11.869565217391305,
|
| 147 |
+
"grad_norm": 22.57859992980957,
|
| 148 |
+
"learning_rate": 1.7971325072229227e-05,
|
| 149 |
+
"loss": 2.3236,
|
| 150 |
+
"step": 60
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.869565217391305,
|
| 154 |
+
"eval_accuracy": 0.5192307692307693,
|
| 155 |
+
"eval_loss": 0.9873736500740051,
|
| 156 |
+
"eval_runtime": 1.8064,
|
| 157 |
+
"eval_samples_per_second": 28.786,
|
| 158 |
+
"eval_steps_per_second": 1.107,
|
| 159 |
+
"step": 60
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.869565217391305,
|
| 163 |
+
"eval_accuracy": 0.5,
|
| 164 |
+
"eval_loss": 1.1123789548873901,
|
| 165 |
+
"eval_runtime": 1.4402,
|
| 166 |
+
"eval_samples_per_second": 36.106,
|
| 167 |
+
"eval_steps_per_second": 1.389,
|
| 168 |
+
"step": 65
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.869565217391305,
|
| 172 |
+
"grad_norm": 28.97609519958496,
|
| 173 |
+
"learning_rate": 1.686241637868734e-05,
|
| 174 |
+
"loss": 1.8037,
|
| 175 |
+
"step": 70
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 13.869565217391305,
|
| 179 |
+
"eval_accuracy": 0.6538461538461539,
|
| 180 |
+
"eval_loss": 0.8936060667037964,
|
| 181 |
+
"eval_runtime": 1.4709,
|
| 182 |
+
"eval_samples_per_second": 35.353,
|
| 183 |
+
"eval_steps_per_second": 1.36,
|
| 184 |
+
"step": 70
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 14.869565217391305,
|
| 188 |
+
"eval_accuracy": 0.4423076923076923,
|
| 189 |
+
"eval_loss": 1.2063868045806885,
|
| 190 |
+
"eval_runtime": 1.855,
|
| 191 |
+
"eval_samples_per_second": 28.032,
|
| 192 |
+
"eval_steps_per_second": 1.078,
|
| 193 |
+
"step": 75
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 15.869565217391305,
|
| 197 |
+
"grad_norm": 27.648298263549805,
|
| 198 |
+
"learning_rate": 1.5564337355766412e-05,
|
| 199 |
+
"loss": 1.6474,
|
| 200 |
+
"step": 80
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 15.869565217391305,
|
| 204 |
+
"eval_accuracy": 0.75,
|
| 205 |
+
"eval_loss": 0.842289388179779,
|
| 206 |
+
"eval_runtime": 1.7992,
|
| 207 |
+
"eval_samples_per_second": 28.901,
|
| 208 |
+
"eval_steps_per_second": 1.112,
|
| 209 |
+
"step": 80
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 16.869565217391305,
|
| 213 |
+
"eval_accuracy": 0.6346153846153846,
|
| 214 |
+
"eval_loss": 1.0133720636367798,
|
| 215 |
+
"eval_runtime": 1.4225,
|
| 216 |
+
"eval_samples_per_second": 36.554,
|
| 217 |
+
"eval_steps_per_second": 1.406,
|
| 218 |
+
"step": 85
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 17.869565217391305,
|
| 222 |
+
"grad_norm": 20.62474250793457,
|
| 223 |
+
"learning_rate": 1.4112871031306118e-05,
|
| 224 |
+
"loss": 1.5505,
|
| 225 |
+
"step": 90
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 17.869565217391305,
|
| 229 |
+
"eval_accuracy": 0.6923076923076923,
|
| 230 |
+
"eval_loss": 0.8965399861335754,
|
| 231 |
+
"eval_runtime": 1.4632,
|
| 232 |
+
"eval_samples_per_second": 35.54,
|
| 233 |
+
"eval_steps_per_second": 1.367,
|
| 234 |
+
"step": 90
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 18.869565217391305,
|
| 238 |
+
"eval_accuracy": 0.6538461538461539,
|
| 239 |
+
"eval_loss": 0.9214943647384644,
|
| 240 |
+
"eval_runtime": 1.4703,
|
| 241 |
+
"eval_samples_per_second": 35.368,
|
| 242 |
+
"eval_steps_per_second": 1.36,
|
| 243 |
+
"step": 95
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 19.869565217391305,
|
| 247 |
+
"grad_norm": 31.890165328979492,
|
| 248 |
+
"learning_rate": 1.2548028728946548e-05,
|
| 249 |
+
"loss": 1.2697,
|
| 250 |
+
"step": 100
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 19.869565217391305,
|
| 254 |
+
"eval_accuracy": 0.6153846153846154,
|
| 255 |
+
"eval_loss": 1.0155353546142578,
|
| 256 |
+
"eval_runtime": 1.4323,
|
| 257 |
+
"eval_samples_per_second": 36.306,
|
| 258 |
+
"eval_steps_per_second": 1.396,
|
| 259 |
+
"step": 100
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 20.869565217391305,
|
| 263 |
+
"eval_accuracy": 0.7115384615384616,
|
| 264 |
+
"eval_loss": 0.8500422835350037,
|
| 265 |
+
"eval_runtime": 1.4418,
|
| 266 |
+
"eval_samples_per_second": 36.065,
|
| 267 |
+
"eval_steps_per_second": 1.387,
|
| 268 |
+
"step": 105
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 21.869565217391305,
|
| 272 |
+
"grad_norm": 16.111915588378906,
|
| 273 |
+
"learning_rate": 1.0912947110386484e-05,
|
| 274 |
+
"loss": 1.1783,
|
| 275 |
+
"step": 110
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 21.869565217391305,
|
| 279 |
+
"eval_accuracy": 0.6538461538461539,
|
| 280 |
+
"eval_loss": 0.9573343992233276,
|
| 281 |
+
"eval_runtime": 1.4883,
|
| 282 |
+
"eval_samples_per_second": 34.938,
|
| 283 |
+
"eval_steps_per_second": 1.344,
|
| 284 |
+
"step": 110
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 22.869565217391305,
|
| 288 |
+
"eval_accuracy": 0.6923076923076923,
|
| 289 |
+
"eval_loss": 0.8914616107940674,
|
| 290 |
+
"eval_runtime": 1.7921,
|
| 291 |
+
"eval_samples_per_second": 29.016,
|
| 292 |
+
"eval_steps_per_second": 1.116,
|
| 293 |
+
"step": 115
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 23.869565217391305,
|
| 297 |
+
"grad_norm": 16.878934860229492,
|
| 298 |
+
"learning_rate": 9.252699064135759e-06,
|
| 299 |
+
"loss": 1.0235,
|
| 300 |
+
"step": 120
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 23.869565217391305,
|
| 304 |
+
"eval_accuracy": 0.6538461538461539,
|
| 305 |
+
"eval_loss": 0.9831422567367554,
|
| 306 |
+
"eval_runtime": 1.4719,
|
| 307 |
+
"eval_samples_per_second": 35.328,
|
| 308 |
+
"eval_steps_per_second": 1.359,
|
| 309 |
+
"step": 120
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 24.869565217391305,
|
| 313 |
+
"eval_accuracy": 0.6538461538461539,
|
| 314 |
+
"eval_loss": 0.9464498162269592,
|
| 315 |
+
"eval_runtime": 1.4685,
|
| 316 |
+
"eval_samples_per_second": 35.409,
|
| 317 |
+
"eval_steps_per_second": 1.362,
|
| 318 |
+
"step": 125
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 25.869565217391305,
|
| 322 |
+
"grad_norm": 22.73305892944336,
|
| 323 |
+
"learning_rate": 7.613051219968624e-06,
|
| 324 |
+
"loss": 0.9706,
|
| 325 |
+
"step": 130
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 25.869565217391305,
|
| 329 |
+
"eval_accuracy": 0.6923076923076923,
|
| 330 |
+
"eval_loss": 0.9413173198699951,
|
| 331 |
+
"eval_runtime": 1.7224,
|
| 332 |
+
"eval_samples_per_second": 30.191,
|
| 333 |
+
"eval_steps_per_second": 1.161,
|
| 334 |
+
"step": 130
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 26.869565217391305,
|
| 338 |
+
"eval_accuracy": 0.6346153846153846,
|
| 339 |
+
"eval_loss": 1.0248907804489136,
|
| 340 |
+
"eval_runtime": 1.7923,
|
| 341 |
+
"eval_samples_per_second": 29.013,
|
| 342 |
+
"eval_steps_per_second": 1.116,
|
| 343 |
+
"step": 135
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 27.869565217391305,
|
| 347 |
+
"grad_norm": 21.775854110717773,
|
| 348 |
+
"learning_rate": 6.039202339608432e-06,
|
| 349 |
+
"loss": 0.9409,
|
| 350 |
+
"step": 140
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 27.869565217391305,
|
| 354 |
+
"eval_accuracy": 0.6538461538461539,
|
| 355 |
+
"eval_loss": 0.9753580093383789,
|
| 356 |
+
"eval_runtime": 1.8553,
|
| 357 |
+
"eval_samples_per_second": 28.028,
|
| 358 |
+
"eval_steps_per_second": 1.078,
|
| 359 |
+
"step": 140
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 28.869565217391305,
|
| 363 |
+
"eval_accuracy": 0.7115384615384616,
|
| 364 |
+
"eval_loss": 0.9530434012413025,
|
| 365 |
+
"eval_runtime": 1.7906,
|
| 366 |
+
"eval_samples_per_second": 29.04,
|
| 367 |
+
"eval_steps_per_second": 1.117,
|
| 368 |
+
"step": 145
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 29.869565217391305,
|
| 372 |
+
"grad_norm": 16.502880096435547,
|
| 373 |
+
"learning_rate": 4.5745373613424075e-06,
|
| 374 |
+
"loss": 0.9447,
|
| 375 |
+
"step": 150
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 29.869565217391305,
|
| 379 |
+
"eval_accuracy": 0.6538461538461539,
|
| 380 |
+
"eval_loss": 1.02655827999115,
|
| 381 |
+
"eval_runtime": 1.4711,
|
| 382 |
+
"eval_samples_per_second": 35.348,
|
| 383 |
+
"eval_steps_per_second": 1.36,
|
| 384 |
+
"step": 150
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.869565217391305,
|
| 388 |
+
"eval_accuracy": 0.6538461538461539,
|
| 389 |
+
"eval_loss": 1.0819494724273682,
|
| 390 |
+
"eval_runtime": 1.4452,
|
| 391 |
+
"eval_samples_per_second": 35.981,
|
| 392 |
+
"eval_steps_per_second": 1.384,
|
| 393 |
+
"step": 155
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 31.869565217391305,
|
| 397 |
+
"grad_norm": 14.975761413574219,
|
| 398 |
+
"learning_rate": 3.2594314447468457e-06,
|
| 399 |
+
"loss": 0.8352,
|
| 400 |
+
"step": 160
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 31.869565217391305,
|
| 404 |
+
"eval_accuracy": 0.6923076923076923,
|
| 405 |
+
"eval_loss": 0.9921611547470093,
|
| 406 |
+
"eval_runtime": 1.6676,
|
| 407 |
+
"eval_samples_per_second": 31.182,
|
| 408 |
+
"eval_steps_per_second": 1.199,
|
| 409 |
+
"step": 160
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 32.869565217391305,
|
| 413 |
+
"eval_accuracy": 0.6923076923076923,
|
| 414 |
+
"eval_loss": 0.9754781126976013,
|
| 415 |
+
"eval_runtime": 1.4838,
|
| 416 |
+
"eval_samples_per_second": 35.046,
|
| 417 |
+
"eval_steps_per_second": 1.348,
|
| 418 |
+
"step": 165
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 33.869565217391305,
|
| 422 |
+
"grad_norm": 16.957916259765625,
|
| 423 |
+
"learning_rate": 2.130136983393112e-06,
|
| 424 |
+
"loss": 0.8055,
|
| 425 |
+
"step": 170
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 33.869565217391305,
|
| 429 |
+
"eval_accuracy": 0.7115384615384616,
|
| 430 |
+
"eval_loss": 0.9768009185791016,
|
| 431 |
+
"eval_runtime": 1.4548,
|
| 432 |
+
"eval_samples_per_second": 35.745,
|
| 433 |
+
"eval_steps_per_second": 1.375,
|
| 434 |
+
"step": 170
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 34.869565217391305,
|
| 438 |
+
"eval_accuracy": 0.6923076923076923,
|
| 439 |
+
"eval_loss": 0.9950000047683716,
|
| 440 |
+
"eval_runtime": 1.6477,
|
| 441 |
+
"eval_samples_per_second": 31.56,
|
| 442 |
+
"eval_steps_per_second": 1.214,
|
| 443 |
+
"step": 175
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 35.869565217391305,
|
| 447 |
+
"grad_norm": 13.693328857421875,
|
| 448 |
+
"learning_rate": 1.2177842662977136e-06,
|
| 449 |
+
"loss": 0.7481,
|
| 450 |
+
"step": 180
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 35.869565217391305,
|
| 454 |
+
"eval_accuracy": 0.6923076923076923,
|
| 455 |
+
"eval_loss": 1.0135220289230347,
|
| 456 |
+
"eval_runtime": 1.4654,
|
| 457 |
+
"eval_samples_per_second": 35.486,
|
| 458 |
+
"eval_steps_per_second": 1.365,
|
| 459 |
+
"step": 180
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 36.869565217391305,
|
| 463 |
+
"eval_accuracy": 0.6923076923076923,
|
| 464 |
+
"eval_loss": 1.0168299674987793,
|
| 465 |
+
"eval_runtime": 1.4666,
|
| 466 |
+
"eval_samples_per_second": 35.456,
|
| 467 |
+
"eval_steps_per_second": 1.364,
|
| 468 |
+
"step": 185
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 37.869565217391305,
|
| 472 |
+
"grad_norm": 16.68096923828125,
|
| 473 |
+
"learning_rate": 5.475233360227516e-07,
|
| 474 |
+
"loss": 0.7483,
|
| 475 |
+
"step": 190
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 37.869565217391305,
|
| 479 |
+
"eval_accuracy": 0.6923076923076923,
|
| 480 |
+
"eval_loss": 1.009111762046814,
|
| 481 |
+
"eval_runtime": 1.4779,
|
| 482 |
+
"eval_samples_per_second": 35.184,
|
| 483 |
+
"eval_steps_per_second": 1.353,
|
| 484 |
+
"step": 190
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 38.869565217391305,
|
| 488 |
+
"eval_accuracy": 0.6923076923076923,
|
| 489 |
+
"eval_loss": 1.005540370941162,
|
| 490 |
+
"eval_runtime": 1.5862,
|
| 491 |
+
"eval_samples_per_second": 32.783,
|
| 492 |
+
"eval_steps_per_second": 1.261,
|
| 493 |
+
"step": 195
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 39.869565217391305,
|
| 497 |
+
"grad_norm": 27.558324813842773,
|
| 498 |
+
"learning_rate": 1.3783069908621772e-07,
|
| 499 |
+
"loss": 0.8145,
|
| 500 |
+
"step": 200
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 39.869565217391305,
|
| 504 |
+
"eval_accuracy": 0.6923076923076923,
|
| 505 |
+
"eval_loss": 1.0039584636688232,
|
| 506 |
+
"eval_runtime": 1.47,
|
| 507 |
+
"eval_samples_per_second": 35.373,
|
| 508 |
+
"eval_steps_per_second": 1.361,
|
| 509 |
+
"step": 200
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 40.869565217391305,
|
| 513 |
+
"eval_accuracy": 0.6923076923076923,
|
| 514 |
+
"eval_loss": 1.0038609504699707,
|
| 515 |
+
"eval_runtime": 1.466,
|
| 516 |
+
"eval_samples_per_second": 35.471,
|
| 517 |
+
"eval_steps_per_second": 1.364,
|
| 518 |
+
"step": 205
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 41.869565217391305,
|
| 522 |
+
"grad_norm": 17.93744468688965,
|
| 523 |
+
"learning_rate": 0.0,
|
| 524 |
+
"loss": 0.7501,
|
| 525 |
+
"step": 210
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 41.869565217391305,
|
| 529 |
+
"eval_accuracy": 0.6923076923076923,
|
| 530 |
+
"eval_loss": 1.0038418769836426,
|
| 531 |
+
"eval_runtime": 1.8649,
|
| 532 |
+
"eval_samples_per_second": 27.884,
|
| 533 |
+
"eval_steps_per_second": 1.072,
|
| 534 |
+
"step": 210
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 41.869565217391305,
|
| 538 |
+
"step": 210,
|
| 539 |
+
"total_flos": 2.8899664857724355e+18,
|
| 540 |
+
"train_loss": 2.0296274548485167,
|
| 541 |
+
"train_runtime": 2115.3253,
|
| 542 |
+
"train_samples_per_second": 14.474,
|
| 543 |
+
"train_steps_per_second": 0.099
|
| 544 |
+
}
|
| 545 |
+
],
|
| 546 |
+
"logging_steps": 10,
|
| 547 |
+
"max_steps": 210,
|
| 548 |
+
"num_input_tokens_seen": 0,
|
| 549 |
+
"num_train_epochs": 42,
|
| 550 |
+
"save_steps": 500,
|
| 551 |
+
"stateful_callbacks": {
|
| 552 |
+
"TrainerControl": {
|
| 553 |
+
"args": {
|
| 554 |
+
"should_epoch_stop": false,
|
| 555 |
+
"should_evaluate": false,
|
| 556 |
+
"should_log": false,
|
| 557 |
+
"should_save": true,
|
| 558 |
+
"should_training_stop": true
|
| 559 |
+
},
|
| 560 |
+
"attributes": {}
|
| 561 |
+
}
|
| 562 |
+
},
|
| 563 |
+
"total_flos": 2.8899664857724355e+18,
|
| 564 |
+
"train_batch_size": 32,
|
| 565 |
+
"trial_name": null,
|
| 566 |
+
"trial_params": null
|
| 567 |
+
}
|