| { | |
| "best_metric": 0.11645537614822388, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1429587482219061, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02275960170697013, | |
| "grad_norm": 1.7705003023147583, | |
| "learning_rate": 0.00015, | |
| "loss": 3.3287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02275960170697013, | |
| "eval_loss": 3.4932775497436523, | |
| "eval_runtime": 0.2913, | |
| "eval_samples_per_second": 171.665, | |
| "eval_steps_per_second": 44.633, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04551920341394026, | |
| "grad_norm": 1.6582751274108887, | |
| "learning_rate": 0.0003, | |
| "loss": 3.318, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06827880512091039, | |
| "grad_norm": 1.748265266418457, | |
| "learning_rate": 0.00029990993452998227, | |
| "loss": 3.3114, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09103840682788052, | |
| "grad_norm": 1.5232975482940674, | |
| "learning_rate": 0.00029963985829457943, | |
| "loss": 2.9468, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11379800853485064, | |
| "grad_norm": 1.5051178932189941, | |
| "learning_rate": 0.0002991901316573927, | |
| "loss": 2.7052, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13655761024182078, | |
| "grad_norm": 1.422306776046753, | |
| "learning_rate": 0.00029856135469013987, | |
| "loss": 2.3768, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1593172119487909, | |
| "grad_norm": 1.5374380350112915, | |
| "learning_rate": 0.0002977543663719779, | |
| "loss": 2.1616, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18207681365576103, | |
| "grad_norm": 1.8372466564178467, | |
| "learning_rate": 0.00029677024347005013, | |
| "loss": 2.0086, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20483641536273114, | |
| "grad_norm": 2.2954390048980713, | |
| "learning_rate": 0.0002956102991027524, | |
| "loss": 1.7581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22759601706970128, | |
| "grad_norm": 2.7270781993865967, | |
| "learning_rate": 0.0002942760809876348, | |
| "loss": 1.5204, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2503556187766714, | |
| "grad_norm": 2.2713541984558105, | |
| "learning_rate": 0.00029276936937627725, | |
| "loss": 1.2835, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.27311522048364156, | |
| "grad_norm": 2.338096857070923, | |
| "learning_rate": 0.000291092174678894, | |
| "loss": 1.1385, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2958748221906117, | |
| "grad_norm": 1.553781270980835, | |
| "learning_rate": 0.00028924673478183645, | |
| "loss": 0.9631, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3186344238975818, | |
| "grad_norm": 1.5467333793640137, | |
| "learning_rate": 0.0002872355120615748, | |
| "loss": 0.8275, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3413940256045519, | |
| "grad_norm": 1.656901240348816, | |
| "learning_rate": 0.00028506119009914, | |
| "loss": 0.7097, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.36415362731152207, | |
| "grad_norm": 1.358717679977417, | |
| "learning_rate": 0.000282726670099414, | |
| "loss": 0.6673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3869132290184922, | |
| "grad_norm": 0.8717578649520874, | |
| "learning_rate": 0.00028023506702004174, | |
| "loss": 0.4671, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4096728307254623, | |
| "grad_norm": 0.977169930934906, | |
| "learning_rate": 0.0002775897054151335, | |
| "loss": 0.4218, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.9587895274162292, | |
| "learning_rate": 0.00027479411499930134, | |
| "loss": 0.4066, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.45519203413940257, | |
| "grad_norm": 0.6970980167388916, | |
| "learning_rate": 0.00027185202593794927, | |
| "loss": 0.3582, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4779516358463727, | |
| "grad_norm": 0.7278751730918884, | |
| "learning_rate": 0.0002687673638701018, | |
| "loss": 0.3208, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5007112375533428, | |
| "grad_norm": 0.7912285327911377, | |
| "learning_rate": 0.00026554424467041055, | |
| "loss": 0.4071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5234708392603129, | |
| "grad_norm": 0.8546118140220642, | |
| "learning_rate": 0.00026218696895732944, | |
| "loss": 0.3329, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5462304409672831, | |
| "grad_norm": 0.4830358326435089, | |
| "learning_rate": 0.0002587000163547856, | |
| "loss": 0.3032, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5689900426742532, | |
| "grad_norm": 0.7155347466468811, | |
| "learning_rate": 0.0002550880395150023, | |
| "loss": 0.2946, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5689900426742532, | |
| "eval_loss": 0.2797185778617859, | |
| "eval_runtime": 0.2962, | |
| "eval_samples_per_second": 168.833, | |
| "eval_steps_per_second": 43.897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5917496443812233, | |
| "grad_norm": 0.5971561670303345, | |
| "learning_rate": 0.0002513558579104503, | |
| "loss": 0.2866, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6145092460881935, | |
| "grad_norm": 0.5399057269096375, | |
| "learning_rate": 0.00024750845140320964, | |
| "loss": 0.3, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6372688477951636, | |
| "grad_norm": 0.5159599781036377, | |
| "learning_rate": 0.00024355095360032364, | |
| "loss": 0.2229, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6600284495021337, | |
| "grad_norm": 0.36613932251930237, | |
| "learning_rate": 0.00023948864500401016, | |
| "loss": 0.2183, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6827880512091038, | |
| "grad_norm": 0.4476757049560547, | |
| "learning_rate": 0.00023532694596587055, | |
| "loss": 0.1993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.705547652916074, | |
| "grad_norm": 0.47915318608283997, | |
| "learning_rate": 0.00023107140945449652, | |
| "loss": 0.177, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7283072546230441, | |
| "grad_norm": 0.47024720907211304, | |
| "learning_rate": 0.0002267277136461262, | |
| "loss": 0.1281, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7510668563300142, | |
| "grad_norm": 0.43254679441452026, | |
| "learning_rate": 0.00022230165434823502, | |
| "loss": 0.2339, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7738264580369844, | |
| "grad_norm": 0.6018503904342651, | |
| "learning_rate": 0.00021779913726617102, | |
| "loss": 0.2309, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7965860597439545, | |
| "grad_norm": 0.42272430658340454, | |
| "learning_rate": 0.00021322617012315288, | |
| "loss": 0.1736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8193456614509246, | |
| "grad_norm": 0.4929526746273041, | |
| "learning_rate": 0.00020858885464414522, | |
| "loss": 0.1818, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.5257923007011414, | |
| "learning_rate": 0.00020389337841430707, | |
| "loss": 0.1759, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.32733604311943054, | |
| "learning_rate": 0.00019914600662287684, | |
| "loss": 0.1765, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.887624466571835, | |
| "grad_norm": 0.3499005138874054, | |
| "learning_rate": 0.00019435307370351017, | |
| "loss": 0.1172, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9103840682788051, | |
| "grad_norm": 0.32600706815719604, | |
| "learning_rate": 0.0001895209748822239, | |
| "loss": 0.1107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9331436699857752, | |
| "grad_norm": 0.3189937174320221, | |
| "learning_rate": 0.00018465615764422566, | |
| "loss": 0.134, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9559032716927454, | |
| "grad_norm": 0.26007068157196045, | |
| "learning_rate": 0.00017976511313101307, | |
| "loss": 0.1037, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9786628733997155, | |
| "grad_norm": 0.3448164463043213, | |
| "learning_rate": 0.00017485436747922248, | |
| "loss": 0.0882, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0064011379800855, | |
| "grad_norm": 0.28717777132987976, | |
| "learning_rate": 0.00016993047311278397, | |
| "loss": 0.2189, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0291607396870555, | |
| "grad_norm": 0.2990550994873047, | |
| "learning_rate": 0.000165, | |
| "loss": 0.1578, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0519203413940257, | |
| "grad_norm": 0.3317011594772339, | |
| "learning_rate": 0.00016006952688721603, | |
| "loss": 0.1449, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0746799431009957, | |
| "grad_norm": 0.31591519713401794, | |
| "learning_rate": 0.0001551456325207775, | |
| "loss": 0.1431, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.097439544807966, | |
| "grad_norm": 0.26354071497917175, | |
| "learning_rate": 0.00015023488686898698, | |
| "loss": 0.1444, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.120199146514936, | |
| "grad_norm": 0.2392982542514801, | |
| "learning_rate": 0.00014534384235577436, | |
| "loss": 0.1312, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1429587482219061, | |
| "grad_norm": 0.3284483551979065, | |
| "learning_rate": 0.0001404790251177761, | |
| "loss": 0.1079, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1429587482219061, | |
| "eval_loss": 0.11645537614822388, | |
| "eval_runtime": 0.2863, | |
| "eval_samples_per_second": 174.617, | |
| "eval_steps_per_second": 45.4, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 88, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.22140137734144e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |