| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10425240054869685, | |
| "eval_steps": 500, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "grad_norm": 0.3216973543167114, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054869684499314125, | |
| "grad_norm": 0.3218615651130676, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.063, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 0.3071180582046509, | |
| "learning_rate": 6e-06, | |
| "loss": 2.0298, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": 0.30708086490631104, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9489, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013717421124828532, | |
| "grad_norm": 0.31064078211784363, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 0.35925883054733276, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.0963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019204389574759947, | |
| "grad_norm": 0.3267571032047272, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 2.0252, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": 0.30728623270988464, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.0108, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 0.2928607761859894, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.9542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "grad_norm": 0.30577352643013, | |
| "learning_rate": 2e-05, | |
| "loss": 2.017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03017832647462277, | |
| "grad_norm": 0.3024803102016449, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.982, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 0.28839072585105896, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.9217, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03566529492455418, | |
| "grad_norm": 0.2843893766403198, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.9608, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038408779149519894, | |
| "grad_norm": 0.2703002095222473, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.9696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 0.24636265635490417, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8818, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "grad_norm": 0.2405432015657425, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.975, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04663923182441701, | |
| "grad_norm": 0.24582137167453766, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.923, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 0.2504767179489136, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.9781, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05212620027434842, | |
| "grad_norm": 0.2394665777683258, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.8959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05486968449931413, | |
| "grad_norm": 0.24969030916690826, | |
| "learning_rate": 4e-05, | |
| "loss": 1.855, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 0.2694351077079773, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.9602, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06035665294924554, | |
| "grad_norm": 0.25622957944869995, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.8208, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06310013717421124, | |
| "grad_norm": 0.24535588920116425, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.7967, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 0.2737885117530823, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.7841, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06858710562414266, | |
| "grad_norm": 0.2646300196647644, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07133058984910837, | |
| "grad_norm": 0.2676407992839813, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.7359, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.2649776041507721, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.7205, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07681755829903979, | |
| "grad_norm": 0.296818345785141, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.696, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07956104252400549, | |
| "grad_norm": 0.31905728578567505, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.7261, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 0.4174517095088959, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6451, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0850480109739369, | |
| "grad_norm": 0.4545894265174866, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.5867, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0877914951989026, | |
| "grad_norm": 0.45722702145576477, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.5184, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09053497942386832, | |
| "grad_norm": 0.4953472316265106, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.4793, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09327846364883402, | |
| "grad_norm": 0.5516601800918579, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.4967, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09602194787379972, | |
| "grad_norm": 0.5295405983924866, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4445, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 0.3918333351612091, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.3956, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10150891632373114, | |
| "grad_norm": 0.4032560884952545, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.3773, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10425240054869685, | |
| "grad_norm": 0.30622419714927673, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.2721, | |
| "step": 38 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 364, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0847572478513971e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |