File size: 5,807 Bytes
8702348 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | {
"best_global_step": 268,
"best_metric": 2.9178810119628906,
"best_model_checkpoint": "gpt2-finetuned/checkpoint-268",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 268,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.037383177570093455,
"grad_norm": 4.323858737945557,
"learning_rate": 1.0588235294117648e-05,
"loss": 3.5710372924804688,
"step": 10
},
{
"epoch": 0.07476635514018691,
"grad_norm": 3.9307808876037598,
"learning_rate": 1.9922928709055876e-05,
"loss": 3.3915550231933596,
"step": 20
},
{
"epoch": 0.11214953271028037,
"grad_norm": 3.703219175338745,
"learning_rate": 1.9537572254335264e-05,
"loss": 3.30927734375,
"step": 30
},
{
"epoch": 0.14953271028037382,
"grad_norm": 3.3923251628875732,
"learning_rate": 1.9152215799614644e-05,
"loss": 3.2569236755371094,
"step": 40
},
{
"epoch": 0.18691588785046728,
"grad_norm": 3.6839487552642822,
"learning_rate": 1.8766859344894028e-05,
"loss": 3.2078022003173827,
"step": 50
},
{
"epoch": 0.22429906542056074,
"grad_norm": 3.1598305702209473,
"learning_rate": 1.838150289017341e-05,
"loss": 3.1958980560302734,
"step": 60
},
{
"epoch": 0.2616822429906542,
"grad_norm": 3.5608792304992676,
"learning_rate": 1.7996146435452795e-05,
"loss": 3.1352081298828125,
"step": 70
},
{
"epoch": 0.29906542056074764,
"grad_norm": 3.694288492202759,
"learning_rate": 1.761078998073218e-05,
"loss": 3.1180818557739256,
"step": 80
},
{
"epoch": 0.3364485981308411,
"grad_norm": 3.2345361709594727,
"learning_rate": 1.722543352601156e-05,
"loss": 3.121156692504883,
"step": 90
},
{
"epoch": 0.37383177570093457,
"grad_norm": 2.8083014488220215,
"learning_rate": 1.6840077071290947e-05,
"loss": 3.091750907897949,
"step": 100
},
{
"epoch": 0.411214953271028,
"grad_norm": 3.5092177391052246,
"learning_rate": 1.645472061657033e-05,
"loss": 3.085820198059082,
"step": 110
},
{
"epoch": 0.4485981308411215,
"grad_norm": 3.606647491455078,
"learning_rate": 1.606936416184971e-05,
"loss": 3.103367233276367,
"step": 120
},
{
"epoch": 0.48598130841121495,
"grad_norm": 2.9848923683166504,
"learning_rate": 1.5684007707129095e-05,
"loss": 3.1185840606689452,
"step": 130
},
{
"epoch": 0.5233644859813084,
"grad_norm": 3.9700093269348145,
"learning_rate": 1.529865125240848e-05,
"loss": 3.111907386779785,
"step": 140
},
{
"epoch": 0.5607476635514018,
"grad_norm": 4.307053565979004,
"learning_rate": 1.4913294797687862e-05,
"loss": 3.1015724182128905,
"step": 150
},
{
"epoch": 0.5981308411214953,
"grad_norm": 4.230574607849121,
"learning_rate": 1.4527938342967245e-05,
"loss": 3.1573991775512695,
"step": 160
},
{
"epoch": 0.6355140186915887,
"grad_norm": 3.484198808670044,
"learning_rate": 1.414258188824663e-05,
"loss": 3.09665470123291,
"step": 170
},
{
"epoch": 0.6728971962616822,
"grad_norm": 3.7458720207214355,
"learning_rate": 1.3757225433526014e-05,
"loss": 3.0797067642211915,
"step": 180
},
{
"epoch": 0.7102803738317757,
"grad_norm": 3.599705457687378,
"learning_rate": 1.3371868978805396e-05,
"loss": 3.02014045715332,
"step": 190
},
{
"epoch": 0.7476635514018691,
"grad_norm": 3.341883659362793,
"learning_rate": 1.298651252408478e-05,
"loss": 3.0037511825561523,
"step": 200
},
{
"epoch": 0.7850467289719626,
"grad_norm": 3.6026880741119385,
"learning_rate": 1.2601156069364162e-05,
"loss": 2.995482063293457,
"step": 210
},
{
"epoch": 0.822429906542056,
"grad_norm": 3.875734329223633,
"learning_rate": 1.2215799614643546e-05,
"loss": 3.0261470794677736,
"step": 220
},
{
"epoch": 0.8598130841121495,
"grad_norm": 3.5683584213256836,
"learning_rate": 1.1830443159922928e-05,
"loss": 2.9946710586547853,
"step": 230
},
{
"epoch": 0.897196261682243,
"grad_norm": 4.219651699066162,
"learning_rate": 1.1445086705202313e-05,
"loss": 3.067545509338379,
"step": 240
},
{
"epoch": 0.9345794392523364,
"grad_norm": 3.2647459506988525,
"learning_rate": 1.1059730250481697e-05,
"loss": 3.047348976135254,
"step": 250
},
{
"epoch": 0.9719626168224299,
"grad_norm": 3.6350138187408447,
"learning_rate": 1.067437379576108e-05,
"loss": 3.044650077819824,
"step": 260
},
{
"epoch": 1.0,
"eval_loss": 2.9178810119628906,
"eval_runtime": 22.6583,
"eval_samples_per_second": 41.927,
"eval_steps_per_second": 20.964,
"step": 268
}
],
"logging_steps": 10,
"max_steps": 536,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 54,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2929569518592000.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|