| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017878693067536764, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017878693067536764, | |
| "grad_norm": 6.169913291931152, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017878693067536764, | |
| "eval_loss": 2.5384013652801514, | |
| "eval_runtime": 103.3097, | |
| "eval_samples_per_second": 22.805, | |
| "eval_steps_per_second": 11.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003575738613507353, | |
| "grad_norm": 7.823967456817627, | |
| "learning_rate": 4e-05, | |
| "loss": 10.7187, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005363607920261028, | |
| "grad_norm": 6.943713665008545, | |
| "learning_rate": 6e-05, | |
| "loss": 11.0742, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005363607920261028, | |
| "eval_loss": 2.5283634662628174, | |
| "eval_runtime": 103.452, | |
| "eval_samples_per_second": 22.774, | |
| "eval_steps_per_second": 11.387, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007151477227014706, | |
| "grad_norm": 5.9732136726379395, | |
| "learning_rate": 8e-05, | |
| "loss": 9.4021, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008939346533768382, | |
| "grad_norm": 3.995457887649536, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6841, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010727215840522057, | |
| "grad_norm": 4.911398410797119, | |
| "learning_rate": 0.00012, | |
| "loss": 9.7591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010727215840522057, | |
| "eval_loss": 2.488743543624878, | |
| "eval_runtime": 103.5404, | |
| "eval_samples_per_second": 22.754, | |
| "eval_steps_per_second": 11.377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012515085147275734, | |
| "grad_norm": 4.511407375335693, | |
| "learning_rate": 0.00014, | |
| "loss": 9.2954, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014302954454029411, | |
| "grad_norm": 4.854757308959961, | |
| "learning_rate": 0.00016, | |
| "loss": 9.1112, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016090823760783086, | |
| "grad_norm": 4.769744873046875, | |
| "learning_rate": 0.00018, | |
| "loss": 9.6523, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016090823760783086, | |
| "eval_loss": 2.458629846572876, | |
| "eval_runtime": 103.4755, | |
| "eval_samples_per_second": 22.769, | |
| "eval_steps_per_second": 11.384, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017878693067536764, | |
| "grad_norm": 5.001588344573975, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1283, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2234653977083904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |