Upload folder using huggingface_hub
Browse files- checkpoint-500/config.json +16 -0
- checkpoint-500/generation_config.json +6 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scaler.pt +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +384 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastHyperNet125mForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"hyperbolic_dim": 64,
|
| 8 |
+
"intermediate_size": 2048,
|
| 9 |
+
"max_position_embeddings": 512,
|
| 10 |
+
"model_type": "fasthypernet_125m_tagless",
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_hidden_layers": 16,
|
| 13 |
+
"transformers_version": "5.13.1",
|
| 14 |
+
"use_cache": false,
|
| 15 |
+
"vocab_size": 8192
|
| 16 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.13.1"
|
| 6 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2eb6f3be4bbc8e435a259879b5470da19b87ccfcc5faa89a5408853a407e2cc
|
| 3 |
+
size 542849784
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bc5275c7e2c5f839cc89f07d4f102a8a4cec1986339677293dd251d8c67310
|
| 3 |
+
size 273342083
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06ea9188bf0c16981a03ed7c517a7c6919332f32448d74940ddafde5c0f34e6
|
| 3 |
+
size 14645
|
checkpoint-500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2912dcd56eb5e2293ca9b49c46dec30cb8788c406c513e45709854caa8c9d6e3
|
| 3 |
+
size 1383
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b92e317fe4f50b77e75285881827d2b3fbb58049a190e528fc87fb721bf320d1
|
| 3 |
+
size 1465
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.017340338830220743,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00034680677660441485,
|
| 14 |
+
"grad_norm": 8.286304473876953,
|
| 15 |
+
"learning_rate": 2.6999999999999996e-06,
|
| 16 |
+
"loss": 36.023321533203124,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0006936135532088297,
|
| 21 |
+
"grad_norm": 5.303624153137207,
|
| 22 |
+
"learning_rate": 5.7e-06,
|
| 23 |
+
"loss": 35.81325988769531,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0010404203298132447,
|
| 28 |
+
"grad_norm": 14.0803861618042,
|
| 29 |
+
"learning_rate": 8.7e-06,
|
| 30 |
+
"loss": 35.61415100097656,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0013872271064176594,
|
| 35 |
+
"grad_norm": 42.10546875,
|
| 36 |
+
"learning_rate": 1.17e-05,
|
| 37 |
+
"loss": 35.36910400390625,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0017340338830220744,
|
| 42 |
+
"grad_norm": 43.37276840209961,
|
| 43 |
+
"learning_rate": 1.47e-05,
|
| 44 |
+
"loss": 34.86077880859375,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0020808406596264893,
|
| 49 |
+
"grad_norm": Infinity,
|
| 50 |
+
"learning_rate": 1.7699999999999997e-05,
|
| 51 |
+
"loss": 34.67452697753906,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.002427647436230904,
|
| 56 |
+
"grad_norm": 86.09446716308594,
|
| 57 |
+
"learning_rate": 2.04e-05,
|
| 58 |
+
"loss": 34.29078979492188,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.002774454212835319,
|
| 63 |
+
"grad_norm": 43.50123977661133,
|
| 64 |
+
"learning_rate": 2.34e-05,
|
| 65 |
+
"loss": 33.816766357421876,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0031212609894397335,
|
| 70 |
+
"grad_norm": 104.7258529663086,
|
| 71 |
+
"learning_rate": 2.6399999999999995e-05,
|
| 72 |
+
"loss": 33.36159057617188,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0034680677660441487,
|
| 77 |
+
"grad_norm": 66.46515655517578,
|
| 78 |
+
"learning_rate": 2.91e-05,
|
| 79 |
+
"loss": 33.181732177734375,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0038148745426485635,
|
| 84 |
+
"grad_norm": 127.66901397705078,
|
| 85 |
+
"learning_rate": 3.2099999999999994e-05,
|
| 86 |
+
"loss": 32.83320007324219,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.004161681319252979,
|
| 91 |
+
"grad_norm": 71.67156982421875,
|
| 92 |
+
"learning_rate": 3.51e-05,
|
| 93 |
+
"loss": 32.48929138183594,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.004508488095857393,
|
| 98 |
+
"grad_norm": 76.15655517578125,
|
| 99 |
+
"learning_rate": 3.81e-05,
|
| 100 |
+
"loss": 32.10602722167969,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.004855294872461808,
|
| 105 |
+
"grad_norm": 38.65349578857422,
|
| 106 |
+
"learning_rate": 4.11e-05,
|
| 107 |
+
"loss": 31.449526977539062,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.005202101649066222,
|
| 112 |
+
"grad_norm": 59.55622863769531,
|
| 113 |
+
"learning_rate": 4.4099999999999995e-05,
|
| 114 |
+
"loss": 31.01339111328125,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.005548908425670638,
|
| 119 |
+
"grad_norm": 130.26136779785156,
|
| 120 |
+
"learning_rate": 4.709999999999999e-05,
|
| 121 |
+
"loss": 30.92586669921875,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.005895715202275053,
|
| 126 |
+
"grad_norm": 77.2778549194336,
|
| 127 |
+
"learning_rate": 5.01e-05,
|
| 128 |
+
"loss": 30.492510986328124,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.006242521978879467,
|
| 133 |
+
"grad_norm": 29.711563110351562,
|
| 134 |
+
"learning_rate": 5.309999999999999e-05,
|
| 135 |
+
"loss": 29.836746215820312,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.006589328755483882,
|
| 140 |
+
"grad_norm": 29.891956329345703,
|
| 141 |
+
"learning_rate": 5.6099999999999995e-05,
|
| 142 |
+
"loss": 29.291275024414062,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.006936135532088297,
|
| 147 |
+
"grad_norm": 30.56305503845215,
|
| 148 |
+
"learning_rate": 5.91e-05,
|
| 149 |
+
"loss": 29.14805908203125,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.007282942308692712,
|
| 154 |
+
"grad_norm": 29.489208221435547,
|
| 155 |
+
"learning_rate": 6.209999999999999e-05,
|
| 156 |
+
"loss": 28.80553283691406,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.007629749085297127,
|
| 161 |
+
"grad_norm": 37.147377014160156,
|
| 162 |
+
"learning_rate": 6.51e-05,
|
| 163 |
+
"loss": 28.694085693359376,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.007976555861901541,
|
| 168 |
+
"grad_norm": 28.496992111206055,
|
| 169 |
+
"learning_rate": 6.81e-05,
|
| 170 |
+
"loss": 28.166943359375,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.008323362638505957,
|
| 175 |
+
"grad_norm": 29.42328453063965,
|
| 176 |
+
"learning_rate": 7.11e-05,
|
| 177 |
+
"loss": 27.878482055664062,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.008670169415110372,
|
| 182 |
+
"grad_norm": 27.867637634277344,
|
| 183 |
+
"learning_rate": 7.41e-05,
|
| 184 |
+
"loss": 26.99749755859375,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.009016976191714786,
|
| 189 |
+
"grad_norm": 29.695758819580078,
|
| 190 |
+
"learning_rate": 7.709999999999999e-05,
|
| 191 |
+
"loss": 27.208102416992187,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0093637829683192,
|
| 196 |
+
"grad_norm": 34.605934143066406,
|
| 197 |
+
"learning_rate": 8.01e-05,
|
| 198 |
+
"loss": 26.798681640625,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.009710589744923616,
|
| 203 |
+
"grad_norm": 35.05394744873047,
|
| 204 |
+
"learning_rate": 8.31e-05,
|
| 205 |
+
"loss": 27.192486572265626,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.01005739652152803,
|
| 210 |
+
"grad_norm": 19.137067794799805,
|
| 211 |
+
"learning_rate": 8.609999999999999e-05,
|
| 212 |
+
"loss": 26.89140930175781,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.010404203298132445,
|
| 217 |
+
"grad_norm": 24.543006896972656,
|
| 218 |
+
"learning_rate": 8.879999999999999e-05,
|
| 219 |
+
"loss": 26.167477416992188,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.010751010074736861,
|
| 224 |
+
"grad_norm": 18.849651336669922,
|
| 225 |
+
"learning_rate": 9.18e-05,
|
| 226 |
+
"loss": 26.41388854980469,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.011097816851341275,
|
| 231 |
+
"grad_norm": 21.179908752441406,
|
| 232 |
+
"learning_rate": 9.479999999999999e-05,
|
| 233 |
+
"loss": 26.003546142578124,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.01144462362794569,
|
| 238 |
+
"grad_norm": 19.344528198242188,
|
| 239 |
+
"learning_rate": 9.779999999999999e-05,
|
| 240 |
+
"loss": 26.271051025390626,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.011791430404550106,
|
| 245 |
+
"grad_norm": 19.74913215637207,
|
| 246 |
+
"learning_rate": 0.0001008,
|
| 247 |
+
"loss": 26.064590454101562,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.01213823718115452,
|
| 252 |
+
"grad_norm": 17.638103485107422,
|
| 253 |
+
"learning_rate": 0.00010379999999999999,
|
| 254 |
+
"loss": 25.863119506835936,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.012485043957758934,
|
| 259 |
+
"grad_norm": 24.873981475830078,
|
| 260 |
+
"learning_rate": 0.00010679999999999998,
|
| 261 |
+
"loss": 26.28948059082031,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.01283185073436335,
|
| 266 |
+
"grad_norm": 17.048828125,
|
| 267 |
+
"learning_rate": 0.00010979999999999999,
|
| 268 |
+
"loss": 26.215179443359375,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.013178657510967764,
|
| 273 |
+
"grad_norm": 21.703975677490234,
|
| 274 |
+
"learning_rate": 0.00011279999999999999,
|
| 275 |
+
"loss": 26.152392578125,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.013525464287572179,
|
| 280 |
+
"grad_norm": 22.66498565673828,
|
| 281 |
+
"learning_rate": 0.0001158,
|
| 282 |
+
"loss": 26.0640625,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.013872271064176595,
|
| 287 |
+
"grad_norm": 16.945016860961914,
|
| 288 |
+
"learning_rate": 0.0001188,
|
| 289 |
+
"loss": 26.023715209960937,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.01421907784078101,
|
| 294 |
+
"grad_norm": 27.866268157958984,
|
| 295 |
+
"learning_rate": 0.00012179999999999999,
|
| 296 |
+
"loss": 25.43433380126953,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.014565884617385423,
|
| 301 |
+
"grad_norm": 22.481279373168945,
|
| 302 |
+
"learning_rate": 0.00012479999999999997,
|
| 303 |
+
"loss": 25.464639282226564,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.014912691393989838,
|
| 308 |
+
"grad_norm": 14.993969917297363,
|
| 309 |
+
"learning_rate": 0.0001278,
|
| 310 |
+
"loss": 25.218385314941408,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.015259498170594254,
|
| 315 |
+
"grad_norm": 14.426427841186523,
|
| 316 |
+
"learning_rate": 0.00013079999999999998,
|
| 317 |
+
"loss": 24.94810333251953,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.015606304947198668,
|
| 322 |
+
"grad_norm": 15.592818260192871,
|
| 323 |
+
"learning_rate": 0.0001338,
|
| 324 |
+
"loss": 25.38585662841797,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.015953111723803082,
|
| 329 |
+
"grad_norm": 14.709174156188965,
|
| 330 |
+
"learning_rate": 0.0001368,
|
| 331 |
+
"loss": 24.31098175048828,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.016299918500407497,
|
| 336 |
+
"grad_norm": 13.651994705200195,
|
| 337 |
+
"learning_rate": 0.00013979999999999998,
|
| 338 |
+
"loss": 24.82652893066406,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.016646725277011915,
|
| 343 |
+
"grad_norm": 17.521072387695312,
|
| 344 |
+
"learning_rate": 0.00014279999999999997,
|
| 345 |
+
"loss": 25.121923828125,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.01699353205361633,
|
| 350 |
+
"grad_norm": 13.458234786987305,
|
| 351 |
+
"learning_rate": 0.0001458,
|
| 352 |
+
"loss": 24.447775268554686,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.017340338830220743,
|
| 357 |
+
"grad_norm": 13.57589340209961,
|
| 358 |
+
"learning_rate": 0.00014879999999999998,
|
| 359 |
+
"loss": 24.76665802001953,
|
| 360 |
+
"step": 500
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"logging_steps": 10,
|
| 364 |
+
"max_steps": 100000,
|
| 365 |
+
"num_input_tokens_seen": 0,
|
| 366 |
+
"num_train_epochs": 4,
|
| 367 |
+
"save_steps": 100,
|
| 368 |
+
"stateful_callbacks": {
|
| 369 |
+
"TrainerControl": {
|
| 370 |
+
"args": {
|
| 371 |
+
"should_epoch_stop": false,
|
| 372 |
+
"should_evaluate": false,
|
| 373 |
+
"should_log": false,
|
| 374 |
+
"should_save": true,
|
| 375 |
+
"should_training_stop": false
|
| 376 |
+
},
|
| 377 |
+
"attributes": {}
|
| 378 |
+
}
|
| 379 |
+
},
|
| 380 |
+
"total_flos": 3109956747264000.0,
|
| 381 |
+
"train_batch_size": 4,
|
| 382 |
+
"trial_name": null,
|
| 383 |
+
"trial_params": null
|
| 384 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbd241599217f087cf90c5afde8d5857bb2c3234f97a197910829d91c3d8c1f7
|
| 3 |
+
size 5137
|