| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 5413, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018474043968224645, | |
| "grad_norm": 0.16043339669704437, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4188, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03694808793644929, | |
| "grad_norm": 0.24347032606601715, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.426, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05542213190467393, | |
| "grad_norm": 0.18731114268302917, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3901, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07389617587289858, | |
| "grad_norm": 0.28469762206077576, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.4127, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09237021984112322, | |
| "grad_norm": 0.38004377484321594, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3162, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11084426380934786, | |
| "grad_norm": 0.416911244392395, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.2961, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1293183077775725, | |
| "grad_norm": 0.5000600814819336, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.2668, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14779235174579716, | |
| "grad_norm": 0.5812170505523682, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.2452, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1662663957140218, | |
| "grad_norm": 0.6577287912368774, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.2119, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18474043968224643, | |
| "grad_norm": 0.5899447798728943, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2027, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2032144836504711, | |
| "grad_norm": 0.649770200252533, | |
| "learning_rate": 1.9974670975035436e-05, | |
| "loss": 2.1942, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.22168852761869573, | |
| "grad_norm": 0.6893395185470581, | |
| "learning_rate": 1.9898812212042866e-05, | |
| "loss": 2.1692, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.24016257158692036, | |
| "grad_norm": 0.6736598610877991, | |
| "learning_rate": 1.9772807996722613e-05, | |
| "loss": 2.1466, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.258636615555145, | |
| "grad_norm": 0.7326681017875671, | |
| "learning_rate": 1.9597296641857785e-05, | |
| "loss": 2.1331, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27711065952336966, | |
| "grad_norm": 0.6430918574333191, | |
| "learning_rate": 1.937316725374616e-05, | |
| "loss": 2.1098, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2955847034915943, | |
| "grad_norm": 0.7850959300994873, | |
| "learning_rate": 1.9101555228161095e-05, | |
| "loss": 2.1525, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.31405874745981893, | |
| "grad_norm": 0.8825465440750122, | |
| "learning_rate": 1.8783836498657935e-05, | |
| "loss": 2.0498, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3325327914280436, | |
| "grad_norm": 0.6566112637519836, | |
| "learning_rate": 1.842162056636294e-05, | |
| "loss": 2.1045, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.35100683539626826, | |
| "grad_norm": 1.326594352722168, | |
| "learning_rate": 1.8016742346554438e-05, | |
| "loss": 2.052, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.36948087936449286, | |
| "grad_norm": 0.833807110786438, | |
| "learning_rate": 1.757125287333986e-05, | |
| "loss": 2.1336, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3879549233327175, | |
| "grad_norm": 0.9102203845977783, | |
| "learning_rate": 1.7087408909516908e-05, | |
| "loss": 2.0542, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4064289673009422, | |
| "grad_norm": 0.7581120133399963, | |
| "learning_rate": 1.6567661514253307e-05, | |
| "loss": 2.0792, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.4249030112691668, | |
| "grad_norm": 0.8886149525642395, | |
| "learning_rate": 1.6014643626499038e-05, | |
| "loss": 2.0729, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.44337705523739146, | |
| "grad_norm": 1.0382766723632812, | |
| "learning_rate": 1.543115672703105e-05, | |
| "loss": 2.0693, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.4618510992056161, | |
| "grad_norm": 0.6785975694656372, | |
| "learning_rate": 1.482015664669798e-05, | |
| "loss": 2.0846, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.48032514317384073, | |
| "grad_norm": 0.8943729996681213, | |
| "learning_rate": 1.4184738592757442e-05, | |
| "loss": 2.0731, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4987991871420654, | |
| "grad_norm": 0.8952649831771851, | |
| "learning_rate": 1.352812146915967e-05, | |
| "loss": 2.0078, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.51727323111029, | |
| "grad_norm": 0.9793375730514526, | |
| "learning_rate": 1.2853631570207828e-05, | |
| "loss": 2.0606, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5357472750785147, | |
| "grad_norm": 0.9555624127388, | |
| "learning_rate": 1.2164685730199688e-05, | |
| "loss": 2.0384, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5542213190467393, | |
| "grad_norm": 0.8237419724464417, | |
| "learning_rate": 1.1464774014411416e-05, | |
| "loss": 2.0578, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5726953630149639, | |
| "grad_norm": 1.0005195140838623, | |
| "learning_rate": 1.0757442039107453e-05, | |
| "loss": 2.033, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5911694069831886, | |
| "grad_norm": 1.155673623085022, | |
| "learning_rate": 1.0046273010139933e-05, | |
| "loss": 2.0838, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6096434509514133, | |
| "grad_norm": 0.974641740322113, | |
| "learning_rate": 9.334869571126606e-06, | |
| "loss": 1.9982, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.6281174949196379, | |
| "grad_norm": 0.9602746367454529, | |
| "learning_rate": 8.626835553160812e-06, | |
| "loss": 1.9969, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6465915388878626, | |
| "grad_norm": 1.0560555458068848, | |
| "learning_rate": 7.925757718505905e-06, | |
| "loss": 2.0479, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6650655828560872, | |
| "grad_norm": 1.1622087955474854, | |
| "learning_rate": 7.235187590757096e-06, | |
| "loss": 2.0234, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.6835396268243118, | |
| "grad_norm": 1.1424589157104492, | |
| "learning_rate": 6.558623463515508e-06, | |
| "loss": 2.0209, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7020136707925365, | |
| "grad_norm": 1.2108582258224487, | |
| "learning_rate": 5.89949267871493e-06, | |
| "loss": 2.0022, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.7204877147607611, | |
| "grad_norm": 1.145391583442688, | |
| "learning_rate": 5.261134264376e-06, | |
| "loss": 2.0385, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7389617587289857, | |
| "grad_norm": 1.037288784980774, | |
| "learning_rate": 4.646782019741341e-06, | |
| "loss": 2.0347, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7574358026972104, | |
| "grad_norm": 0.7393826246261597, | |
| "learning_rate": 4.05954813347923e-06, | |
| "loss": 2.0283, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.775909846665435, | |
| "grad_norm": 0.8227554559707642, | |
| "learning_rate": 3.5024074179427013e-06, | |
| "loss": 1.9719, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.7943838906336597, | |
| "grad_norm": 1.2980815172195435, | |
| "learning_rate": 2.9781822393502733e-06, | |
| "loss": 2.0397, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8128579346018844, | |
| "grad_norm": 1.4079487323760986, | |
| "learning_rate": 2.489528220229076e-06, | |
| "loss": 1.9704, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.831331978570109, | |
| "grad_norm": 0.9588233232498169, | |
| "learning_rate": 2.0389207865489768e-06, | |
| "loss": 2.0161, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8498060225383336, | |
| "grad_norm": 0.9501762390136719, | |
| "learning_rate": 1.6286426276973566e-06, | |
| "loss": 2.025, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.8682800665065583, | |
| "grad_norm": 0.9268977046012878, | |
| "learning_rate": 1.2607721328198097e-06, | |
| "loss": 2.0091, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.8867541104747829, | |
| "grad_norm": 1.1910320520401, | |
| "learning_rate": 9.371728621060306e-07, | |
| "loss": 2.0051, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.9052281544430075, | |
| "grad_norm": 0.8244079351425171, | |
| "learning_rate": 6.594841063573099e-07, | |
| "loss": 1.9783, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.9237021984112322, | |
| "grad_norm": 0.8305772542953491, | |
| "learning_rate": 4.2911258265898814e-07, | |
| "loss": 1.9705, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9421762423794569, | |
| "grad_norm": 1.3943135738372803, | |
| "learning_rate": 2.472253082260456e-07, | |
| "loss": 1.9858, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.9606502863476815, | |
| "grad_norm": 1.1412353515625, | |
| "learning_rate": 1.1474368852145035e-07, | |
| "loss": 2.0018, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.9791243303159062, | |
| "grad_norm": 1.0674628019332886, | |
| "learning_rate": 3.233884959577327e-08, | |
| "loss": 2.0122, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.9975983742841308, | |
| "grad_norm": 1.0804530382156372, | |
| "learning_rate": 4.2823829348170866e-10, | |
| "loss": 2.0582, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 5413, | |
| "total_flos": 9.859643179008e+16, | |
| "train_loss": 2.0996591644456246, | |
| "train_runtime": 1436.8604, | |
| "train_samples_per_second": 7.534, | |
| "train_steps_per_second": 3.767 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5413, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.859643179008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |