Training in progress, epoch 0
Browse files- all_results.json +6 -6
- config.json +0 -1
- model.safetensors +1 -1
- runs/Sep05_11-32-43_1407788d87e8/events.out.tfevents.1725542217.1407788d87e8.1326.1 +3 -0
- runs/Sep05_13-42-34_1407788d87e8/events.out.tfevents.1725543768.1407788d87e8.1326.2 +3 -0
- runs/Sep05_13-44-08_1407788d87e8/events.out.tfevents.1725543858.1407788d87e8.1326.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +349 -62
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.846153846153847,
|
| 3 |
+
"total_flos": 1.0354878719936594e+18,
|
| 4 |
+
"train_loss": 0.8634449824690819,
|
| 5 |
+
"train_runtime": 4124.7516,
|
| 6 |
+
"train_samples_per_second": 10.066,
|
| 7 |
+
"train_steps_per_second": 0.078
|
| 8 |
}
|
config.json
CHANGED
|
@@ -51,7 +51,6 @@
|
|
| 51 |
],
|
| 52 |
"patch_size": 4,
|
| 53 |
"path_norm": true,
|
| 54 |
-
"problem_type": "single_label_classification",
|
| 55 |
"qkv_bias": true,
|
| 56 |
"stage_names": [
|
| 57 |
"stem",
|
|
|
|
| 51 |
],
|
| 52 |
"patch_size": 4,
|
| 53 |
"path_norm": true,
|
|
|
|
| 54 |
"qkv_bias": true,
|
| 55 |
"stage_names": [
|
| 56 |
"stem",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110352060
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7ad562f42b6f4b90a8f67f58b115d8a22acddb9343e0e0e0231956abdc60f38
|
| 3 |
size 110352060
|
runs/Sep05_11-32-43_1407788d87e8/events.out.tfevents.1725542217.1407788d87e8.1326.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd55227a10f1146106ad7717077bb36b93c28e9d04732169315d5f9aa39503f9
|
| 3 |
+
size 560
|
runs/Sep05_13-42-34_1407788d87e8/events.out.tfevents.1725543768.1407788d87e8.1326.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcd8ad18a7c76381b9b72ba20c1d93ad51c63a50ce5a89f9866656c6b5641ef5
|
| 3 |
+
size 5484
|
runs/Sep05_13-44-08_1407788d87e8/events.out.tfevents.1725543858.1407788d87e8.1326.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afac5821b34608324f50fe647fc5f6d86b416574ba01559b0e661286e7babf68
|
| 3 |
+
size 6510
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.846153846153847,
|
| 3 |
+
"total_flos": 1.0354878719936594e+18,
|
| 4 |
+
"train_loss": 0.8634449824690819,
|
| 5 |
+
"train_runtime": 4124.7516,
|
| 6 |
+
"train_samples_per_second": 10.066,
|
| 7 |
+
"train_steps_per_second": 0.078
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,84 +1,371 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
"eval_logLoss": 1.009933590888977,
|
| 24 |
-
"eval_loss": 1.0099334716796875,
|
| 25 |
-
"eval_runtime": 92.538,
|
| 26 |
-
"eval_samples_per_second": 4.323,
|
| 27 |
-
"eval_steps_per_second": 0.14,
|
| 28 |
-
"step": 12
|
| 29 |
-
},
|
| 30 |
-
{
|
| 31 |
-
"epoch": 1.6,
|
| 32 |
-
"grad_norm": 4.288869857788086,
|
| 33 |
-
"learning_rate": 2.5e-05,
|
| 34 |
-
"loss": 0.9637,
|
| 35 |
"step": 20
|
| 36 |
},
|
| 37 |
{
|
| 38 |
-
"epoch":
|
| 39 |
-
"
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
"eval_logLoss": 0.871762752532959,
|
| 43 |
-
"eval_loss": 0.871762752532959,
|
| 44 |
-
"eval_runtime": 9.6171,
|
| 45 |
-
"eval_samples_per_second": 41.593,
|
| 46 |
-
"eval_steps_per_second": 1.352,
|
| 47 |
-
"step": 25
|
| 48 |
-
},
|
| 49 |
-
{
|
| 50 |
-
"epoch": 2.4,
|
| 51 |
-
"grad_norm": 6.406833171844482,
|
| 52 |
-
"learning_rate": 9.375000000000001e-06,
|
| 53 |
-
"loss": 0.9461,
|
| 54 |
"step": 30
|
| 55 |
},
|
| 56 |
{
|
| 57 |
-
"epoch":
|
| 58 |
-
"eval_accuracy":
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second":
|
| 66 |
-
"step":
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
|
| 75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 10,
|
| 79 |
-
"max_steps":
|
| 80 |
"num_input_tokens_seen": 0,
|
| 81 |
-
"num_train_epochs":
|
| 82 |
"save_steps": 500,
|
| 83 |
"stateful_callbacks": {
|
| 84 |
"TrainerControl": {
|
|
@@ -92,7 +379,7 @@
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
-
"total_flos": 1.
|
| 96 |
"train_batch_size": 32,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8847062587738037,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned/checkpoint-320",
|
| 4 |
+
"epoch": 9.846153846153847,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 320,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.3076923076923077,
|
| 13 |
+
"grad_norm": 4.222843647003174,
|
| 14 |
+
"learning_rate": 1.5625e-05,
|
| 15 |
+
"loss": 1.2776,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.6153846153846154,
|
| 20 |
+
"grad_norm": 4.994299411773682,
|
| 21 |
+
"learning_rate": 3.125e-05,
|
| 22 |
+
"loss": 1.1793,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.9230769230769231,
|
| 27 |
+
"grad_norm": 5.790884971618652,
|
| 28 |
+
"learning_rate": 4.6875e-05,
|
| 29 |
+
"loss": 1.089,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.9846153846153847,
|
| 34 |
+
"eval_accuracy": 0.591915303176131,
|
| 35 |
+
"eval_f1": 0.5663015617463389,
|
| 36 |
+
"eval_loss": 1.043319582939148,
|
| 37 |
+
"eval_precision": 0.570578116425331,
|
| 38 |
+
"eval_recall": 0.591915303176131,
|
| 39 |
+
"eval_runtime": 972.9147,
|
| 40 |
+
"eval_samples_per_second": 1.068,
|
| 41 |
+
"eval_steps_per_second": 0.034,
|
| 42 |
+
"step": 32
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.2307692307692308,
|
| 46 |
+
"grad_norm": 5.5890069007873535,
|
| 47 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 48 |
+
"loss": 1.0389,
|
| 49 |
+
"step": 40
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5384615384615383,
|
| 53 |
+
"grad_norm": 7.14047908782959,
|
| 54 |
+
"learning_rate": 4.6875e-05,
|
| 55 |
+
"loss": 1.0614,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.8461538461538463,
|
| 60 |
+
"grad_norm": 5.124348163604736,
|
| 61 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 62 |
+
"loss": 1.0165,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_accuracy": 0.5928777670837344,
|
| 68 |
+
"eval_f1": 0.5521015886078269,
|
| 69 |
+
"eval_loss": 1.0114457607269287,
|
| 70 |
+
"eval_precision": 0.600779215992248,
|
| 71 |
+
"eval_recall": 0.5928777670837344,
|
| 72 |
+
"eval_runtime": 23.8377,
|
| 73 |
+
"eval_samples_per_second": 43.586,
|
| 74 |
+
"eval_steps_per_second": 1.384,
|
| 75 |
+
"step": 65
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.1538461538461537,
|
| 79 |
+
"grad_norm": 3.7715022563934326,
|
| 80 |
+
"learning_rate": 4.340277777777778e-05,
|
| 81 |
+
"loss": 0.9634,
|
| 82 |
+
"step": 70
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.4615384615384617,
|
| 86 |
+
"grad_norm": 6.994911193847656,
|
| 87 |
+
"learning_rate": 4.166666666666667e-05,
|
| 88 |
+
"loss": 0.9796,
|
| 89 |
+
"step": 80
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.769230769230769,
|
| 93 |
+
"grad_norm": 5.106964111328125,
|
| 94 |
+
"learning_rate": 3.993055555555556e-05,
|
| 95 |
+
"loss": 0.935,
|
| 96 |
+
"step": 90
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.9846153846153847,
|
| 100 |
+
"eval_accuracy": 0.6371511068334937,
|
| 101 |
+
"eval_f1": 0.6069098097960562,
|
| 102 |
+
"eval_loss": 0.9436932802200317,
|
| 103 |
+
"eval_precision": 0.6626840278536283,
|
| 104 |
+
"eval_recall": 0.6371511068334937,
|
| 105 |
+
"eval_runtime": 24.0859,
|
| 106 |
+
"eval_samples_per_second": 43.137,
|
| 107 |
+
"eval_steps_per_second": 1.37,
|
| 108 |
+
"step": 97
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.076923076923077,
|
| 112 |
+
"grad_norm": 5.561572551727295,
|
| 113 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 114 |
+
"loss": 0.908,
|
| 115 |
+
"step": 100
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.3846153846153846,
|
| 119 |
+
"grad_norm": 5.457753658294678,
|
| 120 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 121 |
+
"loss": 0.8504,
|
| 122 |
+
"step": 110
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.6923076923076925,
|
| 126 |
+
"grad_norm": 6.219572067260742,
|
| 127 |
+
"learning_rate": 3.472222222222222e-05,
|
| 128 |
+
"loss": 0.8522,
|
| 129 |
+
"step": 120
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.0,
|
| 133 |
+
"grad_norm": 5.555025577545166,
|
| 134 |
+
"learning_rate": 3.2986111111111115e-05,
|
| 135 |
+
"loss": 0.9051,
|
| 136 |
+
"step": 130
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.0,
|
| 140 |
+
"eval_accuracy": 0.6400384985563041,
|
| 141 |
+
"eval_f1": 0.6327783476656897,
|
| 142 |
+
"eval_loss": 0.9238916635513306,
|
| 143 |
+
"eval_precision": 0.6380923158137368,
|
| 144 |
+
"eval_recall": 0.6400384985563041,
|
| 145 |
+
"eval_runtime": 23.787,
|
| 146 |
+
"eval_samples_per_second": 43.679,
|
| 147 |
+
"eval_steps_per_second": 1.387,
|
| 148 |
+
"step": 130
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.3076923076923075,
|
| 152 |
+
"grad_norm": 4.2132954597473145,
|
| 153 |
+
"learning_rate": 3.125e-05,
|
| 154 |
+
"loss": 0.8394,
|
| 155 |
+
"step": 140
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 4.615384615384615,
|
| 159 |
+
"grad_norm": 7.527224540710449,
|
| 160 |
+
"learning_rate": 2.951388888888889e-05,
|
| 161 |
+
"loss": 0.8278,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.923076923076923,
|
| 166 |
+
"grad_norm": 8.78996467590332,
|
| 167 |
+
"learning_rate": 2.777777777777778e-05,
|
| 168 |
+
"loss": 0.856,
|
| 169 |
+
"step": 160
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.984615384615385,
|
| 173 |
+
"eval_accuracy": 0.6381135707410972,
|
| 174 |
+
"eval_f1": 0.631926098346969,
|
| 175 |
+
"eval_loss": 0.9268857836723328,
|
| 176 |
+
"eval_precision": 0.6475643517149878,
|
| 177 |
+
"eval_recall": 0.6381135707410972,
|
| 178 |
+
"eval_runtime": 23.9493,
|
| 179 |
+
"eval_samples_per_second": 43.383,
|
| 180 |
+
"eval_steps_per_second": 1.378,
|
| 181 |
+
"step": 162
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.230769230769231,
|
| 185 |
+
"grad_norm": 4.454049587249756,
|
| 186 |
+
"learning_rate": 2.604166666666667e-05,
|
| 187 |
+
"loss": 0.7715,
|
| 188 |
+
"step": 170
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.538461538461538,
|
| 192 |
+
"grad_norm": 5.65101957321167,
|
| 193 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 194 |
+
"loss": 0.8265,
|
| 195 |
+
"step": 180
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 5.846153846153846,
|
| 199 |
+
"grad_norm": 6.742358207702637,
|
| 200 |
+
"learning_rate": 2.2569444444444447e-05,
|
| 201 |
+
"loss": 0.8317,
|
| 202 |
+
"step": 190
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.0,
|
| 206 |
+
"eval_accuracy": 0.6487006737247353,
|
| 207 |
+
"eval_f1": 0.6366752317854656,
|
| 208 |
+
"eval_loss": 0.911486804485321,
|
| 209 |
+
"eval_precision": 0.653599096662139,
|
| 210 |
+
"eval_recall": 0.6487006737247353,
|
| 211 |
+
"eval_runtime": 23.7936,
|
| 212 |
+
"eval_samples_per_second": 43.667,
|
| 213 |
+
"eval_steps_per_second": 1.387,
|
| 214 |
+
"step": 195
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 6.153846153846154,
|
| 218 |
+
"grad_norm": 6.174919128417969,
|
| 219 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 220 |
+
"loss": 0.7994,
|
| 221 |
+
"step": 200
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 6.461538461538462,
|
| 225 |
+
"grad_norm": 6.239418983459473,
|
| 226 |
+
"learning_rate": 1.9097222222222222e-05,
|
| 227 |
+
"loss": 0.7792,
|
| 228 |
+
"step": 210
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 6.769230769230769,
|
| 232 |
+
"grad_norm": 7.731762886047363,
|
| 233 |
+
"learning_rate": 1.736111111111111e-05,
|
| 234 |
+
"loss": 0.7914,
|
| 235 |
+
"step": 220
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 6.984615384615385,
|
| 239 |
+
"eval_accuracy": 0.6660250240615977,
|
| 240 |
+
"eval_f1": 0.6558142271285787,
|
| 241 |
+
"eval_loss": 0.8913388848304749,
|
| 242 |
+
"eval_precision": 0.6622428442076029,
|
| 243 |
+
"eval_recall": 0.6660250240615977,
|
| 244 |
+
"eval_runtime": 24.0291,
|
| 245 |
+
"eval_samples_per_second": 43.239,
|
| 246 |
+
"eval_steps_per_second": 1.373,
|
| 247 |
+
"step": 227
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.076923076923077,
|
| 251 |
+
"grad_norm": 5.157851219177246,
|
| 252 |
+
"learning_rate": 1.5625e-05,
|
| 253 |
+
"loss": 0.744,
|
| 254 |
+
"step": 230
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.384615384615385,
|
| 258 |
+
"grad_norm": 8.33967113494873,
|
| 259 |
+
"learning_rate": 1.388888888888889e-05,
|
| 260 |
+
"loss": 0.723,
|
| 261 |
+
"step": 240
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.6923076923076925,
|
| 265 |
+
"grad_norm": 6.409264087677002,
|
| 266 |
+
"learning_rate": 1.2152777777777779e-05,
|
| 267 |
+
"loss": 0.7512,
|
| 268 |
+
"step": 250
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.0,
|
| 272 |
+
"grad_norm": 6.12069034576416,
|
| 273 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 274 |
+
"loss": 0.763,
|
| 275 |
+
"step": 260
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 8.0,
|
| 279 |
+
"eval_accuracy": 0.6631376323387873,
|
| 280 |
+
"eval_f1": 0.6567791543544663,
|
| 281 |
+
"eval_loss": 0.8967146873474121,
|
| 282 |
+
"eval_precision": 0.6610152533977022,
|
| 283 |
+
"eval_recall": 0.6631376323387873,
|
| 284 |
+
"eval_runtime": 23.8361,
|
| 285 |
+
"eval_samples_per_second": 43.589,
|
| 286 |
+
"eval_steps_per_second": 1.384,
|
| 287 |
+
"step": 260
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 8.307692307692308,
|
| 291 |
+
"grad_norm": 7.385721683502197,
|
| 292 |
+
"learning_rate": 8.680555555555556e-06,
|
| 293 |
+
"loss": 0.7283,
|
| 294 |
+
"step": 270
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 8.615384615384615,
|
| 298 |
+
"grad_norm": 4.541664123535156,
|
| 299 |
+
"learning_rate": 6.944444444444445e-06,
|
| 300 |
+
"loss": 0.7345,
|
| 301 |
+
"step": 280
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 8.923076923076923,
|
| 305 |
+
"grad_norm": 7.139510631561279,
|
| 306 |
+
"learning_rate": 5.208333333333334e-06,
|
| 307 |
+
"loss": 0.7079,
|
| 308 |
+
"step": 290
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.984615384615385,
|
| 312 |
+
"eval_accuracy": 0.6612127045235804,
|
| 313 |
+
"eval_f1": 0.6518917882622605,
|
| 314 |
+
"eval_loss": 0.9004968404769897,
|
| 315 |
+
"eval_precision": 0.6637745288500654,
|
| 316 |
+
"eval_recall": 0.6612127045235804,
|
| 317 |
+
"eval_runtime": 24.1208,
|
| 318 |
+
"eval_samples_per_second": 43.075,
|
| 319 |
+
"eval_steps_per_second": 1.368,
|
| 320 |
+
"step": 292
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 9.23076923076923,
|
| 324 |
+
"grad_norm": 4.807325839996338,
|
| 325 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 326 |
+
"loss": 0.7071,
|
| 327 |
+
"step": 300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 9.538461538461538,
|
| 331 |
+
"grad_norm": 5.517625331878662,
|
| 332 |
+
"learning_rate": 1.7361111111111112e-06,
|
| 333 |
+
"loss": 0.6935,
|
| 334 |
+
"step": 310
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 9.846153846153847,
|
| 338 |
+
"grad_norm": 5.944396495819092,
|
| 339 |
+
"learning_rate": 0.0,
|
| 340 |
+
"loss": 0.6984,
|
| 341 |
+
"step": 320
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 9.846153846153847,
|
| 345 |
+
"eval_accuracy": 0.6612127045235804,
|
| 346 |
+
"eval_f1": 0.6503718951301083,
|
| 347 |
+
"eval_loss": 0.8847062587738037,
|
| 348 |
+
"eval_precision": 0.6589546644463634,
|
| 349 |
+
"eval_recall": 0.6612127045235804,
|
| 350 |
+
"eval_runtime": 24.299,
|
| 351 |
+
"eval_samples_per_second": 42.759,
|
| 352 |
+
"eval_steps_per_second": 1.358,
|
| 353 |
+
"step": 320
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 9.846153846153847,
|
| 357 |
+
"step": 320,
|
| 358 |
+
"total_flos": 1.0354878719936594e+18,
|
| 359 |
+
"train_loss": 0.8634449824690819,
|
| 360 |
+
"train_runtime": 4124.7516,
|
| 361 |
+
"train_samples_per_second": 10.066,
|
| 362 |
+
"train_steps_per_second": 0.078
|
| 363 |
}
|
| 364 |
],
|
| 365 |
"logging_steps": 10,
|
| 366 |
+
"max_steps": 320,
|
| 367 |
"num_input_tokens_seen": 0,
|
| 368 |
+
"num_train_epochs": 10,
|
| 369 |
"save_steps": 500,
|
| 370 |
"stateful_callbacks": {
|
| 371 |
"TrainerControl": {
|
|
|
|
| 379 |
"attributes": {}
|
| 380 |
}
|
| 381 |
},
|
| 382 |
+
"total_flos": 1.0354878719936594e+18,
|
| 383 |
"train_batch_size": 32,
|
| 384 |
"trial_name": null,
|
| 385 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ae4769b3298841084684642af921b54de20399af54fc73b927531e321266155
|
| 3 |
size 5304
|