| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.176056338028169, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007042253521126761, | |
| "grad_norm": 36.489925384521484, | |
| "learning_rate": 1e-05, | |
| "loss": 16.7418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007042253521126761, | |
| "eval_loss": 8.365168571472168, | |
| "eval_runtime": 5.2379, | |
| "eval_samples_per_second": 22.91, | |
| "eval_steps_per_second": 2.864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014084507042253521, | |
| "grad_norm": 54.84891128540039, | |
| "learning_rate": 2e-05, | |
| "loss": 15.7412, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02112676056338028, | |
| "grad_norm": 64.47398376464844, | |
| "learning_rate": 3e-05, | |
| "loss": 16.7694, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 16.057498931884766, | |
| "learning_rate": 4e-05, | |
| "loss": 16.2653, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035211267605633804, | |
| "grad_norm": 38.04544448852539, | |
| "learning_rate": 5e-05, | |
| "loss": 16.5994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04225352112676056, | |
| "grad_norm": 32.003196716308594, | |
| "learning_rate": 6e-05, | |
| "loss": 16.4649, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04929577464788732, | |
| "grad_norm": 43.975486755371094, | |
| "learning_rate": 7e-05, | |
| "loss": 15.2708, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 23.013490676879883, | |
| "learning_rate": 8e-05, | |
| "loss": 15.9144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06338028169014084, | |
| "grad_norm": 21.642526626586914, | |
| "learning_rate": 9e-05, | |
| "loss": 13.8646, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06338028169014084, | |
| "eval_loss": 5.608087539672852, | |
| "eval_runtime": 5.2413, | |
| "eval_samples_per_second": 22.895, | |
| "eval_steps_per_second": 2.862, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07042253521126761, | |
| "grad_norm": 20.63976287841797, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07746478873239436, | |
| "grad_norm": 22.017879486083984, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 9.8704, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 25.062084197998047, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 6.6076, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09154929577464789, | |
| "grad_norm": 17.164138793945312, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 6.0168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09859154929577464, | |
| "grad_norm": 11.223540306091309, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.8373, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1056338028169014, | |
| "grad_norm": 7.377206325531006, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.6019, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 7.338124752044678, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 4.2857, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11971830985915492, | |
| "grad_norm": 6.844852447509766, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.2959, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "grad_norm": 6.174362659454346, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.6541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "eval_loss": 1.0343117713928223, | |
| "eval_runtime": 5.2408, | |
| "eval_samples_per_second": 22.897, | |
| "eval_steps_per_second": 2.862, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13380281690140844, | |
| "grad_norm": 11.295928001403809, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.0969, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 5.165931224822998, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.1286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14788732394366197, | |
| "grad_norm": 15.428300857543945, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.5216, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15492957746478872, | |
| "grad_norm": 15.729449272155762, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 3.2321, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1619718309859155, | |
| "grad_norm": 6.993392467498779, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.019, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 3.678471326828003, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.176056338028169, | |
| "grad_norm": 4.6879801750183105, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.449, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.63366161088512e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |