Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 368871908
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:950548c8a1009275435aab0abd88d1fdc15cb2c499cc9aa00fc7064a0587c4d8
|
| 3 |
size 368871908
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737866955
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ebf0bf13960cac29e9227879a5d3b35db6c78af896a73ba25a6ab26388da1eb
|
| 3 |
size 737866955
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1957b7b95ab2cf8185f2742cd9f954cf0b2a7260d83a94c56f84fd3fbb2efffe
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2408b440f534d6bf141e5e3eee030bf035f8ee033aa65c33a5266ae6766544ca
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"best_global_step": 2393,
|
| 3 |
-
"best_metric": 0.
|
| 4 |
"best_model_checkpoint": "./results_deberta_framing/checkpoint-2393",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
@@ -9,54 +9,364 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 0.20894274968658588,
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate":
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 500
|
| 18 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
{
|
| 20 |
"epoch": 0.41788549937317176,
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 1000
|
| 25 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{
|
| 27 |
"epoch": 0.6268282490597576,
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 1500
|
| 32 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
{
|
| 34 |
"epoch": 0.8357709987463435,
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 2000
|
| 39 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
{
|
| 41 |
"epoch": 1.0,
|
| 42 |
-
"eval_accuracy": 0.
|
| 43 |
-
"eval_f1": 0.
|
| 44 |
-
"eval_loss":
|
| 45 |
-
"eval_precision": 0.
|
| 46 |
-
"eval_recall":
|
| 47 |
-
"eval_roc_auc": 0.
|
| 48 |
-
"eval_runtime":
|
| 49 |
-
"eval_samples_per_second":
|
| 50 |
-
"eval_steps_per_second": 1.
|
| 51 |
"step": 2393
|
| 52 |
}
|
| 53 |
],
|
| 54 |
-
"logging_steps":
|
| 55 |
"max_steps": 7179,
|
| 56 |
"num_input_tokens_seen": 0,
|
| 57 |
"num_train_epochs": 3,
|
| 58 |
"save_steps": 500,
|
| 59 |
"stateful_callbacks": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"TrainerControl": {
|
| 61 |
"args": {
|
| 62 |
"should_epoch_stop": false,
|
|
@@ -68,7 +378,7 @@
|
|
| 68 |
"attributes": {}
|
| 69 |
}
|
| 70 |
},
|
| 71 |
-
"total_flos":
|
| 72 |
"train_batch_size": 16,
|
| 73 |
"trial_name": null,
|
| 74 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_global_step": 2393,
|
| 3 |
+
"best_metric": 0.7003869916491275,
|
| 4 |
"best_model_checkpoint": "./results_deberta_framing/checkpoint-2393",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.020894274968658588,
|
| 14 |
+
"grad_norm": 1.611328125,
|
| 15 |
+
"learning_rate": 1.1368909512761022e-06,
|
| 16 |
+
"loss": 0.645970458984375,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.041788549937317176,
|
| 21 |
+
"grad_norm": 4.58984375,
|
| 22 |
+
"learning_rate": 2.296983758700696e-06,
|
| 23 |
+
"loss": 0.3519872283935547,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06268282490597576,
|
| 28 |
+
"grad_norm": 208.25,
|
| 29 |
+
"learning_rate": 3.4570765661252904e-06,
|
| 30 |
+
"loss": 0.37210319519042967,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08357709987463435,
|
| 35 |
+
"grad_norm": 4.3828125,
|
| 36 |
+
"learning_rate": 4.617169373549885e-06,
|
| 37 |
+
"loss": 0.6655684661865234,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10447137484329294,
|
| 42 |
+
"grad_norm": 4.5859375,
|
| 43 |
+
"learning_rate": 5.7772621809744785e-06,
|
| 44 |
+
"loss": 0.7237747192382813,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12536564981195153,
|
| 49 |
+
"grad_norm": 2.625,
|
| 50 |
+
"learning_rate": 6.937354988399072e-06,
|
| 51 |
+
"loss": 0.7051520538330078,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14625992478061012,
|
| 56 |
+
"grad_norm": 2.38671875,
|
| 57 |
+
"learning_rate": 8.097447795823666e-06,
|
| 58 |
+
"loss": 0.7176536560058594,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1671541997492687,
|
| 63 |
+
"grad_norm": 7.24609375,
|
| 64 |
+
"learning_rate": 9.257540603248261e-06,
|
| 65 |
+
"loss": 0.7043207550048828,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1880484747179273,
|
| 70 |
+
"grad_norm": 3.458984375,
|
| 71 |
+
"learning_rate": 9.973325429756967e-06,
|
| 72 |
+
"loss": 0.7054608917236328,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
{
|
| 76 |
"epoch": 0.20894274968658588,
|
| 77 |
+
"grad_norm": 5.48828125,
|
| 78 |
+
"learning_rate": 9.899229401304091e-06,
|
| 79 |
+
"loss": 0.6945940399169922,
|
| 80 |
"step": 500
|
| 81 |
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22983702465524447,
|
| 84 |
+
"grad_norm": 2.26171875,
|
| 85 |
+
"learning_rate": 9.825133372851215e-06,
|
| 86 |
+
"loss": 0.7002091217041015,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.25073129962390306,
|
| 91 |
+
"grad_norm": 1.404296875,
|
| 92 |
+
"learning_rate": 9.751037344398341e-06,
|
| 93 |
+
"loss": 0.7054033660888672,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.27162557459256165,
|
| 98 |
+
"grad_norm": 6.20703125,
|
| 99 |
+
"learning_rate": 9.676941315945465e-06,
|
| 100 |
+
"loss": 0.7095681762695313,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.29251984956122024,
|
| 105 |
+
"grad_norm": 3.859375,
|
| 106 |
+
"learning_rate": 9.602845287492591e-06,
|
| 107 |
+
"loss": 0.708401870727539,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3134141245298788,
|
| 112 |
+
"grad_norm": 4.89453125,
|
| 113 |
+
"learning_rate": 9.528749259039716e-06,
|
| 114 |
+
"loss": 0.7023555755615234,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3343083994985374,
|
| 119 |
+
"grad_norm": 1.0517578125,
|
| 120 |
+
"learning_rate": 9.454653230586842e-06,
|
| 121 |
+
"loss": 0.6927510833740235,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.355202674467196,
|
| 126 |
+
"grad_norm": 1.111328125,
|
| 127 |
+
"learning_rate": 9.380557202133966e-06,
|
| 128 |
+
"loss": 0.6971592712402344,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3760969494358546,
|
| 133 |
+
"grad_norm": 3.15234375,
|
| 134 |
+
"learning_rate": 9.306461173681092e-06,
|
| 135 |
+
"loss": 0.6903689575195312,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3969912244045132,
|
| 140 |
+
"grad_norm": 3.423828125,
|
| 141 |
+
"learning_rate": 9.232365145228218e-06,
|
| 142 |
+
"loss": 0.6944327545166016,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
{
|
| 146 |
"epoch": 0.41788549937317176,
|
| 147 |
+
"grad_norm": 3.796875,
|
| 148 |
+
"learning_rate": 9.158269116775342e-06,
|
| 149 |
+
"loss": 0.6978585052490235,
|
| 150 |
"step": 1000
|
| 151 |
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.43877977434183035,
|
| 154 |
+
"grad_norm": 4.015625,
|
| 155 |
+
"learning_rate": 9.084173088322466e-06,
|
| 156 |
+
"loss": 0.7033126831054688,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.45967404931048894,
|
| 161 |
+
"grad_norm": 1.6416015625,
|
| 162 |
+
"learning_rate": 9.010077059869592e-06,
|
| 163 |
+
"loss": 0.6952677917480469,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.48056832427914753,
|
| 168 |
+
"grad_norm": 0.859375,
|
| 169 |
+
"learning_rate": 8.935981031416716e-06,
|
| 170 |
+
"loss": 0.6943918609619141,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5014625992478061,
|
| 175 |
+
"grad_norm": 1.888671875,
|
| 176 |
+
"learning_rate": 8.86188500296384e-06,
|
| 177 |
+
"loss": 0.6895309448242187,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5223568742164647,
|
| 182 |
+
"grad_norm": 0.83154296875,
|
| 183 |
+
"learning_rate": 8.787788974510967e-06,
|
| 184 |
+
"loss": 0.6940658569335938,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5432511491851233,
|
| 189 |
+
"grad_norm": 0.67822265625,
|
| 190 |
+
"learning_rate": 8.713692946058093e-06,
|
| 191 |
+
"loss": 0.6936180877685547,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5641454241537819,
|
| 196 |
+
"grad_norm": 4.69140625,
|
| 197 |
+
"learning_rate": 8.639596917605217e-06,
|
| 198 |
+
"loss": 0.6969568634033203,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5850396991224405,
|
| 203 |
+
"grad_norm": 4.01171875,
|
| 204 |
+
"learning_rate": 8.565500889152341e-06,
|
| 205 |
+
"loss": 2.2344410705566404,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6059339740910991,
|
| 210 |
+
"grad_norm": 16.0625,
|
| 211 |
+
"learning_rate": 8.491404860699467e-06,
|
| 212 |
+
"loss": 0.7197090148925781,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
{
|
| 216 |
"epoch": 0.6268282490597576,
|
| 217 |
+
"grad_norm": 5.19140625,
|
| 218 |
+
"learning_rate": 8.417308832246593e-06,
|
| 219 |
+
"loss": 0.7260000610351562,
|
| 220 |
"step": 1500
|
| 221 |
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6477225240284162,
|
| 224 |
+
"grad_norm": 2.408203125,
|
| 225 |
+
"learning_rate": 8.343212803793717e-06,
|
| 226 |
+
"loss": 0.7103495025634765,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6686167989970748,
|
| 231 |
+
"grad_norm": 2.6953125,
|
| 232 |
+
"learning_rate": 8.269116775340842e-06,
|
| 233 |
+
"loss": 0.7216840362548829,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6895110739657334,
|
| 238 |
+
"grad_norm": 2.78515625,
|
| 239 |
+
"learning_rate": 8.195020746887967e-06,
|
| 240 |
+
"loss": 0.7239863586425781,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.710405348934392,
|
| 245 |
+
"grad_norm": 2.953125,
|
| 246 |
+
"learning_rate": 8.120924718435092e-06,
|
| 247 |
+
"loss": 0.7079918670654297,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7312996239030506,
|
| 252 |
+
"grad_norm": 1.7939453125,
|
| 253 |
+
"learning_rate": 8.046828689982218e-06,
|
| 254 |
+
"loss": 0.6929259490966797,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.7521938988717092,
|
| 259 |
+
"grad_norm": 4.890625,
|
| 260 |
+
"learning_rate": 7.972732661529344e-06,
|
| 261 |
+
"loss": 0.7325093078613282,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7730881738403678,
|
| 266 |
+
"grad_norm": 11.421875,
|
| 267 |
+
"learning_rate": 7.898636633076468e-06,
|
| 268 |
+
"loss": 0.6976766967773438,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7939824488090264,
|
| 273 |
+
"grad_norm": 4.35546875,
|
| 274 |
+
"learning_rate": 7.824540604623592e-06,
|
| 275 |
+
"loss": 0.6973881530761719,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8148767237776849,
|
| 280 |
+
"grad_norm": 10.5625,
|
| 281 |
+
"learning_rate": 7.750444576170718e-06,
|
| 282 |
+
"loss": 0.7010235595703125,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
{
|
| 286 |
"epoch": 0.8357709987463435,
|
| 287 |
+
"grad_norm": 3.947265625,
|
| 288 |
+
"learning_rate": 7.676348547717844e-06,
|
| 289 |
+
"loss": 0.6964045715332031,
|
| 290 |
"step": 2000
|
| 291 |
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.8566652737150021,
|
| 294 |
+
"grad_norm": 1.2109375,
|
| 295 |
+
"learning_rate": 7.6022525192649674e-06,
|
| 296 |
+
"loss": 0.7006184387207032,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.8775595486836607,
|
| 301 |
+
"grad_norm": 11.0625,
|
| 302 |
+
"learning_rate": 7.528156490812093e-06,
|
| 303 |
+
"loss": 0.6912442016601562,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8984538236523193,
|
| 308 |
+
"grad_norm": 0.88232421875,
|
| 309 |
+
"learning_rate": 7.4540604623592185e-06,
|
| 310 |
+
"loss": 0.6953639984130859,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.9193480986209779,
|
| 315 |
+
"grad_norm": 1.3193359375,
|
| 316 |
+
"learning_rate": 7.379964433906344e-06,
|
| 317 |
+
"loss": 0.6934783935546875,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9402423735896365,
|
| 322 |
+
"grad_norm": 2.705078125,
|
| 323 |
+
"learning_rate": 7.305868405453468e-06,
|
| 324 |
+
"loss": 0.6865818786621094,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.9611366485582951,
|
| 329 |
+
"grad_norm": 1.0986328125,
|
| 330 |
+
"learning_rate": 7.231772377000593e-06,
|
| 331 |
+
"loss": 0.6957395935058593,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9820309235269536,
|
| 336 |
+
"grad_norm": 0.5556640625,
|
| 337 |
+
"learning_rate": 7.157676348547719e-06,
|
| 338 |
+
"loss": 0.6910171508789062,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
{
|
| 342 |
"epoch": 1.0,
|
| 343 |
+
"eval_accuracy": 0.5389196531187964,
|
| 344 |
+
"eval_f1": 0.7003869916491275,
|
| 345 |
+
"eval_loss": 0.6902092099189758,
|
| 346 |
+
"eval_precision": 0.5389196531187964,
|
| 347 |
+
"eval_recall": 1.0,
|
| 348 |
+
"eval_roc_auc": 0.5,
|
| 349 |
+
"eval_runtime": 349.1952,
|
| 350 |
+
"eval_samples_per_second": 27.409,
|
| 351 |
+
"eval_steps_per_second": 1.715,
|
| 352 |
"step": 2393
|
| 353 |
}
|
| 354 |
],
|
| 355 |
+
"logging_steps": 50,
|
| 356 |
"max_steps": 7179,
|
| 357 |
"num_input_tokens_seen": 0,
|
| 358 |
"num_train_epochs": 3,
|
| 359 |
"save_steps": 500,
|
| 360 |
"stateful_callbacks": {
|
| 361 |
+
"EarlyStoppingCallback": {
|
| 362 |
+
"args": {
|
| 363 |
+
"early_stopping_patience": 2,
|
| 364 |
+
"early_stopping_threshold": 0.0
|
| 365 |
+
},
|
| 366 |
+
"attributes": {
|
| 367 |
+
"early_stopping_patience_counter": 0
|
| 368 |
+
}
|
| 369 |
+
},
|
| 370 |
"TrainerControl": {
|
| 371 |
"args": {
|
| 372 |
"should_epoch_stop": false,
|
|
|
|
| 378 |
"attributes": {}
|
| 379 |
}
|
| 380 |
},
|
| 381 |
+
"total_flos": 6539240997132864.0,
|
| 382 |
"train_batch_size": 16,
|
| 383 |
"trial_name": null,
|
| 384 |
"trial_params": null
|
last-checkpoint/training_args.bin
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 sha256:14805fea36fd0e71a72e39951ab4c4fd7a35166ebbf437897dda2a50408a9402
|
| 3 |
+
size 5265
|