Upload folder using huggingface_hub
Browse files- config.json +2 -2
- generation_config.json +5 -0
- model.safetensors +2 -2
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +567 -0
- training_args.bin +3 -0
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/home/muhammad.dehan/repository/TokenAlignmentMulti/models/dehanalkautsar/mbert-uncased-modified_embedding_table-multi/checkpoint-
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/muhammad.dehan/repository/TokenAlignmentMulti/models/dehanalkautsar/mbert-uncased-modified_embedding_table-multi/checkpoint-50000",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.47.0"
|
| 5 |
+
}
|
model.safetensors
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 sha256:5a240081e1e5f7ee906d256364e1c6106dc22355716db2f42bb34660749de573
|
| 3 |
+
size 438080896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28add08709a868e7e761d3ac78678fea290eee74ca220b73be678bff6bb91072
|
| 3 |
+
size 876283258
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c78868645b2d464b5e0c4615c3de3a6a7744e3718bf6737eeb1abc88e2db6e45
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81671fd2bf6583821910fae7c5bca0d1a22c2892397397b7354aebc3edac33f7
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.735720157623291,
|
| 3 |
+
"best_model_checkpoint": "models/dehanalkautsar/mbert-uncased-modified_embedding_table-multi/checkpoint-62000",
|
| 4 |
+
"epoch": 44.606610911987254,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 70000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.273994424532059,
|
| 13 |
+
"grad_norm": 14.472808837890625,
|
| 14 |
+
"learning_rate": 4.840662842574888e-05,
|
| 15 |
+
"loss": 6.7847,
|
| 16 |
+
"step": 2000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.273994424532059,
|
| 20 |
+
"eval_loss": 6.310997486114502,
|
| 21 |
+
"eval_runtime": 1.0444,
|
| 22 |
+
"eval_samples_per_second": 134.046,
|
| 23 |
+
"eval_steps_per_second": 2.872,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.547988849064118,
|
| 28 |
+
"grad_norm": 13.92039966583252,
|
| 29 |
+
"learning_rate": 4.6813256851497774e-05,
|
| 30 |
+
"loss": 5.2141,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.547988849064118,
|
| 35 |
+
"eval_loss": 4.0085954666137695,
|
| 36 |
+
"eval_runtime": 1.0423,
|
| 37 |
+
"eval_samples_per_second": 134.315,
|
| 38 |
+
"eval_steps_per_second": 2.878,
|
| 39 |
+
"step": 4000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.8219832735961767,
|
| 43 |
+
"grad_norm": 12.217097282409668,
|
| 44 |
+
"learning_rate": 4.521988527724665e-05,
|
| 45 |
+
"loss": 3.6444,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.8219832735961767,
|
| 50 |
+
"eval_loss": 3.3225996494293213,
|
| 51 |
+
"eval_runtime": 1.0422,
|
| 52 |
+
"eval_samples_per_second": 134.329,
|
| 53 |
+
"eval_steps_per_second": 2.878,
|
| 54 |
+
"step": 6000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 5.09557945041816,
|
| 58 |
+
"grad_norm": 13.112276077270508,
|
| 59 |
+
"learning_rate": 4.362651370299554e-05,
|
| 60 |
+
"loss": 3.185,
|
| 61 |
+
"step": 8000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.09557945041816,
|
| 65 |
+
"eval_loss": 2.9885096549987793,
|
| 66 |
+
"eval_runtime": 1.0432,
|
| 67 |
+
"eval_samples_per_second": 134.208,
|
| 68 |
+
"eval_steps_per_second": 2.876,
|
| 69 |
+
"step": 8000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 6.369573874950219,
|
| 73 |
+
"grad_norm": 9.95456314086914,
|
| 74 |
+
"learning_rate": 4.2033142128744425e-05,
|
| 75 |
+
"loss": 2.9191,
|
| 76 |
+
"step": 10000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 6.369573874950219,
|
| 80 |
+
"eval_loss": 2.759176254272461,
|
| 81 |
+
"eval_runtime": 1.0435,
|
| 82 |
+
"eval_samples_per_second": 134.158,
|
| 83 |
+
"eval_steps_per_second": 2.875,
|
| 84 |
+
"step": 10000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 7.643568299482278,
|
| 88 |
+
"grad_norm": 10.692479133605957,
|
| 89 |
+
"learning_rate": 4.043977055449331e-05,
|
| 90 |
+
"loss": 2.7335,
|
| 91 |
+
"step": 12000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 7.643568299482278,
|
| 95 |
+
"eval_loss": 2.601854085922241,
|
| 96 |
+
"eval_runtime": 1.7999,
|
| 97 |
+
"eval_samples_per_second": 77.783,
|
| 98 |
+
"eval_steps_per_second": 1.667,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 8.917562724014337,
|
| 103 |
+
"grad_norm": 10.000415802001953,
|
| 104 |
+
"learning_rate": 3.8846398980242196e-05,
|
| 105 |
+
"loss": 2.6016,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.917562724014337,
|
| 110 |
+
"eval_loss": 2.4759533405303955,
|
| 111 |
+
"eval_runtime": 2.1495,
|
| 112 |
+
"eval_samples_per_second": 65.131,
|
| 113 |
+
"eval_steps_per_second": 1.396,
|
| 114 |
+
"step": 14000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 10.19115890083632,
|
| 118 |
+
"grad_norm": 9.746127128601074,
|
| 119 |
+
"learning_rate": 3.725302740599108e-05,
|
| 120 |
+
"loss": 2.4983,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 10.19115890083632,
|
| 125 |
+
"eval_loss": 2.3779261112213135,
|
| 126 |
+
"eval_runtime": 2.1857,
|
| 127 |
+
"eval_samples_per_second": 64.052,
|
| 128 |
+
"eval_steps_per_second": 1.373,
|
| 129 |
+
"step": 16000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 11.465153325368378,
|
| 133 |
+
"grad_norm": 26.588117599487305,
|
| 134 |
+
"learning_rate": 3.565965583173996e-05,
|
| 135 |
+
"loss": 2.4195,
|
| 136 |
+
"step": 18000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 11.465153325368378,
|
| 140 |
+
"eval_loss": 2.34489369392395,
|
| 141 |
+
"eval_runtime": 1.0425,
|
| 142 |
+
"eval_samples_per_second": 134.292,
|
| 143 |
+
"eval_steps_per_second": 2.878,
|
| 144 |
+
"step": 18000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.739147749900438,
|
| 148 |
+
"grad_norm": 10.147093772888184,
|
| 149 |
+
"learning_rate": 3.4066284257488853e-05,
|
| 150 |
+
"loss": 2.355,
|
| 151 |
+
"step": 20000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 12.739147749900438,
|
| 155 |
+
"eval_loss": 2.2396912574768066,
|
| 156 |
+
"eval_runtime": 1.0419,
|
| 157 |
+
"eval_samples_per_second": 134.367,
|
| 158 |
+
"eval_steps_per_second": 2.879,
|
| 159 |
+
"step": 20000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 14.012743926722422,
|
| 163 |
+
"grad_norm": 9.359902381896973,
|
| 164 |
+
"learning_rate": 3.247291268323773e-05,
|
| 165 |
+
"loss": 2.3011,
|
| 166 |
+
"step": 22000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 14.012743926722422,
|
| 170 |
+
"eval_loss": 2.2220568656921387,
|
| 171 |
+
"eval_runtime": 1.0421,
|
| 172 |
+
"eval_samples_per_second": 134.349,
|
| 173 |
+
"eval_steps_per_second": 2.879,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 15.296296296296296,
|
| 178 |
+
"grad_norm": 9.719951629638672,
|
| 179 |
+
"learning_rate": 4.550106849623215e-05,
|
| 180 |
+
"loss": 2.2641,
|
| 181 |
+
"step": 24000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 15.296296296296296,
|
| 185 |
+
"eval_loss": 2.1969993114471436,
|
| 186 |
+
"eval_runtime": 1.0459,
|
| 187 |
+
"eval_samples_per_second": 133.856,
|
| 188 |
+
"eval_steps_per_second": 2.868,
|
| 189 |
+
"step": 24000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 16.570290720828353,
|
| 193 |
+
"grad_norm": 10.155664443969727,
|
| 194 |
+
"learning_rate": 4.5126157537584826e-05,
|
| 195 |
+
"loss": 2.2145,
|
| 196 |
+
"step": 26000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 16.570290720828353,
|
| 200 |
+
"eval_loss": 2.1572253704071045,
|
| 201 |
+
"eval_runtime": 1.0453,
|
| 202 |
+
"eval_samples_per_second": 133.93,
|
| 203 |
+
"eval_steps_per_second": 2.87,
|
| 204 |
+
"step": 26000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 17.844285145360413,
|
| 208 |
+
"grad_norm": 9.276083946228027,
|
| 209 |
+
"learning_rate": 4.4751246578937504e-05,
|
| 210 |
+
"loss": 2.1687,
|
| 211 |
+
"step": 28000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 17.844285145360413,
|
| 215 |
+
"eval_loss": 2.1415774822235107,
|
| 216 |
+
"eval_runtime": 1.0448,
|
| 217 |
+
"eval_samples_per_second": 134.002,
|
| 218 |
+
"eval_steps_per_second": 2.871,
|
| 219 |
+
"step": 28000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 19.1178813221824,
|
| 223 |
+
"grad_norm": 9.626545906066895,
|
| 224 |
+
"learning_rate": 4.437633562029018e-05,
|
| 225 |
+
"loss": 2.1288,
|
| 226 |
+
"step": 30000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 19.1178813221824,
|
| 230 |
+
"eval_loss": 2.0869765281677246,
|
| 231 |
+
"eval_runtime": 1.0442,
|
| 232 |
+
"eval_samples_per_second": 134.079,
|
| 233 |
+
"eval_steps_per_second": 2.873,
|
| 234 |
+
"step": 30000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 20.391875746714458,
|
| 238 |
+
"grad_norm": 9.785582542419434,
|
| 239 |
+
"learning_rate": 4.400142466164286e-05,
|
| 240 |
+
"loss": 2.0936,
|
| 241 |
+
"step": 32000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 20.391875746714458,
|
| 245 |
+
"eval_loss": 2.0372226238250732,
|
| 246 |
+
"eval_runtime": 1.0457,
|
| 247 |
+
"eval_samples_per_second": 133.886,
|
| 248 |
+
"eval_steps_per_second": 2.869,
|
| 249 |
+
"step": 32000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 21.665870171246514,
|
| 253 |
+
"grad_norm": 10.339402198791504,
|
| 254 |
+
"learning_rate": 4.362651370299554e-05,
|
| 255 |
+
"loss": 2.0629,
|
| 256 |
+
"step": 34000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 21.665870171246514,
|
| 260 |
+
"eval_loss": 2.0290327072143555,
|
| 261 |
+
"eval_runtime": 1.0449,
|
| 262 |
+
"eval_samples_per_second": 133.981,
|
| 263 |
+
"eval_steps_per_second": 2.871,
|
| 264 |
+
"step": 34000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 22.939864595778573,
|
| 268 |
+
"grad_norm": 33.6297492980957,
|
| 269 |
+
"learning_rate": 4.325160274434822e-05,
|
| 270 |
+
"loss": 2.0352,
|
| 271 |
+
"step": 36000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 22.939864595778573,
|
| 275 |
+
"eval_loss": 1.9997824430465698,
|
| 276 |
+
"eval_runtime": 1.0457,
|
| 277 |
+
"eval_samples_per_second": 133.884,
|
| 278 |
+
"eval_steps_per_second": 2.869,
|
| 279 |
+
"step": 36000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 24.21346077260056,
|
| 283 |
+
"grad_norm": 9.419952392578125,
|
| 284 |
+
"learning_rate": 4.2876691785700895e-05,
|
| 285 |
+
"loss": 2.0085,
|
| 286 |
+
"step": 38000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 24.21346077260056,
|
| 290 |
+
"eval_loss": 1.9848532676696777,
|
| 291 |
+
"eval_runtime": 1.0456,
|
| 292 |
+
"eval_samples_per_second": 133.889,
|
| 293 |
+
"eval_steps_per_second": 2.869,
|
| 294 |
+
"step": 38000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 25.487455197132615,
|
| 298 |
+
"grad_norm": 9.297412872314453,
|
| 299 |
+
"learning_rate": 4.250178082705358e-05,
|
| 300 |
+
"loss": 1.9835,
|
| 301 |
+
"step": 40000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 25.487455197132615,
|
| 305 |
+
"eval_loss": 1.9594355821609497,
|
| 306 |
+
"eval_runtime": 1.0451,
|
| 307 |
+
"eval_samples_per_second": 133.962,
|
| 308 |
+
"eval_steps_per_second": 2.871,
|
| 309 |
+
"step": 40000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 26.761449621664674,
|
| 313 |
+
"grad_norm": 9.560755729675293,
|
| 314 |
+
"learning_rate": 4.212686986840625e-05,
|
| 315 |
+
"loss": 1.9622,
|
| 316 |
+
"step": 42000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 26.761449621664674,
|
| 320 |
+
"eval_loss": 1.9543912410736084,
|
| 321 |
+
"eval_runtime": 1.0446,
|
| 322 |
+
"eval_samples_per_second": 134.027,
|
| 323 |
+
"eval_steps_per_second": 2.872,
|
| 324 |
+
"step": 42000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 28.03504579848666,
|
| 328 |
+
"grad_norm": 9.696600914001465,
|
| 329 |
+
"learning_rate": 4.1751958909758937e-05,
|
| 330 |
+
"loss": 1.9423,
|
| 331 |
+
"step": 44000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 28.03504579848666,
|
| 335 |
+
"eval_loss": 1.9044808149337769,
|
| 336 |
+
"eval_runtime": 1.0452,
|
| 337 |
+
"eval_samples_per_second": 133.942,
|
| 338 |
+
"eval_steps_per_second": 2.87,
|
| 339 |
+
"step": 44000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 29.309040223018716,
|
| 343 |
+
"grad_norm": 9.66083812713623,
|
| 344 |
+
"learning_rate": 4.1377047951111615e-05,
|
| 345 |
+
"loss": 1.9237,
|
| 346 |
+
"step": 46000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 29.309040223018716,
|
| 350 |
+
"eval_loss": 1.872032642364502,
|
| 351 |
+
"eval_runtime": 1.0448,
|
| 352 |
+
"eval_samples_per_second": 134.0,
|
| 353 |
+
"eval_steps_per_second": 2.871,
|
| 354 |
+
"step": 46000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 30.583034647550775,
|
| 358 |
+
"grad_norm": 8.918251991271973,
|
| 359 |
+
"learning_rate": 4.100213699246429e-05,
|
| 360 |
+
"loss": 1.905,
|
| 361 |
+
"step": 48000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 30.583034647550775,
|
| 365 |
+
"eval_loss": 1.857001781463623,
|
| 366 |
+
"eval_runtime": 1.0437,
|
| 367 |
+
"eval_samples_per_second": 134.137,
|
| 368 |
+
"eval_steps_per_second": 2.874,
|
| 369 |
+
"step": 48000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 31.857029072082835,
|
| 373 |
+
"grad_norm": 9.568062782287598,
|
| 374 |
+
"learning_rate": 4.062722603381697e-05,
|
| 375 |
+
"loss": 1.8905,
|
| 376 |
+
"step": 50000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 31.857029072082835,
|
| 380 |
+
"eval_loss": 1.8617095947265625,
|
| 381 |
+
"eval_runtime": 1.0446,
|
| 382 |
+
"eval_samples_per_second": 134.024,
|
| 383 |
+
"eval_steps_per_second": 2.872,
|
| 384 |
+
"step": 50000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 33.14145758661888,
|
| 388 |
+
"grad_norm": 9.223485946655273,
|
| 389 |
+
"learning_rate": 4.025231507516965e-05,
|
| 390 |
+
"loss": 1.8744,
|
| 391 |
+
"step": 52000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 33.14145758661888,
|
| 395 |
+
"eval_loss": 1.8508821725845337,
|
| 396 |
+
"eval_runtime": 1.0449,
|
| 397 |
+
"eval_samples_per_second": 133.978,
|
| 398 |
+
"eval_steps_per_second": 2.871,
|
| 399 |
+
"step": 52000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 34.41545201115093,
|
| 403 |
+
"grad_norm": 9.19514274597168,
|
| 404 |
+
"learning_rate": 3.987740411652233e-05,
|
| 405 |
+
"loss": 1.8594,
|
| 406 |
+
"step": 54000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 34.41545201115093,
|
| 410 |
+
"eval_loss": 1.807867169380188,
|
| 411 |
+
"eval_runtime": 1.0427,
|
| 412 |
+
"eval_samples_per_second": 134.272,
|
| 413 |
+
"eval_steps_per_second": 2.877,
|
| 414 |
+
"step": 54000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 35.689446435682996,
|
| 418 |
+
"grad_norm": 9.288874626159668,
|
| 419 |
+
"learning_rate": 3.9502493157875006e-05,
|
| 420 |
+
"loss": 1.845,
|
| 421 |
+
"step": 56000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 35.689446435682996,
|
| 425 |
+
"eval_loss": 1.8352290391921997,
|
| 426 |
+
"eval_runtime": 1.0447,
|
| 427 |
+
"eval_samples_per_second": 134.011,
|
| 428 |
+
"eval_steps_per_second": 2.872,
|
| 429 |
+
"step": 56000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 36.96344086021505,
|
| 433 |
+
"grad_norm": 8.9916353225708,
|
| 434 |
+
"learning_rate": 3.9127582199227684e-05,
|
| 435 |
+
"loss": 1.8325,
|
| 436 |
+
"step": 58000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 36.96344086021505,
|
| 440 |
+
"eval_loss": 1.8519763946533203,
|
| 441 |
+
"eval_runtime": 1.0422,
|
| 442 |
+
"eval_samples_per_second": 134.334,
|
| 443 |
+
"eval_steps_per_second": 2.879,
|
| 444 |
+
"step": 58000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 38.237037037037034,
|
| 448 |
+
"grad_norm": 9.245351791381836,
|
| 449 |
+
"learning_rate": 3.875267124058036e-05,
|
| 450 |
+
"loss": 1.8204,
|
| 451 |
+
"step": 60000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 38.237037037037034,
|
| 455 |
+
"eval_loss": 1.792788028717041,
|
| 456 |
+
"eval_runtime": 1.0429,
|
| 457 |
+
"eval_samples_per_second": 134.237,
|
| 458 |
+
"eval_steps_per_second": 2.877,
|
| 459 |
+
"step": 60000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 39.5110314615691,
|
| 463 |
+
"grad_norm": 9.415380477905273,
|
| 464 |
+
"learning_rate": 3.837776028193305e-05,
|
| 465 |
+
"loss": 1.808,
|
| 466 |
+
"step": 62000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 39.5110314615691,
|
| 470 |
+
"eval_loss": 1.735720157623291,
|
| 471 |
+
"eval_runtime": 1.0435,
|
| 472 |
+
"eval_samples_per_second": 134.164,
|
| 473 |
+
"eval_steps_per_second": 2.875,
|
| 474 |
+
"step": 62000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 40.78502588610115,
|
| 478 |
+
"grad_norm": 9.212890625,
|
| 479 |
+
"learning_rate": 3.800284932328572e-05,
|
| 480 |
+
"loss": 1.7973,
|
| 481 |
+
"step": 64000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 40.78502588610115,
|
| 485 |
+
"eval_loss": 1.7825311422348022,
|
| 486 |
+
"eval_runtime": 1.0432,
|
| 487 |
+
"eval_samples_per_second": 134.204,
|
| 488 |
+
"eval_steps_per_second": 2.876,
|
| 489 |
+
"step": 64000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 42.058622062923135,
|
| 493 |
+
"grad_norm": 12.76929759979248,
|
| 494 |
+
"learning_rate": 3.76279383646384e-05,
|
| 495 |
+
"loss": 1.7868,
|
| 496 |
+
"step": 66000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 42.058622062923135,
|
| 500 |
+
"eval_loss": 1.8231488466262817,
|
| 501 |
+
"eval_runtime": 1.0438,
|
| 502 |
+
"eval_samples_per_second": 134.121,
|
| 503 |
+
"eval_steps_per_second": 2.874,
|
| 504 |
+
"step": 66000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 43.3326164874552,
|
| 508 |
+
"grad_norm": 9.313870429992676,
|
| 509 |
+
"learning_rate": 3.725302740599108e-05,
|
| 510 |
+
"loss": 1.776,
|
| 511 |
+
"step": 68000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 43.3326164874552,
|
| 515 |
+
"eval_loss": 1.7821528911590576,
|
| 516 |
+
"eval_runtime": 1.0442,
|
| 517 |
+
"eval_samples_per_second": 134.071,
|
| 518 |
+
"eval_steps_per_second": 2.873,
|
| 519 |
+
"step": 68000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 44.606610911987254,
|
| 523 |
+
"grad_norm": 9.745814323425293,
|
| 524 |
+
"learning_rate": 3.687811644734376e-05,
|
| 525 |
+
"loss": 1.7671,
|
| 526 |
+
"step": 70000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 44.606610911987254,
|
| 530 |
+
"eval_loss": 1.7638314962387085,
|
| 531 |
+
"eval_runtime": 1.0433,
|
| 532 |
+
"eval_samples_per_second": 134.193,
|
| 533 |
+
"eval_steps_per_second": 2.876,
|
| 534 |
+
"step": 70000
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"logging_steps": 2000,
|
| 538 |
+
"max_steps": 266730,
|
| 539 |
+
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 170,
|
| 541 |
+
"save_steps": 2000,
|
| 542 |
+
"stateful_callbacks": {
|
| 543 |
+
"EarlyStoppingCallback": {
|
| 544 |
+
"args": {
|
| 545 |
+
"early_stopping_patience": 5,
|
| 546 |
+
"early_stopping_threshold": 0.0
|
| 547 |
+
},
|
| 548 |
+
"attributes": {
|
| 549 |
+
"early_stopping_patience_counter": 0
|
| 550 |
+
}
|
| 551 |
+
},
|
| 552 |
+
"TrainerControl": {
|
| 553 |
+
"args": {
|
| 554 |
+
"should_epoch_stop": false,
|
| 555 |
+
"should_evaluate": false,
|
| 556 |
+
"should_log": false,
|
| 557 |
+
"should_save": true,
|
| 558 |
+
"should_training_stop": false
|
| 559 |
+
},
|
| 560 |
+
"attributes": {}
|
| 561 |
+
}
|
| 562 |
+
},
|
| 563 |
+
"total_flos": 4.714819396263936e+18,
|
| 564 |
+
"train_batch_size": 32,
|
| 565 |
+
"trial_name": null,
|
| 566 |
+
"trial_params": null
|
| 567 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0859029f81c2b65a69c216a2fdb4537ab79bccb40900dfe4c7ade46b45c9739f
|
| 3 |
+
size 5304
|