| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03307888040712468, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 3.013115882873535, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "eval_loss": 1.6131161451339722, | |
| "eval_runtime": 4.1535, | |
| "eval_samples_per_second": 39.966, | |
| "eval_steps_per_second": 19.983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 3.4997785091400146, | |
| "learning_rate": 1e-05, | |
| "loss": 1.447, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 2.859135627746582, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 2.542371988296509, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8844, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 2.9563982486724854, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2164, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 3.415498733520508, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3261, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 3.1173617839813232, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.2456, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 2.952441453933716, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0949, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": 3.2792415618896484, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.1191, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 2.428950786590576, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027989821882951654, | |
| "grad_norm": 3.6672072410583496, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 1.1482, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": 2.3909623622894287, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.7157, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03307888040712468, | |
| "grad_norm": 2.3522462844848633, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.5238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03307888040712468, | |
| "eval_loss": 0.7261966466903687, | |
| "eval_runtime": 4.1767, | |
| "eval_samples_per_second": 39.744, | |
| "eval_steps_per_second": 19.872, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 650126529921024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |