| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 387, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07751937984496124, | |
| "grad_norm": 2.9215729246190634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7501, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 1.7390484139778606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6417, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 2.6303600299328775, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 1.7365672816191515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 2.5822057210689393, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5869, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 1.746996607003936, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5776, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5426356589147286, | |
| "grad_norm": 1.8948006480184871, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5742, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 2.4400520626498414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5726, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 2.067112415972005, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 1.78188199676091, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8527131782945736, | |
| "grad_norm": 1.8707814480818752, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 1.1858683276722362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5603, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0077519379844961, | |
| "grad_norm": 2.4440942695562193, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5535, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0852713178294573, | |
| "grad_norm": 3.010730904678519, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5174, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "grad_norm": 2.260676020857914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.51, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2403100775193798, | |
| "grad_norm": 2.8965772384726995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5111, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3178294573643412, | |
| "grad_norm": 2.561493912479322, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5109, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 2.381325960362653, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.4728682170542635, | |
| "grad_norm": 2.597163347347591, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5098, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.550387596899225, | |
| "grad_norm": 2.3386390647615833, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5105, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 2.423259280958861, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5073, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7054263565891472, | |
| "grad_norm": 1.8305441285397837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5113, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.7829457364341086, | |
| "grad_norm": 1.972210760081399, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5104, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 2.1286521963156813, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5119, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.937984496124031, | |
| "grad_norm": 2.384913511133737, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5111, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0155038759689923, | |
| "grad_norm": 2.287778661831066, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5034, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 1.5497189232645128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4659, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.1705426356589146, | |
| "grad_norm": 1.1700554228567934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4658, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.248062015503876, | |
| "grad_norm": 1.3050664193052923, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4645, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "grad_norm": 1.4446705398465065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4667, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.4031007751937983, | |
| "grad_norm": 1.4968160462249973, | |
| "learning_rate": 5e-06, | |
| "loss": 0.47, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.4806201550387597, | |
| "grad_norm": 1.4716364495623662, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4705, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.558139534883721, | |
| "grad_norm": 1.172790704057467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4707, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.6356589147286824, | |
| "grad_norm": 1.7971924928025738, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4725, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.7131782945736433, | |
| "grad_norm": 1.9994960190730922, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4722, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.7906976744186047, | |
| "grad_norm": 1.1272436920505606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4711, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.8682170542635657, | |
| "grad_norm": 1.297666789751404, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4743, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.945736434108527, | |
| "grad_norm": 1.3226222258312366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4716, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 387, | |
| "total_flos": 2589607581450240.0, | |
| "train_loss": 0.5259489261518769, | |
| "train_runtime": 12288.9627, | |
| "train_samples_per_second": 64.441, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 387, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2589607581450240.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |