| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9980636237897649, | |
| "eval_steps": 23, | |
| "global_step": 451, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05089903181189488, | |
| "grad_norm": 0.7468199729919434, | |
| "learning_rate": 0.001825741858350554, | |
| "loss": 1.4222, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10179806362378976, | |
| "grad_norm": 0.33098104596138, | |
| "learning_rate": 0.0008451542547285166, | |
| "loss": 1.2833, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15269709543568466, | |
| "grad_norm": 0.3552784323692322, | |
| "learning_rate": 0.0006262242910851496, | |
| "loss": 1.095, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.20359612724757953, | |
| "grad_norm": 0.32930678129196167, | |
| "learning_rate": 0.0005198752449100363, | |
| "loss": 1.0648, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2544951590594744, | |
| "grad_norm": 0.32375234365463257, | |
| "learning_rate": 0.0004540766091864998, | |
| "loss": 1.0184, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3053941908713693, | |
| "grad_norm": 0.37444040179252625, | |
| "learning_rate": 0.0004082482904638631, | |
| "loss": 1.0037, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3562932226832642, | |
| "grad_norm": 0.398503839969635, | |
| "learning_rate": 0.00037397879600338285, | |
| "loss": 0.9613, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.40719225449515906, | |
| "grad_norm": 0.36333534121513367, | |
| "learning_rate": 0.00034710506725031166, | |
| "loss": 0.9395, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4580912863070539, | |
| "grad_norm": 0.3362521231174469, | |
| "learning_rate": 0.0003253000243161777, | |
| "loss": 0.929, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.5089903181189488, | |
| "grad_norm": 0.3286592960357666, | |
| "learning_rate": 0.0003071475584169756, | |
| "loss": 0.9067, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5598893499308437, | |
| "grad_norm": 0.37335479259490967, | |
| "learning_rate": 0.0002917299829957891, | |
| "loss": 0.8955, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.6107883817427386, | |
| "grad_norm": 0.3964427411556244, | |
| "learning_rate": 0.0002784230231948523, | |
| "loss": 0.8665, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.6616874135546335, | |
| "grad_norm": 0.39572906494140625, | |
| "learning_rate": 0.0002667852642561041, | |
| "loss": 0.8622, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.7125864453665284, | |
| "grad_norm": 0.4889402389526367, | |
| "learning_rate": 0.0002564945880212886, | |
| "loss": 0.8716, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.7634854771784232, | |
| "grad_norm": 0.3482915163040161, | |
| "learning_rate": 0.00024730968341474897, | |
| "loss": 0.8326, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8143845089903181, | |
| "grad_norm": 0.4124608337879181, | |
| "learning_rate": 0.00023904572186687873, | |
| "loss": 0.8199, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.865283540802213, | |
| "grad_norm": 0.3616255819797516, | |
| "learning_rate": 0.00023155842232374464, | |
| "loss": 0.8103, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.9161825726141078, | |
| "grad_norm": 0.42308276891708374, | |
| "learning_rate": 0.00022473328748774736, | |
| "loss": 0.8067, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.9670816044260028, | |
| "grad_norm": 0.4363687038421631, | |
| "learning_rate": 0.00021847813825958586, | |
| "loss": 0.8163, | |
| "step": 437 | |
| } | |
| ], | |
| "logging_steps": 23, | |
| "max_steps": 451, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 23, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.580565166436909e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |