Commit
·
7f7aba6
1
Parent(s):
9da7035
Training in progress, epoch 33
Browse files- checkpoint-10/trainer_state.json +0 -22
- {checkpoint-10 → checkpoint-320}/added_tokens.json +0 -0
- {checkpoint-10 → checkpoint-320}/config.json +0 -0
- {checkpoint-10 → checkpoint-320}/optimizer.pt +2 -2
- {checkpoint-10 → checkpoint-320}/pytorch_model.bin +1 -1
- {checkpoint-10 → checkpoint-320}/rng_state.pth +1 -1
- {checkpoint-10 → checkpoint-320}/scheduler.pt +1 -1
- {checkpoint-10 → checkpoint-320}/special_tokens_map.json +0 -0
- {checkpoint-10 → checkpoint-320}/spm.model +0 -0
- {checkpoint-10 → checkpoint-320}/tokenizer.json +0 -0
- {checkpoint-10 → checkpoint-320}/tokenizer_config.json +0 -0
- checkpoint-320/trainer_state.json +334 -0
- {checkpoint-10 → checkpoint-320}/training_args.bin +0 -0
- checkpoint-330/added_tokens.json +3 -0
- checkpoint-330/config.json +59 -0
- checkpoint-330/optimizer.pt +3 -0
- checkpoint-330/pytorch_model.bin +3 -0
- checkpoint-330/rng_state.pth +3 -0
- checkpoint-330/scheduler.pt +3 -0
- checkpoint-330/special_tokens_map.json +9 -0
- checkpoint-330/spm.model +3 -0
- checkpoint-330/tokenizer.json +0 -0
- checkpoint-330/tokenizer_config.json +16 -0
- checkpoint-330/trainer_state.json +360 -0
- checkpoint-330/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063253.9cc823f43576.282.1 +2 -2
checkpoint-10/trainer_state.json
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.0,
|
| 5 |
-
"global_step": 10,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.1,
|
| 12 |
-
"learning_rate": 1.9960000000000002e-05,
|
| 13 |
-
"loss": 2.314,
|
| 14 |
-
"step": 1
|
| 15 |
-
}
|
| 16 |
-
],
|
| 17 |
-
"max_steps": 500,
|
| 18 |
-
"num_train_epochs": 50,
|
| 19 |
-
"total_flos": 3354967079424.0,
|
| 20 |
-
"trial_name": null,
|
| 21 |
-
"trial_params": null
|
| 22 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-10 → checkpoint-320}/added_tokens.json
RENAMED
|
File without changes
|
{checkpoint-10 → checkpoint-320}/config.json
RENAMED
|
File without changes
|
{checkpoint-10 → checkpoint-320}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10d02ebf27d06e75305b818f564bc0d6388b260a305ac331618c2ddf0c12353a
|
| 3 |
+
size 1475557125
|
{checkpoint-10 → checkpoint-320}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545aa19eb4410fc3feed598b75c981bfdcbb6c952229824c6bd1b04e161f9f84
|
| 3 |
size 737788917
|
{checkpoint-10 → checkpoint-320}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3143a2798a49b9dcf15a141512c86b6add165baf4f859e660e7985e9d40e60
|
| 3 |
size 14575
|
{checkpoint-10 → checkpoint-320}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29ea6a10a633bcfa1c650a32be0ea72bf6870f43bc564bbaa5c04ac08767fab3
|
| 3 |
size 627
|
{checkpoint-10 → checkpoint-320}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-10 → checkpoint-320}/spm.model
RENAMED
|
File without changes
|
{checkpoint-10 → checkpoint-320}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-10 → checkpoint-320}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoint-320/trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 32.0,
|
| 5 |
+
"global_step": 320,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 1.9960000000000002e-05,
|
| 13 |
+
"loss": 2.314,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.5,
|
| 18 |
+
"learning_rate": 1.9e-05,
|
| 19 |
+
"loss": 2.311,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.5,
|
| 24 |
+
"eval_accuracy": 0.15,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 36.27968215942383,
|
| 27 |
+
"eval_f1": 0.08571428571428572,
|
| 28 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 29 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 40,
|
| 32 |
+
"eval_loss": 2.3033015727996826,
|
| 33 |
+
"eval_precision": 0.11052631578947367,
|
| 34 |
+
"eval_recall": 0.15,
|
| 35 |
+
"eval_runtime": 0.2186,
|
| 36 |
+
"eval_samples_per_second": 91.494,
|
| 37 |
+
"eval_steps_per_second": 13.724,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 5.000797271728516,
|
| 40 |
+
"step": 25
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.0,
|
| 44 |
+
"learning_rate": 1.8e-05,
|
| 45 |
+
"loss": 2.2703,
|
| 46 |
+
"step": 50
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 5.0,
|
| 50 |
+
"eval_accuracy": 0.2,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 36.279693603515625,
|
| 53 |
+
"eval_f1": 0.06857142857142857,
|
| 54 |
+
"eval_gpu_ram_allocated": 4.843057632446289,
|
| 55 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 38,
|
| 58 |
+
"eval_loss": 2.3011314868927,
|
| 59 |
+
"eval_precision": 0.041666666666666664,
|
| 60 |
+
"eval_recall": 0.2,
|
| 61 |
+
"eval_runtime": 0.2293,
|
| 62 |
+
"eval_samples_per_second": 87.241,
|
| 63 |
+
"eval_steps_per_second": 13.086,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 5.012126922607422,
|
| 66 |
+
"step": 50
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 7.5,
|
| 70 |
+
"learning_rate": 1.704e-05,
|
| 71 |
+
"loss": 2.0062,
|
| 72 |
+
"step": 75
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.5,
|
| 76 |
+
"eval_accuracy": 0.15,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 36.27973175048828,
|
| 79 |
+
"eval_f1": 0.07936507936507937,
|
| 80 |
+
"eval_gpu_ram_allocated": 4.843067646026611,
|
| 81 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 42,
|
| 84 |
+
"eval_loss": 2.2817370891571045,
|
| 85 |
+
"eval_precision": 0.05428571428571429,
|
| 86 |
+
"eval_recall": 0.15,
|
| 87 |
+
"eval_runtime": 0.208,
|
| 88 |
+
"eval_samples_per_second": 96.173,
|
| 89 |
+
"eval_steps_per_second": 14.426,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 4.985599517822266,
|
| 92 |
+
"step": 75
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 10.0,
|
| 96 |
+
"learning_rate": 1.6040000000000002e-05,
|
| 97 |
+
"loss": 1.49,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 10.0,
|
| 102 |
+
"eval_accuracy": 0.2,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 36.27973556518555,
|
| 105 |
+
"eval_f1": 0.11777777777777779,
|
| 106 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 107 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 37,
|
| 110 |
+
"eval_loss": 2.3280632495880127,
|
| 111 |
+
"eval_precision": 0.0869047619047619,
|
| 112 |
+
"eval_recall": 0.2,
|
| 113 |
+
"eval_runtime": 0.208,
|
| 114 |
+
"eval_samples_per_second": 96.137,
|
| 115 |
+
"eval_steps_per_second": 14.421,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 4.982398986816406,
|
| 118 |
+
"step": 100
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 12.5,
|
| 122 |
+
"learning_rate": 1.5040000000000002e-05,
|
| 123 |
+
"loss": 0.9424,
|
| 124 |
+
"step": 125
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 12.5,
|
| 128 |
+
"eval_accuracy": 0.25,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 36.27980041503906,
|
| 131 |
+
"eval_f1": 0.17333333333333334,
|
| 132 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 133 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 42,
|
| 136 |
+
"eval_loss": 2.3475446701049805,
|
| 137 |
+
"eval_precision": 0.14166666666666666,
|
| 138 |
+
"eval_recall": 0.25,
|
| 139 |
+
"eval_runtime": 0.2046,
|
| 140 |
+
"eval_samples_per_second": 97.736,
|
| 141 |
+
"eval_steps_per_second": 14.66,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 4.944629669189453,
|
| 144 |
+
"step": 125
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 15.0,
|
| 148 |
+
"learning_rate": 1.4040000000000001e-05,
|
| 149 |
+
"loss": 0.5591,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 15.0,
|
| 154 |
+
"eval_accuracy": 0.25,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 36.27981948852539,
|
| 157 |
+
"eval_f1": 0.17444444444444446,
|
| 158 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 159 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 29,
|
| 162 |
+
"eval_loss": 2.4503185749053955,
|
| 163 |
+
"eval_precision": 0.14523809523809522,
|
| 164 |
+
"eval_recall": 0.25,
|
| 165 |
+
"eval_runtime": 0.2141,
|
| 166 |
+
"eval_samples_per_second": 93.429,
|
| 167 |
+
"eval_steps_per_second": 14.014,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 4.920143127441406,
|
| 170 |
+
"step": 150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.5,
|
| 174 |
+
"learning_rate": 1.3080000000000002e-05,
|
| 175 |
+
"loss": 0.2893,
|
| 176 |
+
"step": 175
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.5,
|
| 180 |
+
"eval_accuracy": 0.25,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 36.27982711791992,
|
| 183 |
+
"eval_f1": 0.17444444444444446,
|
| 184 |
+
"eval_gpu_ram_allocated": 4.843067646026611,
|
| 185 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 43,
|
| 188 |
+
"eval_loss": 2.555687665939331,
|
| 189 |
+
"eval_precision": 0.14523809523809522,
|
| 190 |
+
"eval_recall": 0.25,
|
| 191 |
+
"eval_runtime": 0.2265,
|
| 192 |
+
"eval_samples_per_second": 88.288,
|
| 193 |
+
"eval_steps_per_second": 13.243,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 4.961811065673828,
|
| 196 |
+
"step": 175
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 20.0,
|
| 200 |
+
"learning_rate": 1.2080000000000001e-05,
|
| 201 |
+
"loss": 0.1623,
|
| 202 |
+
"step": 200
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 20.0,
|
| 206 |
+
"eval_accuracy": 0.3,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 36.279876708984375,
|
| 209 |
+
"eval_f1": 0.2411111111111111,
|
| 210 |
+
"eval_gpu_ram_allocated": 4.843057632446289,
|
| 211 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 30,
|
| 214 |
+
"eval_loss": 2.621793270111084,
|
| 215 |
+
"eval_precision": 0.2452380952380952,
|
| 216 |
+
"eval_recall": 0.3,
|
| 217 |
+
"eval_runtime": 0.217,
|
| 218 |
+
"eval_samples_per_second": 92.146,
|
| 219 |
+
"eval_steps_per_second": 13.822,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 4.910972595214844,
|
| 222 |
+
"step": 200
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 22.5,
|
| 226 |
+
"learning_rate": 1.1080000000000002e-05,
|
| 227 |
+
"loss": 0.0817,
|
| 228 |
+
"step": 225
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 22.5,
|
| 232 |
+
"eval_accuracy": 0.3,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 36.279930114746094,
|
| 235 |
+
"eval_f1": 0.24,
|
| 236 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 237 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 38,
|
| 240 |
+
"eval_loss": 2.734551191329956,
|
| 241 |
+
"eval_precision": 0.24166666666666664,
|
| 242 |
+
"eval_recall": 0.3,
|
| 243 |
+
"eval_runtime": 0.2092,
|
| 244 |
+
"eval_samples_per_second": 95.586,
|
| 245 |
+
"eval_steps_per_second": 14.338,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 4.941272735595703,
|
| 248 |
+
"step": 225
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 25.0,
|
| 252 |
+
"learning_rate": 1.008e-05,
|
| 253 |
+
"loss": 0.0475,
|
| 254 |
+
"step": 250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 25.0,
|
| 258 |
+
"eval_accuracy": 0.3,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 36.27995300292969,
|
| 261 |
+
"eval_f1": 0.23444444444444446,
|
| 262 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 263 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 40,
|
| 266 |
+
"eval_loss": 2.9325406551361084,
|
| 267 |
+
"eval_precision": 0.23690476190476187,
|
| 268 |
+
"eval_recall": 0.3,
|
| 269 |
+
"eval_runtime": 0.2145,
|
| 270 |
+
"eval_samples_per_second": 93.259,
|
| 271 |
+
"eval_steps_per_second": 13.989,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 4.931392669677734,
|
| 274 |
+
"step": 250
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 27.5,
|
| 278 |
+
"learning_rate": 9.080000000000001e-06,
|
| 279 |
+
"loss": 0.0322,
|
| 280 |
+
"step": 275
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 27.5,
|
| 284 |
+
"eval_accuracy": 0.3,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 36.28001403808594,
|
| 287 |
+
"eval_f1": 0.2511111111111112,
|
| 288 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 289 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 42,
|
| 292 |
+
"eval_loss": 3.123502254486084,
|
| 293 |
+
"eval_precision": 0.2869047619047619,
|
| 294 |
+
"eval_recall": 0.3,
|
| 295 |
+
"eval_runtime": 0.2104,
|
| 296 |
+
"eval_samples_per_second": 95.043,
|
| 297 |
+
"eval_steps_per_second": 14.256,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 4.933628082275391,
|
| 300 |
+
"step": 275
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 30.0,
|
| 304 |
+
"learning_rate": 8.08e-06,
|
| 305 |
+
"loss": 0.0254,
|
| 306 |
+
"step": 300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 30.0,
|
| 310 |
+
"eval_accuracy": 0.3,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 36.280025482177734,
|
| 313 |
+
"eval_f1": 0.23444444444444446,
|
| 314 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 315 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 30,
|
| 318 |
+
"eval_loss": 3.145473003387451,
|
| 319 |
+
"eval_precision": 0.23690476190476187,
|
| 320 |
+
"eval_recall": 0.3,
|
| 321 |
+
"eval_runtime": 0.2137,
|
| 322 |
+
"eval_samples_per_second": 93.578,
|
| 323 |
+
"eval_steps_per_second": 14.037,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.938743591308594,
|
| 326 |
+
"step": 300
|
| 327 |
+
}
|
| 328 |
+
],
|
| 329 |
+
"max_steps": 500,
|
| 330 |
+
"num_train_epochs": 50,
|
| 331 |
+
"total_flos": 107663196007104.0,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|
{checkpoint-10 → checkpoint-320}/training_args.bin
RENAMED
|
File without changes
|
checkpoint-330/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-330/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Society & Culture",
|
| 12 |
+
"1": "Science & Mathematics",
|
| 13 |
+
"2": "Health",
|
| 14 |
+
"3": "Education & Reference",
|
| 15 |
+
"4": "Computers & Internet",
|
| 16 |
+
"5": "Sports",
|
| 17 |
+
"6": "Business & Finance",
|
| 18 |
+
"7": "Entertainment & Music",
|
| 19 |
+
"8": "Family & Relationships",
|
| 20 |
+
"9": "Politics & Government"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"Business & Finance": 6,
|
| 26 |
+
"Computers & Internet": 4,
|
| 27 |
+
"Education & Reference": 3,
|
| 28 |
+
"Entertainment & Music": 7,
|
| 29 |
+
"Family & Relationships": 8,
|
| 30 |
+
"Health": 2,
|
| 31 |
+
"Politics & Government": 9,
|
| 32 |
+
"Science & Mathematics": 1,
|
| 33 |
+
"Society & Culture": 0,
|
| 34 |
+
"Sports": 5
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"max_position_embeddings": 512,
|
| 38 |
+
"max_relative_positions": -1,
|
| 39 |
+
"model_type": "deberta-v2",
|
| 40 |
+
"norm_rel_ebd": "layer_norm",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"pooler_dropout": 0,
|
| 45 |
+
"pooler_hidden_act": "gelu",
|
| 46 |
+
"pooler_hidden_size": 768,
|
| 47 |
+
"pos_att_type": [
|
| 48 |
+
"p2c",
|
| 49 |
+
"c2p"
|
| 50 |
+
],
|
| 51 |
+
"position_biased_input": false,
|
| 52 |
+
"position_buckets": 256,
|
| 53 |
+
"relative_attention": true,
|
| 54 |
+
"share_att_key": true,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.31.0",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
checkpoint-330/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed024c714c4752b95f5020e1ffd2f59940ea99f2bac5826eb9ebfc11a6402ee0
|
| 3 |
+
size 1475557125
|
checkpoint-330/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd18743bdfde8be92fbd991f5cad7d7c0cd7aaca0583e919148be21d96ce8668
|
| 3 |
+
size 737788917
|
checkpoint-330/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:172ad3783b50b89f49d659f4f234a7bb8ccb479b05073e534df5e40060af3c37
|
| 3 |
+
size 14575
|
checkpoint-330/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfeff0174eed12f41b793614fed3bdc8efce764c415e04518a3297ac70a962f8
|
| 3 |
+
size 627
|
checkpoint-330/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
checkpoint-330/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-330/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-330/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
checkpoint-330/trainer_state.json
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 33.0,
|
| 5 |
+
"global_step": 330,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 1.9960000000000002e-05,
|
| 13 |
+
"loss": 2.314,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.5,
|
| 18 |
+
"learning_rate": 1.9e-05,
|
| 19 |
+
"loss": 2.311,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.5,
|
| 24 |
+
"eval_accuracy": 0.15,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 36.27968215942383,
|
| 27 |
+
"eval_f1": 0.08571428571428572,
|
| 28 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 29 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 40,
|
| 32 |
+
"eval_loss": 2.3033015727996826,
|
| 33 |
+
"eval_precision": 0.11052631578947367,
|
| 34 |
+
"eval_recall": 0.15,
|
| 35 |
+
"eval_runtime": 0.2186,
|
| 36 |
+
"eval_samples_per_second": 91.494,
|
| 37 |
+
"eval_steps_per_second": 13.724,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 5.000797271728516,
|
| 40 |
+
"step": 25
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.0,
|
| 44 |
+
"learning_rate": 1.8e-05,
|
| 45 |
+
"loss": 2.2703,
|
| 46 |
+
"step": 50
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 5.0,
|
| 50 |
+
"eval_accuracy": 0.2,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 36.279693603515625,
|
| 53 |
+
"eval_f1": 0.06857142857142857,
|
| 54 |
+
"eval_gpu_ram_allocated": 4.843057632446289,
|
| 55 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 38,
|
| 58 |
+
"eval_loss": 2.3011314868927,
|
| 59 |
+
"eval_precision": 0.041666666666666664,
|
| 60 |
+
"eval_recall": 0.2,
|
| 61 |
+
"eval_runtime": 0.2293,
|
| 62 |
+
"eval_samples_per_second": 87.241,
|
| 63 |
+
"eval_steps_per_second": 13.086,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 5.012126922607422,
|
| 66 |
+
"step": 50
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 7.5,
|
| 70 |
+
"learning_rate": 1.704e-05,
|
| 71 |
+
"loss": 2.0062,
|
| 72 |
+
"step": 75
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.5,
|
| 76 |
+
"eval_accuracy": 0.15,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 36.27973175048828,
|
| 79 |
+
"eval_f1": 0.07936507936507937,
|
| 80 |
+
"eval_gpu_ram_allocated": 4.843067646026611,
|
| 81 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 42,
|
| 84 |
+
"eval_loss": 2.2817370891571045,
|
| 85 |
+
"eval_precision": 0.05428571428571429,
|
| 86 |
+
"eval_recall": 0.15,
|
| 87 |
+
"eval_runtime": 0.208,
|
| 88 |
+
"eval_samples_per_second": 96.173,
|
| 89 |
+
"eval_steps_per_second": 14.426,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 4.985599517822266,
|
| 92 |
+
"step": 75
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 10.0,
|
| 96 |
+
"learning_rate": 1.6040000000000002e-05,
|
| 97 |
+
"loss": 1.49,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 10.0,
|
| 102 |
+
"eval_accuracy": 0.2,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 36.27973556518555,
|
| 105 |
+
"eval_f1": 0.11777777777777779,
|
| 106 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 107 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 37,
|
| 110 |
+
"eval_loss": 2.3280632495880127,
|
| 111 |
+
"eval_precision": 0.0869047619047619,
|
| 112 |
+
"eval_recall": 0.2,
|
| 113 |
+
"eval_runtime": 0.208,
|
| 114 |
+
"eval_samples_per_second": 96.137,
|
| 115 |
+
"eval_steps_per_second": 14.421,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 4.982398986816406,
|
| 118 |
+
"step": 100
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 12.5,
|
| 122 |
+
"learning_rate": 1.5040000000000002e-05,
|
| 123 |
+
"loss": 0.9424,
|
| 124 |
+
"step": 125
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 12.5,
|
| 128 |
+
"eval_accuracy": 0.25,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 36.27980041503906,
|
| 131 |
+
"eval_f1": 0.17333333333333334,
|
| 132 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 133 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 42,
|
| 136 |
+
"eval_loss": 2.3475446701049805,
|
| 137 |
+
"eval_precision": 0.14166666666666666,
|
| 138 |
+
"eval_recall": 0.25,
|
| 139 |
+
"eval_runtime": 0.2046,
|
| 140 |
+
"eval_samples_per_second": 97.736,
|
| 141 |
+
"eval_steps_per_second": 14.66,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 4.944629669189453,
|
| 144 |
+
"step": 125
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 15.0,
|
| 148 |
+
"learning_rate": 1.4040000000000001e-05,
|
| 149 |
+
"loss": 0.5591,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 15.0,
|
| 154 |
+
"eval_accuracy": 0.25,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 36.27981948852539,
|
| 157 |
+
"eval_f1": 0.17444444444444446,
|
| 158 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 159 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 29,
|
| 162 |
+
"eval_loss": 2.4503185749053955,
|
| 163 |
+
"eval_precision": 0.14523809523809522,
|
| 164 |
+
"eval_recall": 0.25,
|
| 165 |
+
"eval_runtime": 0.2141,
|
| 166 |
+
"eval_samples_per_second": 93.429,
|
| 167 |
+
"eval_steps_per_second": 14.014,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 4.920143127441406,
|
| 170 |
+
"step": 150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.5,
|
| 174 |
+
"learning_rate": 1.3080000000000002e-05,
|
| 175 |
+
"loss": 0.2893,
|
| 176 |
+
"step": 175
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.5,
|
| 180 |
+
"eval_accuracy": 0.25,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 36.27982711791992,
|
| 183 |
+
"eval_f1": 0.17444444444444446,
|
| 184 |
+
"eval_gpu_ram_allocated": 4.843067646026611,
|
| 185 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 43,
|
| 188 |
+
"eval_loss": 2.555687665939331,
|
| 189 |
+
"eval_precision": 0.14523809523809522,
|
| 190 |
+
"eval_recall": 0.25,
|
| 191 |
+
"eval_runtime": 0.2265,
|
| 192 |
+
"eval_samples_per_second": 88.288,
|
| 193 |
+
"eval_steps_per_second": 13.243,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 4.961811065673828,
|
| 196 |
+
"step": 175
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 20.0,
|
| 200 |
+
"learning_rate": 1.2080000000000001e-05,
|
| 201 |
+
"loss": 0.1623,
|
| 202 |
+
"step": 200
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 20.0,
|
| 206 |
+
"eval_accuracy": 0.3,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 36.279876708984375,
|
| 209 |
+
"eval_f1": 0.2411111111111111,
|
| 210 |
+
"eval_gpu_ram_allocated": 4.843057632446289,
|
| 211 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 30,
|
| 214 |
+
"eval_loss": 2.621793270111084,
|
| 215 |
+
"eval_precision": 0.2452380952380952,
|
| 216 |
+
"eval_recall": 0.3,
|
| 217 |
+
"eval_runtime": 0.217,
|
| 218 |
+
"eval_samples_per_second": 92.146,
|
| 219 |
+
"eval_steps_per_second": 13.822,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 4.910972595214844,
|
| 222 |
+
"step": 200
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 22.5,
|
| 226 |
+
"learning_rate": 1.1080000000000002e-05,
|
| 227 |
+
"loss": 0.0817,
|
| 228 |
+
"step": 225
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 22.5,
|
| 232 |
+
"eval_accuracy": 0.3,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 36.279930114746094,
|
| 235 |
+
"eval_f1": 0.24,
|
| 236 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 237 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 38,
|
| 240 |
+
"eval_loss": 2.734551191329956,
|
| 241 |
+
"eval_precision": 0.24166666666666664,
|
| 242 |
+
"eval_recall": 0.3,
|
| 243 |
+
"eval_runtime": 0.2092,
|
| 244 |
+
"eval_samples_per_second": 95.586,
|
| 245 |
+
"eval_steps_per_second": 14.338,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 4.941272735595703,
|
| 248 |
+
"step": 225
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 25.0,
|
| 252 |
+
"learning_rate": 1.008e-05,
|
| 253 |
+
"loss": 0.0475,
|
| 254 |
+
"step": 250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 25.0,
|
| 258 |
+
"eval_accuracy": 0.3,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 36.27995300292969,
|
| 261 |
+
"eval_f1": 0.23444444444444446,
|
| 262 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 263 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 40,
|
| 266 |
+
"eval_loss": 2.9325406551361084,
|
| 267 |
+
"eval_precision": 0.23690476190476187,
|
| 268 |
+
"eval_recall": 0.3,
|
| 269 |
+
"eval_runtime": 0.2145,
|
| 270 |
+
"eval_samples_per_second": 93.259,
|
| 271 |
+
"eval_steps_per_second": 13.989,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 4.931392669677734,
|
| 274 |
+
"step": 250
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 27.5,
|
| 278 |
+
"learning_rate": 9.080000000000001e-06,
|
| 279 |
+
"loss": 0.0322,
|
| 280 |
+
"step": 275
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 27.5,
|
| 284 |
+
"eval_accuracy": 0.3,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 36.28001403808594,
|
| 287 |
+
"eval_f1": 0.2511111111111112,
|
| 288 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 289 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 42,
|
| 292 |
+
"eval_loss": 3.123502254486084,
|
| 293 |
+
"eval_precision": 0.2869047619047619,
|
| 294 |
+
"eval_recall": 0.3,
|
| 295 |
+
"eval_runtime": 0.2104,
|
| 296 |
+
"eval_samples_per_second": 95.043,
|
| 297 |
+
"eval_steps_per_second": 14.256,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 4.933628082275391,
|
| 300 |
+
"step": 275
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 30.0,
|
| 304 |
+
"learning_rate": 8.08e-06,
|
| 305 |
+
"loss": 0.0254,
|
| 306 |
+
"step": 300
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 30.0,
|
| 310 |
+
"eval_accuracy": 0.3,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 36.280025482177734,
|
| 313 |
+
"eval_f1": 0.23444444444444446,
|
| 314 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 315 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 30,
|
| 318 |
+
"eval_loss": 3.145473003387451,
|
| 319 |
+
"eval_precision": 0.23690476190476187,
|
| 320 |
+
"eval_recall": 0.3,
|
| 321 |
+
"eval_runtime": 0.2137,
|
| 322 |
+
"eval_samples_per_second": 93.578,
|
| 323 |
+
"eval_steps_per_second": 14.037,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.938743591308594,
|
| 326 |
+
"step": 300
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 32.5,
|
| 330 |
+
"learning_rate": 7.08e-06,
|
| 331 |
+
"loss": 0.0195,
|
| 332 |
+
"step": 325
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 32.5,
|
| 336 |
+
"eval_accuracy": 0.3,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 36.28008270263672,
|
| 339 |
+
"eval_f1": 0.23444444444444446,
|
| 340 |
+
"eval_gpu_ram_allocated": 4.843059062957764,
|
| 341 |
+
"eval_gpu_ram_cached": 7.046875,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 38,
|
| 344 |
+
"eval_loss": 3.276718854904175,
|
| 345 |
+
"eval_precision": 0.23690476190476187,
|
| 346 |
+
"eval_recall": 0.3,
|
| 347 |
+
"eval_runtime": 0.2064,
|
| 348 |
+
"eval_samples_per_second": 96.908,
|
| 349 |
+
"eval_steps_per_second": 14.536,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 4.919792175292969,
|
| 352 |
+
"step": 325
|
| 353 |
+
}
|
| 354 |
+
],
|
| 355 |
+
"max_steps": 500,
|
| 356 |
+
"num_train_epochs": 50,
|
| 357 |
+
"total_flos": 111026386045056.0,
|
| 358 |
+
"trial_name": null,
|
| 359 |
+
"trial_params": null
|
| 360 |
+
}
|
checkpoint-330/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47900edd0b53679608a0ede66451399bbfa5cd566fbc3709079b0e0cd194e43b
|
| 3 |
+
size 4091
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd18743bdfde8be92fbd991f5cad7d7c0cd7aaca0583e919148be21d96ce8668
|
| 3 |
size 737788917
|
runs/Jul22_22-00-48_9cc823f43576/events.out.tfevents.1690063253.9cc823f43576.282.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e999567e134d87b11c54fa290ab2e27a310e33b30d4b21ec4cb70c2181feb3b4
|
| 3 |
+
size 19330
|