Training in progress, epoch 1
Browse files- all_results.json +7 -7
- eval_results.json +4 -3
- model.safetensors +1 -1
- runs/Dec03_16-36-36_l-hvjvvxgp4c.local/events.out.tfevents.1733262559.l-hvjvvxgp4c.local.87043.7 +3 -0
- runs/Dec03_16-54-59_l-hvjvvxgp4c.local/events.out.tfevents.1733262907.l-hvjvvxgp4c.local.90109.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +327 -14
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 6.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
"eval_model_preparation_time": 0.0027,
|
| 6 |
"eval_runtime": 4.4666,
|
| 7 |
-
"eval_samples_per_second": 29.
|
| 8 |
"eval_steps_per_second": 3.806,
|
| 9 |
"total_flos": 1.542108645707858e+17,
|
| 10 |
-
"train_loss": 0.
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.9924812030075187,
|
| 4 |
+
"eval_loss": 0.332000732421875,
|
| 5 |
"eval_model_preparation_time": 0.0027,
|
| 6 |
"eval_runtime": 4.4666,
|
| 7 |
+
"eval_samples_per_second": 29.777,
|
| 8 |
"eval_steps_per_second": 3.806,
|
| 9 |
"total_flos": 1.542108645707858e+17,
|
| 10 |
+
"train_loss": 0.5066085149080325,
|
| 11 |
+
"train_runtime": 701.1808,
|
| 12 |
+
"train_samples_per_second": 8.848,
|
| 13 |
+
"train_steps_per_second": 0.556
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
|
|
|
| 4 |
"eval_model_preparation_time": 0.0027,
|
| 5 |
"eval_runtime": 4.4666,
|
| 6 |
-
"eval_samples_per_second": 29.
|
| 7 |
"eval_steps_per_second": 3.806
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_accuracy": 0.9924812030075187,
|
| 4 |
+
"eval_loss": 0.332000732421875,
|
| 5 |
"eval_model_preparation_time": 0.0027,
|
| 6 |
"eval_runtime": 4.4666,
|
| 7 |
+
"eval_samples_per_second": 29.777,
|
| 8 |
"eval_steps_per_second": 3.806
|
| 9 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110345908
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b3b519e253030147b90f87f6c934a194765f0371cde0c0d75ce22b27f78c25
|
| 3 |
size 110345908
|
runs/Dec03_16-36-36_l-hvjvvxgp4c.local/events.out.tfevents.1733262559.l-hvjvvxgp4c.local.87043.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d783f8a2c496aa9c73353ff21484604acfa0bc1c9af5c25fad74c3b94978ca9b
|
| 3 |
+
size 477
|
runs/Dec03_16-54-59_l-hvjvvxgp4c.local/events.out.tfevents.1733262907.l-hvjvvxgp4c.local.90109.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bc56a2af3505237b3e4ea91ffd24fc2dfec0c02d7c02a591d47e059ae73e822
|
| 3 |
+
size 6027
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 6.0,
|
| 3 |
"total_flos": 1.542108645707858e+17,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 6.0,
|
| 3 |
"total_flos": 1.542108645707858e+17,
|
| 4 |
+
"train_loss": 0.5066085149080325,
|
| 5 |
+
"train_runtime": 701.1808,
|
| 6 |
+
"train_samples_per_second": 8.848,
|
| 7 |
+
"train_steps_per_second": 0.556
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,32 +1,345 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"num_input_tokens_seen": 0,
|
| 14 |
-
"num_train_epochs":
|
| 15 |
-
"save_steps":
|
| 16 |
"stateful_callbacks": {
|
| 17 |
"TrainerControl": {
|
| 18 |
"args": {
|
| 19 |
"should_epoch_stop": false,
|
| 20 |
"should_evaluate": false,
|
| 21 |
"should_log": false,
|
| 22 |
-
"should_save":
|
| 23 |
-
"should_training_stop":
|
| 24 |
},
|
| 25 |
"attributes": {}
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"total_flos":
|
| 29 |
-
"train_batch_size":
|
| 30 |
"trial_name": null,
|
| 31 |
"trial_params": null
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.34840309619903564,
|
| 3 |
+
"best_model_checkpoint": "plant_classification/checkpoint-300",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 390,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15384615384615385,
|
| 13 |
+
"grad_norm": 6.1840081214904785,
|
| 14 |
+
"learning_rate": 2.564102564102564e-06,
|
| 15 |
+
"loss": 1.097,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3076923076923077,
|
| 20 |
+
"grad_norm": 5.466547966003418,
|
| 21 |
+
"learning_rate": 5.128205128205128e-06,
|
| 22 |
+
"loss": 1.0789,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.46153846153846156,
|
| 27 |
+
"grad_norm": 4.893115997314453,
|
| 28 |
+
"learning_rate": 7.692307692307694e-06,
|
| 29 |
+
"loss": 1.0142,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.6153846153846154,
|
| 34 |
+
"grad_norm": 6.236436367034912,
|
| 35 |
+
"learning_rate": 9.971509971509972e-06,
|
| 36 |
+
"loss": 0.9414,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7692307692307693,
|
| 41 |
+
"grad_norm": 5.752598762512207,
|
| 42 |
+
"learning_rate": 9.686609686609687e-06,
|
| 43 |
+
"loss": 0.8319,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9230769230769231,
|
| 48 |
+
"grad_norm": 8.083925247192383,
|
| 49 |
+
"learning_rate": 9.401709401709402e-06,
|
| 50 |
+
"loss": 0.7291,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0769230769230769,
|
| 55 |
+
"grad_norm": 8.074342727661133,
|
| 56 |
+
"learning_rate": 9.116809116809118e-06,
|
| 57 |
+
"loss": 0.6521,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.2307692307692308,
|
| 62 |
+
"grad_norm": 5.033174514770508,
|
| 63 |
+
"learning_rate": 8.831908831908833e-06,
|
| 64 |
+
"loss": 0.596,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.3846153846153846,
|
| 69 |
+
"grad_norm": 8.695470809936523,
|
| 70 |
+
"learning_rate": 8.547008547008548e-06,
|
| 71 |
+
"loss": 0.5473,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.5384615384615383,
|
| 76 |
+
"grad_norm": 8.49801254272461,
|
| 77 |
+
"learning_rate": 8.262108262108262e-06,
|
| 78 |
+
"loss": 0.484,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.5384615384615383,
|
| 83 |
+
"eval_accuracy": 0.9097744360902256,
|
| 84 |
+
"eval_loss": 0.4657277762889862,
|
| 85 |
+
"eval_model_preparation_time": 0.0027,
|
| 86 |
+
"eval_runtime": 5.3487,
|
| 87 |
+
"eval_samples_per_second": 24.866,
|
| 88 |
+
"eval_steps_per_second": 3.178,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.6923076923076923,
|
| 93 |
+
"grad_norm": 5.612356662750244,
|
| 94 |
+
"learning_rate": 7.977207977207979e-06,
|
| 95 |
+
"loss": 0.4621,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.8461538461538463,
|
| 100 |
+
"grad_norm": 3.638047933578491,
|
| 101 |
+
"learning_rate": 7.692307692307694e-06,
|
| 102 |
+
"loss": 0.4771,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.0,
|
| 107 |
+
"grad_norm": 10.50847339630127,
|
| 108 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 109 |
+
"loss": 0.452,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.1538461538461537,
|
| 114 |
+
"grad_norm": 5.7228593826293945,
|
| 115 |
+
"learning_rate": 7.122507122507123e-06,
|
| 116 |
+
"loss": 0.4428,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.3076923076923075,
|
| 121 |
+
"grad_norm": 7.263442516326904,
|
| 122 |
+
"learning_rate": 6.837606837606839e-06,
|
| 123 |
+
"loss": 0.4217,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.4615384615384617,
|
| 128 |
+
"grad_norm": 7.28318452835083,
|
| 129 |
+
"learning_rate": 6.552706552706553e-06,
|
| 130 |
+
"loss": 0.4084,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.6153846153846154,
|
| 135 |
+
"grad_norm": 8.621001243591309,
|
| 136 |
+
"learning_rate": 6.267806267806268e-06,
|
| 137 |
+
"loss": 0.4402,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.769230769230769,
|
| 142 |
+
"grad_norm": 9.766897201538086,
|
| 143 |
+
"learning_rate": 5.982905982905983e-06,
|
| 144 |
+
"loss": 0.4183,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.9230769230769234,
|
| 149 |
+
"grad_norm": 5.3531975746154785,
|
| 150 |
+
"learning_rate": 5.6980056980056985e-06,
|
| 151 |
+
"loss": 0.4135,
|
| 152 |
+
"step": 190
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.076923076923077,
|
| 156 |
+
"grad_norm": 5.893077373504639,
|
| 157 |
+
"learning_rate": 5.413105413105414e-06,
|
| 158 |
+
"loss": 0.4002,
|
| 159 |
+
"step": 200
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.076923076923077,
|
| 163 |
+
"eval_accuracy": 0.9699248120300752,
|
| 164 |
+
"eval_loss": 0.3610040843486786,
|
| 165 |
+
"eval_model_preparation_time": 0.0027,
|
| 166 |
+
"eval_runtime": 5.6532,
|
| 167 |
+
"eval_samples_per_second": 23.527,
|
| 168 |
+
"eval_steps_per_second": 3.007,
|
| 169 |
+
"step": 200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.230769230769231,
|
| 173 |
+
"grad_norm": 5.7207183837890625,
|
| 174 |
+
"learning_rate": 5.128205128205128e-06,
|
| 175 |
+
"loss": 0.3907,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.3846153846153846,
|
| 180 |
+
"grad_norm": 5.367263317108154,
|
| 181 |
+
"learning_rate": 4.8433048433048435e-06,
|
| 182 |
+
"loss": 0.4029,
|
| 183 |
+
"step": 220
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.5384615384615383,
|
| 187 |
+
"grad_norm": 9.18671989440918,
|
| 188 |
+
"learning_rate": 4.558404558404559e-06,
|
| 189 |
+
"loss": 0.4166,
|
| 190 |
+
"step": 230
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.6923076923076925,
|
| 194 |
+
"grad_norm": 5.503479480743408,
|
| 195 |
+
"learning_rate": 4.273504273504274e-06,
|
| 196 |
+
"loss": 0.4059,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.8461538461538463,
|
| 201 |
+
"grad_norm": 5.8476786613464355,
|
| 202 |
+
"learning_rate": 3.9886039886039894e-06,
|
| 203 |
+
"loss": 0.3642,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.0,
|
| 208 |
+
"grad_norm": 7.110011577606201,
|
| 209 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 210 |
+
"loss": 0.4197,
|
| 211 |
+
"step": 260
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 4.153846153846154,
|
| 215 |
+
"grad_norm": 9.354405403137207,
|
| 216 |
+
"learning_rate": 3.4188034188034193e-06,
|
| 217 |
+
"loss": 0.3733,
|
| 218 |
+
"step": 270
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.3076923076923075,
|
| 222 |
+
"grad_norm": 3.5231635570526123,
|
| 223 |
+
"learning_rate": 3.133903133903134e-06,
|
| 224 |
+
"loss": 0.4287,
|
| 225 |
+
"step": 280
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.461538461538462,
|
| 229 |
+
"grad_norm": 4.517345905303955,
|
| 230 |
+
"learning_rate": 2.8490028490028492e-06,
|
| 231 |
+
"loss": 0.3868,
|
| 232 |
+
"step": 290
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.615384615384615,
|
| 236 |
+
"grad_norm": 10.131566047668457,
|
| 237 |
+
"learning_rate": 2.564102564102564e-06,
|
| 238 |
+
"loss": 0.4059,
|
| 239 |
+
"step": 300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.615384615384615,
|
| 243 |
+
"eval_accuracy": 0.9849624060150376,
|
| 244 |
+
"eval_loss": 0.34840309619903564,
|
| 245 |
+
"eval_model_preparation_time": 0.0027,
|
| 246 |
+
"eval_runtime": 6.7969,
|
| 247 |
+
"eval_samples_per_second": 19.568,
|
| 248 |
+
"eval_steps_per_second": 2.501,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.769230769230769,
|
| 253 |
+
"grad_norm": 3.7114639282226562,
|
| 254 |
+
"learning_rate": 2.2792022792022796e-06,
|
| 255 |
+
"loss": 0.4177,
|
| 256 |
+
"step": 310
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.923076923076923,
|
| 260 |
+
"grad_norm": 5.1394124031066895,
|
| 261 |
+
"learning_rate": 1.9943019943019947e-06,
|
| 262 |
+
"loss": 0.3838,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.076923076923077,
|
| 267 |
+
"grad_norm": 5.99159049987793,
|
| 268 |
+
"learning_rate": 1.7094017094017097e-06,
|
| 269 |
+
"loss": 0.348,
|
| 270 |
+
"step": 330
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.230769230769231,
|
| 274 |
+
"grad_norm": 2.067537307739258,
|
| 275 |
+
"learning_rate": 1.4245014245014246e-06,
|
| 276 |
+
"loss": 0.3965,
|
| 277 |
+
"step": 340
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.384615384615385,
|
| 281 |
+
"grad_norm": 8.420255661010742,
|
| 282 |
+
"learning_rate": 1.1396011396011398e-06,
|
| 283 |
+
"loss": 0.403,
|
| 284 |
+
"step": 350
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.538461538461538,
|
| 288 |
+
"grad_norm": 5.098587512969971,
|
| 289 |
+
"learning_rate": 8.547008547008548e-07,
|
| 290 |
+
"loss": 0.3657,
|
| 291 |
+
"step": 360
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 5.6923076923076925,
|
| 295 |
+
"grad_norm": 7.574987411499023,
|
| 296 |
+
"learning_rate": 5.698005698005699e-07,
|
| 297 |
+
"loss": 0.3783,
|
| 298 |
+
"step": 370
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 5.846153846153846,
|
| 302 |
+
"grad_norm": 8.597725868225098,
|
| 303 |
+
"learning_rate": 2.8490028490028494e-07,
|
| 304 |
+
"loss": 0.3845,
|
| 305 |
+
"step": 380
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 6.0,
|
| 309 |
+
"grad_norm": 16.919288635253906,
|
| 310 |
+
"learning_rate": 0.0,
|
| 311 |
+
"loss": 0.3776,
|
| 312 |
+
"step": 390
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 6.0,
|
| 316 |
+
"step": 390,
|
| 317 |
+
"total_flos": 1.542108645707858e+17,
|
| 318 |
+
"train_loss": 0.5066085149080325,
|
| 319 |
+
"train_runtime": 701.1808,
|
| 320 |
+
"train_samples_per_second": 8.848,
|
| 321 |
+
"train_steps_per_second": 0.556
|
| 322 |
+
}
|
| 323 |
+
],
|
| 324 |
+
"logging_steps": 10,
|
| 325 |
+
"max_steps": 390,
|
| 326 |
"num_input_tokens_seen": 0,
|
| 327 |
+
"num_train_epochs": 6,
|
| 328 |
+
"save_steps": 100,
|
| 329 |
"stateful_callbacks": {
|
| 330 |
"TrainerControl": {
|
| 331 |
"args": {
|
| 332 |
"should_epoch_stop": false,
|
| 333 |
"should_evaluate": false,
|
| 334 |
"should_log": false,
|
| 335 |
+
"should_save": true,
|
| 336 |
+
"should_training_stop": true
|
| 337 |
},
|
| 338 |
"attributes": {}
|
| 339 |
}
|
| 340 |
},
|
| 341 |
+
"total_flos": 1.542108645707858e+17,
|
| 342 |
+
"train_batch_size": 16,
|
| 343 |
"trial_name": null,
|
| 344 |
"trial_params": null
|
| 345 |
}
|
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:b6dac486ee10a56bc8293ae2538c014911af98251123a5cc54d47afbcea2aeaa
|
| 3 |
size 5304
|