| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 11.52, | |
| "eval_steps": 500, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.9926958680152893, | |
| "learning_rate": 0.00019444444444444446, | |
| "loss": 9.5849, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.7527631521224976, | |
| "learning_rate": 0.00018888888888888888, | |
| "loss": 9.1705, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 2.0137224197387695, | |
| "learning_rate": 0.00018333333333333334, | |
| "loss": 8.4125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.948047399520874, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 7.9081, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.1467063426971436, | |
| "learning_rate": 0.00017222222222222224, | |
| "loss": 7.6057, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.0256859064102173, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 7.4069, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.2744684219360352, | |
| "learning_rate": 0.0001611111111111111, | |
| "loss": 7.3171, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 1.0262680053710938, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 7.2517, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.5943800210952759, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 7.1989, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.7326172590255737, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 7.1975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 0.5042484998703003, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 7.1582, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 0.512372612953186, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 7.1793, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 0.5498717427253723, | |
| "learning_rate": 0.00012777777777777776, | |
| "loss": 7.1182, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 0.5042092800140381, | |
| "learning_rate": 0.00012222222222222224, | |
| "loss": 7.1492, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.4820415675640106, | |
| "learning_rate": 0.00011666666666666668, | |
| "loss": 7.0726, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "grad_norm": 0.5835886597633362, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 7.1349, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "grad_norm": 0.35386550426483154, | |
| "learning_rate": 0.00010555555555555557, | |
| "loss": 7.0469, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "grad_norm": 0.5533877015113831, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0824, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "grad_norm": 0.6554893851280212, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 7.0484, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 0.3372606337070465, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 7.0252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "grad_norm": 0.299753338098526, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 7.0648, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "grad_norm": 0.35728025436401367, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 7.1132, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "grad_norm": 0.29526084661483765, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 7.0196, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "grad_norm": 0.42963483929634094, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.0818, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.2951211929321289, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 7.0431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "grad_norm": 0.4070325791835785, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 6.9709, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "grad_norm": 0.2796075642108917, | |
| "learning_rate": 5e-05, | |
| "loss": 7.0826, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "grad_norm": 0.37583762407302856, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 7.0513, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "grad_norm": 0.4634278416633606, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 7.0616, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 0.45491114258766174, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 7.0114, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "grad_norm": 0.5008836388587952, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 7.058, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "grad_norm": 0.2694868743419647, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 6.9724, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "grad_norm": 0.2757045030593872, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 7.0447, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "grad_norm": 0.336161732673645, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 7.032, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 0.2434120923280716, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 7.0543, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "grad_norm": 0.37180185317993164, | |
| "learning_rate": 0.0, | |
| "loss": 7.038, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "step": 72, | |
| "total_flos": 279672397179648.0, | |
| "train_loss": 7.299143155415853, | |
| "train_runtime": 353.7388, | |
| "train_samples_per_second": 3.392, | |
| "train_steps_per_second": 0.204 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 72, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 279672397179648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |