Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +64 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.15443275785175e+16,
|
| 4 |
+
"train_loss": 0.3380747139453888,
|
| 5 |
+
"train_runtime": 1182.7003,
|
| 6 |
+
"train_samples_per_second": 2.242,
|
| 7 |
+
"train_steps_per_second": 0.018
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13354685
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec22804de987ed993b1220cc03709ac3c8b2aa86804f6f9fc4340de71d766e43
|
| 3 |
size 13354685
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.15443275785175e+16,
|
| 4 |
+
"train_loss": 0.3380747139453888,
|
| 5 |
+
"train_runtime": 1182.7003,
|
| 6 |
+
"train_samples_per_second": 2.242,
|
| 7 |
+
"train_steps_per_second": 0.018
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9494949494949495,
|
| 3 |
+
"best_model_checkpoint": "mit-b0-finetuned-eurosat\\checkpoint-21",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 21,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.8080808080808081,
|
| 13 |
+
"eval_loss": 0.38276588916778564,
|
| 14 |
+
"eval_runtime": 18.5626,
|
| 15 |
+
"eval_samples_per_second": 5.333,
|
| 16 |
+
"eval_steps_per_second": 0.215,
|
| 17 |
+
"step": 7
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.43,
|
| 21 |
+
"learning_rate": 3.055555555555556e-05,
|
| 22 |
+
"loss": 0.4864,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_accuracy": 0.9191919191919192,
|
| 28 |
+
"eval_loss": 0.2223997414112091,
|
| 29 |
+
"eval_runtime": 18.4144,
|
| 30 |
+
"eval_samples_per_second": 5.376,
|
| 31 |
+
"eval_steps_per_second": 0.217,
|
| 32 |
+
"step": 14
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.86,
|
| 36 |
+
"learning_rate": 2.777777777777778e-06,
|
| 37 |
+
"loss": 0.2035,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_accuracy": 0.9494949494949495,
|
| 43 |
+
"eval_loss": 0.17816942930221558,
|
| 44 |
+
"eval_runtime": 17.3231,
|
| 45 |
+
"eval_samples_per_second": 5.715,
|
| 46 |
+
"eval_steps_per_second": 0.231,
|
| 47 |
+
"step": 21
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"step": 21,
|
| 52 |
+
"total_flos": 4.15443275785175e+16,
|
| 53 |
+
"train_loss": 0.3380747139453888,
|
| 54 |
+
"train_runtime": 1182.7003,
|
| 55 |
+
"train_samples_per_second": 2.242,
|
| 56 |
+
"train_steps_per_second": 0.018
|
| 57 |
+
}
|
| 58 |
+
],
|
| 59 |
+
"max_steps": 21,
|
| 60 |
+
"num_train_epochs": 3,
|
| 61 |
+
"total_flos": 4.15443275785175e+16,
|
| 62 |
+
"trial_name": null,
|
| 63 |
+
"trial_params": null
|
| 64 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2991
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bcd025f04143c8a6dbf5f3d7920c8c62167a7c2c152b246b8634d508a3c646c
|
| 3 |
size 2991
|