| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06823609689525759, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001364721937905152, | |
| "eval_loss": 11.117195129394531, | |
| "eval_runtime": 2.2681, | |
| "eval_samples_per_second": 136.238, | |
| "eval_steps_per_second": 68.34, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006823609689525759, | |
| "grad_norm": 1.0152312517166138, | |
| "learning_rate": 5e-05, | |
| "loss": 44.4797, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013647219379051518, | |
| "grad_norm": 1.3089722394943237, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4643, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013647219379051518, | |
| "eval_loss": 11.114002227783203, | |
| "eval_runtime": 1.4627, | |
| "eval_samples_per_second": 211.247, | |
| "eval_steps_per_second": 105.965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02047082906857728, | |
| "grad_norm": 1.2206295728683472, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.4605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027294438758103036, | |
| "grad_norm": 1.3797295093536377, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.4063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027294438758103036, | |
| "eval_loss": 11.104840278625488, | |
| "eval_runtime": 1.5504, | |
| "eval_samples_per_second": 199.298, | |
| "eval_steps_per_second": 99.971, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03411804844762879, | |
| "grad_norm": 1.3237910270690918, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.4212, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04094165813715456, | |
| "grad_norm": 1.2200846672058105, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04094165813715456, | |
| "eval_loss": 11.096440315246582, | |
| "eval_runtime": 1.4689, | |
| "eval_samples_per_second": 210.355, | |
| "eval_steps_per_second": 105.518, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047765267826680315, | |
| "grad_norm": 1.2810032367706299, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.3709, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05458887751620607, | |
| "grad_norm": 1.3760566711425781, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05458887751620607, | |
| "eval_loss": 11.091919898986816, | |
| "eval_runtime": 1.5363, | |
| "eval_samples_per_second": 201.133, | |
| "eval_steps_per_second": 100.892, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06141248720573183, | |
| "grad_norm": 1.3825722932815552, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 44.3642, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06823609689525759, | |
| "grad_norm": 1.4432040452957153, | |
| "learning_rate": 0.0, | |
| "loss": 44.3796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06823609689525759, | |
| "eval_loss": 11.090957641601562, | |
| "eval_runtime": 1.48, | |
| "eval_samples_per_second": 208.778, | |
| "eval_steps_per_second": 104.727, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 482240102400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |