Upload folder using huggingface_hub
Browse files- checkpoints-v1.3/checkpoint-10240/model.safetensors +3 -0
- checkpoints-v1.3/checkpoint-10240/optimizer.pt +3 -0
- checkpoints-v1.3/checkpoint-10240/rng_state.pth +3 -0
- checkpoints-v1.3/checkpoint-10240/scaler.pt +3 -0
- checkpoints-v1.3/checkpoint-10240/scheduler.pt +3 -0
- checkpoints-v1.3/checkpoint-10240/trainer_state.json +524 -0
- checkpoints-v1.3/checkpoint-10240/training_args.bin +3 -0
checkpoints-v1.3/checkpoint-10240/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6634a78b327712856504fb465a0635797eade7db44f8aa3a353dce7134f07b
|
| 3 |
+
size 4634068
|
checkpoints-v1.3/checkpoint-10240/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1742382c8e27fd8b5e625bfc706a8e0c4a5c0253e348693b7489219efc2a07f9
|
| 3 |
+
size 1121995
|
checkpoints-v1.3/checkpoint-10240/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d95ec4ff72b3a3694a7e0170340b972320337fb9ed91ccae10da983d02ef0337
|
| 3 |
+
size 14645
|
checkpoints-v1.3/checkpoint-10240/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df1fbd7e12410fdb6bb0abd3113128f3412b14ebe6a73178008f5074beadf68a
|
| 3 |
+
size 1383
|
checkpoints-v1.3/checkpoint-10240/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca1522025c020e1c97d736fab7ff200620e603348507bd723aae3d12bd3b97ff
|
| 3 |
+
size 1465
|
checkpoints-v1.3/checkpoint-10240/trainer_state.json
ADDED
|
@@ -0,0 +1,524 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1042191451791012,
|
| 6 |
+
"eval_steps": 1024,
|
| 7 |
+
"global_step": 10240,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0026054786294775305,
|
| 14 |
+
"grad_norm": 0.6768632531166077,
|
| 15 |
+
"learning_rate": 4.9804687500000004e-05,
|
| 16 |
+
"loss": 0.666217029094696,
|
| 17 |
+
"step": 256
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.005210957258955061,
|
| 21 |
+
"grad_norm": 0.7611387372016907,
|
| 22 |
+
"learning_rate": 9.98046875e-05,
|
| 23 |
+
"loss": 0.46460574865341187,
|
| 24 |
+
"step": 512
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.007816435888432591,
|
| 28 |
+
"grad_norm": 3.202936887741089,
|
| 29 |
+
"learning_rate": 9.999832063013975e-05,
|
| 30 |
+
"loss": 0.3047865331172943,
|
| 31 |
+
"step": 768
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.010421914517910122,
|
| 35 |
+
"grad_norm": 2.767078161239624,
|
| 36 |
+
"learning_rate": 9.999325626552273e-05,
|
| 37 |
+
"loss": 0.20353302359580994,
|
| 38 |
+
"step": 1024
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.010421914517910122,
|
| 42 |
+
"eval_acc": 0.9056051816259112,
|
| 43 |
+
"eval_gap": 0.65849609375,
|
| 44 |
+
"eval_loss": 0.24813499578407833,
|
| 45 |
+
"eval_neg": 0.10586111886160714,
|
| 46 |
+
"eval_pos": 0.7643833705357143,
|
| 47 |
+
"step": 1024
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.010421914517910122,
|
| 51 |
+
"eval_acc": 0.9056051816259112,
|
| 52 |
+
"eval_gap": 0.65849609375,
|
| 53 |
+
"eval_loss": 0.24813499578407833,
|
| 54 |
+
"eval_neg": 0.10586111886160714,
|
| 55 |
+
"eval_pos": 0.7643833705357143,
|
| 56 |
+
"eval_runtime": 11.5511,
|
| 57 |
+
"eval_samples_per_second": 190.458,
|
| 58 |
+
"eval_steps_per_second": 3.03,
|
| 59 |
+
"step": 1024
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.01302739314738765,
|
| 63 |
+
"grad_norm": 1.7397773265838623,
|
| 64 |
+
"learning_rate": 9.99848072231934e-05,
|
| 65 |
+
"loss": 0.10323332250118256,
|
| 66 |
+
"step": 1280
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.015632871776865183,
|
| 70 |
+
"grad_norm": 0.5150644183158875,
|
| 71 |
+
"learning_rate": 9.997297407517456e-05,
|
| 72 |
+
"loss": 0.08242284506559372,
|
| 73 |
+
"step": 1536
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.018238350406342713,
|
| 77 |
+
"grad_norm": 0.7313013076782227,
|
| 78 |
+
"learning_rate": 9.995775762260215e-05,
|
| 79 |
+
"loss": 0.06939949095249176,
|
| 80 |
+
"step": 1792
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.020843829035820244,
|
| 84 |
+
"grad_norm": 2.599472999572754,
|
| 85 |
+
"learning_rate": 9.993915889567087e-05,
|
| 86 |
+
"loss": 0.06290815025568008,
|
| 87 |
+
"step": 2048
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.020843829035820244,
|
| 91 |
+
"eval_acc": 0.9576885104179382,
|
| 92 |
+
"eval_gap": 0.8409040178571429,
|
| 93 |
+
"eval_loss": 0.10907792725733348,
|
| 94 |
+
"eval_neg": 0.09029192243303572,
|
| 95 |
+
"eval_pos": 0.9311662946428572,
|
| 96 |
+
"step": 2048
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.020843829035820244,
|
| 100 |
+
"eval_acc": 0.9576885104179382,
|
| 101 |
+
"eval_gap": 0.8409040178571429,
|
| 102 |
+
"eval_loss": 0.10907792725733348,
|
| 103 |
+
"eval_neg": 0.09029192243303572,
|
| 104 |
+
"eval_pos": 0.9311662946428572,
|
| 105 |
+
"eval_runtime": 11.5084,
|
| 106 |
+
"eval_samples_per_second": 191.164,
|
| 107 |
+
"eval_steps_per_second": 3.041,
|
| 108 |
+
"step": 2048
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.023449307665297774,
|
| 112 |
+
"grad_norm": 0.5858944654464722,
|
| 113 |
+
"learning_rate": 9.991717915356446e-05,
|
| 114 |
+
"loss": 0.05567435547709465,
|
| 115 |
+
"step": 2304
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0260547862947753,
|
| 119 |
+
"grad_norm": 0.7901586890220642,
|
| 120 |
+
"learning_rate": 9.989181988437053e-05,
|
| 121 |
+
"loss": 0.05114856734871864,
|
| 122 |
+
"step": 2560
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.028660264924252832,
|
| 126 |
+
"grad_norm": 0.8466191291809082,
|
| 127 |
+
"learning_rate": 9.986308280497967e-05,
|
| 128 |
+
"loss": 0.04558824002742767,
|
| 129 |
+
"step": 2816
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.031265743553730366,
|
| 133 |
+
"grad_norm": 0.2479318380355835,
|
| 134 |
+
"learning_rate": 9.983096986096934e-05,
|
| 135 |
+
"loss": 0.04197113215923309,
|
| 136 |
+
"step": 3072
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.031265743553730366,
|
| 140 |
+
"eval_acc": 0.9745039888790675,
|
| 141 |
+
"eval_gap": 0.9002511160714286,
|
| 142 |
+
"eval_loss": 0.07157694122620992,
|
| 143 |
+
"eval_neg": 0.04814627511160714,
|
| 144 |
+
"eval_pos": 0.9484235491071429,
|
| 145 |
+
"step": 3072
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.031265743553730366,
|
| 149 |
+
"eval_acc": 0.9745039888790675,
|
| 150 |
+
"eval_gap": 0.9002511160714286,
|
| 151 |
+
"eval_loss": 0.07157694122620992,
|
| 152 |
+
"eval_neg": 0.04814627511160714,
|
| 153 |
+
"eval_pos": 0.9484235491071429,
|
| 154 |
+
"eval_runtime": 11.6071,
|
| 155 |
+
"eval_samples_per_second": 189.539,
|
| 156 |
+
"eval_steps_per_second": 3.015,
|
| 157 |
+
"step": 3072
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03387122218320789,
|
| 161 |
+
"grad_norm": 0.44913774728775024,
|
| 162 |
+
"learning_rate": 9.97954832264721e-05,
|
| 163 |
+
"loss": 0.04050295054912567,
|
| 164 |
+
"step": 3328
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.03647670081268543,
|
| 168 |
+
"grad_norm": 0.4910290539264679,
|
| 169 |
+
"learning_rate": 9.975662530402843e-05,
|
| 170 |
+
"loss": 0.03661082684993744,
|
| 171 |
+
"step": 3584
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.039082179442162954,
|
| 175 |
+
"grad_norm": 0.7061027884483337,
|
| 176 |
+
"learning_rate": 9.971439872442399e-05,
|
| 177 |
+
"loss": 0.03790655359625816,
|
| 178 |
+
"step": 3840
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.04168765807164049,
|
| 182 |
+
"grad_norm": 1.5880284309387207,
|
| 183 |
+
"learning_rate": 9.966880634651166e-05,
|
| 184 |
+
"loss": 0.03482869639992714,
|
| 185 |
+
"step": 4096
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.04168765807164049,
|
| 189 |
+
"eval_acc": 0.9759424822671073,
|
| 190 |
+
"eval_gap": 0.9098214285714286,
|
| 191 |
+
"eval_loss": 0.06747848434107644,
|
| 192 |
+
"eval_neg": 0.04893787928989955,
|
| 193 |
+
"eval_pos": 0.9588588169642858,
|
| 194 |
+
"step": 4096
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.04168765807164049,
|
| 198 |
+
"eval_acc": 0.9759424822671073,
|
| 199 |
+
"eval_gap": 0.9098214285714286,
|
| 200 |
+
"eval_loss": 0.06747848434107644,
|
| 201 |
+
"eval_neg": 0.04893787928989955,
|
| 202 |
+
"eval_pos": 0.9588588169642858,
|
| 203 |
+
"eval_runtime": 11.7135,
|
| 204 |
+
"eval_samples_per_second": 187.818,
|
| 205 |
+
"eval_steps_per_second": 2.988,
|
| 206 |
+
"step": 4096
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.044293136701118015,
|
| 210 |
+
"grad_norm": 0.18764200806617737,
|
| 211 |
+
"learning_rate": 9.961985125701787e-05,
|
| 212 |
+
"loss": 0.0340995118021965,
|
| 213 |
+
"step": 4352
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.04689861533059555,
|
| 217 |
+
"grad_norm": 0.12677673995494843,
|
| 218 |
+
"learning_rate": 9.956753677033363e-05,
|
| 219 |
+
"loss": 0.032815080136060715,
|
| 220 |
+
"step": 4608
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.049504093960073076,
|
| 224 |
+
"grad_norm": 0.3894726634025574,
|
| 225 |
+
"learning_rate": 9.95118664282902e-05,
|
| 226 |
+
"loss": 0.03092392161488533,
|
| 227 |
+
"step": 4864
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0521095725895506,
|
| 231 |
+
"grad_norm": 0.5825901031494141,
|
| 232 |
+
"learning_rate": 9.945284399991925e-05,
|
| 233 |
+
"loss": 0.0337848924100399,
|
| 234 |
+
"step": 5120
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0521095725895506,
|
| 238 |
+
"eval_acc": 0.9801587496485029,
|
| 239 |
+
"eval_gap": 0.9224609375,
|
| 240 |
+
"eval_loss": 0.05970690926270825,
|
| 241 |
+
"eval_neg": 0.04791543143136161,
|
| 242 |
+
"eval_pos": 0.9703404017857142,
|
| 243 |
+
"step": 5120
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.0521095725895506,
|
| 247 |
+
"eval_acc": 0.9801587496485029,
|
| 248 |
+
"eval_gap": 0.9224609375,
|
| 249 |
+
"eval_loss": 0.05970690926270825,
|
| 250 |
+
"eval_neg": 0.04791543143136161,
|
| 251 |
+
"eval_pos": 0.9703404017857142,
|
| 252 |
+
"eval_runtime": 11.5781,
|
| 253 |
+
"eval_samples_per_second": 190.013,
|
| 254 |
+
"eval_steps_per_second": 3.023,
|
| 255 |
+
"step": 5120
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.05471505121902814,
|
| 259 |
+
"grad_norm": 0.38748735189437866,
|
| 260 |
+
"learning_rate": 9.939047348119769e-05,
|
| 261 |
+
"loss": 0.030142318457365036,
|
| 262 |
+
"step": 5376
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.057320529848505664,
|
| 266 |
+
"grad_norm": 0.27703332901000977,
|
| 267 |
+
"learning_rate": 9.932475909477713e-05,
|
| 268 |
+
"loss": 0.03031122498214245,
|
| 269 |
+
"step": 5632
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0599260084779832,
|
| 273 |
+
"grad_norm": 0.4905368685722351,
|
| 274 |
+
"learning_rate": 9.925570528969803e-05,
|
| 275 |
+
"loss": 0.027261599898338318,
|
| 276 |
+
"step": 5888
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.06253148710746073,
|
| 280 |
+
"grad_norm": 0.6853195428848267,
|
| 281 |
+
"learning_rate": 9.918331674108844e-05,
|
| 282 |
+
"loss": 0.028637079522013664,
|
| 283 |
+
"step": 6144
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.06253148710746073,
|
| 287 |
+
"eval_acc": 0.9826885104179383,
|
| 288 |
+
"eval_gap": 0.9291155133928571,
|
| 289 |
+
"eval_loss": 0.0543118260002562,
|
| 290 |
+
"eval_neg": 0.04116423470633371,
|
| 291 |
+
"eval_pos": 0.9702566964285714,
|
| 292 |
+
"step": 6144
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.06253148710746073,
|
| 296 |
+
"eval_acc": 0.9826885104179383,
|
| 297 |
+
"eval_gap": 0.9291155133928571,
|
| 298 |
+
"eval_loss": 0.0543118260002562,
|
| 299 |
+
"eval_neg": 0.04116423470633371,
|
| 300 |
+
"eval_pos": 0.9702566964285714,
|
| 301 |
+
"eval_runtime": 11.3233,
|
| 302 |
+
"eval_samples_per_second": 194.289,
|
| 303 |
+
"eval_steps_per_second": 3.091,
|
| 304 |
+
"step": 6144
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.06513696573693825,
|
| 308 |
+
"grad_norm": 0.34094464778900146,
|
| 309 |
+
"learning_rate": 9.91075983498475e-05,
|
| 310 |
+
"loss": 0.02751798741519451,
|
| 311 |
+
"step": 6400
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.06774244436641579,
|
| 315 |
+
"grad_norm": 0.5183176398277283,
|
| 316 |
+
"learning_rate": 9.902855524231368e-05,
|
| 317 |
+
"loss": 0.028319211676716805,
|
| 318 |
+
"step": 6656
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.07034792299589332,
|
| 322 |
+
"grad_norm": 0.4686974287033081,
|
| 323 |
+
"learning_rate": 9.89461927699176e-05,
|
| 324 |
+
"loss": 0.027841968461871147,
|
| 325 |
+
"step": 6912
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.07295340162537085,
|
| 329 |
+
"grad_norm": 0.48985323309898376,
|
| 330 |
+
"learning_rate": 9.886051650881986e-05,
|
| 331 |
+
"loss": 0.025898020714521408,
|
| 332 |
+
"step": 7168
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.07295340162537085,
|
| 336 |
+
"eval_acc": 0.9843254157475063,
|
| 337 |
+
"eval_gap": 0.93515625,
|
| 338 |
+
"eval_loss": 0.05201355703175068,
|
| 339 |
+
"eval_neg": 0.03936669485909598,
|
| 340 |
+
"eval_pos": 0.9745256696428571,
|
| 341 |
+
"step": 7168
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.07295340162537085,
|
| 345 |
+
"eval_acc": 0.9843254157475063,
|
| 346 |
+
"eval_gap": 0.93515625,
|
| 347 |
+
"eval_loss": 0.05201355703175068,
|
| 348 |
+
"eval_neg": 0.03936669485909598,
|
| 349 |
+
"eval_pos": 0.9745256696428571,
|
| 350 |
+
"eval_runtime": 11.3523,
|
| 351 |
+
"eval_samples_per_second": 193.793,
|
| 352 |
+
"eval_steps_per_second": 3.083,
|
| 353 |
+
"step": 7168
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.07555888025484837,
|
| 357 |
+
"grad_norm": 0.9054098129272461,
|
| 358 |
+
"learning_rate": 9.877153225953341e-05,
|
| 359 |
+
"loss": 0.02771976962685585,
|
| 360 |
+
"step": 7424
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.07816435888432591,
|
| 364 |
+
"grad_norm": 0.1680811196565628,
|
| 365 |
+
"learning_rate": 9.867924604653094e-05,
|
| 366 |
+
"loss": 0.027917755767703056,
|
| 367 |
+
"step": 7680
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.08076983751380344,
|
| 371 |
+
"grad_norm": 0.19059687852859497,
|
| 372 |
+
"learning_rate": 9.858366411783688e-05,
|
| 373 |
+
"loss": 0.025375036522746086,
|
| 374 |
+
"step": 7936
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.08337531614328098,
|
| 378 |
+
"grad_norm": 0.5264661312103271,
|
| 379 |
+
"learning_rate": 9.848479294460454e-05,
|
| 380 |
+
"loss": 0.02571159414947033,
|
| 381 |
+
"step": 8192
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.08337531614328098,
|
| 385 |
+
"eval_acc": 0.9853174788611275,
|
| 386 |
+
"eval_gap": 0.9412806919642858,
|
| 387 |
+
"eval_loss": 0.048451720497437886,
|
| 388 |
+
"eval_neg": 0.03673537118094308,
|
| 389 |
+
"eval_pos": 0.9779017857142858,
|
| 390 |
+
"step": 8192
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.08337531614328098,
|
| 394 |
+
"eval_acc": 0.9853174788611275,
|
| 395 |
+
"eval_gap": 0.9412806919642858,
|
| 396 |
+
"eval_loss": 0.048451720497437886,
|
| 397 |
+
"eval_neg": 0.03673537118094308,
|
| 398 |
+
"eval_pos": 0.9779017857142858,
|
| 399 |
+
"eval_runtime": 11.4872,
|
| 400 |
+
"eval_samples_per_second": 191.517,
|
| 401 |
+
"eval_steps_per_second": 3.047,
|
| 402 |
+
"step": 8192
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.0859807947727585,
|
| 406 |
+
"grad_norm": 0.7129268050193787,
|
| 407 |
+
"learning_rate": 9.838263922067783e-05,
|
| 408 |
+
"loss": 0.024671752005815506,
|
| 409 |
+
"step": 8448
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.08858627340223603,
|
| 413 |
+
"grad_norm": 0.26395970582962036,
|
| 414 |
+
"learning_rate": 9.827720986213824e-05,
|
| 415 |
+
"loss": 0.022725798189640045,
|
| 416 |
+
"step": 8704
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.09119175203171356,
|
| 420 |
+
"grad_norm": 0.3604643642902374,
|
| 421 |
+
"learning_rate": 9.816851200683649e-05,
|
| 422 |
+
"loss": 0.025862637907266617,
|
| 423 |
+
"step": 8960
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0937972306611911,
|
| 427 |
+
"grad_norm": 0.17066827416419983,
|
| 428 |
+
"learning_rate": 9.805655301390928e-05,
|
| 429 |
+
"loss": 0.025739867240190506,
|
| 430 |
+
"step": 9216
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.0937972306611911,
|
| 434 |
+
"eval_acc": 0.9840277961322239,
|
| 435 |
+
"eval_gap": 0.9294921875,
|
| 436 |
+
"eval_loss": 0.05072044464094298,
|
| 437 |
+
"eval_neg": 0.04041453770228794,
|
| 438 |
+
"eval_pos": 0.9698381696428572,
|
| 439 |
+
"step": 9216
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.0937972306611911,
|
| 443 |
+
"eval_acc": 0.9840277961322239,
|
| 444 |
+
"eval_gap": 0.9294921875,
|
| 445 |
+
"eval_loss": 0.05072044464094298,
|
| 446 |
+
"eval_neg": 0.04041453770228794,
|
| 447 |
+
"eval_pos": 0.9698381696428572,
|
| 448 |
+
"eval_runtime": 11.5447,
|
| 449 |
+
"eval_samples_per_second": 190.563,
|
| 450 |
+
"eval_steps_per_second": 3.032,
|
| 451 |
+
"step": 9216
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.09640270929066862,
|
| 455 |
+
"grad_norm": 0.12745517492294312,
|
| 456 |
+
"learning_rate": 9.794134046328113e-05,
|
| 457 |
+
"loss": 0.024888301268219948,
|
| 458 |
+
"step": 9472
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.09900818792014615,
|
| 462 |
+
"grad_norm": 0.5470172166824341,
|
| 463 |
+
"learning_rate": 9.782288215515113e-05,
|
| 464 |
+
"loss": 0.02433888427913189,
|
| 465 |
+
"step": 9728
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.10161366654962369,
|
| 469 |
+
"grad_norm": 0.2533114552497864,
|
| 470 |
+
"learning_rate": 9.770118610946487e-05,
|
| 471 |
+
"loss": 0.026410939171910286,
|
| 472 |
+
"step": 9984
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.1042191451791012,
|
| 476 |
+
"grad_norm": 0.16786547005176544,
|
| 477 |
+
"learning_rate": 9.757626056537147e-05,
|
| 478 |
+
"loss": 0.023928755894303322,
|
| 479 |
+
"step": 10240
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.1042191451791012,
|
| 483 |
+
"eval_acc": 0.9864087496485029,
|
| 484 |
+
"eval_gap": 0.9403738839285715,
|
| 485 |
+
"eval_loss": 0.043760570218520506,
|
| 486 |
+
"eval_neg": 0.0355271475655692,
|
| 487 |
+
"eval_pos": 0.9759068080357143,
|
| 488 |
+
"step": 10240
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.1042191451791012,
|
| 492 |
+
"eval_acc": 0.9864087496485029,
|
| 493 |
+
"eval_gap": 0.9403738839285715,
|
| 494 |
+
"eval_loss": 0.043760570218520506,
|
| 495 |
+
"eval_neg": 0.0355271475655692,
|
| 496 |
+
"eval_pos": 0.9759068080357143,
|
| 497 |
+
"eval_runtime": 11.2984,
|
| 498 |
+
"eval_samples_per_second": 194.717,
|
| 499 |
+
"eval_steps_per_second": 3.098,
|
| 500 |
+
"step": 10240
|
| 501 |
+
}
|
| 502 |
+
],
|
| 503 |
+
"logging_steps": 256,
|
| 504 |
+
"max_steps": 98255,
|
| 505 |
+
"num_input_tokens_seen": 0,
|
| 506 |
+
"num_train_epochs": 1,
|
| 507 |
+
"save_steps": 1024,
|
| 508 |
+
"stateful_callbacks": {
|
| 509 |
+
"TrainerControl": {
|
| 510 |
+
"args": {
|
| 511 |
+
"should_epoch_stop": false,
|
| 512 |
+
"should_evaluate": false,
|
| 513 |
+
"should_log": false,
|
| 514 |
+
"should_save": true,
|
| 515 |
+
"should_training_stop": false
|
| 516 |
+
},
|
| 517 |
+
"attributes": {}
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"total_flos": 0.0,
|
| 521 |
+
"train_batch_size": 64,
|
| 522 |
+
"trial_name": null,
|
| 523 |
+
"trial_params": null
|
| 524 |
+
}
|
checkpoints-v1.3/checkpoint-10240/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa5ebeb5ef161964405bdeb26634ed974ccd3ca70a293defa183a0abc5178c7
|
| 3 |
+
size 5137
|