| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.039278815196394, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.5357372826786864, | |
| "grad_norm": 1.0864949226379395, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3438, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5563425627817128, | |
| "grad_norm": 1.1756632328033447, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.475, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5769478428847392, | |
| "grad_norm": 1.0386406183242798, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3067, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5975531229877656, | |
| "grad_norm": 1.084520697593689, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3079, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6181584030907921, | |
| "grad_norm": 1.199838638305664, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2165, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6387636831938184, | |
| "grad_norm": 1.2528841495513916, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2907, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6593689632968448, | |
| "grad_norm": 1.1232812404632568, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2557, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6799742433998712, | |
| "grad_norm": 1.1742340326309204, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2703, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7005795235028976, | |
| "grad_norm": 1.1688557863235474, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2046, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.721184803605924, | |
| "grad_norm": 1.1665050983428955, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1234, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7417900837089504, | |
| "grad_norm": 1.281623125076294, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.1562, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7623953638119768, | |
| "grad_norm": 1.1950199604034424, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.4527, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7830006439150032, | |
| "grad_norm": 1.2145071029663086, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4938, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8036059240180297, | |
| "grad_norm": 1.1486097574234009, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3334, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.824211204121056, | |
| "grad_norm": 1.0132158994674683, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.3069, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8448164842240824, | |
| "grad_norm": 1.069280743598938, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2995, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8654217643271088, | |
| "grad_norm": 1.0366171598434448, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.1784, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8860270444301352, | |
| "grad_norm": 0.9968025088310242, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1579, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9066323245331617, | |
| "grad_norm": 1.0707521438598633, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2042, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.927237604636188, | |
| "grad_norm": 1.0155386924743652, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.164, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9478428847392144, | |
| "grad_norm": 1.0132240056991577, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1677, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9684481648422408, | |
| "grad_norm": 1.047545075416565, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0935, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9890534449452673, | |
| "grad_norm": 1.1519137620925903, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0777, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0186735350933678, | |
| "grad_norm": 3.185882806777954, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.4695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.039278815196394, | |
| "grad_norm": 1.053970456123352, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3533, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.039278815196394, | |
| "eval_loss": 1.2204114198684692, | |
| "eval_runtime": 3.4847, | |
| "eval_samples_per_second": 14.348, | |
| "eval_steps_per_second": 3.731, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |