commit files to HF hub
Browse files- .gitignore +1 -0
- checkpoint-10000/config.json +1 -1
- checkpoint-10000/optimizer.pt +2 -2
- checkpoint-10000/pytorch_model.bin +1 -1
- checkpoint-10000/rng_state.pth +1 -1
- checkpoint-10000/scaler.pt +1 -1
- checkpoint-10000/scheduler.pt +1 -1
- checkpoint-10000/trainer_state.json +605 -125
- checkpoint-10000/training_args.bin +1 -1
- checkpoint-2000/config.json +1 -1
- checkpoint-2000/optimizer.pt +2 -2
- checkpoint-2000/pytorch_model.bin +1 -1
- checkpoint-2000/rng_state.pth +1 -1
- checkpoint-2000/scaler.pt +1 -1
- checkpoint-2000/scheduler.pt +1 -1
- checkpoint-2000/trainer_state.json +124 -28
- checkpoint-2000/training_args.bin +1 -1
- config.json +1 -1
- pytorch_model.bin +1 -1
- runs/Jul03_17-16-15_8a98c40ff775/events.out.tfevents.1656868588.8a98c40ff775.71.0 +0 -3
- runs/Jul03_21-34-55_8a98c40ff775/events.out.tfevents.1656884100.8a98c40ff775.71.4 +0 -3
- runs/Jul03_23-15-45_8a98c40ff775/1656890147.0297482/events.out.tfevents.1656890147.8a98c40ff775.71.7 +0 -3
- runs/Jul03_23-16-08_8a98c40ff775/1656890170.9030218/events.out.tfevents.1656890170.8a98c40ff775.71.9 +0 -3
- runs/Jul03_23-16-08_8a98c40ff775/events.out.tfevents.1656890170.8a98c40ff775.71.8 +0 -3
- runs/Jul03_23-26-33_8a98c40ff775/1656890797.636419/events.out.tfevents.1656890797.8a98c40ff775.5349.1 +0 -3
- runs/Jul03_23-26-33_8a98c40ff775/events.out.tfevents.1656890797.8a98c40ff775.5349.0 +0 -3
- runs/Jul04_00-33-28_8a98c40ff775/1656894810.6894863/events.out.tfevents.1656894810.8a98c40ff775.8083.1 +0 -3
- runs/{Jul03_17-16-15_8a98c40ff775/1656868588.8381069/events.out.tfevents.1656868588.8a98c40ff775.71.1 → Jul26_21-03-46_1fe91f198d71/1658869435.620103/events.out.tfevents.1658869435.1fe91f198d71.71.1} +1 -1
- runs/{Jul03_19-51-55_8a98c40ff775/events.out.tfevents.1656877916.8a98c40ff775.71.2 → Jul26_21-03-46_1fe91f198d71/events.out.tfevents.1658869435.1fe91f198d71.71.0} +2 -2
- runs/{Jul03_21-34-55_8a98c40ff775/1656884100.2687025/events.out.tfevents.1656884100.8a98c40ff775.71.5 → Jul26_21-10-23_1fe91f198d71/1658869825.093272/events.out.tfevents.1658869825.1fe91f198d71.71.3} +1 -1
- runs/{Jul03_23-15-45_8a98c40ff775/events.out.tfevents.1656890147.8a98c40ff775.71.6 → Jul26_21-10-23_1fe91f198d71/events.out.tfevents.1658869825.1fe91f198d71.71.2} +1 -1
- runs/{Jul03_19-51-55_8a98c40ff775/1656877916.4434352/events.out.tfevents.1656877916.8a98c40ff775.71.3 → Jul26_21-13-22_1fe91f198d71/1658870005.9725268/events.out.tfevents.1658870005.1fe91f198d71.1213.1} +1 -1
- runs/{Jul04_00-33-28_8a98c40ff775/events.out.tfevents.1656894810.8a98c40ff775.8083.0 → Jul26_21-13-22_1fe91f198d71/events.out.tfevents.1658870005.1fe91f198d71.1213.0} +1 -1
- training_args.bin +1 -1
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint*
|
checkpoint-10000/config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
-
"hidden_dropout_prob": 0.
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
|
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.2,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
checkpoint-10000/optimizer.pt
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:f720256e4e70820d89c9e06666f88dbcad39f323aa192001b302a880db22b488
|
| 3 |
+
size 1475512793
|
checkpoint-10000/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737770027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a23605ea589e2551eb0df2eb5509e159ed31156dfca15b2eeba8eb53c93f51f
|
| 3 |
size 737770027
|
checkpoint-10000/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a41b1f8f5d265afac85d7d1219ee0f67a2407025613329d1f86629642de0409
|
| 3 |
size 14503
|
checkpoint-10000/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdbc1a65543b77f14ca91d846aa90008d71866cbb1b49f2d46285e1f600dd308
|
| 3 |
size 559
|
checkpoint-10000/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63309151ebd54520ac76370f164e851299d6d6a0b59b77db141c9a804e76fd13
|
| 3 |
size 623
|
checkpoint-10000/trainer_state.json
CHANGED
|
@@ -1,296 +1,776 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-
|
| 4 |
"epoch": 4.835287009063444,
|
| 5 |
"global_step": 10000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.24,
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.24,
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
"step": 500
|
| 23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{
|
| 25 |
"epoch": 0.48,
|
| 26 |
-
"learning_rate":
|
| 27 |
-
"loss": 0.
|
| 28 |
"step": 1000
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 0.48,
|
| 32 |
-
"eval_loss": 0.
|
| 33 |
-
"eval_runtime":
|
| 34 |
-
"eval_samples_per_second":
|
| 35 |
-
"eval_steps_per_second":
|
| 36 |
"step": 1000
|
| 37 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
{
|
| 39 |
"epoch": 0.73,
|
| 40 |
-
"learning_rate":
|
| 41 |
-
"loss": 0.
|
| 42 |
"step": 1500
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 0.73,
|
| 46 |
-
"eval_loss": 0.
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second":
|
| 50 |
"step": 1500
|
| 51 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
{
|
| 53 |
"epoch": 0.97,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 2000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.97,
|
| 60 |
-
"eval_loss": 0.
|
| 61 |
-
"eval_runtime":
|
| 62 |
-
"eval_samples_per_second":
|
| 63 |
-
"eval_steps_per_second":
|
| 64 |
"step": 2000
|
| 65 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
{
|
| 67 |
"epoch": 1.21,
|
| 68 |
-
"learning_rate":
|
| 69 |
-
"loss": 0.
|
| 70 |
"step": 2500
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 1.21,
|
| 74 |
-
"eval_loss": 0.
|
| 75 |
-
"eval_runtime":
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second": 31.
|
| 78 |
"step": 2500
|
| 79 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
{
|
| 81 |
"epoch": 1.45,
|
| 82 |
-
"learning_rate":
|
| 83 |
-
"loss": 0.
|
| 84 |
"step": 3000
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 1.45,
|
| 88 |
-
"eval_loss": 0.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second":
|
| 91 |
-
"eval_steps_per_second":
|
| 92 |
"step": 3000
|
| 93 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
{
|
| 95 |
"epoch": 1.69,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 3500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.69,
|
| 102 |
-
"eval_loss": 0.
|
| 103 |
-
"eval_runtime":
|
| 104 |
-
"eval_samples_per_second":
|
| 105 |
-
"eval_steps_per_second":
|
| 106 |
"step": 3500
|
| 107 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
{
|
| 109 |
"epoch": 1.93,
|
| 110 |
-
"learning_rate":
|
| 111 |
-
"loss": 0.
|
| 112 |
"step": 4000
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.93,
|
| 116 |
-
"eval_loss": 0.
|
| 117 |
-
"eval_runtime":
|
| 118 |
-
"eval_samples_per_second":
|
| 119 |
-
"eval_steps_per_second":
|
| 120 |
"step": 4000
|
| 121 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
{
|
| 123 |
"epoch": 2.18,
|
| 124 |
-
"learning_rate":
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 4500
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 2.18,
|
| 130 |
-
"eval_loss": 0.
|
| 131 |
-
"eval_runtime":
|
| 132 |
-
"eval_samples_per_second":
|
| 133 |
-
"eval_steps_per_second":
|
| 134 |
"step": 4500
|
| 135 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
{
|
| 137 |
"epoch": 2.42,
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 5000
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 2.42,
|
| 144 |
-
"eval_loss": 0.
|
| 145 |
-
"eval_runtime": 28.
|
| 146 |
-
"eval_samples_per_second":
|
| 147 |
-
"eval_steps_per_second":
|
| 148 |
"step": 5000
|
| 149 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
{
|
| 151 |
"epoch": 2.66,
|
| 152 |
-
"learning_rate":
|
| 153 |
-
"loss": 0.
|
| 154 |
"step": 5500
|
| 155 |
},
|
| 156 |
{
|
| 157 |
"epoch": 2.66,
|
| 158 |
-
"eval_loss": 0.
|
| 159 |
-
"eval_runtime":
|
| 160 |
-
"eval_samples_per_second":
|
| 161 |
-
"eval_steps_per_second":
|
| 162 |
"step": 5500
|
| 163 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
{
|
| 165 |
"epoch": 2.9,
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 6000
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 2.9,
|
| 172 |
-
"eval_loss": 0.
|
| 173 |
-
"eval_runtime":
|
| 174 |
-
"eval_samples_per_second":
|
| 175 |
-
"eval_steps_per_second":
|
| 176 |
"step": 6000
|
| 177 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
{
|
| 179 |
"epoch": 3.14,
|
| 180 |
-
"learning_rate": 3.
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 6500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 3.14,
|
| 186 |
-
"eval_loss": 0.
|
| 187 |
-
"eval_runtime":
|
| 188 |
-
"eval_samples_per_second":
|
| 189 |
-
"eval_steps_per_second":
|
| 190 |
"step": 6500
|
| 191 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
{
|
| 193 |
"epoch": 3.38,
|
| 194 |
-
"learning_rate":
|
| 195 |
-
"loss": 0.
|
| 196 |
"step": 7000
|
| 197 |
},
|
| 198 |
{
|
| 199 |
"epoch": 3.38,
|
| 200 |
-
"eval_loss": 0.
|
| 201 |
-
"eval_runtime":
|
| 202 |
-
"eval_samples_per_second":
|
| 203 |
-
"eval_steps_per_second":
|
| 204 |
"step": 7000
|
| 205 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
{
|
| 207 |
"epoch": 3.63,
|
| 208 |
-
"learning_rate":
|
| 209 |
-
"loss": 0.
|
| 210 |
"step": 7500
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 3.63,
|
| 214 |
-
"eval_loss": 0.
|
| 215 |
-
"eval_runtime":
|
| 216 |
-
"eval_samples_per_second":
|
| 217 |
-
"eval_steps_per_second":
|
| 218 |
"step": 7500
|
| 219 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
{
|
| 221 |
"epoch": 3.87,
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 8000
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 3.87,
|
| 228 |
-
"eval_loss": 0.
|
| 229 |
-
"eval_runtime":
|
| 230 |
-
"eval_samples_per_second":
|
| 231 |
-
"eval_steps_per_second":
|
| 232 |
"step": 8000
|
| 233 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 234 |
{
|
| 235 |
"epoch": 4.11,
|
| 236 |
-
"learning_rate":
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 8500
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 4.11,
|
| 242 |
-
"eval_loss": 0.
|
| 243 |
-
"eval_runtime":
|
| 244 |
-
"eval_samples_per_second":
|
| 245 |
-
"eval_steps_per_second":
|
| 246 |
"step": 8500
|
| 247 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
{
|
| 249 |
"epoch": 4.35,
|
| 250 |
-
"learning_rate":
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 9000
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 4.35,
|
| 256 |
-
"eval_loss": 0.
|
| 257 |
-
"eval_runtime":
|
| 258 |
-
"eval_samples_per_second":
|
| 259 |
-
"eval_steps_per_second":
|
| 260 |
"step": 9000
|
| 261 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 262 |
{
|
| 263 |
"epoch": 4.59,
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 9500
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 4.59,
|
| 270 |
-
"eval_loss": 0.
|
| 271 |
-
"eval_runtime":
|
| 272 |
-
"eval_samples_per_second":
|
| 273 |
-
"eval_steps_per_second":
|
| 274 |
"step": 9500
|
| 275 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 276 |
{
|
| 277 |
"epoch": 4.84,
|
| 278 |
-
"learning_rate":
|
| 279 |
-
"loss": 0.
|
| 280 |
"step": 10000
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 4.84,
|
| 284 |
-
"eval_loss": 0.
|
| 285 |
-
"eval_runtime":
|
| 286 |
-
"eval_samples_per_second":
|
| 287 |
-
"eval_steps_per_second":
|
| 288 |
"step": 10000
|
| 289 |
}
|
| 290 |
],
|
| 291 |
-
"max_steps":
|
| 292 |
-
"num_train_epochs":
|
| 293 |
-
"total_flos":
|
| 294 |
"trial_name": null,
|
| 295 |
"trial_params": null
|
| 296 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.727655291557312,
|
| 3 |
+
"best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-10000",
|
| 4 |
"epoch": 4.835287009063444,
|
| 5 |
"global_step": 10000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 2e-07,
|
| 13 |
+
"loss": 1.0361,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 3.98e-07,
|
| 19 |
+
"loss": 0.9751,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 5.979999999999999e-07,
|
| 25 |
+
"loss": 0.9807,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.19,
|
| 30 |
+
"learning_rate": 7.94e-07,
|
| 31 |
+
"loss": 0.9513,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
{
|
| 35 |
"epoch": 0.24,
|
| 36 |
+
"learning_rate": 9.94e-07,
|
| 37 |
+
"loss": 0.9237,
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.24,
|
| 42 |
+
"eval_loss": 0.9464540481567383,
|
| 43 |
+
"eval_runtime": 37.5769,
|
| 44 |
+
"eval_samples_per_second": 97.587,
|
| 45 |
+
"eval_steps_per_second": 24.403,
|
| 46 |
"step": 500
|
| 47 |
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.29,
|
| 50 |
+
"learning_rate": 9.955915919781764e-07,
|
| 51 |
+
"loss": 0.9367,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.34,
|
| 56 |
+
"learning_rate": 9.81900265076038e-07,
|
| 57 |
+
"loss": 0.8993,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.39,
|
| 62 |
+
"learning_rate": 9.594490241150311e-07,
|
| 63 |
+
"loss": 0.8586,
|
| 64 |
+
"step": 800
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.44,
|
| 68 |
+
"learning_rate": 9.282057505552949e-07,
|
| 69 |
+
"loss": 0.854,
|
| 70 |
+
"step": 900
|
| 71 |
+
},
|
| 72 |
{
|
| 73 |
"epoch": 0.48,
|
| 74 |
+
"learning_rate": 8.889381125453379e-07,
|
| 75 |
+
"loss": 0.8642,
|
| 76 |
"step": 1000
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.48,
|
| 80 |
+
"eval_loss": 0.8270628452301025,
|
| 81 |
+
"eval_runtime": 28.2214,
|
| 82 |
+
"eval_samples_per_second": 129.937,
|
| 83 |
+
"eval_steps_per_second": 32.493,
|
| 84 |
"step": 1000
|
| 85 |
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.53,
|
| 88 |
+
"learning_rate": 8.423819662432867e-07,
|
| 89 |
+
"loss": 0.8314,
|
| 90 |
+
"step": 1100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.58,
|
| 94 |
+
"learning_rate": 7.894097508558568e-07,
|
| 95 |
+
"loss": 0.8317,
|
| 96 |
+
"step": 1200
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.63,
|
| 100 |
+
"learning_rate": 7.310141395581585e-07,
|
| 101 |
+
"loss": 0.7939,
|
| 102 |
+
"step": 1300
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.68,
|
| 106 |
+
"learning_rate": 6.682894372882701e-07,
|
| 107 |
+
"loss": 0.803,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
{
|
| 111 |
"epoch": 0.73,
|
| 112 |
+
"learning_rate": 6.024110740127264e-07,
|
| 113 |
+
"loss": 0.8029,
|
| 114 |
"step": 1500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.73,
|
| 118 |
+
"eval_loss": 0.7635419368743896,
|
| 119 |
+
"eval_runtime": 28.2809,
|
| 120 |
+
"eval_samples_per_second": 129.663,
|
| 121 |
+
"eval_steps_per_second": 32.425,
|
| 122 |
"step": 1500
|
| 123 |
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.77,
|
| 126 |
+
"learning_rate": 5.346135777490083e-07,
|
| 127 |
+
"loss": 0.7959,
|
| 128 |
+
"step": 1600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.82,
|
| 132 |
+
"learning_rate": 4.6616744011972247e-07,
|
| 133 |
+
"loss": 0.7708,
|
| 134 |
+
"step": 1700
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.87,
|
| 138 |
+
"learning_rate": 3.9835530796656867e-07,
|
| 139 |
+
"loss": 0.7636,
|
| 140 |
+
"step": 1800
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.92,
|
| 144 |
+
"learning_rate": 3.3244794718149894e-07,
|
| 145 |
+
"loss": 0.7864,
|
| 146 |
+
"step": 1900
|
| 147 |
+
},
|
| 148 |
{
|
| 149 |
"epoch": 0.97,
|
| 150 |
+
"learning_rate": 2.696804291810131e-07,
|
| 151 |
+
"loss": 0.8005,
|
| 152 |
"step": 2000
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.97,
|
| 156 |
+
"eval_loss": 0.7537589073181152,
|
| 157 |
+
"eval_runtime": 28.4034,
|
| 158 |
+
"eval_samples_per_second": 129.104,
|
| 159 |
+
"eval_steps_per_second": 32.285,
|
| 160 |
"step": 2000
|
| 161 |
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.02,
|
| 164 |
+
"learning_rate": 2.1122898627730768e-07,
|
| 165 |
+
"loss": 0.7924,
|
| 166 |
+
"step": 2100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.06,
|
| 170 |
+
"learning_rate": 1.5818896966520534e-07,
|
| 171 |
+
"loss": 0.8072,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.11,
|
| 176 |
+
"learning_rate": 1.1155432308130763e-07,
|
| 177 |
+
"loss": 0.7997,
|
| 178 |
+
"step": 2300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.16,
|
| 182 |
+
"learning_rate": 7.219895678887305e-08,
|
| 183 |
+
"loss": 0.7931,
|
| 184 |
+
"step": 2400
|
| 185 |
+
},
|
| 186 |
{
|
| 187 |
"epoch": 1.21,
|
| 188 |
+
"learning_rate": 4.0860370930748286e-08,
|
| 189 |
+
"loss": 0.7734,
|
| 190 |
"step": 2500
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"epoch": 1.21,
|
| 194 |
+
"eval_loss": 0.7621562480926514,
|
| 195 |
+
"eval_runtime": 28.9226,
|
| 196 |
+
"eval_samples_per_second": 126.786,
|
| 197 |
+
"eval_steps_per_second": 31.705,
|
| 198 |
"step": 2500
|
| 199 |
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.26,
|
| 202 |
+
"learning_rate": 1.812583514064109e-08,
|
| 203 |
+
"loss": 0.7487,
|
| 204 |
+
"step": 2600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.31,
|
| 208 |
+
"learning_rate": 4.421383399995704e-09,
|
| 209 |
+
"loss": 0.7911,
|
| 210 |
+
"step": 2700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.35,
|
| 214 |
+
"learning_rate": 9.999961696285757e-07,
|
| 215 |
+
"loss": 0.7794,
|
| 216 |
+
"step": 2800
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.4,
|
| 220 |
+
"learning_rate": 9.950440411813353e-07,
|
| 221 |
+
"loss": 0.7922,
|
| 222 |
+
"step": 2900
|
| 223 |
+
},
|
| 224 |
{
|
| 225 |
"epoch": 1.45,
|
| 226 |
+
"learning_rate": 9.810025090182484e-07,
|
| 227 |
+
"loss": 0.7842,
|
| 228 |
"step": 3000
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.45,
|
| 232 |
+
"eval_loss": 0.748653769493103,
|
| 233 |
+
"eval_runtime": 27.9531,
|
| 234 |
+
"eval_samples_per_second": 131.184,
|
| 235 |
+
"eval_steps_per_second": 32.805,
|
| 236 |
"step": 3000
|
| 237 |
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.5,
|
| 240 |
+
"learning_rate": 9.581263257645987e-07,
|
| 241 |
+
"loss": 0.7731,
|
| 242 |
+
"step": 3100
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.55,
|
| 246 |
+
"learning_rate": 9.264785067160785e-07,
|
| 247 |
+
"loss": 0.7849,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.6,
|
| 252 |
+
"learning_rate": 8.868386909145071e-07,
|
| 253 |
+
"loss": 0.7745,
|
| 254 |
+
"step": 3300
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.64,
|
| 258 |
+
"learning_rate": 8.399497089461603e-07,
|
| 259 |
+
"loss": 0.7611,
|
| 260 |
+
"step": 3400
|
| 261 |
+
},
|
| 262 |
{
|
| 263 |
"epoch": 1.69,
|
| 264 |
+
"learning_rate": 7.872511787610445e-07,
|
| 265 |
+
"loss": 0.7543,
|
| 266 |
"step": 3500
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 1.69,
|
| 270 |
+
"eval_loss": 0.7955728769302368,
|
| 271 |
+
"eval_runtime": 28.0818,
|
| 272 |
+
"eval_samples_per_second": 130.583,
|
| 273 |
+
"eval_steps_per_second": 32.655,
|
| 274 |
"step": 3500
|
| 275 |
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.74,
|
| 278 |
+
"learning_rate": 7.286677103241362e-07,
|
| 279 |
+
"loss": 0.7793,
|
| 280 |
+
"step": 3600
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.79,
|
| 284 |
+
"learning_rate": 6.657991218409446e-07,
|
| 285 |
+
"loss": 0.7359,
|
| 286 |
+
"step": 3700
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.84,
|
| 290 |
+
"learning_rate": 5.998235396346351e-07,
|
| 291 |
+
"loss": 0.7602,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.89,
|
| 296 |
+
"learning_rate": 5.319773135574745e-07,
|
| 297 |
+
"loss": 0.7664,
|
| 298 |
+
"step": 3900
|
| 299 |
+
},
|
| 300 |
{
|
| 301 |
"epoch": 1.93,
|
| 302 |
+
"learning_rate": 4.635318484047261e-07,
|
| 303 |
+
"loss": 0.7883,
|
| 304 |
"step": 4000
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.93,
|
| 308 |
+
"eval_loss": 0.7467952370643616,
|
| 309 |
+
"eval_runtime": 28.6183,
|
| 310 |
+
"eval_samples_per_second": 128.135,
|
| 311 |
+
"eval_steps_per_second": 32.042,
|
| 312 |
"step": 4000
|
| 313 |
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.98,
|
| 316 |
+
"learning_rate": 3.9576977841621134e-07,
|
| 317 |
+
"loss": 0.7493,
|
| 318 |
+
"step": 4100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.03,
|
| 322 |
+
"learning_rate": 3.299609313436215e-07,
|
| 323 |
+
"loss": 0.7312,
|
| 324 |
+
"step": 4200
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.08,
|
| 328 |
+
"learning_rate": 2.6733853250510007e-07,
|
| 329 |
+
"loss": 0.7387,
|
| 330 |
+
"step": 4300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.13,
|
| 334 |
+
"learning_rate": 2.0907609475136373e-07,
|
| 335 |
+
"loss": 0.7492,
|
| 336 |
+
"step": 4400
|
| 337 |
+
},
|
| 338 |
{
|
| 339 |
"epoch": 2.18,
|
| 340 |
+
"learning_rate": 1.562654274139964e-07,
|
| 341 |
+
"loss": 0.7515,
|
| 342 |
"step": 4500
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 2.18,
|
| 346 |
+
"eval_loss": 0.7437878847122192,
|
| 347 |
+
"eval_runtime": 27.6555,
|
| 348 |
+
"eval_samples_per_second": 132.595,
|
| 349 |
+
"eval_steps_per_second": 33.158,
|
| 350 |
"step": 4500
|
| 351 |
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.22,
|
| 354 |
+
"learning_rate": 1.0989617633737314e-07,
|
| 355 |
+
"loss": 0.7218,
|
| 356 |
+
"step": 4600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.27,
|
| 360 |
+
"learning_rate": 7.083727840391568e-08,
|
| 361 |
+
"loss": 0.7554,
|
| 362 |
+
"step": 4700
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.32,
|
| 366 |
+
"learning_rate": 4.00889953873248e-08,
|
| 367 |
+
"loss": 0.768,
|
| 368 |
+
"step": 4800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.37,
|
| 372 |
+
"learning_rate": 1.7607339075303706e-08,
|
| 373 |
+
"loss": 0.725,
|
| 374 |
+
"step": 4900
|
| 375 |
+
},
|
| 376 |
{
|
| 377 |
"epoch": 2.42,
|
| 378 |
+
"learning_rate": 4.165483173136253e-09,
|
| 379 |
+
"loss": 0.716,
|
| 380 |
"step": 5000
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 2.42,
|
| 384 |
+
"eval_loss": 0.7440274953842163,
|
| 385 |
+
"eval_runtime": 28.4825,
|
| 386 |
+
"eval_samples_per_second": 128.746,
|
| 387 |
+
"eval_steps_per_second": 32.195,
|
| 388 |
"step": 5000
|
| 389 |
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.47,
|
| 392 |
+
"learning_rate": 9.999846785729901e-07,
|
| 393 |
+
"loss": 0.7534,
|
| 394 |
+
"step": 5100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.51,
|
| 398 |
+
"learning_rate": 9.947653741800156e-07,
|
| 399 |
+
"loss": 0.7644,
|
| 400 |
+
"step": 5200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.56,
|
| 404 |
+
"learning_rate": 9.80274410836591e-07,
|
| 405 |
+
"loss": 0.7631,
|
| 406 |
+
"step": 5300
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.61,
|
| 410 |
+
"learning_rate": 9.567833420446291e-07,
|
| 411 |
+
"loss": 0.7624,
|
| 412 |
+
"step": 5400
|
| 413 |
+
},
|
| 414 |
{
|
| 415 |
"epoch": 2.66,
|
| 416 |
+
"learning_rate": 9.24732378840687e-07,
|
| 417 |
+
"loss": 0.743,
|
| 418 |
"step": 5500
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 2.66,
|
| 422 |
+
"eval_loss": 0.7312911152839661,
|
| 423 |
+
"eval_runtime": 28.3334,
|
| 424 |
+
"eval_samples_per_second": 129.423,
|
| 425 |
+
"eval_steps_per_second": 32.365,
|
| 426 |
"step": 5500
|
| 427 |
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.71,
|
| 430 |
+
"learning_rate": 8.847221404583831e-07,
|
| 431 |
+
"loss": 0.7522,
|
| 432 |
+
"step": 5600
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.76,
|
| 436 |
+
"learning_rate": 8.380074821716343e-07,
|
| 437 |
+
"loss": 0.7367,
|
| 438 |
+
"step": 5700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.8,
|
| 442 |
+
"learning_rate": 7.845215744177952e-07,
|
| 443 |
+
"loss": 0.7557,
|
| 444 |
+
"step": 5800
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.85,
|
| 448 |
+
"learning_rate": 7.257038727678722e-07,
|
| 449 |
+
"loss": 0.7329,
|
| 450 |
+
"step": 5900
|
| 451 |
+
},
|
| 452 |
{
|
| 453 |
"epoch": 2.9,
|
| 454 |
+
"learning_rate": 6.626565919248464e-07,
|
| 455 |
+
"loss": 0.726,
|
| 456 |
"step": 6000
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 2.9,
|
| 460 |
+
"eval_loss": 0.7325854301452637,
|
| 461 |
+
"eval_runtime": 27.7597,
|
| 462 |
+
"eval_samples_per_second": 132.098,
|
| 463 |
+
"eval_steps_per_second": 33.034,
|
| 464 |
"step": 6000
|
| 465 |
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.95,
|
| 468 |
+
"learning_rate": 5.965612068185233e-07,
|
| 469 |
+
"loss": 0.7804,
|
| 470 |
+
"step": 6100
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.0,
|
| 474 |
+
"learning_rate": 5.286563123483964e-07,
|
| 475 |
+
"loss": 0.7319,
|
| 476 |
+
"step": 6200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.05,
|
| 480 |
+
"learning_rate": 4.602144127264582e-07,
|
| 481 |
+
"loss": 0.732,
|
| 482 |
+
"step": 6300
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.09,
|
| 486 |
+
"learning_rate": 3.925180753762438e-07,
|
| 487 |
+
"loss": 0.7665,
|
| 488 |
+
"step": 6400
|
| 489 |
+
},
|
| 490 |
{
|
| 491 |
"epoch": 3.14,
|
| 492 |
+
"learning_rate": 3.268358962522407e-07,
|
| 493 |
+
"loss": 0.7499,
|
| 494 |
"step": 6500
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"epoch": 3.14,
|
| 498 |
+
"eval_loss": 0.7382772564888,
|
| 499 |
+
"eval_runtime": 27.6004,
|
| 500 |
+
"eval_samples_per_second": 132.86,
|
| 501 |
+
"eval_steps_per_second": 33.224,
|
| 502 |
"step": 6500
|
| 503 |
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 3.19,
|
| 506 |
+
"learning_rate": 2.64398726977746e-07,
|
| 507 |
+
"loss": 0.739,
|
| 508 |
+
"step": 6600
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 3.24,
|
| 512 |
+
"learning_rate": 2.063766092928542e-07,
|
| 513 |
+
"loss": 0.7201,
|
| 514 |
+
"step": 6700
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.29,
|
| 518 |
+
"learning_rate": 1.5385684904965596e-07,
|
| 519 |
+
"loss": 0.7013,
|
| 520 |
+
"step": 6800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 3.34,
|
| 524 |
+
"learning_rate": 1.0782364063714005e-07,
|
| 525 |
+
"loss": 0.7234,
|
| 526 |
+
"step": 6900
|
| 527 |
+
},
|
| 528 |
{
|
| 529 |
"epoch": 3.38,
|
| 530 |
+
"learning_rate": 6.913962366403719e-08,
|
| 531 |
+
"loss": 0.7377,
|
| 532 |
"step": 7000
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 3.38,
|
| 536 |
+
"eval_loss": 0.7334151864051819,
|
| 537 |
+
"eval_runtime": 27.6353,
|
| 538 |
+
"eval_samples_per_second": 132.693,
|
| 539 |
+
"eval_steps_per_second": 33.182,
|
| 540 |
"step": 7000
|
| 541 |
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.43,
|
| 544 |
+
"learning_rate": 3.852971751825379e-08,
|
| 545 |
+
"loss": 0.7272,
|
| 546 |
+
"step": 7100
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.48,
|
| 550 |
+
"learning_rate": 1.6567536735284103e-08,
|
| 551 |
+
"loss": 0.7323,
|
| 552 |
+
"step": 7200
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.53,
|
| 556 |
+
"learning_rate": 3.664641744888397e-09,
|
| 557 |
+
"loss": 0.6981,
|
| 558 |
+
"step": 7300
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 3.58,
|
| 562 |
+
"learning_rate": 9.99937173568261e-07,
|
| 563 |
+
"loss": 0.6917,
|
| 564 |
+
"step": 7400
|
| 565 |
+
},
|
| 566 |
{
|
| 567 |
"epoch": 3.63,
|
| 568 |
+
"learning_rate": 9.94170412962655e-07,
|
| 569 |
+
"loss": 0.7459,
|
| 570 |
"step": 7500
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 3.63,
|
| 574 |
+
"eval_loss": 0.7427003979682922,
|
| 575 |
+
"eval_runtime": 27.4459,
|
| 576 |
+
"eval_samples_per_second": 133.608,
|
| 577 |
+
"eval_steps_per_second": 33.411,
|
| 578 |
"step": 7500
|
| 579 |
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.67,
|
| 582 |
+
"learning_rate": 9.79143142686205e-07,
|
| 583 |
+
"loss": 0.7406,
|
| 584 |
+
"step": 7600
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.72,
|
| 588 |
+
"learning_rate": 9.551369663680862e-07,
|
| 589 |
+
"loss": 0.7304,
|
| 590 |
+
"step": 7700
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.77,
|
| 594 |
+
"learning_rate": 9.226017479056962e-07,
|
| 595 |
+
"loss": 0.7278,
|
| 596 |
+
"step": 7800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.82,
|
| 600 |
+
"learning_rate": 8.821471812372215e-07,
|
| 601 |
+
"loss": 0.7273,
|
| 602 |
+
"step": 7900
|
| 603 |
+
},
|
| 604 |
{
|
| 605 |
"epoch": 3.87,
|
| 606 |
+
"learning_rate": 8.345313649781101e-07,
|
| 607 |
+
"loss": 0.7186,
|
| 608 |
"step": 8000
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 3.87,
|
| 612 |
+
"eval_loss": 0.7306970953941345,
|
| 613 |
+
"eval_runtime": 27.6504,
|
| 614 |
+
"eval_samples_per_second": 132.62,
|
| 615 |
+
"eval_steps_per_second": 33.164,
|
| 616 |
"step": 8000
|
| 617 |
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.92,
|
| 620 |
+
"learning_rate": 7.806465960271379e-07,
|
| 621 |
+
"loss": 0.6956,
|
| 622 |
+
"step": 8100
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.96,
|
| 626 |
+
"learning_rate": 7.215026483628598e-07,
|
| 627 |
+
"loss": 0.7794,
|
| 628 |
+
"step": 8200
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.01,
|
| 632 |
+
"learning_rate": 6.582078503775666e-07,
|
| 633 |
+
"loss": 0.7304,
|
| 634 |
+
"step": 8300
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 4.06,
|
| 638 |
+
"learning_rate": 5.919483153501647e-07,
|
| 639 |
+
"loss": 0.7477,
|
| 640 |
+
"step": 8400
|
| 641 |
+
},
|
| 642 |
{
|
| 643 |
"epoch": 4.11,
|
| 644 |
+
"learning_rate": 5.239657142686591e-07,
|
| 645 |
+
"loss": 0.723,
|
| 646 |
"step": 8500
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 4.11,
|
| 650 |
+
"eval_loss": 0.7324436902999878,
|
| 651 |
+
"eval_runtime": 27.6456,
|
| 652 |
+
"eval_samples_per_second": 132.643,
|
| 653 |
+
"eval_steps_per_second": 33.17,
|
| 654 |
"step": 8500
|
| 655 |
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.16,
|
| 658 |
+
"learning_rate": 4.555340075285952e-07,
|
| 659 |
+
"loss": 0.7081,
|
| 660 |
+
"step": 8600
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.21,
|
| 664 |
+
"learning_rate": 3.8793557154393083e-07,
|
| 665 |
+
"loss": 0.717,
|
| 666 |
+
"step": 8700
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.26,
|
| 670 |
+
"learning_rate": 3.2243716764587667e-07,
|
| 671 |
+
"loss": 0.7229,
|
| 672 |
+
"step": 8800
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.3,
|
| 676 |
+
"learning_rate": 2.602662036006858e-07,
|
| 677 |
+
"loss": 0.713,
|
| 678 |
+
"step": 8900
|
| 679 |
+
},
|
| 680 |
{
|
| 681 |
"epoch": 4.35,
|
| 682 |
+
"learning_rate": 2.025877325938261e-07,
|
| 683 |
+
"loss": 0.7275,
|
| 684 |
"step": 9000
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 4.35,
|
| 688 |
+
"eval_loss": 0.7325617074966431,
|
| 689 |
+
"eval_runtime": 27.8844,
|
| 690 |
+
"eval_samples_per_second": 131.507,
|
| 691 |
+
"eval_steps_per_second": 32.886,
|
| 692 |
"step": 9000
|
| 693 |
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 4.4,
|
| 696 |
+
"learning_rate": 1.504826207082261e-07,
|
| 697 |
+
"loss": 0.693,
|
| 698 |
+
"step": 9100
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.45,
|
| 702 |
+
"learning_rate": 1.049272920272809e-07,
|
| 703 |
+
"loss": 0.689,
|
| 704 |
+
"step": 9200
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.5,
|
| 708 |
+
"learning_rate": 6.677543092937843e-08,
|
| 709 |
+
"loss": 0.7001,
|
| 710 |
+
"step": 9300
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.55,
|
| 714 |
+
"learning_rate": 3.674198446393789e-08,
|
| 715 |
+
"loss": 0.7398,
|
| 716 |
+
"step": 9400
|
| 717 |
+
},
|
| 718 |
{
|
| 719 |
"epoch": 4.59,
|
| 720 |
+
"learning_rate": 1.538976459652064e-08,
|
| 721 |
+
"loss": 0.7371,
|
| 722 |
"step": 9500
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 4.59,
|
| 726 |
+
"eval_loss": 0.7348757982254028,
|
| 727 |
+
"eval_runtime": 27.6591,
|
| 728 |
+
"eval_samples_per_second": 132.579,
|
| 729 |
+
"eval_steps_per_second": 33.154,
|
| 730 |
"step": 9500
|
| 731 |
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.64,
|
| 734 |
+
"learning_rate": 3.1189013903395455e-09,
|
| 735 |
+
"loss": 0.7164,
|
| 736 |
+
"step": 9600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.69,
|
| 740 |
+
"learning_rate": 9.998406552336684e-07,
|
| 741 |
+
"loss": 0.7045,
|
| 742 |
+
"step": 9700
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 4.74,
|
| 746 |
+
"learning_rate": 9.934334446448806e-07,
|
| 747 |
+
"loss": 0.7095,
|
| 748 |
+
"step": 9800
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.79,
|
| 752 |
+
"learning_rate": 9.777795348078374e-07,
|
| 753 |
+
"loss": 0.7265,
|
| 754 |
+
"step": 9900
|
| 755 |
+
},
|
| 756 |
{
|
| 757 |
"epoch": 4.84,
|
| 758 |
+
"learning_rate": 9.531722722678393e-07,
|
| 759 |
+
"loss": 0.7267,
|
| 760 |
"step": 10000
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 4.84,
|
| 764 |
+
"eval_loss": 0.727655291557312,
|
| 765 |
+
"eval_runtime": 27.3264,
|
| 766 |
+
"eval_samples_per_second": 134.193,
|
| 767 |
+
"eval_steps_per_second": 33.557,
|
| 768 |
"step": 10000
|
| 769 |
}
|
| 770 |
],
|
| 771 |
+
"max_steps": 16544,
|
| 772 |
+
"num_train_epochs": 8,
|
| 773 |
+
"total_flos": 9147892997166300.0,
|
| 774 |
"trial_name": null,
|
| 775 |
"trial_params": null
|
| 776 |
}
|
checkpoint-10000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
|
| 3 |
size 3375
|
checkpoint-2000/config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
-
"hidden_dropout_prob": 0.
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
|
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.2,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
checkpoint-2000/optimizer.pt
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 sha256:626d2c0f57e0d16c0069652656de4057825c16712166a707211c8fe154203bc8
|
| 3 |
+
size 1475512793
|
checkpoint-2000/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737770027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab0240bd69843fd06b929f55bc2e760f01226d976e947792a27a2de9cf7783d
|
| 3 |
size 737770027
|
checkpoint-2000/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3be3a7e37abbb30b18f1d72e9e82d80209a1ffafba792a578625451aef21e954
|
| 3 |
size 14503
|
checkpoint-2000/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eccc082304cdb1b781a00d1171288ffa36d40ca690860809f81bcac4e20adae
|
| 3 |
size 559
|
checkpoint-2000/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3abeb5aa5be592899ee5dc8748f9e3bf735434f8a9f384cf814f8b27ee9adb78
|
| 3 |
size 623
|
checkpoint-2000/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
|
| 4 |
"epoch": 0.9667673716012085,
|
| 5 |
"global_step": 2000,
|
|
@@ -7,66 +7,162 @@
|
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.24,
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.24,
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
"step": 500
|
| 23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{
|
| 25 |
"epoch": 0.48,
|
| 26 |
-
"learning_rate":
|
| 27 |
-
"loss": 0.
|
| 28 |
"step": 1000
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 0.48,
|
| 32 |
-
"eval_loss": 0.
|
| 33 |
-
"eval_runtime":
|
| 34 |
-
"eval_samples_per_second":
|
| 35 |
-
"eval_steps_per_second":
|
| 36 |
"step": 1000
|
| 37 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
{
|
| 39 |
"epoch": 0.73,
|
| 40 |
-
"learning_rate":
|
| 41 |
-
"loss": 0.
|
| 42 |
"step": 1500
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 0.73,
|
| 46 |
-
"eval_loss": 0.
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second":
|
| 50 |
"step": 1500
|
| 51 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
{
|
| 53 |
"epoch": 0.97,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 2000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.97,
|
| 60 |
-
"eval_loss": 0.
|
| 61 |
-
"eval_runtime":
|
| 62 |
-
"eval_samples_per_second":
|
| 63 |
-
"eval_steps_per_second":
|
| 64 |
"step": 2000
|
| 65 |
}
|
| 66 |
],
|
| 67 |
-
"max_steps":
|
| 68 |
-
"num_train_epochs":
|
| 69 |
-
"total_flos":
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|
| 72 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7537589073181152,
|
| 3 |
"best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
|
| 4 |
"epoch": 0.9667673716012085,
|
| 5 |
"global_step": 2000,
|
|
|
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 2e-07,
|
| 13 |
+
"loss": 1.0361,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 3.98e-07,
|
| 19 |
+
"loss": 0.9751,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 5.979999999999999e-07,
|
| 25 |
+
"loss": 0.9807,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.19,
|
| 30 |
+
"learning_rate": 7.94e-07,
|
| 31 |
+
"loss": 0.9513,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
{
|
| 35 |
"epoch": 0.24,
|
| 36 |
+
"learning_rate": 9.94e-07,
|
| 37 |
+
"loss": 0.9237,
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.24,
|
| 42 |
+
"eval_loss": 0.9464540481567383,
|
| 43 |
+
"eval_runtime": 37.5769,
|
| 44 |
+
"eval_samples_per_second": 97.587,
|
| 45 |
+
"eval_steps_per_second": 24.403,
|
| 46 |
"step": 500
|
| 47 |
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.29,
|
| 50 |
+
"learning_rate": 9.955915919781764e-07,
|
| 51 |
+
"loss": 0.9367,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.34,
|
| 56 |
+
"learning_rate": 9.81900265076038e-07,
|
| 57 |
+
"loss": 0.8993,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.39,
|
| 62 |
+
"learning_rate": 9.594490241150311e-07,
|
| 63 |
+
"loss": 0.8586,
|
| 64 |
+
"step": 800
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.44,
|
| 68 |
+
"learning_rate": 9.282057505552949e-07,
|
| 69 |
+
"loss": 0.854,
|
| 70 |
+
"step": 900
|
| 71 |
+
},
|
| 72 |
{
|
| 73 |
"epoch": 0.48,
|
| 74 |
+
"learning_rate": 8.889381125453379e-07,
|
| 75 |
+
"loss": 0.8642,
|
| 76 |
"step": 1000
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"epoch": 0.48,
|
| 80 |
+
"eval_loss": 0.8270628452301025,
|
| 81 |
+
"eval_runtime": 28.2214,
|
| 82 |
+
"eval_samples_per_second": 129.937,
|
| 83 |
+
"eval_steps_per_second": 32.493,
|
| 84 |
"step": 1000
|
| 85 |
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.53,
|
| 88 |
+
"learning_rate": 8.423819662432867e-07,
|
| 89 |
+
"loss": 0.8314,
|
| 90 |
+
"step": 1100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.58,
|
| 94 |
+
"learning_rate": 7.894097508558568e-07,
|
| 95 |
+
"loss": 0.8317,
|
| 96 |
+
"step": 1200
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.63,
|
| 100 |
+
"learning_rate": 7.310141395581585e-07,
|
| 101 |
+
"loss": 0.7939,
|
| 102 |
+
"step": 1300
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.68,
|
| 106 |
+
"learning_rate": 6.682894372882701e-07,
|
| 107 |
+
"loss": 0.803,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
{
|
| 111 |
"epoch": 0.73,
|
| 112 |
+
"learning_rate": 6.024110740127264e-07,
|
| 113 |
+
"loss": 0.8029,
|
| 114 |
"step": 1500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.73,
|
| 118 |
+
"eval_loss": 0.7635419368743896,
|
| 119 |
+
"eval_runtime": 28.2809,
|
| 120 |
+
"eval_samples_per_second": 129.663,
|
| 121 |
+
"eval_steps_per_second": 32.425,
|
| 122 |
"step": 1500
|
| 123 |
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.77,
|
| 126 |
+
"learning_rate": 5.346135777490083e-07,
|
| 127 |
+
"loss": 0.7959,
|
| 128 |
+
"step": 1600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.82,
|
| 132 |
+
"learning_rate": 4.6616744011972247e-07,
|
| 133 |
+
"loss": 0.7708,
|
| 134 |
+
"step": 1700
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.87,
|
| 138 |
+
"learning_rate": 3.9835530796656867e-07,
|
| 139 |
+
"loss": 0.7636,
|
| 140 |
+
"step": 1800
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.92,
|
| 144 |
+
"learning_rate": 3.3244794718149894e-07,
|
| 145 |
+
"loss": 0.7864,
|
| 146 |
+
"step": 1900
|
| 147 |
+
},
|
| 148 |
{
|
| 149 |
"epoch": 0.97,
|
| 150 |
+
"learning_rate": 2.696804291810131e-07,
|
| 151 |
+
"loss": 0.8005,
|
| 152 |
"step": 2000
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.97,
|
| 156 |
+
"eval_loss": 0.7537589073181152,
|
| 157 |
+
"eval_runtime": 28.4034,
|
| 158 |
+
"eval_samples_per_second": 129.104,
|
| 159 |
+
"eval_steps_per_second": 32.285,
|
| 160 |
"step": 2000
|
| 161 |
}
|
| 162 |
],
|
| 163 |
+
"max_steps": 16544,
|
| 164 |
+
"num_train_epochs": 8,
|
| 165 |
+
"total_flos": 1828884830909760.0,
|
| 166 |
"trial_name": null,
|
| 167 |
"trial_params": null
|
| 168 |
}
|
checkpoint-2000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
|
| 3 |
size 3375
|
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
-
"hidden_dropout_prob": 0.
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
|
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.2,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
"0": "LABEL_0",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737770027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:183b92732073ecb3e37d10ffc34996ac6fe70d5a5295f1d211ad7775260a3e4f
|
| 3 |
size 737770027
|
runs/Jul03_17-16-15_8a98c40ff775/events.out.tfevents.1656868588.8a98c40ff775.71.0
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1b3617a801c60d083a94daa04872ab8100ae1aa4bc27f09980a749aaf121cb98
|
| 3 |
-
size 12918
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_21-34-55_8a98c40ff775/events.out.tfevents.1656884100.8a98c40ff775.71.4
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b5e60884f2f24cd30d861b6d76f2432d12a76a66f3a0189fb8ddbabac92b6b68
|
| 3 |
-
size 9495
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_23-15-45_8a98c40ff775/1656890147.0297482/events.out.tfevents.1656890147.8a98c40ff775.71.7
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7841a1cc1f026e1d8f7e27ebfc6c2345433308cf68d12ab48b2256e8b26519a2
|
| 3 |
-
size 5435
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_23-16-08_8a98c40ff775/1656890170.9030218/events.out.tfevents.1656890170.8a98c40ff775.71.9
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5dbfc67c518b8e9b6453cf23fcecb24d018090efab32201f1068779e87121f75
|
| 3 |
-
size 5435
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_23-16-08_8a98c40ff775/events.out.tfevents.1656890170.8a98c40ff775.71.8
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aeaeddd48689ec141326ec77032494af4461bb353420d795c77f5dd6b7bae92d
|
| 3 |
-
size 4005
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_23-26-33_8a98c40ff775/1656890797.636419/events.out.tfevents.1656890797.8a98c40ff775.5349.1
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:83ee3cfe3d4c4e5adfe96c2d421fe9902f2b13d7880adfdaa4f942184344c537
|
| 3 |
-
size 5435
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul03_23-26-33_8a98c40ff775/events.out.tfevents.1656890797.8a98c40ff775.5349.0
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:15a8e80f13acce54563ebb8cb7c22816065730ffe17ebaba086b1299d54ba061
|
| 3 |
-
size 7001
|
|
|
|
|
|
|
|
|
|
|
|
runs/Jul04_00-33-28_8a98c40ff775/1656894810.6894863/events.out.tfevents.1656894810.8a98c40ff775.8083.1
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0f8db2b966d521d474da361acfa1a1d7fdbf1c646c12217f96f06b8c168f5766
|
| 3 |
-
size 5435
|
|
|
|
|
|
|
|
|
|
|
|
runs/{Jul03_17-16-15_8a98c40ff775/1656868588.8381069/events.out.tfevents.1656868588.8a98c40ff775.71.1 → Jul26_21-03-46_1fe91f198d71/1658869435.620103/events.out.tfevents.1658869435.1fe91f198d71.71.1}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5435
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6485b7a2dffeb1975234009c45dcfd6419d71586d0e5c9b414f400258d1ce9b
|
| 3 |
size 5435
|
runs/{Jul03_19-51-55_8a98c40ff775/events.out.tfevents.1656877916.8a98c40ff775.71.2 → Jul26_21-03-46_1fe91f198d71/events.out.tfevents.1658869435.1fe91f198d71.71.0}
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:a4f66a750ddef0868289783b7c625cada735943a5b2c56c08ec75354fbdd384c
|
| 3 |
+
size 6742
|
runs/{Jul03_21-34-55_8a98c40ff775/1656884100.2687025/events.out.tfevents.1656884100.8a98c40ff775.71.5 → Jul26_21-10-23_1fe91f198d71/1658869825.093272/events.out.tfevents.1658869825.1fe91f198d71.71.3}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5435
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3507bdbfe9d3f6eb69447dba21acc822c993a5cb10a358dc39ed139bc7ca44ae
|
| 3 |
size 5435
|
runs/{Jul03_23-15-45_8a98c40ff775/events.out.tfevents.1656890147.8a98c40ff775.71.6 → Jul26_21-10-23_1fe91f198d71/events.out.tfevents.1658869825.1fe91f198d71.71.2}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4100
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f04c78aa68e1a98a7ea678d1ec309091ec845b61e79e79a4e85923665acc8c20
|
| 3 |
size 4100
|
runs/{Jul03_19-51-55_8a98c40ff775/1656877916.4434352/events.out.tfevents.1656877916.8a98c40ff775.71.3 → Jul26_21-13-22_1fe91f198d71/1658870005.9725268/events.out.tfevents.1658870005.1fe91f198d71.1213.1}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5435
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8514910d27122ee8e76b361c1ee7444303a7c1520614670837bc4fab14114a2
|
| 3 |
size 5435
|
runs/{Jul04_00-33-28_8a98c40ff775/events.out.tfevents.1656894810.8a98c40ff775.8083.0 → Jul26_21-13-22_1fe91f198d71/events.out.tfevents.1658870005.1fe91f198d71.1213.0}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39221
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb9bbc6749502c5c71b9d1df2d6d1835de4ccc9b642bed7b8318b2d995d27a47
|
| 3 |
size 39221
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ffb2d40861e346c298ecb026926b1cd6fcf3c2ff8a5a38a5b78b121f9949508
|
| 3 |
size 3375
|