| { | |
| "best_metric": 0.4722478687763214, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22598870056497175, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004519774011299435, | |
| "grad_norm": 8.189549446105957, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004519774011299435, | |
| "eval_loss": 5.951687812805176, | |
| "eval_runtime": 45.2222, | |
| "eval_samples_per_second": 32.971, | |
| "eval_steps_per_second": 4.135, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00903954802259887, | |
| "grad_norm": 12.978795051574707, | |
| "learning_rate": 0.0001, | |
| "loss": 5.023, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013559322033898305, | |
| "grad_norm": 10.654461860656738, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.5711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01807909604519774, | |
| "grad_norm": 8.767965316772461, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3917, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022598870056497175, | |
| "grad_norm": 8.292922019958496, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8848, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02711864406779661, | |
| "grad_norm": 4.057251930236816, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2433, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031638418079096044, | |
| "grad_norm": 3.746001958847046, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0778, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03615819209039548, | |
| "grad_norm": 3.8420121669769287, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9294, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04067796610169491, | |
| "grad_norm": 2.5137362480163574, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6981, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 2.808502435684204, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6918, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04971751412429379, | |
| "grad_norm": 4.480010509490967, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0107, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05423728813559322, | |
| "grad_norm": 5.038733005523682, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2113, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05875706214689266, | |
| "grad_norm": 3.371286630630493, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8762, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06327683615819209, | |
| "grad_norm": 3.8310582637786865, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6748, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 3.792715549468994, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3205, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07231638418079096, | |
| "grad_norm": 4.308435916900635, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4917, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0768361581920904, | |
| "grad_norm": 2.934105157852173, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4651, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08135593220338982, | |
| "grad_norm": 2.135993242263794, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4288, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08587570621468926, | |
| "grad_norm": 2.0684380531311035, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4179, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 2.2669215202331543, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09491525423728814, | |
| "grad_norm": 1.2706658840179443, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3906, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09943502824858758, | |
| "grad_norm": 1.0730197429656982, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3677, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.103954802259887, | |
| "grad_norm": 1.1756868362426758, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4669, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10847457627118644, | |
| "grad_norm": 2.5567104816436768, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7847, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 3.0226149559020996, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "eval_loss": 0.5778371691703796, | |
| "eval_runtime": 45.286, | |
| "eval_samples_per_second": 32.924, | |
| "eval_steps_per_second": 4.129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11751412429378531, | |
| "grad_norm": 1.7103195190429688, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3885, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12203389830508475, | |
| "grad_norm": 2.540452480316162, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3325, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12655367231638417, | |
| "grad_norm": 2.0381650924682617, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2664, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1310734463276836, | |
| "grad_norm": 1.8808456659317017, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3471, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 1.5149118900299072, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3276, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1401129943502825, | |
| "grad_norm": 1.6971021890640259, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3439, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14463276836158193, | |
| "grad_norm": 1.2903318405151367, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.39, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14915254237288136, | |
| "grad_norm": 1.122199296951294, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3097, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1536723163841808, | |
| "grad_norm": 1.0199609994888306, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3251, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15819209039548024, | |
| "grad_norm": 1.3618215322494507, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.476, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16271186440677965, | |
| "grad_norm": 1.6055341958999634, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6691, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1672316384180791, | |
| "grad_norm": 2.307286024093628, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9103, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17175141242937852, | |
| "grad_norm": 1.8381061553955078, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6667, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17627118644067796, | |
| "grad_norm": 2.2784359455108643, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3198, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 1.9385861158370972, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18531073446327684, | |
| "grad_norm": 1.723340630531311, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2729, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18983050847457628, | |
| "grad_norm": 1.352947473526001, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3033, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1943502824858757, | |
| "grad_norm": 1.3377389907836914, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2928, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19887005649717515, | |
| "grad_norm": 1.2967225313186646, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2915, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 1.1458157300949097, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2949, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.207909604519774, | |
| "grad_norm": 1.1767059564590454, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3244, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21242937853107344, | |
| "grad_norm": 0.8545200824737549, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3141, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21694915254237288, | |
| "grad_norm": 1.389214038848877, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6378, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2214689265536723, | |
| "grad_norm": 1.9914606809616089, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7584, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 2.9483211040496826, | |
| "learning_rate": 0.0, | |
| "loss": 1.1446, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 0.4722478687763214, | |
| "eval_runtime": 45.2655, | |
| "eval_samples_per_second": 32.939, | |
| "eval_steps_per_second": 4.131, | |
| "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": 5.9736786926882e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |