| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011189437171310284, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005594718585655141, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.3986013986013987e-08, | |
| "loss": 1.4848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011189437171310282, | |
| "grad_norm": 1.0, | |
| "learning_rate": 2.7972027972027974e-08, | |
| "loss": 1.4825, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016784155756965425, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 4.195804195804196e-08, | |
| "loss": 1.452, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0022378874342620565, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 5.594405594405595e-08, | |
| "loss": 1.5023, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.002797359292827571, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 6.993006993006993e-08, | |
| "loss": 1.5079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.003356831151393085, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 8.391608391608393e-08, | |
| "loss": 1.4874, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003916303009958599, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 9.790209790209792e-08, | |
| "loss": 1.4273, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.004475774868524113, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 1.118881118881119e-07, | |
| "loss": 1.4738, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.005035246727089627, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.258741258741259e-07, | |
| "loss": 1.4768, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.005594718585655142, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.3986013986013987e-07, | |
| "loss": 1.4834, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.006154190444220655, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.5384615384615387e-07, | |
| "loss": 1.5255, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.00671366230278617, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.6783216783216785e-07, | |
| "loss": 1.4849, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.007273134161351684, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.8181818181818183e-07, | |
| "loss": 1.5231, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.007832606019917199, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.9580419580419583e-07, | |
| "loss": 1.4558, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.008392077878482713, | |
| "grad_norm": 1.2890625, | |
| "learning_rate": 2.097902097902098e-07, | |
| "loss": 1.5004, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.008951549737048226, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 2.237762237762238e-07, | |
| "loss": 1.4348, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.00951102159561374, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 2.3776223776223777e-07, | |
| "loss": 1.4752, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.010070493454179255, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 2.517482517482518e-07, | |
| "loss": 1.4899, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.01062996531274477, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 2.6573426573426575e-07, | |
| "loss": 1.4307, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.011189437171310284, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 2.7972027972027973e-07, | |
| "loss": 1.4233, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 35748, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 7.36836603346944e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |