| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.51513200257566, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0206052801030264, | |
| "grad_norm": 3.2468912601470947, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0206052801030264, | |
| "eval_loss": 3.228774309158325, | |
| "eval_runtime": 3.4328, | |
| "eval_samples_per_second": 14.566, | |
| "eval_steps_per_second": 3.787, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0412105602060528, | |
| "grad_norm": 3.9502065181732178, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2572, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.061815840309079204, | |
| "grad_norm": 3.576547384262085, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.0055, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0824211204121056, | |
| "grad_norm": 2.5420279502868652, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.3547, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.103026400515132, | |
| "grad_norm": 2.1390628814697266, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12363168061815841, | |
| "grad_norm": 1.7916548252105713, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.7607, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1442369607211848, | |
| "grad_norm": 1.8303478956222534, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6577, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1648422408242112, | |
| "grad_norm": 1.7895830869674683, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6774, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1854475209272376, | |
| "grad_norm": 1.265881061553955, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.206052801030264, | |
| "grad_norm": 1.290668249130249, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4451, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22665808113329042, | |
| "grad_norm": 1.081251859664917, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.4128, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24726336123631681, | |
| "grad_norm": 1.317069411277771, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.326, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2678686413393432, | |
| "grad_norm": 1.264490008354187, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6552, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2884739214423696, | |
| "grad_norm": 1.1361223459243774, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6278, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.30907920154539603, | |
| "grad_norm": 1.0125176906585693, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3296844816484224, | |
| "grad_norm": 1.0024099349975586, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.485, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3502897617514488, | |
| "grad_norm": 1.19777512550354, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4315, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3708950418544752, | |
| "grad_norm": 1.0741177797317505, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3615, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3915003219575016, | |
| "grad_norm": 1.0112042427062988, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4198, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.412105602060528, | |
| "grad_norm": 1.0728622674942017, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.4319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4327108821635544, | |
| "grad_norm": 1.076214075088501, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3549, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.45331616226658084, | |
| "grad_norm": 1.0060209035873413, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2328, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4739214423696072, | |
| "grad_norm": 1.0517760515213013, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2736, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.49452672247263363, | |
| "grad_norm": 1.1817563772201538, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.2071, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.51513200257566, | |
| "grad_norm": 1.1937774419784546, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5126, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.51513200257566, | |
| "eval_loss": 1.314895749092102, | |
| "eval_runtime": 3.4937, | |
| "eval_samples_per_second": 14.312, | |
| "eval_steps_per_second": 3.721, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |