| { | |
| "best_metric": 0.4051450192928314, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3215434083601286, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006430868167202572, | |
| "grad_norm": 1.1741244792938232, | |
| "learning_rate": 5e-05, | |
| "loss": 0.275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006430868167202572, | |
| "eval_loss": 1.5831472873687744, | |
| "eval_runtime": 13.6291, | |
| "eval_samples_per_second": 76.894, | |
| "eval_steps_per_second": 9.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012861736334405145, | |
| "grad_norm": 1.2310876846313477, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2784, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01929260450160772, | |
| "grad_norm": 0.7390908002853394, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.2904, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02572347266881029, | |
| "grad_norm": 0.8888787627220154, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3147, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03215434083601286, | |
| "grad_norm": 1.2557035684585571, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03858520900321544, | |
| "grad_norm": 1.3247170448303223, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2689, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04501607717041801, | |
| "grad_norm": 1.3375511169433594, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.263, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05144694533762058, | |
| "grad_norm": 1.3982009887695312, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.313, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05787781350482315, | |
| "grad_norm": 1.0606058835983276, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.089, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06430868167202572, | |
| "grad_norm": 1.1118919849395752, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0707395498392283, | |
| "grad_norm": 0.7233728766441345, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7097, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07717041800643087, | |
| "grad_norm": 0.8905820250511169, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8601, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08360128617363344, | |
| "grad_norm": 0.4793507158756256, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09003215434083602, | |
| "grad_norm": 0.453144371509552, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.209, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09646302250803858, | |
| "grad_norm": 0.36994224786758423, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.197, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10289389067524116, | |
| "grad_norm": 0.4986703097820282, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1649, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10932475884244373, | |
| "grad_norm": 0.5127981901168823, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3502, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1157556270096463, | |
| "grad_norm": 1.721727967262268, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9344, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12218649517684887, | |
| "grad_norm": 1.6984795331954956, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0396, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12861736334405144, | |
| "grad_norm": 0.9952530264854431, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13504823151125403, | |
| "grad_norm": 1.5977221727371216, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0747, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1414790996784566, | |
| "grad_norm": 1.39043128490448, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8697, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14790996784565916, | |
| "grad_norm": 1.1344813108444214, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8943, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15434083601286175, | |
| "grad_norm": 0.7542354464530945, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5706, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1607717041800643, | |
| "grad_norm": 1.0474071502685547, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1607717041800643, | |
| "eval_loss": 0.5616207122802734, | |
| "eval_runtime": 13.6879, | |
| "eval_samples_per_second": 76.564, | |
| "eval_steps_per_second": 9.57, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16720257234726688, | |
| "grad_norm": 0.32802271842956543, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2042, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17363344051446947, | |
| "grad_norm": 0.3432858884334564, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1963, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18006430868167203, | |
| "grad_norm": 0.47117841243743896, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1536, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1864951768488746, | |
| "grad_norm": 0.7523587346076965, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1858, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19292604501607716, | |
| "grad_norm": 1.9443529844284058, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5641, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19935691318327975, | |
| "grad_norm": 1.7204391956329346, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8415, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2057877813504823, | |
| "grad_norm": 1.6888691186904907, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8393, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.21221864951768488, | |
| "grad_norm": 1.8478753566741943, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7366, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21864951768488747, | |
| "grad_norm": 1.4996860027313232, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6738, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22508038585209003, | |
| "grad_norm": 1.2945411205291748, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6364, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2315112540192926, | |
| "grad_norm": 1.1487884521484375, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5501, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2379421221864952, | |
| "grad_norm": 0.9475870728492737, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3431, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24437299035369775, | |
| "grad_norm": 0.3858092725276947, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2235, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2508038585209003, | |
| "grad_norm": 0.3695223927497864, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1923, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2572347266881029, | |
| "grad_norm": 0.3529227674007416, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26366559485530544, | |
| "grad_norm": 0.6777685284614563, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1207, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.27009646302250806, | |
| "grad_norm": 0.6900791525840759, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1935, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2765273311897106, | |
| "grad_norm": 1.5598366260528564, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6328, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2829581993569132, | |
| "grad_norm": 1.3518791198730469, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6282, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28938906752411575, | |
| "grad_norm": 1.361425518989563, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6111, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2958199356913183, | |
| "grad_norm": 1.2370153665542603, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.488, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3022508038585209, | |
| "grad_norm": 1.0256456136703491, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5618, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3086816720257235, | |
| "grad_norm": 0.8804541826248169, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4539, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31511254019292606, | |
| "grad_norm": 0.9141364693641663, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4084, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3215434083601286, | |
| "grad_norm": 0.9475950598716736, | |
| "learning_rate": 0.0, | |
| "loss": 0.3759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3215434083601286, | |
| "eval_loss": 0.4051450192928314, | |
| "eval_runtime": 13.6625, | |
| "eval_samples_per_second": 76.707, | |
| "eval_steps_per_second": 9.588, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |