| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03773050983351413, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018865254916757064, | |
| "eval_loss": 10.55636215209961, | |
| "eval_runtime": 16.929, | |
| "eval_samples_per_second": 131.845, | |
| "eval_steps_per_second": 65.922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009432627458378531, | |
| "grad_norm": 0.5172281861305237, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5517, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018865254916757062, | |
| "grad_norm": 0.5462555289268494, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028297882375135593, | |
| "grad_norm": 0.882411539554596, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 10.5115, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0037730509833514125, | |
| "grad_norm": 1.194800853729248, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 10.4611, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004716313729189266, | |
| "grad_norm": 1.6541850566864014, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 10.3586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005659576475027119, | |
| "grad_norm": 1.7374366521835327, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 10.1604, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006602839220864972, | |
| "grad_norm": 2.3538756370544434, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 9.9388, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007546101966702825, | |
| "grad_norm": 2.1705451011657715, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 9.7997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008489364712540678, | |
| "grad_norm": 2.5297393798828125, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 9.9183, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009432627458378532, | |
| "grad_norm": 3.2198193073272705, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 9.9767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009432627458378532, | |
| "eval_loss": 9.477534294128418, | |
| "eval_runtime": 16.3657, | |
| "eval_samples_per_second": 136.383, | |
| "eval_steps_per_second": 68.191, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010375890204216384, | |
| "grad_norm": 1.530024766921997, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 9.627, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.011319152950054237, | |
| "grad_norm": 1.2234160900115967, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 9.3521, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012262415695892091, | |
| "grad_norm": 1.3077903985977173, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 9.2344, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.013205678441729944, | |
| "grad_norm": 1.3821742534637451, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 9.057, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.014148941187567796, | |
| "grad_norm": 1.7761777639389038, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 8.8848, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01509220393340565, | |
| "grad_norm": 1.6039808988571167, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 8.707, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.016035466679243503, | |
| "grad_norm": 1.177860975265503, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 8.5494, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.016978729425081357, | |
| "grad_norm": 1.4950674772262573, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 8.8237, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01792199217091921, | |
| "grad_norm": 2.425677537918091, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 9.3061, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.018865254916757064, | |
| "grad_norm": 3.5191574096679688, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 9.3926, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.018865254916757064, | |
| "eval_loss": 8.911721229553223, | |
| "eval_runtime": 16.3034, | |
| "eval_samples_per_second": 136.904, | |
| "eval_steps_per_second": 68.452, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019808517662594914, | |
| "grad_norm": 1.3204089403152466, | |
| "learning_rate": 5e-05, | |
| "loss": 9.2913, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.020751780408432768, | |
| "grad_norm": 1.4044511318206787, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 8.9501, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02169504315427062, | |
| "grad_norm": 0.9451562762260437, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 8.8392, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.022638305900108475, | |
| "grad_norm": 0.943010687828064, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 8.8905, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02358156864594633, | |
| "grad_norm": 1.3241652250289917, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 8.7438, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.024524831391784182, | |
| "grad_norm": 1.5031572580337524, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 8.3413, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.025468094137622035, | |
| "grad_norm": 1.2354382276535034, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 8.4801, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02641135688345989, | |
| "grad_norm": 1.9950472116470337, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 8.7475, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.027354619629297743, | |
| "grad_norm": 4.139790058135986, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 9.1915, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.028297882375135593, | |
| "grad_norm": 3.3802685737609863, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 9.3817, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.028297882375135593, | |
| "eval_loss": 8.854145050048828, | |
| "eval_runtime": 15.8892, | |
| "eval_samples_per_second": 140.472, | |
| "eval_steps_per_second": 70.236, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029241145120973446, | |
| "grad_norm": 1.1691869497299194, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 8.9873, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.0301844078668113, | |
| "grad_norm": 0.8915231227874756, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 8.9943, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.031127670612649153, | |
| "grad_norm": 1.2210413217544556, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 8.8053, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03207093335848701, | |
| "grad_norm": 1.7825607061386108, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 8.8807, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03301419610432486, | |
| "grad_norm": 0.8315479755401611, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 8.7147, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.033957458850162714, | |
| "grad_norm": 1.1837198734283447, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 8.279, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.034900721596000564, | |
| "grad_norm": 1.7369810342788696, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 8.3227, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03584398434183842, | |
| "grad_norm": 1.4928843975067139, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 8.6611, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03678724708767627, | |
| "grad_norm": 2.157352924346924, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 9.056, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.03773050983351413, | |
| "grad_norm": 3.332998752593994, | |
| "learning_rate": 0.0, | |
| "loss": 9.2979, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03773050983351413, | |
| "eval_loss": 8.849549293518066, | |
| "eval_runtime": 15.9376, | |
| "eval_samples_per_second": 140.046, | |
| "eval_steps_per_second": 70.023, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2341939536986112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |