| { | |
| "best_metric": 0.7366423606872559, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2736914129319193, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005473828258638385, | |
| "grad_norm": 80.21852111816406, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005473828258638385, | |
| "eval_loss": 12.75658893585205, | |
| "eval_runtime": 83.0748, | |
| "eval_samples_per_second": 14.818, | |
| "eval_steps_per_second": 1.854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01094765651727677, | |
| "grad_norm": 78.58786010742188, | |
| "learning_rate": 0.0001, | |
| "loss": 10.76, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016421484775915155, | |
| "grad_norm": 31.18596839904785, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.1443, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02189531303455354, | |
| "grad_norm": 57.82615280151367, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.6021, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027369141293191925, | |
| "grad_norm": 21.90471076965332, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.4739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03284296955183031, | |
| "grad_norm": 27.173906326293945, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8579, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0383167978104687, | |
| "grad_norm": 30.951807022094727, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.1034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04379062606910708, | |
| "grad_norm": 68.20462036132812, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.2752, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04926445432774547, | |
| "grad_norm": 100.14580535888672, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.3939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05473828258638385, | |
| "grad_norm": 129.48590087890625, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.7986, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06021211084502224, | |
| "grad_norm": 110.82846069335938, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.3033, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06568593910366062, | |
| "grad_norm": 72.98750305175781, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.3745, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07115976736229901, | |
| "grad_norm": 54.32399368286133, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.1847, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0766335956209374, | |
| "grad_norm": 30.086524963378906, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8005, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08210742387957577, | |
| "grad_norm": 20.039278030395508, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08758125213821416, | |
| "grad_norm": 18.342777252197266, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09305508039685255, | |
| "grad_norm": 14.00782299041748, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.496, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09852890865549094, | |
| "grad_norm": 9.570558547973633, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4343, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10400273691412931, | |
| "grad_norm": 6.4017462730407715, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3559, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1094765651727677, | |
| "grad_norm": 23.88624382019043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11495039343140609, | |
| "grad_norm": 27.678808212280273, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0919, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12042422169004448, | |
| "grad_norm": 40.224674224853516, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4092, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12589804994868287, | |
| "grad_norm": 38.322757720947266, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4436, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13137187820732124, | |
| "grad_norm": 36.773887634277344, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.2339, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13684570646595964, | |
| "grad_norm": 33.566959381103516, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0319, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13684570646595964, | |
| "eval_loss": 0.8193092346191406, | |
| "eval_runtime": 83.0842, | |
| "eval_samples_per_second": 14.816, | |
| "eval_steps_per_second": 1.854, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14231953472459802, | |
| "grad_norm": 9.52985954284668, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4696, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1477933629832364, | |
| "grad_norm": 8.148707389831543, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4566, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1532671912418748, | |
| "grad_norm": 7.2753167152404785, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15874101950051317, | |
| "grad_norm": 6.7363362312316895, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16421484775915154, | |
| "grad_norm": 6.560089111328125, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3864, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16968867601778995, | |
| "grad_norm": 5.433276653289795, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3603, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17516250427642832, | |
| "grad_norm": 4.504647731781006, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3751, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18063633253506672, | |
| "grad_norm": 29.756072998046875, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2571, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1861101607937051, | |
| "grad_norm": 21.17481231689453, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3568, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19158398905234347, | |
| "grad_norm": 25.06121063232422, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19705781731098188, | |
| "grad_norm": 26.118518829345703, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5774, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 25.818099975585938, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20800547382825862, | |
| "grad_norm": 10.016300201416016, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7467, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21347930208689703, | |
| "grad_norm": 4.078773021697998, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3262, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2189531303455354, | |
| "grad_norm": 3.9033899307250977, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3171, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2244269586041738, | |
| "grad_norm": 4.623664379119873, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3126, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22990078686281218, | |
| "grad_norm": 3.3982760906219482, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3121, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23537461512145055, | |
| "grad_norm": 3.1137397289276123, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3226, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.24084844338008896, | |
| "grad_norm": 3.218012571334839, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3051, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.24632227163872733, | |
| "grad_norm": 16.81735610961914, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8468, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.25179609989736573, | |
| "grad_norm": 32.98430633544922, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2786, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2572699281560041, | |
| "grad_norm": 22.147462844848633, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2577, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2627437564146425, | |
| "grad_norm": 24.14130973815918, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2225, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2682175846732809, | |
| "grad_norm": 23.990203857421875, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2855, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2736914129319193, | |
| "grad_norm": 23.418981552124023, | |
| "learning_rate": 0.0, | |
| "loss": 1.2908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2736914129319193, | |
| "eval_loss": 0.7366423606872559, | |
| "eval_runtime": 83.0375, | |
| "eval_samples_per_second": 14.825, | |
| "eval_steps_per_second": 1.855, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |