| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07598784194528875, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00303951367781155, | |
| "grad_norm": 13.49870491027832, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.1121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00303951367781155, | |
| "eval_loss": 4.797636032104492, | |
| "eval_runtime": 36.7942, | |
| "eval_samples_per_second": 3.778, | |
| "eval_steps_per_second": 1.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0060790273556231, | |
| "grad_norm": 12.006007194519043, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.7642, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00911854103343465, | |
| "grad_norm": 11.162591934204102, | |
| "learning_rate": 5e-05, | |
| "loss": 3.077, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0121580547112462, | |
| "grad_norm": 8.176030158996582, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 2.8574, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015197568389057751, | |
| "grad_norm": 6.960273265838623, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 2.5954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0182370820668693, | |
| "grad_norm": 7.929886817932129, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 2.6525, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02127659574468085, | |
| "grad_norm": 6.948627948760986, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 2.2277, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 6.242570877075195, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 1.5744, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02735562310030395, | |
| "grad_norm": 7.785113334655762, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 2.0428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030395136778115502, | |
| "grad_norm": 7.158974647521973, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 1.4865, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03343465045592705, | |
| "grad_norm": 7.481812953948975, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 1.6615, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0364741641337386, | |
| "grad_norm": 13.22747802734375, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 2.5028, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03951367781155015, | |
| "grad_norm": 7.720076560974121, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 1.1715, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 6.172296047210693, | |
| "learning_rate": 4.717527082945554e-05, | |
| "loss": 0.7897, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04559270516717325, | |
| "grad_norm": 7.666730880737305, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 1.42, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 8.414482116699219, | |
| "learning_rate": 4.608478614532215e-05, | |
| "loss": 1.0577, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05167173252279635, | |
| "grad_norm": 8.490312576293945, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 1.4698, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0547112462006079, | |
| "grad_norm": 6.877030372619629, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 1.1734, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.057750759878419454, | |
| "grad_norm": 7.7711052894592285, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 1.1899, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.060790273556231005, | |
| "grad_norm": 6.355740547180176, | |
| "learning_rate": 4.34319334202531e-05, | |
| "loss": 1.0894, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 5.492956161499023, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.5664, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0668693009118541, | |
| "grad_norm": 5.8868303298950195, | |
| "learning_rate": 4.188975519039151e-05, | |
| "loss": 0.7452, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06990881458966565, | |
| "grad_norm": 5.961940288543701, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 0.8316, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0729483282674772, | |
| "grad_norm": 10.402515411376953, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 1.2375, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07598784194528875, | |
| "grad_norm": 9.500027656555176, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 1.34, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07598784194528875, | |
| "eval_loss": 1.3861757516860962, | |
| "eval_runtime": 37.3804, | |
| "eval_samples_per_second": 3.719, | |
| "eval_steps_per_second": 1.873, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8294216761344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |