| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026215755669157164, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3172, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2325, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0105, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9342, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0416, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9842, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001993103448275862, | |
| "loss": 1.0408, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019862068965517243, | |
| "loss": 1.0982, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019793103448275862, | |
| "loss": 0.9466, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019724137931034484, | |
| "loss": 0.9478, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019655172413793104, | |
| "loss": 0.9209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019586206896551723, | |
| "loss": 0.8859, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019517241379310345, | |
| "loss": 1.0665, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019448275862068965, | |
| "loss": 0.9732, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019379310344827587, | |
| "loss": 0.8971, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001931034482758621, | |
| "loss": 0.9835, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001924137931034483, | |
| "loss": 0.8633, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001917241379310345, | |
| "loss": 0.8358, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001910344827586207, | |
| "loss": 0.9131, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001903448275862069, | |
| "loss": 0.9166, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018965517241379312, | |
| "loss": 0.9324, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018896551724137932, | |
| "loss": 1.0667, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018827586206896554, | |
| "loss": 1.1394, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018758620689655173, | |
| "loss": 1.1141, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018689655172413793, | |
| "loss": 1.0591, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018620689655172415, | |
| "loss": 1.0821, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018551724137931034, | |
| "loss": 1.213, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018482758620689654, | |
| "loss": 1.0316, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018413793103448276, | |
| "loss": 1.4176, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018344827586206896, | |
| "loss": 1.3285, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018275862068965518, | |
| "loss": 1.389, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001820689655172414, | |
| "loss": 1.3994, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001813793103448276, | |
| "loss": 1.3383, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018068965517241382, | |
| "loss": 1.3001, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3318, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001793103448275862, | |
| "loss": 1.4562, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017862068965517243, | |
| "loss": 1.3684, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017793103448275862, | |
| "loss": 1.1345, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017724137931034484, | |
| "loss": 1.2256, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017655172413793104, | |
| "loss": 1.3794, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017586206896551723, | |
| "loss": 1.225, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017517241379310346, | |
| "loss": 1.2118, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017448275862068965, | |
| "loss": 1.2635, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00017379310344827587, | |
| "loss": 1.4038, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00017310344827586207, | |
| "loss": 1.4166, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00017241379310344826, | |
| "loss": 1.2504, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 3.4034939514740736e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |