| { | |
| "best_metric": 1.3316872119903564, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2598870056497176, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 0.44638949632644653, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "eval_loss": 1.8486380577087402, | |
| "eval_runtime": 2.6606, | |
| "eval_samples_per_second": 56.378, | |
| "eval_steps_per_second": 7.141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 0.6294108033180237, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6111, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.6636074185371399, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 0.650401771068573, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7914, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 0.7133181691169739, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7302, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.3775063157081604, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5634, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 0.31381529569625854, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.484, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 0.43298181891441345, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4775, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.6578243374824524, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4816, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 1.1834920644760132, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 1.7032532691955566, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4201, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.25004395842552185, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4841, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 0.2866630256175995, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3962, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 0.6441053748130798, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3796, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.2238999605178833, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.3343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 0.8174284100532532, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.768361581920904, | |
| "grad_norm": 0.1801910400390625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4167, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.23991882801055908, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8587570621468926, | |
| "grad_norm": 0.3171876072883606, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 0.4910401701927185, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.6115542650222778, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3144, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 0.7648242115974426, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3021, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.03954802259887, | |
| "grad_norm": 0.49429404735565186, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.6061, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.2421720325946808, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3316, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "grad_norm": 0.25602591037750244, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "eval_loss": 1.3445146083831787, | |
| "eval_runtime": 2.654, | |
| "eval_samples_per_second": 56.518, | |
| "eval_steps_per_second": 7.159, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1751412429378532, | |
| "grad_norm": 0.2728276550769806, | |
| "learning_rate": 5e-05, | |
| "loss": 1.307, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.3243846893310547, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2456, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2655367231638417, | |
| "grad_norm": 0.19411033391952515, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2509, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.310734463276836, | |
| "grad_norm": 0.1757993847131729, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.5307, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.21353618800640106, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4011299435028248, | |
| "grad_norm": 0.2679908871650696, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3144, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4463276836158192, | |
| "grad_norm": 0.31348928809165955, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2523, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.2946011424064636, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2485, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.536723163841808, | |
| "grad_norm": 0.15832407772541046, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3634, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5819209039548023, | |
| "grad_norm": 0.17590704560279846, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3351, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.2035454660654068, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3247, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.672316384180791, | |
| "grad_norm": 0.2129197120666504, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2981, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7175141242937855, | |
| "grad_norm": 0.29245874285697937, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 0.17280784249305725, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.807909604519774, | |
| "grad_norm": 0.15356288850307465, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8531073446327684, | |
| "grad_norm": 0.1719873696565628, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3178, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.19485509395599365, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.303, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.943502824858757, | |
| "grad_norm": 0.25505155324935913, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2617, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9887005649717513, | |
| "grad_norm": 0.36434733867645264, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2443, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.4829481542110443, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.5418, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.07909604519774, | |
| "grad_norm": 0.14236965775489807, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.333, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1242937853107344, | |
| "grad_norm": 0.17663514614105225, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3061, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.20408064126968384, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2736, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.214689265536723, | |
| "grad_norm": 0.2776390314102173, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2458, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "grad_norm": 0.1917027235031128, | |
| "learning_rate": 0.0, | |
| "loss": 1.0958, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "eval_loss": 1.3316872119903564, | |
| "eval_runtime": 2.6518, | |
| "eval_samples_per_second": 56.565, | |
| "eval_steps_per_second": 7.165, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |