| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004906395179466736, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002453197589733368, | |
| "grad_norm": 0.24776850640773773, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1303, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002453197589733368, | |
| "eval_loss": 2.115117073059082, | |
| "eval_runtime": 163.5082, | |
| "eval_samples_per_second": 41.992, | |
| "eval_steps_per_second": 20.996, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004906395179466736, | |
| "grad_norm": 0.2624139189720154, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1278, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007359592769200105, | |
| "grad_norm": 0.2442760169506073, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1148, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009812790358933472, | |
| "grad_norm": 0.2723299264907837, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1568, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001226598794866684, | |
| "grad_norm": 0.24925272166728973, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0273, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001226598794866684, | |
| "eval_loss": 2.103795289993286, | |
| "eval_runtime": 82.5574, | |
| "eval_samples_per_second": 83.166, | |
| "eval_steps_per_second": 41.583, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001471918553840021, | |
| "grad_norm": 0.2547450065612793, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1506, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017172383128133577, | |
| "grad_norm": 0.26850205659866333, | |
| "learning_rate": 7e-05, | |
| "loss": 2.0881, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019625580717866943, | |
| "grad_norm": 0.25618699193000793, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1066, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002207877830760031, | |
| "grad_norm": 0.25713080167770386, | |
| "learning_rate": 9e-05, | |
| "loss": 2.0748, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002453197589733368, | |
| "grad_norm": 0.25452324748039246, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2807, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002453197589733368, | |
| "eval_loss": 2.075286626815796, | |
| "eval_runtime": 82.6768, | |
| "eval_samples_per_second": 83.046, | |
| "eval_steps_per_second": 41.523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002698517348706705, | |
| "grad_norm": 0.29315394163131714, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1677, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002943837107680042, | |
| "grad_norm": 0.28309640288352966, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.1386, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0031891568666533787, | |
| "grad_norm": 0.28708046674728394, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.0224, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0034344766256267155, | |
| "grad_norm": 0.30222126841545105, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1017, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0036797963846000523, | |
| "grad_norm": 0.30490654706954956, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2138, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036797963846000523, | |
| "eval_loss": 2.048198938369751, | |
| "eval_runtime": 82.6378, | |
| "eval_samples_per_second": 83.085, | |
| "eval_steps_per_second": 41.543, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003925116143573389, | |
| "grad_norm": 0.3192310631275177, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1727, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004170435902546726, | |
| "grad_norm": 0.310372918844223, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.9488, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004415755661520062, | |
| "grad_norm": 0.2975858151912689, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.9315, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004661075420493399, | |
| "grad_norm": 0.2612904906272888, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 2.1132, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004906395179466736, | |
| "grad_norm": 0.28620487451553345, | |
| "learning_rate": 0.0, | |
| "loss": 2.0732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004906395179466736, | |
| "eval_loss": 2.0405490398406982, | |
| "eval_runtime": 82.616, | |
| "eval_samples_per_second": 83.107, | |
| "eval_steps_per_second": 41.554, | |
| "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": 3048403630030848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |