| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11321422253670617, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0056607111268353084, | |
| "grad_norm": 0.24056661128997803, | |
| "learning_rate": 1e-05, | |
| "loss": 10.4071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0056607111268353084, | |
| "eval_loss": 10.435810089111328, | |
| "eval_runtime": 7.8807, | |
| "eval_samples_per_second": 75.501, | |
| "eval_steps_per_second": 37.814, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011321422253670617, | |
| "grad_norm": 0.2668295204639435, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016982133380505925, | |
| "grad_norm": 0.23038893938064575, | |
| "learning_rate": 3e-05, | |
| "loss": 10.4385, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022642844507341234, | |
| "grad_norm": 0.2281711995601654, | |
| "learning_rate": 4e-05, | |
| "loss": 10.4232, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "grad_norm": 0.2743370532989502, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4297, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "eval_loss": 10.434837341308594, | |
| "eval_runtime": 7.8713, | |
| "eval_samples_per_second": 75.591, | |
| "eval_steps_per_second": 37.859, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03396426676101185, | |
| "grad_norm": 0.23880141973495483, | |
| "learning_rate": 6e-05, | |
| "loss": 10.4333, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03962497788784716, | |
| "grad_norm": 0.2584647536277771, | |
| "learning_rate": 7e-05, | |
| "loss": 10.4085, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04528568901468247, | |
| "grad_norm": 0.22347287833690643, | |
| "learning_rate": 8e-05, | |
| "loss": 10.4365, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05094640014151778, | |
| "grad_norm": 0.25124576687812805, | |
| "learning_rate": 9e-05, | |
| "loss": 10.4249, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056607111268353084, | |
| "grad_norm": 0.25805941224098206, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4151, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.056607111268353084, | |
| "eval_loss": 10.431522369384766, | |
| "eval_runtime": 7.8709, | |
| "eval_samples_per_second": 75.595, | |
| "eval_steps_per_second": 37.861, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.062267822395188396, | |
| "grad_norm": 0.24282322824001312, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.4583, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0679285335220237, | |
| "grad_norm": 0.22543445229530334, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.073589244648859, | |
| "grad_norm": 0.2722141444683075, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.4259, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07924995577569433, | |
| "grad_norm": 0.26514723896980286, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.4125, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08491066690252963, | |
| "grad_norm": 0.23801234364509583, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4257, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08491066690252963, | |
| "eval_loss": 10.427189826965332, | |
| "eval_runtime": 7.8704, | |
| "eval_samples_per_second": 75.6, | |
| "eval_steps_per_second": 37.863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09057137802936494, | |
| "grad_norm": 0.24435019493103027, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.4197, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09623208915620025, | |
| "grad_norm": 0.24444067478179932, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.4299, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10189280028303556, | |
| "grad_norm": 0.26259520649909973, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.4198, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10755351140987086, | |
| "grad_norm": 0.2749709188938141, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 10.4089, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11321422253670617, | |
| "grad_norm": 0.2748180031776428, | |
| "learning_rate": 0.0, | |
| "loss": 10.421, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11321422253670617, | |
| "eval_loss": 10.425971984863281, | |
| "eval_runtime": 7.8732, | |
| "eval_samples_per_second": 75.573, | |
| "eval_steps_per_second": 37.85, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 16736782909440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |