| { | |
| "best_metric": 2.800990581512451, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01597635499460798, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003195270998921596, | |
| "grad_norm": 0.4542631208896637, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 15.1568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003195270998921596, | |
| "eval_loss": 2.822023630142212, | |
| "eval_runtime": 886.3385, | |
| "eval_samples_per_second": 5.947, | |
| "eval_steps_per_second": 1.487, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006390541997843192, | |
| "grad_norm": 0.4103067219257355, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 15.4511, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009585812996764789, | |
| "grad_norm": 0.44541919231414795, | |
| "learning_rate": 1.5e-06, | |
| "loss": 12.3824, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012781083995686384, | |
| "grad_norm": 0.6393632292747498, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 15.0988, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001597635499460798, | |
| "grad_norm": 0.6381840109825134, | |
| "learning_rate": 2.5e-06, | |
| "loss": 15.25, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019171625993529577, | |
| "grad_norm": 0.7214181423187256, | |
| "learning_rate": 3e-06, | |
| "loss": 16.3453, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002236689699245117, | |
| "grad_norm": 0.8121290802955627, | |
| "learning_rate": 3.5e-06, | |
| "loss": 17.3123, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002556216799137277, | |
| "grad_norm": 0.7688579559326172, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 17.9848, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028757438990294364, | |
| "grad_norm": 0.8018252849578857, | |
| "learning_rate": 4.5e-06, | |
| "loss": 16.204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003195270998921596, | |
| "grad_norm": 0.8581808805465698, | |
| "learning_rate": 5e-06, | |
| "loss": 17.314, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035147980988137558, | |
| "grad_norm": 0.8556950092315674, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 16.6607, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0038343251987059154, | |
| "grad_norm": 1.0415091514587402, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 17.439, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004153852298598075, | |
| "grad_norm": 0.9096566438674927, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 17.4097, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004473379398490234, | |
| "grad_norm": 1.0269314050674438, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 17.4317, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004792906498382394, | |
| "grad_norm": 1.1478707790374756, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 18.5223, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005112433598274554, | |
| "grad_norm": 1.636509895324707, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 18.0751, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005431960698166713, | |
| "grad_norm": 1.154109001159668, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 17.521, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005751487798058873, | |
| "grad_norm": 1.0234571695327759, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 18.8366, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0060710148979510326, | |
| "grad_norm": 1.3324098587036133, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 19.0732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006390541997843192, | |
| "grad_norm": 1.424180030822754, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 19.0163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006710069097735352, | |
| "grad_norm": 1.2417484521865845, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 19.9384, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0070295961976275115, | |
| "grad_norm": 1.5843204259872437, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 18.4232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007349123297519671, | |
| "grad_norm": 1.378356695175171, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 19.6798, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007668650397411831, | |
| "grad_norm": 1.4657114744186401, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 19.7077, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00798817749730399, | |
| "grad_norm": 1.4137859344482422, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 19.1794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00830770459719615, | |
| "grad_norm": 1.708204746246338, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 20.172, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00862723169708831, | |
| "grad_norm": 1.3741956949234009, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 19.5121, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008946758796980469, | |
| "grad_norm": 1.672687292098999, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 19.3691, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009266285896872629, | |
| "grad_norm": 1.9943945407867432, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 17.0405, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009585812996764788, | |
| "grad_norm": 2.3718981742858887, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 17.6282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009905340096656948, | |
| "grad_norm": 2.2666637897491455, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 17.6547, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010224867196549107, | |
| "grad_norm": 2.4329729080200195, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 18.943, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010544394296441268, | |
| "grad_norm": 2.7743804454803467, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 19.7421, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010863921396333426, | |
| "grad_norm": 2.731886148452759, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 24.2004, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011183448496225585, | |
| "grad_norm": 2.7625598907470703, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 26.9592, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011502975596117746, | |
| "grad_norm": 3.5860679149627686, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 28.8936, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011822502696009905, | |
| "grad_norm": 2.9752390384674072, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 28.598, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012142029795902065, | |
| "grad_norm": 3.910142183303833, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 29.005, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012461556895794224, | |
| "grad_norm": 3.509363889694214, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 29.2251, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012781083995686384, | |
| "grad_norm": 4.890401840209961, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 29.8219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013100611095578543, | |
| "grad_norm": 4.316377639770508, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 29.8349, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013420138195470704, | |
| "grad_norm": 5.008350372314453, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 31.3168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013739665295362863, | |
| "grad_norm": 4.941371440887451, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 31.449, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014059192395255023, | |
| "grad_norm": 6.248507022857666, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 32.5496, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.014378719495147182, | |
| "grad_norm": 5.927119255065918, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 33.2277, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014698246595039342, | |
| "grad_norm": 6.774079322814941, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 33.6978, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.015017773694931501, | |
| "grad_norm": 7.833065986633301, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 34.0778, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015337300794823662, | |
| "grad_norm": 8.638693809509277, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 35.4129, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01565682789471582, | |
| "grad_norm": 10.667224884033203, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 38.1759, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01597635499460798, | |
| "grad_norm": 14.18898868560791, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 42.3519, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01597635499460798, | |
| "eval_loss": 2.800990581512451, | |
| "eval_runtime": 885.3579, | |
| "eval_samples_per_second": 5.954, | |
| "eval_steps_per_second": 1.489, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.3298703771107328e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |