| { | |
| "best_metric": 11.034313201904297, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.09225092250922509, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036900369003690036, | |
| "grad_norm": 1.791113018989563, | |
| "learning_rate": 2e-05, | |
| "loss": 44.5973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036900369003690036, | |
| "eval_loss": 11.170838356018066, | |
| "eval_runtime": 1.9984, | |
| "eval_samples_per_second": 57.545, | |
| "eval_steps_per_second": 29.023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007380073800738007, | |
| "grad_norm": 2.3068079948425293, | |
| "learning_rate": 4e-05, | |
| "loss": 44.6951, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01107011070110701, | |
| "grad_norm": 2.204294443130493, | |
| "learning_rate": 6e-05, | |
| "loss": 44.6784, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014760147601476014, | |
| "grad_norm": 2.4943387508392334, | |
| "learning_rate": 8e-05, | |
| "loss": 44.5942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01845018450184502, | |
| "grad_norm": 2.697859287261963, | |
| "learning_rate": 0.0001, | |
| "loss": 44.7435, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01845018450184502, | |
| "eval_loss": 11.16266918182373, | |
| "eval_runtime": 0.897, | |
| "eval_samples_per_second": 128.199, | |
| "eval_steps_per_second": 64.657, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02214022140221402, | |
| "grad_norm": 2.368184804916382, | |
| "learning_rate": 0.00012, | |
| "loss": 44.6444, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025830258302583026, | |
| "grad_norm": 2.20993709564209, | |
| "learning_rate": 0.00014, | |
| "loss": 44.5774, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02952029520295203, | |
| "grad_norm": 2.647223949432373, | |
| "learning_rate": 0.00016, | |
| "loss": 44.6219, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.033210332103321034, | |
| "grad_norm": 2.0904574394226074, | |
| "learning_rate": 0.00018, | |
| "loss": 44.5955, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03690036900369004, | |
| "grad_norm": 2.8271727561950684, | |
| "learning_rate": 0.0002, | |
| "loss": 44.5294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03690036900369004, | |
| "eval_loss": 11.130102157592773, | |
| "eval_runtime": 0.895, | |
| "eval_samples_per_second": 128.492, | |
| "eval_steps_per_second": 64.805, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04059040590405904, | |
| "grad_norm": 2.5687215328216553, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.541, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04428044280442804, | |
| "grad_norm": 2.665268898010254, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.4935, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04797047970479705, | |
| "grad_norm": 3.064598560333252, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.3673, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05166051660516605, | |
| "grad_norm": 2.704948902130127, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.4678, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.055350553505535055, | |
| "grad_norm": 2.82173228263855, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.3777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.055350553505535055, | |
| "eval_loss": 11.077457427978516, | |
| "eval_runtime": 0.8924, | |
| "eval_samples_per_second": 128.87, | |
| "eval_steps_per_second": 64.995, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05904059040590406, | |
| "grad_norm": 3.1735241413116455, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.2805, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06273062730627306, | |
| "grad_norm": 3.064631700515747, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.2625, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06642066420664207, | |
| "grad_norm": 2.9129655361175537, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.2758, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07011070110701106, | |
| "grad_norm": 2.705364942550659, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.2338, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07380073800738007, | |
| "grad_norm": 3.0325767993927, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.2377, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07380073800738007, | |
| "eval_loss": 11.041491508483887, | |
| "eval_runtime": 0.9676, | |
| "eval_samples_per_second": 118.849, | |
| "eval_steps_per_second": 59.941, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07749077490774908, | |
| "grad_norm": 2.9936363697052, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.1306, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08118081180811808, | |
| "grad_norm": 2.515326499938965, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.2357, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08487084870848709, | |
| "grad_norm": 3.491044521331787, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.0782, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08856088560885608, | |
| "grad_norm": 2.6066572666168213, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.2835, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09225092250922509, | |
| "grad_norm": 3.1168739795684814, | |
| "learning_rate": 0.0, | |
| "loss": 44.0841, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09225092250922509, | |
| "eval_loss": 11.034313201904297, | |
| "eval_runtime": 0.9091, | |
| "eval_samples_per_second": 126.496, | |
| "eval_steps_per_second": 63.798, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 479828901888.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |