| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0243116756822464, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000121558378411232, | |
| "eval_loss": 2.5203659534454346, | |
| "eval_runtime": 129.4621, | |
| "eval_samples_per_second": 26.757, | |
| "eval_steps_per_second": 13.378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00121558378411232, | |
| "grad_norm": 1.6431328058242798, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 9.3908, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00243116756822464, | |
| "grad_norm": 2.2140567302703857, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 9.4789, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036467513523369597, | |
| "grad_norm": 2.526764392852783, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 9.2779, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00486233513644928, | |
| "grad_norm": 1.9266506433486938, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 9.338, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "grad_norm": 3.146573066711426, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 9.01, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "eval_loss": 2.222339153289795, | |
| "eval_runtime": 129.5944, | |
| "eval_samples_per_second": 26.73, | |
| "eval_steps_per_second": 13.365, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007293502704673919, | |
| "grad_norm": 1.2259963750839233, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 9.0436, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00850908648878624, | |
| "grad_norm": 1.6642357110977173, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.0942, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00972467027289856, | |
| "grad_norm": 1.8353936672210693, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 8.8742, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010940254057010879, | |
| "grad_norm": 1.792574405670166, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 8.9033, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "grad_norm": 1.7031313180923462, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 9.0372, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "eval_loss": 2.2013378143310547, | |
| "eval_runtime": 129.5196, | |
| "eval_samples_per_second": 26.745, | |
| "eval_steps_per_second": 13.372, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01337142162523552, | |
| "grad_norm": 1.7284899950027466, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 9.078, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.014587005409347839, | |
| "grad_norm": 2.15350604057312, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 8.5944, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01580258919346016, | |
| "grad_norm": 2.8749678134918213, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 8.6681, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01701817297757248, | |
| "grad_norm": 3.2664244174957275, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 8.6425, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "grad_norm": 1.5569379329681396, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 8.5449, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "eval_loss": 2.1931543350219727, | |
| "eval_runtime": 129.4831, | |
| "eval_samples_per_second": 26.753, | |
| "eval_steps_per_second": 13.376, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01944934054579712, | |
| "grad_norm": 1.8313133716583252, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 8.7938, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.020664924329909438, | |
| "grad_norm": 1.3177337646484375, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 8.6881, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.021880508114021757, | |
| "grad_norm": 1.4380029439926147, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 8.9628, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02309609189813408, | |
| "grad_norm": 2.021592140197754, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 8.7991, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "grad_norm": 1.8787529468536377, | |
| "learning_rate": 0.0, | |
| "loss": 9.1146, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "eval_loss": 2.1915578842163086, | |
| "eval_runtime": 129.4737, | |
| "eval_samples_per_second": 26.754, | |
| "eval_steps_per_second": 13.377, | |
| "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": 3.762410749113139e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |