| { | |
| "best_metric": 11.009994506835938, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.45146726862302483, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 3.750006675720215, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0929, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "eval_loss": 11.096587181091309, | |
| "eval_runtime": 0.8114, | |
| "eval_samples_per_second": 919.384, | |
| "eval_steps_per_second": 115.847, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 4.8399176597595215, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0941, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 5.616316318511963, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.0924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03611738148984198, | |
| "grad_norm": 5.4299516677856445, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.0915, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 5.6426496505737305, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.0885, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05417607223476298, | |
| "grad_norm": 5.4403157234191895, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.0865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06320541760722348, | |
| "grad_norm": 6.042210578918457, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.0802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07223476297968397, | |
| "grad_norm": 6.877292156219482, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.0769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08126410835214447, | |
| "grad_norm": 7.701770305633545, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.0701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 8.907994270324707, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.0631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09932279909706546, | |
| "grad_norm": 10.842832565307617, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.0523, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10835214446952596, | |
| "grad_norm": 12.793913841247559, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.0402, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11738148984198646, | |
| "grad_norm": 8.947713851928711, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.0511, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12641083521444696, | |
| "grad_norm": 4.386719226837158, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0687, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13544018058690746, | |
| "grad_norm": 5.060362339019775, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.0608, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14446952595936793, | |
| "grad_norm": 4.53698205947876, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.0622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15349887133182843, | |
| "grad_norm": 4.828124523162842, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.058, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16252821670428894, | |
| "grad_norm": 4.844457626342773, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.0532, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17155756207674944, | |
| "grad_norm": 4.8259758949279785, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.0529, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18058690744920994, | |
| "grad_norm": 5.085660934448242, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.0476, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18961625282167044, | |
| "grad_norm": 5.966355323791504, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.0382, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1986455981941309, | |
| "grad_norm": 6.541262149810791, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.0309, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2076749435665914, | |
| "grad_norm": 8.057042121887207, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.0132, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21670428893905191, | |
| "grad_norm": 9.53342342376709, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.9933, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "grad_norm": 11.74023151397705, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.976, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "eval_loss": 11.027515411376953, | |
| "eval_runtime": 0.814, | |
| "eval_samples_per_second": 916.41, | |
| "eval_steps_per_second": 115.473, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23476297968397292, | |
| "grad_norm": 3.8216607570648193, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0528, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24379232505643342, | |
| "grad_norm": 4.446141242980957, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.0429, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2528216704288939, | |
| "grad_norm": 4.9208245277404785, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.0356, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2618510158013544, | |
| "grad_norm": 4.09058141708374, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.0414, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2708803611738149, | |
| "grad_norm": 4.733359336853027, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.0324, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2799097065462754, | |
| "grad_norm": 4.318568706512451, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.0351, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28893905191873587, | |
| "grad_norm": 4.726495742797852, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.0296, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2979683972911964, | |
| "grad_norm": 5.066720962524414, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.0244, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30699774266365687, | |
| "grad_norm": 5.5661749839782715, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.0142, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3160270880361174, | |
| "grad_norm": 6.597118854522705, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.0002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32505643340857787, | |
| "grad_norm": 8.559455871582031, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.9691, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3340857787810384, | |
| "grad_norm": 9.815827369689941, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.9537, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3431151241534989, | |
| "grad_norm": 7.0843892097473145, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.9942, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35214446952595935, | |
| "grad_norm": 3.887183904647827, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.0425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3611738148984199, | |
| "grad_norm": 4.052178859710693, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.0384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37020316027088035, | |
| "grad_norm": 4.703183650970459, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.0254, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3792325056433409, | |
| "grad_norm": 4.300675868988037, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.0295, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38826185101580135, | |
| "grad_norm": 4.41107702255249, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.0304, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3972911963882618, | |
| "grad_norm": 4.380729675292969, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.0285, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40632054176072235, | |
| "grad_norm": 4.796936988830566, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.0226, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4153498871331828, | |
| "grad_norm": 5.204959392547607, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.0148, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42437923250564336, | |
| "grad_norm": 6.0904412269592285, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.0041, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43340857787810383, | |
| "grad_norm": 6.825149059295654, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.9894, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.44243792325056436, | |
| "grad_norm": 8.704109191894531, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.9616, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "grad_norm": 10.714920043945312, | |
| "learning_rate": 0.0, | |
| "loss": 10.9407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45146726862302483, | |
| "eval_loss": 11.009994506835938, | |
| "eval_runtime": 0.8089, | |
| "eval_samples_per_second": 922.276, | |
| "eval_steps_per_second": 116.212, | |
| "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": 4214512680960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |