| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15328019619865113, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0061312078479460455, | |
| "grad_norm": 1.8461681604385376, | |
| "learning_rate": 0.00019936113105200085, | |
| "loss": 2.9781, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012262415695892091, | |
| "grad_norm": 3.338013172149658, | |
| "learning_rate": 0.0001971631732914674, | |
| "loss": 1.7629, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018393623543838136, | |
| "grad_norm": 2.6224777698516846, | |
| "learning_rate": 0.00019343289424566122, | |
| "loss": 0.8836, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024524831391784182, | |
| "grad_norm": 2.1204261779785156, | |
| "learning_rate": 0.00018822912264349534, | |
| "loss": 0.5916, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030656039239730228, | |
| "grad_norm": 1.0972894430160522, | |
| "learning_rate": 0.00018163392507171842, | |
| "loss": 0.2375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03678724708767627, | |
| "grad_norm": 7.48022985458374, | |
| "learning_rate": 0.0001737513117358174, | |
| "loss": 0.3354, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04291845493562232, | |
| "grad_norm": 0.04426204413175583, | |
| "learning_rate": 0.00016470559615694446, | |
| "loss": 0.2289, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.049049662783568364, | |
| "grad_norm": 2.7863688468933105, | |
| "learning_rate": 0.00015463943467342693, | |
| "loss": 0.1755, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05518087063151441, | |
| "grad_norm": 0.12476109713315964, | |
| "learning_rate": 0.0001437115766650933, | |
| "loss": 0.1166, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.061312078479460456, | |
| "grad_norm": 2.828798770904541, | |
| "learning_rate": 0.00013209436098072095, | |
| "loss": 0.2017, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0674432863274065, | |
| "grad_norm": 0.5962816476821899, | |
| "learning_rate": 0.00011997099805144069, | |
| "loss": 0.158, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07357449417535254, | |
| "grad_norm": 1.1787047386169434, | |
| "learning_rate": 0.00010753268055279329, | |
| "loss": 0.1305, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07970570202329859, | |
| "grad_norm": 0.029666101559996605, | |
| "learning_rate": 9.497556818202306e-05, | |
| "loss": 0.2012, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 0.8552451133728027, | |
| "learning_rate": 8.249769410247239e-05, | |
| "loss": 0.0833, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09196811771919068, | |
| "grad_norm": 6.994303226470947, | |
| "learning_rate": 7.029584184229653e-05, | |
| "loss": 0.1842, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09809932556713673, | |
| "grad_norm": 0.14720402657985687, | |
| "learning_rate": 5.856244190067159e-05, | |
| "loss": 0.0773, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10423053341508277, | |
| "grad_norm": 0.9132323265075684, | |
| "learning_rate": 4.748253700387042e-05, | |
| "loss": 0.0718, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11036174126302882, | |
| "grad_norm": 0.5882895588874817, | |
| "learning_rate": 3.7230863870929964e-05, | |
| "loss": 0.0874, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11649294911097487, | |
| "grad_norm": 7.029378414154053, | |
| "learning_rate": 2.7969097511209308e-05, | |
| "loss": 0.1575, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12262415695892091, | |
| "grad_norm": 0.9121600985527039, | |
| "learning_rate": 1.9843301512912327e-05, | |
| "loss": 0.0978, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12875536480686695, | |
| "grad_norm": 1.3362879753112793, | |
| "learning_rate": 1.2981624533047432e-05, | |
| "loss": 0.15, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.134886572654813, | |
| "grad_norm": 2.2885565757751465, | |
| "learning_rate": 7.492279316554207e-06, | |
| "loss": 0.1171, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14101778050275904, | |
| "grad_norm": 0.739460825920105, | |
| "learning_rate": 3.461836116672612e-06, | |
| "loss": 0.1375, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.14714898835070508, | |
| "grad_norm": 0.732049286365509, | |
| "learning_rate": 9.538574303348813e-07, | |
| "loss": 0.0661, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15328019619865113, | |
| "grad_norm": 0.795531153678894, | |
| "learning_rate": 7.895579618388827e-09, | |
| "loss": 0.176, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 138282270720000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |