| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6552006552006552, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013104013104013105, | |
| "grad_norm": 3.543196439743042, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013104013104013105, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.817, | |
| "eval_samples_per_second": 75.4, | |
| "eval_steps_per_second": 9.535, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02620802620802621, | |
| "grad_norm": 2.185093641281128, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1588, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03931203931203931, | |
| "grad_norm": 2.191917657852173, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05241605241605242, | |
| "grad_norm": 1.802222490310669, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0023, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06552006552006552, | |
| "grad_norm": 1.8301430940628052, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07862407862407862, | |
| "grad_norm": 2.621662139892578, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.067, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09172809172809172, | |
| "grad_norm": 2.933565378189087, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3266, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10483210483210484, | |
| "grad_norm": 5.475414276123047, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.352, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11793611793611794, | |
| "grad_norm": 3.636732578277588, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1737, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13104013104013104, | |
| "grad_norm": 2.8256919384002686, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 3.4781036376953125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2158, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15724815724815724, | |
| "grad_norm": 4.758241653442383, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0151, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17035217035217035, | |
| "grad_norm": 2.0737156867980957, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3831, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18345618345618345, | |
| "grad_norm": 2.2898342609405518, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4108, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19656019656019655, | |
| "grad_norm": 2.0651965141296387, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8827, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20966420966420968, | |
| "grad_norm": 1.6442537307739258, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5754, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22276822276822278, | |
| "grad_norm": 1.400604248046875, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5229, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23587223587223588, | |
| "grad_norm": 1.7442450523376465, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5699, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24897624897624898, | |
| "grad_norm": 1.6871769428253174, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4418, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2620802620802621, | |
| "grad_norm": 1.6878656148910522, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2751842751842752, | |
| "grad_norm": 2.397327423095703, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.268, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 2.2971067428588867, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3743, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3013923013923014, | |
| "grad_norm": 2.160508155822754, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6056, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3144963144963145, | |
| "grad_norm": 2.3705620765686035, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5989, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3276003276003276, | |
| "grad_norm": 3.6411032676696777, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9425, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3276003276003276, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8242, | |
| "eval_samples_per_second": 75.32, | |
| "eval_steps_per_second": 9.525, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3407043407043407, | |
| "grad_norm": 1.8005356788635254, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9829, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3538083538083538, | |
| "grad_norm": 1.772329568862915, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3669123669123669, | |
| "grad_norm": 1.5069606304168701, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.5007, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.38001638001638, | |
| "grad_norm": 1.6165857315063477, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1671, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3931203931203931, | |
| "grad_norm": 1.6595863103866577, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3591, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4062244062244062, | |
| "grad_norm": 1.8731105327606201, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0039, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41932841932841936, | |
| "grad_norm": 1.8856438398361206, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4461, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 1.9924148321151733, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1221, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44553644553644556, | |
| "grad_norm": 2.2074906826019287, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0594, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45864045864045866, | |
| "grad_norm": 2.3928334712982178, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1962, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47174447174447176, | |
| "grad_norm": 2.2513129711151123, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1857, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 2.4426679611206055, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1917, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49795249795249796, | |
| "grad_norm": 1.7712135314941406, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0161, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5110565110565111, | |
| "grad_norm": 1.5969468355178833, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.955, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5241605241605242, | |
| "grad_norm": 1.6872109174728394, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4407, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5372645372645373, | |
| "grad_norm": 1.7902907133102417, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2382, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5503685503685504, | |
| "grad_norm": 1.5357950925827026, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3056, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5634725634725635, | |
| "grad_norm": 1.6491217613220215, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1163, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 1.644583821296692, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3071, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5896805896805897, | |
| "grad_norm": 1.6915448904037476, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.078, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6027846027846028, | |
| "grad_norm": 1.5991367101669312, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9096, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6158886158886159, | |
| "grad_norm": 1.7828935384750366, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0314, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.628992628992629, | |
| "grad_norm": 1.9073837995529175, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0454, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6420966420966421, | |
| "grad_norm": 1.964453935623169, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0232, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6552006552006552, | |
| "grad_norm": 2.5052285194396973, | |
| "learning_rate": 0.0, | |
| "loss": 1.5223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6552006552006552, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8264, | |
| "eval_samples_per_second": 75.296, | |
| "eval_steps_per_second": 9.522, | |
| "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": 1 | |
| } | |
| }, | |
| "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 | |
| } | |