Upload folder using huggingface_hub
Browse files- adapter_model.bin +1 -1
- all_results.json +15 -15
- eval_results.json +10 -10
- runs/Mar25_18-04-56_bf76bf365f95/events.out.tfevents.1711389899.bf76bf365f95.34.0 +3 -0
- runs/Mar25_20-11-39_f542ff02488e/events.out.tfevents.1711397501.f542ff02488e.34.0 +3 -0
- runs/Mar25_20-11-39_f542ff02488e/events.out.tfevents.1711426328.f542ff02488e.34.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +229 -13
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 160086542
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f807cf91166999ea3123988f2e2b2ce66a6dad049d9f6c14b3c3202300b1673
|
| 3 |
size 160086542
|
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_score": 0.
|
| 5 |
-
"eval_gmean": 0.
|
| 6 |
-
"eval_loss": 0.
|
| 7 |
-
"eval_precision": 0.
|
| 8 |
-
"eval_recall": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second": 0.
|
| 12 |
-
"total_flos":
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second":
|
| 16 |
-
"train_steps_per_second": 0.
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.78,
|
| 4 |
+
"eval_f1_score": 0.7785897435897436,
|
| 5 |
+
"eval_gmean": 0.7961000720231877,
|
| 6 |
+
"eval_loss": 0.5531054735183716,
|
| 7 |
+
"eval_precision": 0.8186666666666668,
|
| 8 |
+
"eval_recall": 0.78,
|
| 9 |
+
"eval_runtime": 273.9816,
|
| 10 |
+
"eval_samples_per_second": 0.365,
|
| 11 |
+
"eval_steps_per_second": 0.047,
|
| 12 |
+
"total_flos": 1.6845278653034496e+17,
|
| 13 |
+
"train_loss": 0.7047583736590485,
|
| 14 |
+
"train_runtime": 28553.3073,
|
| 15 |
+
"train_samples_per_second": 0.3,
|
| 16 |
+
"train_steps_per_second": 0.005
|
| 17 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_score": 0.
|
| 5 |
-
"eval_gmean": 0.
|
| 6 |
-
"eval_loss": 0.
|
| 7 |
-
"eval_precision": 0.
|
| 8 |
-
"eval_recall": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.78,
|
| 4 |
+
"eval_f1_score": 0.7785897435897436,
|
| 5 |
+
"eval_gmean": 0.7961000720231877,
|
| 6 |
+
"eval_loss": 0.5531054735183716,
|
| 7 |
+
"eval_precision": 0.8186666666666668,
|
| 8 |
+
"eval_recall": 0.78,
|
| 9 |
+
"eval_runtime": 273.9816,
|
| 10 |
+
"eval_samples_per_second": 0.365,
|
| 11 |
+
"eval_steps_per_second": 0.047
|
| 12 |
}
|
runs/Mar25_18-04-56_bf76bf365f95/events.out.tfevents.1711389899.bf76bf365f95.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33cd72fb9d13a78dde70e74225946888a01961b1b5cdc6c03af22a06b2af7c8d
|
| 3 |
+
size 5873
|
runs/Mar25_20-11-39_f542ff02488e/events.out.tfevents.1711397501.f542ff02488e.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41624f153ce1ae2dd0d5edcd1f31cad0b2835060bf26664f448e80caebf9db06
|
| 3 |
+
size 12759
|
runs/Mar25_20-11-39_f542ff02488e/events.out.tfevents.1711426328.f542ff02488e.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:088cc617217456fe0310d4d222532846befd09b65f5796f4e83615c712ebdda8
|
| 3 |
+
size 615
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.6845278653034496e+17,
|
| 4 |
+
"train_loss": 0.7047583736590485,
|
| 5 |
+
"train_runtime": 28553.3073,
|
| 6 |
+
"train_samples_per_second": 0.3,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,30 +1,246 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0
|
| 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 |
-
"epoch": 0.
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 8,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
"num_train_epochs": 1,
|
| 25 |
"save_steps": 500,
|
| 26 |
-
"total_flos":
|
| 27 |
-
"train_batch_size":
|
| 28 |
"trial_name": null,
|
| 29 |
"trial_params": null
|
| 30 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 16,
|
| 6 |
+
"global_step": 134,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 53.25,
|
| 14 |
+
"learning_rate": 1.9090909090909094e-05,
|
| 15 |
+
"loss": 1.1167,
|
| 16 |
+
"step": 8
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12,
|
| 20 |
+
"grad_norm": 44.5,
|
| 21 |
+
"learning_rate": 1.787878787878788e-05,
|
| 22 |
+
"loss": 0.895,
|
| 23 |
+
"step": 16
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"eval_accuracy": 0.66,
|
| 28 |
+
"eval_f1_score": 0.644367816091954,
|
| 29 |
+
"eval_gmean": 0.6885077030381411,
|
| 30 |
+
"eval_loss": 0.8683984279632568,
|
| 31 |
+
"eval_precision": 0.7505555555555555,
|
| 32 |
+
"eval_recall": 0.66,
|
| 33 |
+
"eval_runtime": 272.9997,
|
| 34 |
+
"eval_samples_per_second": 0.366,
|
| 35 |
+
"eval_steps_per_second": 0.048,
|
| 36 |
+
"step": 16
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.18,
|
| 40 |
+
"grad_norm": 46.5,
|
| 41 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 42 |
+
"loss": 0.829,
|
| 43 |
+
"step": 24
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.24,
|
| 47 |
+
"grad_norm": 30.875,
|
| 48 |
+
"learning_rate": 1.5454545454545454e-05,
|
| 49 |
+
"loss": 0.747,
|
| 50 |
+
"step": 32
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"eval_accuracy": 0.72,
|
| 55 |
+
"eval_f1_score": 0.7137777777777776,
|
| 56 |
+
"eval_gmean": 0.7423479773532891,
|
| 57 |
+
"eval_loss": 0.7020312547683716,
|
| 58 |
+
"eval_precision": 0.783921568627451,
|
| 59 |
+
"eval_recall": 0.72,
|
| 60 |
+
"eval_runtime": 273.193,
|
| 61 |
+
"eval_samples_per_second": 0.366,
|
| 62 |
+
"eval_steps_per_second": 0.048,
|
| 63 |
+
"step": 32
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.3,
|
| 67 |
+
"grad_norm": 29.375,
|
| 68 |
+
"learning_rate": 1.4242424242424245e-05,
|
| 69 |
+
"loss": 0.7173,
|
| 70 |
+
"step": 40
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.36,
|
| 74 |
+
"grad_norm": 28.875,
|
| 75 |
+
"learning_rate": 1.3030303030303032e-05,
|
| 76 |
+
"loss": 0.7169,
|
| 77 |
+
"step": 48
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.36,
|
| 81 |
+
"eval_accuracy": 0.74,
|
| 82 |
+
"eval_f1_score": 0.7358132045088567,
|
| 83 |
+
"eval_gmean": 0.7602742157385604,
|
| 84 |
+
"eval_loss": 0.6424999833106995,
|
| 85 |
+
"eval_precision": 0.7952083333333333,
|
| 86 |
+
"eval_recall": 0.74,
|
| 87 |
+
"eval_runtime": 273.7345,
|
| 88 |
+
"eval_samples_per_second": 0.365,
|
| 89 |
+
"eval_steps_per_second": 0.047,
|
| 90 |
+
"step": 48
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.42,
|
| 94 |
+
"grad_norm": 32.25,
|
| 95 |
+
"learning_rate": 1.181818181818182e-05,
|
| 96 |
+
"loss": 0.6892,
|
| 97 |
+
"step": 56
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.48,
|
| 101 |
+
"grad_norm": 35.25,
|
| 102 |
+
"learning_rate": 1.0606060606060606e-05,
|
| 103 |
+
"loss": 0.7526,
|
| 104 |
+
"step": 64
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.48,
|
| 108 |
+
"eval_accuracy": 0.77,
|
| 109 |
+
"eval_f1_score": 0.7680401002506266,
|
| 110 |
+
"eval_gmean": 0.7871467461661771,
|
| 111 |
+
"eval_loss": 0.6016992330551147,
|
| 112 |
+
"eval_precision": 0.8126607818411097,
|
| 113 |
+
"eval_recall": 0.77,
|
| 114 |
+
"eval_runtime": 274.3064,
|
| 115 |
+
"eval_samples_per_second": 0.365,
|
| 116 |
+
"eval_steps_per_second": 0.047,
|
| 117 |
+
"step": 64
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.54,
|
| 121 |
+
"grad_norm": 28.875,
|
| 122 |
+
"learning_rate": 9.393939393939396e-06,
|
| 123 |
+
"loss": 0.6553,
|
| 124 |
+
"step": 72
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.6,
|
| 128 |
+
"grad_norm": 25.625,
|
| 129 |
+
"learning_rate": 8.181818181818183e-06,
|
| 130 |
+
"loss": 0.5781,
|
| 131 |
+
"step": 80
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.6,
|
| 135 |
+
"eval_accuracy": 0.78,
|
| 136 |
+
"eval_f1_score": 0.7785897435897436,
|
| 137 |
+
"eval_gmean": 0.7961000720231877,
|
| 138 |
+
"eval_loss": 0.5736328363418579,
|
| 139 |
+
"eval_precision": 0.8186666666666668,
|
| 140 |
+
"eval_recall": 0.78,
|
| 141 |
+
"eval_runtime": 273.4905,
|
| 142 |
+
"eval_samples_per_second": 0.366,
|
| 143 |
+
"eval_steps_per_second": 0.048,
|
| 144 |
+
"step": 80
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.66,
|
| 148 |
+
"grad_norm": 16.5,
|
| 149 |
+
"learning_rate": 6.969696969696971e-06,
|
| 150 |
+
"loss": 0.56,
|
| 151 |
+
"step": 88
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.72,
|
| 155 |
+
"grad_norm": 32.5,
|
| 156 |
+
"learning_rate": 5.7575757575757586e-06,
|
| 157 |
+
"loss": 0.6035,
|
| 158 |
+
"step": 96
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.72,
|
| 162 |
+
"eval_accuracy": 0.78,
|
| 163 |
+
"eval_f1_score": 0.7785897435897436,
|
| 164 |
+
"eval_gmean": 0.7961000720231877,
|
| 165 |
+
"eval_loss": 0.5596484541893005,
|
| 166 |
+
"eval_precision": 0.8186666666666668,
|
| 167 |
+
"eval_recall": 0.78,
|
| 168 |
+
"eval_runtime": 273.6048,
|
| 169 |
+
"eval_samples_per_second": 0.365,
|
| 170 |
+
"eval_steps_per_second": 0.048,
|
| 171 |
+
"step": 96
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.78,
|
| 175 |
+
"grad_norm": 24.0,
|
| 176 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 177 |
+
"loss": 0.6456,
|
| 178 |
+
"step": 104
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.84,
|
| 182 |
+
"grad_norm": 34.75,
|
| 183 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 184 |
+
"loss": 0.655,
|
| 185 |
+
"step": 112
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.84,
|
| 189 |
+
"eval_accuracy": 0.78,
|
| 190 |
+
"eval_f1_score": 0.7785897435897436,
|
| 191 |
+
"eval_gmean": 0.7961000720231877,
|
| 192 |
+
"eval_loss": 0.5552539229393005,
|
| 193 |
+
"eval_precision": 0.8186666666666668,
|
| 194 |
+
"eval_recall": 0.78,
|
| 195 |
+
"eval_runtime": 273.6051,
|
| 196 |
+
"eval_samples_per_second": 0.365,
|
| 197 |
+
"eval_steps_per_second": 0.048,
|
| 198 |
+
"step": 112
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9,
|
| 202 |
+
"grad_norm": 25.625,
|
| 203 |
+
"learning_rate": 2.1212121212121216e-06,
|
| 204 |
+
"loss": 0.5464,
|
| 205 |
+
"step": 120
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.96,
|
| 209 |
+
"grad_norm": 16.625,
|
| 210 |
+
"learning_rate": 9.090909090909091e-07,
|
| 211 |
+
"loss": 0.606,
|
| 212 |
+
"step": 128
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.96,
|
| 216 |
+
"eval_accuracy": 0.78,
|
| 217 |
+
"eval_f1_score": 0.7785897435897436,
|
| 218 |
+
"eval_gmean": 0.7961000720231877,
|
| 219 |
+
"eval_loss": 0.5531054735183716,
|
| 220 |
+
"eval_precision": 0.8186666666666668,
|
| 221 |
+
"eval_recall": 0.78,
|
| 222 |
+
"eval_runtime": 273.8068,
|
| 223 |
+
"eval_samples_per_second": 0.365,
|
| 224 |
+
"eval_steps_per_second": 0.047,
|
| 225 |
+
"step": 128
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.0,
|
| 229 |
+
"step": 134,
|
| 230 |
+
"total_flos": 1.6845278653034496e+17,
|
| 231 |
+
"train_loss": 0.7047583736590485,
|
| 232 |
+
"train_runtime": 28553.3073,
|
| 233 |
+
"train_samples_per_second": 0.3,
|
| 234 |
+
"train_steps_per_second": 0.005
|
| 235 |
}
|
| 236 |
],
|
| 237 |
"logging_steps": 8,
|
| 238 |
+
"max_steps": 134,
|
| 239 |
"num_input_tokens_seen": 0,
|
| 240 |
"num_train_epochs": 1,
|
| 241 |
"save_steps": 500,
|
| 242 |
+
"total_flos": 1.6845278653034496e+17,
|
| 243 |
+
"train_batch_size": 16,
|
| 244 |
"trial_name": null,
|
| 245 |
"trial_params": null
|
| 246 |
}
|