| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02126528442317916, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 7.85447359085083, | |
| "eval_runtime": 43.0645, | |
| "eval_samples_per_second": 22.989, | |
| "eval_steps_per_second": 11.494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 6.904982089996338, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2507, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 8.058303833007812, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2992, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 6.549283981323242, | |
| "eval_runtime": 42.3073, | |
| "eval_samples_per_second": 23.4, | |
| "eval_steps_per_second": 11.7, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 8.274881362915039, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.7451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": 3.4021964073181152, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": 3.175553798675537, | |
| "eval_runtime": 41.6034, | |
| "eval_samples_per_second": 23.796, | |
| "eval_steps_per_second": 11.898, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 3.960761308670044, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.7442, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 8.499146461486816, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3788, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "eval_loss": 2.4144866466522217, | |
| "eval_runtime": 41.7376, | |
| "eval_samples_per_second": 23.72, | |
| "eval_steps_per_second": 11.86, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014885699096225412, | |
| "grad_norm": 3.365118980407715, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.7027, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "grad_norm": 4.345822811126709, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.571, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "eval_loss": 2.0501210689544678, | |
| "eval_runtime": 41.8304, | |
| "eval_samples_per_second": 23.667, | |
| "eval_steps_per_second": 11.833, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019138755980861243, | |
| "grad_norm": 1.684922456741333, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.47, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "grad_norm": 1.7763071060180664, | |
| "learning_rate": 0.0, | |
| "loss": 1.1022, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "eval_loss": 2.0081968307495117, | |
| "eval_runtime": 41.6129, | |
| "eval_samples_per_second": 23.791, | |
| "eval_steps_per_second": 11.895, | |
| "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": 2399807113003008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |