| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007647452442405124, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.647452442405124e-05, | |
| "grad_norm": 2.9455153942108154, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.647452442405124e-05, | |
| "eval_loss": 1.946945309638977, | |
| "eval_runtime": 423.6619, | |
| "eval_samples_per_second": 12.996, | |
| "eval_steps_per_second": 6.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015294904884810247, | |
| "grad_norm": 1.5943584442138672, | |
| "learning_rate": 4e-05, | |
| "loss": 6.5713, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002294235732721537, | |
| "grad_norm": 1.5698645114898682, | |
| "learning_rate": 6e-05, | |
| "loss": 8.1815, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002294235732721537, | |
| "eval_loss": 1.9463348388671875, | |
| "eval_runtime": 490.8565, | |
| "eval_samples_per_second": 11.217, | |
| "eval_steps_per_second": 5.609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00030589809769620494, | |
| "grad_norm": 1.9310548305511475, | |
| "learning_rate": 8e-05, | |
| "loss": 7.199, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003823726221202562, | |
| "grad_norm": 1.1266244649887085, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4947, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004588471465443074, | |
| "grad_norm": 0.9711716175079346, | |
| "learning_rate": 0.00012, | |
| "loss": 6.7757, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004588471465443074, | |
| "eval_loss": 1.9415016174316406, | |
| "eval_runtime": 232.2567, | |
| "eval_samples_per_second": 23.707, | |
| "eval_steps_per_second": 11.853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005353216709683586, | |
| "grad_norm": 1.7889138460159302, | |
| "learning_rate": 0.00014, | |
| "loss": 7.3426, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006117961953924099, | |
| "grad_norm": 1.6418790817260742, | |
| "learning_rate": 0.00016, | |
| "loss": 8.5315, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006882707198164612, | |
| "grad_norm": 3.5855391025543213, | |
| "learning_rate": 0.00018, | |
| "loss": 6.8276, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006882707198164612, | |
| "eval_loss": 1.9200159311294556, | |
| "eval_runtime": 253.2443, | |
| "eval_samples_per_second": 21.742, | |
| "eval_steps_per_second": 10.871, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007647452442405124, | |
| "grad_norm": 4.5468244552612305, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9645, | |
| "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": 1669467973091328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |