| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.41450777202072536, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002072538860103627, | |
| "eval_loss": 0.7757489085197449, | |
| "eval_runtime": 21.4463, | |
| "eval_samples_per_second": 9.512, | |
| "eval_steps_per_second": 4.756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 2.0602431297302246, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 2.9893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.9440550804138184, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 2.4423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 1.6078230142593384, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 2.5943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.8488917350769043, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 2.5973, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 0.5597093105316162, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 2.4491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "eval_loss": 0.6410841345787048, | |
| "eval_runtime": 21.4898, | |
| "eval_samples_per_second": 9.493, | |
| "eval_steps_per_second": 4.746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12435233160621761, | |
| "grad_norm": 0.7345647811889648, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 2.4479, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14507772020725387, | |
| "grad_norm": 0.7027221322059631, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.5233, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16580310880829016, | |
| "grad_norm": 0.6218558549880981, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 2.3496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18652849740932642, | |
| "grad_norm": 0.7521792650222778, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 2.5815, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.5388895273208618, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 2.4037, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "eval_loss": 0.6285238265991211, | |
| "eval_runtime": 21.468, | |
| "eval_samples_per_second": 9.503, | |
| "eval_steps_per_second": 4.751, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22797927461139897, | |
| "grad_norm": 0.8191409707069397, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 2.3543, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.24870466321243523, | |
| "grad_norm": 0.9439878463745117, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 2.5457, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2694300518134715, | |
| "grad_norm": 0.7924945950508118, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 2.6822, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29015544041450775, | |
| "grad_norm": 0.7882089614868164, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 2.5139, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "grad_norm": 0.8719218373298645, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 2.3399, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "eval_loss": 0.6230465173721313, | |
| "eval_runtime": 21.4544, | |
| "eval_samples_per_second": 9.509, | |
| "eval_steps_per_second": 4.754, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3316062176165803, | |
| "grad_norm": 0.7077692151069641, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 2.5644, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.35233160621761656, | |
| "grad_norm": 0.6462181210517883, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 2.3797, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.37305699481865284, | |
| "grad_norm": 0.9239203929901123, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 2.4447, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.39378238341968913, | |
| "grad_norm": 1.950250506401062, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 2.3303, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 0.7704319357872009, | |
| "learning_rate": 0.0, | |
| "loss": 2.3666, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "eval_loss": 0.6215264797210693, | |
| "eval_runtime": 21.4235, | |
| "eval_samples_per_second": 9.522, | |
| "eval_steps_per_second": 4.761, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.301191701037056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |