| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008537886872998933, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.268943436499467e-05, | |
| "eval_loss": 11.11116886138916, | |
| "eval_runtime": 26.7787, | |
| "eval_samples_per_second": 368.353, | |
| "eval_steps_per_second": 184.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042689434364994664, | |
| "grad_norm": 0.8201702833175659, | |
| "learning_rate": 0.0002, | |
| "loss": 44.4495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008537886872998933, | |
| "grad_norm": 1.0575289726257324, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012806830309498398, | |
| "grad_norm": 1.1616137027740479, | |
| "learning_rate": 0.0002, | |
| "loss": 44.2795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017075773745997866, | |
| "grad_norm": 1.2281877994537354, | |
| "learning_rate": 0.0002, | |
| "loss": 44.1531, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021344717182497333, | |
| "grad_norm": 1.488601565361023, | |
| "learning_rate": 0.0002, | |
| "loss": 43.9426, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021344717182497333, | |
| "eval_loss": 10.959285736083984, | |
| "eval_runtime": 25.947, | |
| "eval_samples_per_second": 380.159, | |
| "eval_steps_per_second": 190.079, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0025613660618996796, | |
| "grad_norm": 1.1621413230895996, | |
| "learning_rate": 0.0002, | |
| "loss": 43.7882, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0029882604055496264, | |
| "grad_norm": 0.8476995229721069, | |
| "learning_rate": 0.0002, | |
| "loss": 43.6368, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003415154749199573, | |
| "grad_norm": 0.7544131875038147, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5856, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00384204909284952, | |
| "grad_norm": 0.9888026714324951, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5509, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "grad_norm": 1.0631221532821655, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5477, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "eval_loss": 10.883926391601562, | |
| "eval_runtime": 25.5532, | |
| "eval_samples_per_second": 386.018, | |
| "eval_steps_per_second": 193.009, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004695837780149413, | |
| "grad_norm": 0.8417938947677612, | |
| "learning_rate": 0.0002, | |
| "loss": 43.525, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005122732123799359, | |
| "grad_norm": 0.7629103660583496, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5057, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.005549626467449306, | |
| "grad_norm": 0.763012170791626, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4606, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005976520811099253, | |
| "grad_norm": 0.8534968495368958, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4568, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0064034151547491995, | |
| "grad_norm": 0.9974360466003418, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4598, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0064034151547491995, | |
| "eval_loss": 10.865395545959473, | |
| "eval_runtime": 25.6883, | |
| "eval_samples_per_second": 383.987, | |
| "eval_steps_per_second": 191.994, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006830309498399146, | |
| "grad_norm": 0.7604882717132568, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4926, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007257203842049093, | |
| "grad_norm": 0.9254680275917053, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4299, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.00768409818569904, | |
| "grad_norm": 0.7746944427490234, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4712, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.008110992529348986, | |
| "grad_norm": 1.0943514108657837, | |
| "learning_rate": 0.0002, | |
| "loss": 43.433, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "grad_norm": 0.7889847755432129, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4282, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "eval_loss": 10.85505485534668, | |
| "eval_runtime": 25.7217, | |
| "eval_samples_per_second": 383.489, | |
| "eval_steps_per_second": 191.744, | |
| "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": 2698133372928.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |