Training in progress, epoch 0
Browse files- all_results.json +6 -6
- model.safetensors +1 -1
- runs/Sep04_15-28-02_0ea876ca526a/events.out.tfevents.1725465739.0ea876ca526a.551.1 +3 -0
- runs/Sep04_16-03-11_0ea876ca526a/events.out.tfevents.1725465798.0ea876ca526a.551.2 +3 -0
- train_results.json +6 -6
- trainer_state.json +332 -49
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 18.823529411764707,
|
| 3 |
+
"total_flos": 5.146567075115827e+17,
|
| 4 |
+
"train_loss": 1.2247119784355163,
|
| 5 |
+
"train_runtime": 1875.9294,
|
| 6 |
+
"train_samples_per_second": 11.6,
|
| 7 |
+
"train_steps_per_second": 0.085
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 111317164
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f18802a2e13a010c49f4068a1fdefab3cfe4630601027959e3737248c185ff36
|
| 3 |
size 111317164
|
runs/Sep04_15-28-02_0ea876ca526a/events.out.tfevents.1725465739.0ea876ca526a.551.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e200d7eb2d845034cdcbb77fe3036b9a9c786e1144c934dbcdf9349cc4eeec3c
|
| 3 |
+
size 410
|
runs/Sep04_16-03-11_0ea876ca526a/events.out.tfevents.1725465798.0ea876ca526a.551.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c587e34b9c643d20fe5db467e41df1fd90e8befdb70089d59d17c0e14d0a4d
|
| 3 |
+
size 5476
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 18.823529411764707,
|
| 3 |
+
"total_flos": 5.146567075115827e+17,
|
| 4 |
+
"train_loss": 1.2247119784355163,
|
| 5 |
+
"train_runtime": 1875.9294,
|
| 6 |
+
"train_samples_per_second": 11.6,
|
| 7 |
+
"train_steps_per_second": 0.085
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,84 +1,367 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "convnext-tiny-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 |
-
"
|
| 14 |
-
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0
|
| 20 |
"eval_accuracy": {
|
| 21 |
-
"accuracy": 0.
|
| 22 |
},
|
| 23 |
-
"eval_logLoss": 1.
|
| 24 |
-
"eval_loss": 1.
|
| 25 |
-
"eval_runtime":
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second":
|
| 28 |
-
"step":
|
| 29 |
},
|
| 30 |
{
|
| 31 |
-
"epoch":
|
| 32 |
-
"grad_norm": 1.
|
| 33 |
-
"learning_rate":
|
| 34 |
-
"loss": 1.
|
| 35 |
"step": 20
|
| 36 |
},
|
| 37 |
{
|
| 38 |
-
"epoch": 2.
|
| 39 |
"eval_accuracy": {
|
| 40 |
-
"accuracy": 0.
|
| 41 |
},
|
| 42 |
-
"eval_logLoss": 1.
|
| 43 |
-
"eval_loss": 1.
|
| 44 |
-
"eval_runtime":
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second": 1.
|
| 47 |
"step": 25
|
| 48 |
},
|
| 49 |
{
|
| 50 |
-
"epoch":
|
| 51 |
-
"grad_norm": 1.
|
| 52 |
-
"learning_rate":
|
| 53 |
-
"loss": 1.
|
| 54 |
"step": 30
|
| 55 |
},
|
| 56 |
{
|
| 57 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
"eval_accuracy": {
|
| 59 |
-
"accuracy": 0.
|
| 60 |
},
|
| 61 |
-
"eval_logLoss": 1.
|
| 62 |
-
"eval_loss": 1.
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second": 1.
|
| 66 |
-
"step":
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"step":
|
| 71 |
-
"total_flos":
|
| 72 |
-
"train_loss": 1.
|
| 73 |
-
"train_runtime":
|
| 74 |
-
"train_samples_per_second":
|
| 75 |
-
"train_steps_per_second": 0.
|
| 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 +375,7 @@
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
-
"total_flos":
|
| 96 |
"train_batch_size": 32,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1656934022903442,
|
| 3 |
+
"best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-160",
|
| 4 |
+
"epoch": 18.823529411764707,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.9411764705882353,
|
| 13 |
+
"eval_accuracy": {
|
| 14 |
+
"accuracy": 0.18382352941176472
|
| 15 |
+
},
|
| 16 |
+
"eval_logLoss": 1.6071832180023193,
|
| 17 |
+
"eval_loss": 1.6071830987930298,
|
| 18 |
+
"eval_runtime": 244.9974,
|
| 19 |
+
"eval_samples_per_second": 1.11,
|
| 20 |
+
"eval_steps_per_second": 0.037,
|
| 21 |
+
"step": 8
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.1764705882352942,
|
| 25 |
+
"grad_norm": 1.0974622964859009,
|
| 26 |
+
"learning_rate": 3.125e-05,
|
| 27 |
+
"loss": 1.6101,
|
| 28 |
"step": 10
|
| 29 |
},
|
| 30 |
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
"eval_accuracy": {
|
| 33 |
+
"accuracy": 0.31985294117647056
|
| 34 |
},
|
| 35 |
+
"eval_logLoss": 1.5668261051177979,
|
| 36 |
+
"eval_loss": 1.5668261051177979,
|
| 37 |
+
"eval_runtime": 4.797,
|
| 38 |
+
"eval_samples_per_second": 56.702,
|
| 39 |
+
"eval_steps_per_second": 1.876,
|
| 40 |
+
"step": 17
|
| 41 |
},
|
| 42 |
{
|
| 43 |
+
"epoch": 2.3529411764705883,
|
| 44 |
+
"grad_norm": 1.2453666925430298,
|
| 45 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 46 |
+
"loss": 1.5645,
|
| 47 |
"step": 20
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 2.9411764705882355,
|
| 51 |
"eval_accuracy": {
|
| 52 |
+
"accuracy": 0.33455882352941174
|
| 53 |
},
|
| 54 |
+
"eval_logLoss": 1.5246020555496216,
|
| 55 |
+
"eval_loss": 1.5246021747589111,
|
| 56 |
+
"eval_runtime": 4.7926,
|
| 57 |
+
"eval_samples_per_second": 56.754,
|
| 58 |
+
"eval_steps_per_second": 1.878,
|
| 59 |
"step": 25
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 3.5294117647058822,
|
| 63 |
+
"grad_norm": 1.36457097530365,
|
| 64 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 65 |
+
"loss": 1.4902,
|
| 66 |
"step": 30
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"eval_accuracy": {
|
| 71 |
+
"accuracy": 0.4007352941176471
|
| 72 |
+
},
|
| 73 |
+
"eval_logLoss": 1.4773920774459839,
|
| 74 |
+
"eval_loss": 1.4773920774459839,
|
| 75 |
+
"eval_runtime": 4.9915,
|
| 76 |
+
"eval_samples_per_second": 54.493,
|
| 77 |
+
"eval_steps_per_second": 1.803,
|
| 78 |
+
"step": 34
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.705882352941177,
|
| 82 |
+
"grad_norm": 1.3080309629440308,
|
| 83 |
+
"learning_rate": 4.166666666666667e-05,
|
| 84 |
+
"loss": 1.4243,
|
| 85 |
+
"step": 40
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.9411764705882355,
|
| 89 |
+
"eval_accuracy": {
|
| 90 |
+
"accuracy": 0.44485294117647056
|
| 91 |
+
},
|
| 92 |
+
"eval_logLoss": 1.4283257722854614,
|
| 93 |
+
"eval_loss": 1.4283257722854614,
|
| 94 |
+
"eval_runtime": 4.7862,
|
| 95 |
+
"eval_samples_per_second": 56.831,
|
| 96 |
+
"eval_steps_per_second": 1.88,
|
| 97 |
+
"step": 42
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 5.882352941176471,
|
| 101 |
+
"grad_norm": 1.7825312614440918,
|
| 102 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 103 |
+
"loss": 1.3502,
|
| 104 |
+
"step": 50
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"eval_accuracy": {
|
| 109 |
+
"accuracy": 0.48161764705882354
|
| 110 |
+
},
|
| 111 |
+
"eval_logLoss": 1.3747049570083618,
|
| 112 |
+
"eval_loss": 1.3747047185897827,
|
| 113 |
+
"eval_runtime": 4.9735,
|
| 114 |
+
"eval_samples_per_second": 54.69,
|
| 115 |
+
"eval_steps_per_second": 1.81,
|
| 116 |
+
"step": 51
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.9411764705882355,
|
| 120 |
+
"eval_accuracy": {
|
| 121 |
+
"accuracy": 0.48161764705882354
|
| 122 |
+
},
|
| 123 |
+
"eval_logLoss": 1.3332045078277588,
|
| 124 |
+
"eval_loss": 1.3332043886184692,
|
| 125 |
+
"eval_runtime": 4.9941,
|
| 126 |
+
"eval_samples_per_second": 54.464,
|
| 127 |
+
"eval_steps_per_second": 1.802,
|
| 128 |
+
"step": 59
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.0588235294117645,
|
| 132 |
+
"grad_norm": 1.616268515586853,
|
| 133 |
+
"learning_rate": 3.472222222222222e-05,
|
| 134 |
+
"loss": 1.2906,
|
| 135 |
+
"step": 60
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_accuracy": {
|
| 140 |
+
"accuracy": 0.5036764705882353
|
| 141 |
+
},
|
| 142 |
+
"eval_logLoss": 1.2978487014770508,
|
| 143 |
+
"eval_loss": 1.2978484630584717,
|
| 144 |
+
"eval_runtime": 4.9213,
|
| 145 |
+
"eval_samples_per_second": 55.27,
|
| 146 |
+
"eval_steps_per_second": 1.829,
|
| 147 |
+
"step": 68
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.235294117647058,
|
| 151 |
+
"grad_norm": 1.5584542751312256,
|
| 152 |
+
"learning_rate": 3.125e-05,
|
| 153 |
+
"loss": 1.2371,
|
| 154 |
+
"step": 70
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 8.941176470588236,
|
| 158 |
+
"eval_accuracy": {
|
| 159 |
+
"accuracy": 0.5147058823529411
|
| 160 |
+
},
|
| 161 |
+
"eval_logLoss": 1.2702081203460693,
|
| 162 |
+
"eval_loss": 1.2702082395553589,
|
| 163 |
+
"eval_runtime": 5.014,
|
| 164 |
+
"eval_samples_per_second": 54.248,
|
| 165 |
+
"eval_steps_per_second": 1.795,
|
| 166 |
+
"step": 76
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 9.411764705882353,
|
| 170 |
+
"grad_norm": 1.5939627885818481,
|
| 171 |
+
"learning_rate": 2.777777777777778e-05,
|
| 172 |
+
"loss": 1.1856,
|
| 173 |
+
"step": 80
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 10.0,
|
| 177 |
+
"eval_accuracy": {
|
| 178 |
+
"accuracy": 0.5404411764705882
|
| 179 |
+
},
|
| 180 |
+
"eval_logLoss": 1.243437647819519,
|
| 181 |
+
"eval_loss": 1.2434377670288086,
|
| 182 |
+
"eval_runtime": 4.901,
|
| 183 |
+
"eval_samples_per_second": 55.499,
|
| 184 |
+
"eval_steps_per_second": 1.836,
|
| 185 |
+
"step": 85
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 10.588235294117647,
|
| 189 |
+
"grad_norm": 1.362315058708191,
|
| 190 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 191 |
+
"loss": 1.1506,
|
| 192 |
+
"step": 90
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 10.941176470588236,
|
| 196 |
+
"eval_accuracy": {
|
| 197 |
+
"accuracy": 0.5477941176470589
|
| 198 |
+
},
|
| 199 |
+
"eval_logLoss": 1.2299580574035645,
|
| 200 |
+
"eval_loss": 1.2299582958221436,
|
| 201 |
+
"eval_runtime": 4.9331,
|
| 202 |
+
"eval_samples_per_second": 55.138,
|
| 203 |
+
"eval_steps_per_second": 1.824,
|
| 204 |
+
"step": 93
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 11.764705882352942,
|
| 208 |
+
"grad_norm": 1.4996492862701416,
|
| 209 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 210 |
+
"loss": 1.0987,
|
| 211 |
+
"step": 100
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 12.0,
|
| 215 |
+
"eval_accuracy": {
|
| 216 |
+
"accuracy": 0.5588235294117647
|
| 217 |
+
},
|
| 218 |
+
"eval_logLoss": 1.2087745666503906,
|
| 219 |
+
"eval_loss": 1.2087748050689697,
|
| 220 |
+
"eval_runtime": 4.8571,
|
| 221 |
+
"eval_samples_per_second": 56.0,
|
| 222 |
+
"eval_steps_per_second": 1.853,
|
| 223 |
+
"step": 102
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 12.941176470588236,
|
| 227 |
+
"grad_norm": 1.7451958656311035,
|
| 228 |
+
"learning_rate": 1.736111111111111e-05,
|
| 229 |
+
"loss": 1.0758,
|
| 230 |
+
"step": 110
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 12.941176470588236,
|
| 234 |
+
"eval_accuracy": {
|
| 235 |
+
"accuracy": 0.5514705882352942
|
| 236 |
+
},
|
| 237 |
+
"eval_logLoss": 1.1948641538619995,
|
| 238 |
+
"eval_loss": 1.19486403465271,
|
| 239 |
+
"eval_runtime": 4.994,
|
| 240 |
+
"eval_samples_per_second": 54.465,
|
| 241 |
+
"eval_steps_per_second": 1.802,
|
| 242 |
+
"step": 110
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 14.0,
|
| 246 |
+
"eval_accuracy": {
|
| 247 |
+
"accuracy": 0.5588235294117647
|
| 248 |
+
},
|
| 249 |
+
"eval_logLoss": 1.1896252632141113,
|
| 250 |
+
"eval_loss": 1.1896252632141113,
|
| 251 |
+
"eval_runtime": 4.9288,
|
| 252 |
+
"eval_samples_per_second": 55.186,
|
| 253 |
+
"eval_steps_per_second": 1.826,
|
| 254 |
+
"step": 119
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.117647058823529,
|
| 258 |
+
"grad_norm": 1.9521229267120361,
|
| 259 |
+
"learning_rate": 1.388888888888889e-05,
|
| 260 |
+
"loss": 1.0483,
|
| 261 |
+
"step": 120
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 14.941176470588236,
|
| 265 |
+
"eval_accuracy": {
|
| 266 |
+
"accuracy": 0.5698529411764706
|
| 267 |
+
},
|
| 268 |
+
"eval_logLoss": 1.177284598350525,
|
| 269 |
+
"eval_loss": 1.177284598350525,
|
| 270 |
+
"eval_runtime": 4.8123,
|
| 271 |
+
"eval_samples_per_second": 56.521,
|
| 272 |
+
"eval_steps_per_second": 1.87,
|
| 273 |
+
"step": 127
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 15.294117647058824,
|
| 277 |
+
"grad_norm": 1.6353868246078491,
|
| 278 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 279 |
+
"loss": 1.0346,
|
| 280 |
+
"step": 130
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 16.0,
|
| 284 |
+
"eval_accuracy": {
|
| 285 |
+
"accuracy": 0.5735294117647058
|
| 286 |
+
},
|
| 287 |
+
"eval_logLoss": 1.1718555688858032,
|
| 288 |
+
"eval_loss": 1.1718555688858032,
|
| 289 |
+
"eval_runtime": 4.8108,
|
| 290 |
+
"eval_samples_per_second": 56.539,
|
| 291 |
+
"eval_steps_per_second": 1.871,
|
| 292 |
+
"step": 136
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 16.470588235294116,
|
| 296 |
+
"grad_norm": 1.8729331493377686,
|
| 297 |
+
"learning_rate": 6.944444444444445e-06,
|
| 298 |
+
"loss": 1.0215,
|
| 299 |
+
"step": 140
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 16.941176470588236,
|
| 303 |
+
"eval_accuracy": {
|
| 304 |
+
"accuracy": 0.5698529411764706
|
| 305 |
+
},
|
| 306 |
+
"eval_logLoss": 1.170174241065979,
|
| 307 |
+
"eval_loss": 1.1701741218566895,
|
| 308 |
+
"eval_runtime": 4.747,
|
| 309 |
+
"eval_samples_per_second": 57.299,
|
| 310 |
+
"eval_steps_per_second": 1.896,
|
| 311 |
+
"step": 144
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 17.647058823529413,
|
| 315 |
+
"grad_norm": 2.009471893310547,
|
| 316 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 317 |
+
"loss": 1.0177,
|
| 318 |
+
"step": 150
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 18.0,
|
| 322 |
+
"eval_accuracy": {
|
| 323 |
+
"accuracy": 0.5772058823529411
|
| 324 |
+
},
|
| 325 |
+
"eval_logLoss": 1.1665880680084229,
|
| 326 |
+
"eval_loss": 1.1665880680084229,
|
| 327 |
+
"eval_runtime": 4.8261,
|
| 328 |
+
"eval_samples_per_second": 56.361,
|
| 329 |
+
"eval_steps_per_second": 1.865,
|
| 330 |
+
"step": 153
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 18.823529411764707,
|
| 334 |
+
"grad_norm": 1.6420903205871582,
|
| 335 |
+
"learning_rate": 0.0,
|
| 336 |
+
"loss": 0.9956,
|
| 337 |
+
"step": 160
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 18.823529411764707,
|
| 341 |
"eval_accuracy": {
|
| 342 |
+
"accuracy": 0.5808823529411765
|
| 343 |
},
|
| 344 |
+
"eval_logLoss": 1.1656935214996338,
|
| 345 |
+
"eval_loss": 1.1656934022903442,
|
| 346 |
+
"eval_runtime": 5.2789,
|
| 347 |
+
"eval_samples_per_second": 51.526,
|
| 348 |
+
"eval_steps_per_second": 1.705,
|
| 349 |
+
"step": 160
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 18.823529411764707,
|
| 353 |
+
"step": 160,
|
| 354 |
+
"total_flos": 5.146567075115827e+17,
|
| 355 |
+
"train_loss": 1.2247119784355163,
|
| 356 |
+
"train_runtime": 1875.9294,
|
| 357 |
+
"train_samples_per_second": 11.6,
|
| 358 |
+
"train_steps_per_second": 0.085
|
| 359 |
}
|
| 360 |
],
|
| 361 |
"logging_steps": 10,
|
| 362 |
+
"max_steps": 160,
|
| 363 |
"num_input_tokens_seen": 0,
|
| 364 |
+
"num_train_epochs": 20,
|
| 365 |
"save_steps": 500,
|
| 366 |
"stateful_callbacks": {
|
| 367 |
"TrainerControl": {
|
|
|
|
| 375 |
"attributes": {}
|
| 376 |
}
|
| 377 |
},
|
| 378 |
+
"total_flos": 5.146567075115827e+17,
|
| 379 |
"train_batch_size": 32,
|
| 380 |
"trial_name": null,
|
| 381 |
"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 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c61624ff0d74b4057fab81648b93ab779baa0aae583ac972116fc9f8c81f829
|
| 3 |
size 5176
|