| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027434842249657063, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "grad_norm": 131.4941864013672, | |
| "learning_rate": 2e-05, | |
| "loss": 11.6798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "eval_loss": 1.8134424686431885, | |
| "eval_runtime": 3.2066, | |
| "eval_samples_per_second": 48.025, | |
| "eval_steps_per_second": 24.013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054869684499314125, | |
| "grad_norm": 68.26287841796875, | |
| "learning_rate": 4e-05, | |
| "loss": 7.2574, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 86.97447204589844, | |
| "learning_rate": 6e-05, | |
| "loss": 6.595, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "eval_loss": 1.8126391172409058, | |
| "eval_runtime": 3.3611, | |
| "eval_samples_per_second": 45.818, | |
| "eval_steps_per_second": 22.909, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010973936899862825, | |
| "grad_norm": 81.33331298828125, | |
| "learning_rate": 8e-05, | |
| "loss": 7.0646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013717421124828532, | |
| "grad_norm": 190.9860076904297, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 65.72985076904297, | |
| "learning_rate": 0.00012, | |
| "loss": 6.893, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "eval_loss": 1.800175428390503, | |
| "eval_runtime": 3.4767, | |
| "eval_samples_per_second": 44.295, | |
| "eval_steps_per_second": 22.148, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019204389574759947, | |
| "grad_norm": 86.56372833251953, | |
| "learning_rate": 0.00014, | |
| "loss": 5.6625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "grad_norm": 80.3042984008789, | |
| "learning_rate": 0.00016, | |
| "loss": 9.7957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 109.0301513671875, | |
| "learning_rate": 0.00018, | |
| "loss": 10.7531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "eval_loss": 1.7538036108016968, | |
| "eval_runtime": 3.5013, | |
| "eval_samples_per_second": 43.984, | |
| "eval_steps_per_second": 21.992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027434842249657063, | |
| "grad_norm": 50.703880310058594, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5974, | |
| "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": 173263917416448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |