| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7451564828614009, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029806259314456036, | |
| "grad_norm": 0.22671940922737122, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3506, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05961251862891207, | |
| "grad_norm": 0.05189573019742966, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8372, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08941877794336811, | |
| "grad_norm": 0.049646440893411636, | |
| "learning_rate": 0.0001999871938117722, | |
| "loss": 0.7053, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11922503725782414, | |
| "grad_norm": 0.04605806618928909, | |
| "learning_rate": 0.0001998847639849245, | |
| "loss": 0.5957, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14903129657228018, | |
| "grad_norm": 0.04606040194630623, | |
| "learning_rate": 0.0001996800092633612, | |
| "loss": 0.5457, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17883755588673622, | |
| "grad_norm": 0.03791499882936478, | |
| "learning_rate": 0.0001993731394038509, | |
| "loss": 0.5301, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20864381520119224, | |
| "grad_norm": 0.047940950840711594, | |
| "learning_rate": 0.0001989644687729177, | |
| "loss": 0.5223, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23845007451564829, | |
| "grad_norm": 0.0519738644361496, | |
| "learning_rate": 0.0001984544160247949, | |
| "loss": 0.5117, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.26825633383010433, | |
| "grad_norm": 0.04569224268198013, | |
| "learning_rate": 0.00019784350367254322, | |
| "loss": 0.5181, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.29806259314456035, | |
| "grad_norm": 0.045780543237924576, | |
| "learning_rate": 0.0001971323575527731, | |
| "loss": 0.5168, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 0.046496499329805374, | |
| "learning_rate": 0.0001963217061845192, | |
| "loss": 0.5051, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.35767511177347244, | |
| "grad_norm": 0.04850991442799568, | |
| "learning_rate": 0.00019541238002292394, | |
| "loss": 0.5083, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.38748137108792846, | |
| "grad_norm": 0.046593230217695236, | |
| "learning_rate": 0.00019440531060849504, | |
| "loss": 0.5066, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4172876304023845, | |
| "grad_norm": 0.050816215574741364, | |
| "learning_rate": 0.00019330152961280765, | |
| "loss": 0.5021, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.44709388971684055, | |
| "grad_norm": 0.0533340722322464, | |
| "learning_rate": 0.00019210216778162994, | |
| "loss": 0.5017, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47690014903129657, | |
| "grad_norm": 0.10607749223709106, | |
| "learning_rate": 0.00019080845377655352, | |
| "loss": 0.4996, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5067064083457526, | |
| "grad_norm": 0.054169464856386185, | |
| "learning_rate": 0.00018942171291631653, | |
| "loss": 0.5014, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5365126676602087, | |
| "grad_norm": 0.047340892255306244, | |
| "learning_rate": 0.000187943365819108, | |
| "loss": 0.4988, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5663189269746647, | |
| "grad_norm": 0.04948943480849266, | |
| "learning_rate": 0.00018637492694724466, | |
| "loss": 0.4975, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5961251862891207, | |
| "grad_norm": 0.04684118553996086, | |
| "learning_rate": 0.00018471800305571129, | |
| "loss": 0.4961, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6259314456035767, | |
| "grad_norm": 0.04512176662683487, | |
| "learning_rate": 0.00018297429154615338, | |
| "loss": 0.4956, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 0.05711393430829048, | |
| "learning_rate": 0.00018114557872800905, | |
| "loss": 0.4944, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6855439642324889, | |
| "grad_norm": 0.05339927598834038, | |
| "learning_rate": 0.000179233737988561, | |
| "loss": 0.4922, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7153502235469449, | |
| "grad_norm": 0.04622140899300575, | |
| "learning_rate": 0.00017724072787378333, | |
| "loss": 0.4846, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7451564828614009, | |
| "grad_norm": 0.0447109080851078, | |
| "learning_rate": 0.00017516859008194938, | |
| "loss": 0.4855, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 2013, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.84201450094592e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |