| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016106052158830454, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.12975696380268e-05, | |
| "eval_loss": 2.346364736557007, | |
| "eval_runtime": 858.736, | |
| "eval_samples_per_second": 11.873, | |
| "eval_steps_per_second": 5.937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000206487848190134, | |
| "grad_norm": 1.7139934301376343, | |
| "learning_rate": 5e-05, | |
| "loss": 8.9352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000412975696380268, | |
| "grad_norm": 2.3543801307678223, | |
| "learning_rate": 0.0001, | |
| "loss": 9.1421, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000412975696380268, | |
| "eval_loss": 2.2850396633148193, | |
| "eval_runtime": 861.552, | |
| "eval_samples_per_second": 11.834, | |
| "eval_steps_per_second": 5.917, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000619463544570402, | |
| "grad_norm": 8.154956817626953, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.9455, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000825951392760536, | |
| "grad_norm": 8.846421241760254, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.7014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000825951392760536, | |
| "eval_loss": 2.078970432281494, | |
| "eval_runtime": 864.8514, | |
| "eval_samples_per_second": 11.789, | |
| "eval_steps_per_second": 5.895, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00103243924095067, | |
| "grad_norm": 9.013049125671387, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.0292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001238927089140804, | |
| "grad_norm": 9.03317928314209, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001238927089140804, | |
| "eval_loss": 2.0168118476867676, | |
| "eval_runtime": 865.0006, | |
| "eval_samples_per_second": 11.787, | |
| "eval_steps_per_second": 5.894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001445414937330938, | |
| "grad_norm": 6.451173305511475, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.1509, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9672432332046336.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |