| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09216589861751152, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004608294930875576, | |
| "eval_loss": 1.9200087785720825, | |
| "eval_runtime": 33.9108, | |
| "eval_samples_per_second": 26.953, | |
| "eval_steps_per_second": 13.477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004608294930875576, | |
| "grad_norm": 0.9508271813392639, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6798, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009216589861751152, | |
| "grad_norm": 0.9293316602706909, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013824884792626729, | |
| "grad_norm": 0.8375762104988098, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018433179723502304, | |
| "grad_norm": 0.7371276021003723, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2615, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02304147465437788, | |
| "grad_norm": 0.9093273878097534, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02304147465437788, | |
| "eval_loss": 1.2262965440750122, | |
| "eval_runtime": 32.9245, | |
| "eval_samples_per_second": 27.76, | |
| "eval_steps_per_second": 13.88, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.027649769585253458, | |
| "grad_norm": 0.9648954272270203, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2425, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 1.180851697921753, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1576, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03686635944700461, | |
| "grad_norm": 0.9131804704666138, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1993, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.041474654377880185, | |
| "grad_norm": 0.9733966588973999, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04608294930875576, | |
| "grad_norm": 1.0335547924041748, | |
| "learning_rate": 0.0002, | |
| "loss": 1.223, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04608294930875576, | |
| "eval_loss": 1.1788889169692993, | |
| "eval_runtime": 32.9063, | |
| "eval_samples_per_second": 27.776, | |
| "eval_steps_per_second": 13.888, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05069124423963134, | |
| "grad_norm": 1.0844675302505493, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2192, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.055299539170506916, | |
| "grad_norm": 0.8243290185928345, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2125, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.059907834101382486, | |
| "grad_norm": 0.940923273563385, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2913, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 0.918209969997406, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2533, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06912442396313365, | |
| "grad_norm": 0.9641485214233398, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2138, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06912442396313365, | |
| "eval_loss": 1.1654969453811646, | |
| "eval_runtime": 32.9162, | |
| "eval_samples_per_second": 27.767, | |
| "eval_steps_per_second": 13.884, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07373271889400922, | |
| "grad_norm": 0.9913356900215149, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1885, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07834101382488479, | |
| "grad_norm": 1.1817073822021484, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2213, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08294930875576037, | |
| "grad_norm": 0.7574412226676941, | |
| "learning_rate": 0.0002, | |
| "loss": 1.182, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08755760368663594, | |
| "grad_norm": 0.9810389876365662, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1954, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09216589861751152, | |
| "grad_norm": 1.1037870645523071, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1147, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09216589861751152, | |
| "eval_loss": 1.137990951538086, | |
| "eval_runtime": 32.949, | |
| "eval_samples_per_second": 27.74, | |
| "eval_steps_per_second": 13.87, | |
| "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": 4.526497129719398e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |