| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05241090146750524, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010482180293501049, | |
| "eval_loss": 10.35714054107666, | |
| "eval_runtime": 22.31, | |
| "eval_samples_per_second": 18.019, | |
| "eval_steps_per_second": 9.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005241090146750524, | |
| "grad_norm": 9.293054580688477, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5317, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "grad_norm": 6.366726398468018, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "eval_loss": 9.710428237915039, | |
| "eval_runtime": 22.3173, | |
| "eval_samples_per_second": 18.013, | |
| "eval_steps_per_second": 9.006, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015723270440251572, | |
| "grad_norm": 8.73572063446045, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.6493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "grad_norm": 9.366942405700684, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.6943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "eval_loss": 5.824213981628418, | |
| "eval_runtime": 22.3607, | |
| "eval_samples_per_second": 17.978, | |
| "eval_steps_per_second": 8.989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02620545073375262, | |
| "grad_norm": 9.473739624023438, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.038, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "grad_norm": 10.36804485321045, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4984, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "eval_loss": 4.253625869750977, | |
| "eval_runtime": 22.3864, | |
| "eval_samples_per_second": 17.957, | |
| "eval_steps_per_second": 8.979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03668763102725367, | |
| "grad_norm": 9.573823928833008, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.0202, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "grad_norm": 9.178057670593262, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.1284, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "eval_loss": 3.834207057952881, | |
| "eval_runtime": 22.4515, | |
| "eval_samples_per_second": 17.905, | |
| "eval_steps_per_second": 8.953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04716981132075472, | |
| "grad_norm": 10.221997261047363, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6687, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "grad_norm": 8.347268104553223, | |
| "learning_rate": 0.0, | |
| "loss": 3.7156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "eval_loss": 3.7798588275909424, | |
| "eval_runtime": 22.3536, | |
| "eval_samples_per_second": 17.984, | |
| "eval_steps_per_second": 8.992, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5235315918766080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |