| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0396000396000396, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000198000198000198, | |
| "eval_loss": 1.105994701385498, | |
| "eval_runtime": 178.9466, | |
| "eval_samples_per_second": 11.886, | |
| "eval_steps_per_second": 5.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00198000198000198, | |
| "grad_norm": 1.0191270112991333, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 4.1654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00396000396000396, | |
| "grad_norm": 1.2664660215377808, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 3.8117, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00594000594000594, | |
| "grad_norm": 0.9743459224700928, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 3.8164, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00792000792000792, | |
| "grad_norm": 1.1033498048782349, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 3.657, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "grad_norm": 1.9051858186721802, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 3.9283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "eval_loss": 0.8947995901107788, | |
| "eval_runtime": 178.7865, | |
| "eval_samples_per_second": 11.897, | |
| "eval_steps_per_second": 5.951, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01188001188001188, | |
| "grad_norm": 1.570327639579773, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 3.783, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01386001386001386, | |
| "grad_norm": 1.0465843677520752, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.9758, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01584001584001584, | |
| "grad_norm": 1.319621205329895, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 3.6048, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01782001782001782, | |
| "grad_norm": 1.6770116090774536, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 3.5316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "grad_norm": 0.9391918778419495, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 3.4507, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "eval_loss": 0.8597908616065979, | |
| "eval_runtime": 178.7551, | |
| "eval_samples_per_second": 11.899, | |
| "eval_steps_per_second": 5.952, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02178002178002178, | |
| "grad_norm": 0.9822765588760376, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 3.1689, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02376002376002376, | |
| "grad_norm": 1.117750883102417, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 3.1231, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02574002574002574, | |
| "grad_norm": 2.2837934494018555, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 3.7971, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02772002772002772, | |
| "grad_norm": 1.7023260593414307, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 3.367, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "grad_norm": 1.4030767679214478, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 3.2886, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "eval_loss": 0.8444181680679321, | |
| "eval_runtime": 178.7934, | |
| "eval_samples_per_second": 11.896, | |
| "eval_steps_per_second": 5.951, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03168003168003168, | |
| "grad_norm": 1.8827073574066162, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 3.3219, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03366003366003366, | |
| "grad_norm": 1.6092329025268555, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 3.3611, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03564003564003564, | |
| "grad_norm": 1.6704670190811157, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 3.8902, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03762003762003762, | |
| "grad_norm": 1.419443964958191, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 3.5671, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "grad_norm": 1.2906014919281006, | |
| "learning_rate": 0.0, | |
| "loss": 3.1066, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "eval_loss": 0.8420388102531433, | |
| "eval_runtime": 178.7659, | |
| "eval_samples_per_second": 11.898, | |
| "eval_steps_per_second": 5.952, | |
| "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": 9.680730813628416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |