| { | |
| "best_metric": 0.15092426538467407, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007527003123706296, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015054006247412592, | |
| "grad_norm": 0.13432709872722626, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015054006247412592, | |
| "eval_loss": 0.2719675600528717, | |
| "eval_runtime": 5.8281, | |
| "eval_samples_per_second": 8.579, | |
| "eval_steps_per_second": 1.201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030108012494825184, | |
| "grad_norm": 0.13893114030361176, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.2357, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00045162018742237776, | |
| "grad_norm": 0.23538532853126526, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.2321, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006021602498965037, | |
| "grad_norm": 0.12552545964717865, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.153, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007527003123706296, | |
| "grad_norm": 0.12770973145961761, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2248, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009032403748447555, | |
| "grad_norm": 0.13605402410030365, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.201, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010537804373188814, | |
| "grad_norm": 0.1637810617685318, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.2183, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012043204997930074, | |
| "grad_norm": 0.12221050262451172, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.124, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013548605622671333, | |
| "grad_norm": 0.1582375317811966, | |
| "learning_rate": 0.00027, | |
| "loss": 0.162, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015054006247412592, | |
| "grad_norm": 0.13441474735736847, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1341, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016559406872153851, | |
| "grad_norm": 0.17374110221862793, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.2062, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001806480749689511, | |
| "grad_norm": 0.14382176101207733, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.1631, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001957020812163637, | |
| "grad_norm": 0.11867301911115646, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.1372, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002107560874637763, | |
| "grad_norm": 0.10297456383705139, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.1205, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002258100937111889, | |
| "grad_norm": 0.13378922641277313, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.173, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0024086409995860147, | |
| "grad_norm": 0.2846575081348419, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.2639, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0025591810620601407, | |
| "grad_norm": 0.21519090235233307, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.2581, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0027097211245342666, | |
| "grad_norm": 0.19943968951702118, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.2171, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0028602611870083925, | |
| "grad_norm": 0.20476272702217102, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3608, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0030108012494825184, | |
| "grad_norm": 0.18420757353305817, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.2178, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0031613413119566443, | |
| "grad_norm": 0.1748962551355362, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.2517, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0033118813744307703, | |
| "grad_norm": 0.20323532819747925, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.2238, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003462421436904896, | |
| "grad_norm": 0.2342359721660614, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2862, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003612961499379022, | |
| "grad_norm": 0.14597725868225098, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.1902, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003763501561853148, | |
| "grad_norm": 0.1760072559118271, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.2673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003763501561853148, | |
| "eval_loss": 0.1731989085674286, | |
| "eval_runtime": 5.8861, | |
| "eval_samples_per_second": 8.495, | |
| "eval_steps_per_second": 1.189, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003914041624327274, | |
| "grad_norm": 0.16469714045524597, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.2375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0040645816868014, | |
| "grad_norm": 0.1807279884815216, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.2787, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004215121749275526, | |
| "grad_norm": 0.1720961630344391, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.2626, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004365661811749652, | |
| "grad_norm": 0.17341332137584686, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.2325, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004516201874223778, | |
| "grad_norm": 0.16063857078552246, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.2144, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0046667419366979036, | |
| "grad_norm": 0.166489839553833, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.2199, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0048172819991720295, | |
| "grad_norm": 0.1735871136188507, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.2436, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004967822061646155, | |
| "grad_norm": 0.17148464918136597, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.2547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005118362124120281, | |
| "grad_norm": 0.17381110787391663, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.2313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005268902186594407, | |
| "grad_norm": 0.19464297592639923, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.2857, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005419442249068533, | |
| "grad_norm": 0.17032398283481598, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.2546, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005569982311542659, | |
| "grad_norm": 0.190896674990654, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.2831, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005720522374016785, | |
| "grad_norm": 0.24636401236057281, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.3094, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005871062436490911, | |
| "grad_norm": 0.17670078575611115, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.2858, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006021602498965037, | |
| "grad_norm": 0.23208720982074738, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.3023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006172142561439163, | |
| "grad_norm": 0.22071202099323273, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.3636, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006322682623913289, | |
| "grad_norm": 0.19284580647945404, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.2341, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006473222686387415, | |
| "grad_norm": 0.20681974291801453, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.2126, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0066237627488615405, | |
| "grad_norm": 0.22657203674316406, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2376, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0067743028113356665, | |
| "grad_norm": 0.2658374309539795, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2796, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006924842873809792, | |
| "grad_norm": 0.19090871512889862, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.1877, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007075382936283918, | |
| "grad_norm": 0.2513241767883301, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.2573, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007225922998758044, | |
| "grad_norm": 0.29451292753219604, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.264, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00737646306123217, | |
| "grad_norm": 0.2619107663631439, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.2481, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007527003123706296, | |
| "grad_norm": 0.3190884590148926, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.2778, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007527003123706296, | |
| "eval_loss": 0.15092426538467407, | |
| "eval_runtime": 5.883, | |
| "eval_samples_per_second": 8.499, | |
| "eval_steps_per_second": 1.19, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.0054853763072e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |