| { | |
| "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": 11.111263275146484, | |
| "eval_runtime": 26.7188, | |
| "eval_samples_per_second": 369.178, | |
| "eval_steps_per_second": 184.589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042689434364994664, | |
| "grad_norm": 0.7761024832725525, | |
| "learning_rate": 0.0002, | |
| "loss": 44.4515, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008537886872998933, | |
| "grad_norm": 1.0055408477783203, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3908, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012806830309498398, | |
| "grad_norm": 1.0959935188293457, | |
| "learning_rate": 0.0002, | |
| "loss": 44.2882, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017075773745997866, | |
| "grad_norm": 1.2277438640594482, | |
| "learning_rate": 0.0002, | |
| "loss": 44.17, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021344717182497333, | |
| "grad_norm": 1.5021330118179321, | |
| "learning_rate": 0.0002, | |
| "loss": 43.9566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021344717182497333, | |
| "eval_loss": 10.962719917297363, | |
| "eval_runtime": 25.7354, | |
| "eval_samples_per_second": 383.285, | |
| "eval_steps_per_second": 191.643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0025613660618996796, | |
| "grad_norm": 1.1975489854812622, | |
| "learning_rate": 0.0002, | |
| "loss": 43.8035, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0029882604055496264, | |
| "grad_norm": 0.8993712067604065, | |
| "learning_rate": 0.0002, | |
| "loss": 43.647, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.003415154749199573, | |
| "grad_norm": 0.7272806167602539, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5916, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00384204909284952, | |
| "grad_norm": 1.0062687397003174, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5633, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "grad_norm": 1.130202054977417, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5667, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004268943436499467, | |
| "eval_loss": 10.890177726745605, | |
| "eval_runtime": 25.8725, | |
| "eval_samples_per_second": 381.254, | |
| "eval_steps_per_second": 190.627, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004695837780149413, | |
| "grad_norm": 0.8456355333328247, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5493, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005122732123799359, | |
| "grad_norm": 0.7490809559822083, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5334, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.005549626467449306, | |
| "grad_norm": 0.8240365982055664, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4919, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.005976520811099253, | |
| "grad_norm": 0.9284916520118713, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4898, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0064034151547491995, | |
| "grad_norm": 1.0496503114700317, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4868, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0064034151547491995, | |
| "eval_loss": 10.8709716796875, | |
| "eval_runtime": 26.0745, | |
| "eval_samples_per_second": 378.301, | |
| "eval_steps_per_second": 189.15, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006830309498399146, | |
| "grad_norm": 0.7669797539710999, | |
| "learning_rate": 0.0002, | |
| "loss": 43.5103, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007257203842049093, | |
| "grad_norm": 1.0080665349960327, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4395, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.00768409818569904, | |
| "grad_norm": 0.8390846252441406, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4707, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.008110992529348986, | |
| "grad_norm": 1.1518946886062622, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4299, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "grad_norm": 0.8257205486297607, | |
| "learning_rate": 0.0002, | |
| "loss": 43.4201, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008537886872998933, | |
| "eval_loss": 10.853501319885254, | |
| "eval_runtime": 26.0893, | |
| "eval_samples_per_second": 378.086, | |
| "eval_steps_per_second": 189.043, | |
| "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 | |
| } | |