| { | |
| "best_metric": 4.613088607788086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6802721088435374, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 27.515722274780273, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6836, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "eval_loss": 8.449374198913574, | |
| "eval_runtime": 9.0397, | |
| "eval_samples_per_second": 54.759, | |
| "eval_steps_per_second": 6.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 32.550697326660156, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3159, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 13.637520790100098, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1822, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 25.350894927978516, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 22.392393112182617, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.2888, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 6.79727840423584, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.7948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 7.612893581390381, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.6847, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 4.999279499053955, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.908, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 3.3941338062286377, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.6743, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 3.2951481342315674, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.45, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 3.8956491947174072, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.4729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 5.605069160461426, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.8887, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 4.416469097137451, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.9375, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 3.5549886226654053, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.393, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 3.4301156997680664, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.3768, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 2.7782843112945557, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.5796, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 2.676288366317749, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.5826, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 2.8562517166137695, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 2.6313741207122803, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.5512, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 2.268949508666992, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.7819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.595299243927002, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 5.0168, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 2.4830331802368164, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.9585, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 2.0794520378112793, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 5.0383, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 2.8583076000213623, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 5.3664, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 4.755614757537842, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 5.6709, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 4.725675582885742, | |
| "eval_runtime": 9.0392, | |
| "eval_samples_per_second": 54.762, | |
| "eval_steps_per_second": 6.859, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35374149659863946, | |
| "grad_norm": 2.5993564128875732, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8505, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 2.5245633125305176, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 4.1639, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.204711675643921, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 4.1353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3945578231292517, | |
| "grad_norm": 1.923013687133789, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.4266, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 2.102698564529419, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.3867, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4217687074829932, | |
| "grad_norm": 1.8343956470489502, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.4635, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43537414965986393, | |
| "grad_norm": 1.8821370601654053, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.4229, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 2.1628355979919434, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.9361, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46258503401360546, | |
| "grad_norm": 2.0924601554870605, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.9282, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 2.0800721645355225, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.8883, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 2.4742178916931152, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 5.0422, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5034013605442177, | |
| "grad_norm": 3.6025562286376953, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 5.6058, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5170068027210885, | |
| "grad_norm": 1.8626090288162231, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.4827, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 1.6383427381515503, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.8985, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 1.6859347820281982, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.021, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5578231292517006, | |
| "grad_norm": 1.714751124382019, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.2328, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.5772175788879395, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.3372, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5850340136054422, | |
| "grad_norm": 1.8678478002548218, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 4.3201, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5986394557823129, | |
| "grad_norm": 1.673134446144104, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.3886, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 2.0004281997680664, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.8627, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6258503401360545, | |
| "grad_norm": 2.623873472213745, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.8831, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6394557823129252, | |
| "grad_norm": 1.9565924406051636, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.9377, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 2.1026477813720703, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.9891, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.7066915035247803, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 5.4155, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 4.02397346496582, | |
| "learning_rate": 0.0, | |
| "loss": 5.9606, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "eval_loss": 4.613088607788086, | |
| "eval_runtime": 9.0406, | |
| "eval_samples_per_second": 54.753, | |
| "eval_steps_per_second": 6.858, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |