| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 1000, | |
| "global_step": 11032, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036258158085569254, | |
| "grad_norm": 7.228061676025391, | |
| "learning_rate": 0.0, | |
| "loss": 4.1707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "grad_norm": 5.671091556549072, | |
| "learning_rate": 6.036253776435046e-06, | |
| "loss": 3.5534, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36258158085569253, | |
| "eval_cosine_accuracy": 0.9460511207580566, | |
| "eval_loss": 0.562572181224823, | |
| "eval_runtime": 36.9213, | |
| "eval_samples_per_second": 257.548, | |
| "eval_steps_per_second": 1.029, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "grad_norm": 7.58541202545166, | |
| "learning_rate": 1.20785498489426e-05, | |
| "loss": 2.3098, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7251631617113851, | |
| "eval_cosine_accuracy": 0.9515196084976196, | |
| "eval_loss": 0.48958125710487366, | |
| "eval_runtime": 37.07, | |
| "eval_samples_per_second": 256.515, | |
| "eval_steps_per_second": 1.025, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0877447425670776, | |
| "grad_norm": 4.796350955963135, | |
| "learning_rate": 1.8120845921450153e-05, | |
| "loss": 1.8951, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0877447425670776, | |
| "eval_cosine_accuracy": 0.9584603905677795, | |
| "eval_loss": 0.4585486352443695, | |
| "eval_runtime": 37.6018, | |
| "eval_samples_per_second": 252.887, | |
| "eval_steps_per_second": 1.011, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4503263234227701, | |
| "grad_norm": 5.870883941650391, | |
| "learning_rate": 1.8959057259404747e-05, | |
| "loss": 2.1013, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.4503263234227701, | |
| "eval_cosine_accuracy": 0.9627721309661865, | |
| "eval_loss": 0.4440576136112213, | |
| "eval_runtime": 36.7641, | |
| "eval_samples_per_second": 258.649, | |
| "eval_steps_per_second": 1.034, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.8129079042784626, | |
| "grad_norm": 7.082819938659668, | |
| "learning_rate": 1.7449765825653423e-05, | |
| "loss": 1.3955, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.8129079042784626, | |
| "eval_cosine_accuracy": 0.9620359539985657, | |
| "eval_loss": 0.4221404790878296, | |
| "eval_runtime": 35.3504, | |
| "eval_samples_per_second": 268.993, | |
| "eval_steps_per_second": 1.075, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.1754894851341553, | |
| "grad_norm": 4.699057579040527, | |
| "learning_rate": 1.5938963589666113e-05, | |
| "loss": 1.5692, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.1754894851341553, | |
| "eval_cosine_accuracy": 0.9658218622207642, | |
| "eval_loss": 0.43071484565734863, | |
| "eval_runtime": 35.2189, | |
| "eval_samples_per_second": 269.997, | |
| "eval_steps_per_second": 1.079, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.5380710659898478, | |
| "grad_norm": 5.574090003967285, | |
| "learning_rate": 1.4429672155914791e-05, | |
| "loss": 1.5498, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.5380710659898478, | |
| "eval_cosine_accuracy": 0.9675044417381287, | |
| "eval_loss": 0.4103427529335022, | |
| "eval_runtime": 34.5343, | |
| "eval_samples_per_second": 275.35, | |
| "eval_steps_per_second": 1.1, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.9006526468455403, | |
| "grad_norm": 6.49234676361084, | |
| "learning_rate": 1.2918869919927484e-05, | |
| "loss": 1.0831, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.9006526468455403, | |
| "eval_cosine_accuracy": 0.9663476943969727, | |
| "eval_loss": 0.3991580605506897, | |
| "eval_runtime": 34.1907, | |
| "eval_samples_per_second": 278.116, | |
| "eval_steps_per_second": 1.111, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.2632342277012327, | |
| "grad_norm": 4.949916839599609, | |
| "learning_rate": 1.1409578486176161e-05, | |
| "loss": 1.553, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.2632342277012327, | |
| "eval_cosine_accuracy": 0.9682406187057495, | |
| "eval_loss": 0.40829211473464966, | |
| "eval_runtime": 35.8733, | |
| "eval_samples_per_second": 265.072, | |
| "eval_steps_per_second": 1.059, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.625815808556925, | |
| "grad_norm": 6.085237979888916, | |
| "learning_rate": 9.89877625018885e-06, | |
| "loss": 1.2422, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.625815808556925, | |
| "eval_cosine_accuracy": 0.9673992991447449, | |
| "eval_loss": 0.40137091279029846, | |
| "eval_runtime": 35.6433, | |
| "eval_samples_per_second": 266.782, | |
| "eval_steps_per_second": 1.066, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.9883973894126177, | |
| "grad_norm": 6.651495456695557, | |
| "learning_rate": 8.389484816437529e-06, | |
| "loss": 0.9319, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.9883973894126177, | |
| "eval_cosine_accuracy": 0.9668734669685364, | |
| "eval_loss": 0.39452314376831055, | |
| "eval_runtime": 36.1394, | |
| "eval_samples_per_second": 263.12, | |
| "eval_steps_per_second": 1.051, | |
| "step": 11000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 16548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |