| { | |
| "best_metric": 2.4238104820251465, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012189918937039069, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024379837874078137, | |
| "grad_norm": 0.7880333065986633, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024379837874078137, | |
| "eval_loss": 2.817047119140625, | |
| "eval_runtime": 170.6978, | |
| "eval_samples_per_second": 10.117, | |
| "eval_steps_per_second": 5.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00048759675748156274, | |
| "grad_norm": 0.9518876075744629, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4162, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007313951362223441, | |
| "grad_norm": 1.040359377861023, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 2.4627, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009751935149631255, | |
| "grad_norm": 1.2321381568908691, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 2.3829, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012189918937039069, | |
| "grad_norm": 1.4454079866409302, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 2.5894, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014627902724446882, | |
| "grad_norm": 1.4295002222061157, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.4868, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017065886511854697, | |
| "grad_norm": 1.400195598602295, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 2.7311, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001950387029926251, | |
| "grad_norm": 1.2690297365188599, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.5423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0021941854086670325, | |
| "grad_norm": 1.1994316577911377, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 2.2934, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024379837874078138, | |
| "grad_norm": 1.305603265762329, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.3459, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002681782166148595, | |
| "grad_norm": 1.228868007659912, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.3414, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029255805448893763, | |
| "grad_norm": 1.3673356771469116, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.3696, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003169378923630158, | |
| "grad_norm": 1.4410384893417358, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 2.5193, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0034131773023709394, | |
| "grad_norm": 1.3858963251113892, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.4366, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0036569756811117207, | |
| "grad_norm": 1.4355295896530151, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 2.5017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003900774059852502, | |
| "grad_norm": 1.4359281063079834, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 2.2762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004144572438593283, | |
| "grad_norm": 1.6476869583129883, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.5998, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004388370817334065, | |
| "grad_norm": 1.595936894416809, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.3624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004632169196074846, | |
| "grad_norm": 1.6734445095062256, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 2.3356, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0048759675748156275, | |
| "grad_norm": 1.562049388885498, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.3303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005119765953556409, | |
| "grad_norm": 1.8779476881027222, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 2.8601, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00536356433229719, | |
| "grad_norm": 1.7535594701766968, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 2.261, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005607362711037972, | |
| "grad_norm": 1.8804701566696167, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.2453, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005851161089778753, | |
| "grad_norm": 2.1846208572387695, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.0311, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006094959468519534, | |
| "grad_norm": 2.3699631690979004, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.2299, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006094959468519534, | |
| "eval_loss": 2.5090396404266357, | |
| "eval_runtime": 171.9027, | |
| "eval_samples_per_second": 10.046, | |
| "eval_steps_per_second": 5.026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006338757847260316, | |
| "grad_norm": 1.9765174388885498, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5108, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006582556226001097, | |
| "grad_norm": 2.027369737625122, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 2.5258, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006826354604741879, | |
| "grad_norm": 2.7139859199523926, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.4354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00707015298348266, | |
| "grad_norm": 2.5592691898345947, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 2.3317, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007313951362223441, | |
| "grad_norm": 3.9472053050994873, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 2.2022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007557749740964222, | |
| "grad_norm": 2.6229476928710938, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 2.5237, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007801548119705004, | |
| "grad_norm": 2.831041097640991, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.228, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008045346498445785, | |
| "grad_norm": 2.713304042816162, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 2.0782, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008289144877186566, | |
| "grad_norm": 3.9535391330718994, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.0093, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008532943255927348, | |
| "grad_norm": 4.031512260437012, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.1973, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00877674163466813, | |
| "grad_norm": 3.933284282684326, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 2.6964, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009020540013408912, | |
| "grad_norm": 3.9383676052093506, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.0572, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009264338392149692, | |
| "grad_norm": 3.3363380432128906, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.7806, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009508136770890473, | |
| "grad_norm": 5.100573539733887, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.9677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009751935149631255, | |
| "grad_norm": 3.5059847831726074, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.2317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009995733528372037, | |
| "grad_norm": 5.321730613708496, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.1228, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010239531907112819, | |
| "grad_norm": 4.9000630378723145, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 2.4057, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010483330285853599, | |
| "grad_norm": 5.210293769836426, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.1145, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01072712866459438, | |
| "grad_norm": 4.690629959106445, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.3281, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010970927043335162, | |
| "grad_norm": 6.070462226867676, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.1419, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011214725422075944, | |
| "grad_norm": 7.646251201629639, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 3.2018, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011458523800816725, | |
| "grad_norm": 7.303621768951416, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 2.7462, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011702322179557505, | |
| "grad_norm": 5.764501571655273, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.3094, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011946120558298287, | |
| "grad_norm": 7.291966438293457, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.6926, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012189918937039069, | |
| "grad_norm": 13.362791061401367, | |
| "learning_rate": 0.0, | |
| "loss": 2.6087, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012189918937039069, | |
| "eval_loss": 2.4238104820251465, | |
| "eval_runtime": 172.7252, | |
| "eval_samples_per_second": 9.999, | |
| "eval_steps_per_second": 5.002, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 9677225695641600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |