| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036501679077237553, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.30033581544751e-05, | |
| "eval_loss": 1.424984097480774, | |
| "eval_runtime": 818.0369, | |
| "eval_samples_per_second": 7.051, | |
| "eval_steps_per_second": 3.526, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036501679077237555, | |
| "grad_norm": 0.5504812598228455, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4219, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007300335815447511, | |
| "grad_norm": 0.6794695258140564, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3627, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007300335815447511, | |
| "eval_loss": 1.190058946609497, | |
| "eval_runtime": 834.2628, | |
| "eval_samples_per_second": 6.914, | |
| "eval_steps_per_second": 3.457, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010950503723171265, | |
| "grad_norm": 0.5121544003486633, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0811, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014600671630895022, | |
| "grad_norm": 0.49107033014297485, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014600671630895022, | |
| "eval_loss": 0.8011711835861206, | |
| "eval_runtime": 833.856, | |
| "eval_samples_per_second": 6.917, | |
| "eval_steps_per_second": 3.459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018250839538618776, | |
| "grad_norm": 0.44594714045524597, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8083, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002190100744634253, | |
| "grad_norm": 0.36000218987464905, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7373, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002190100744634253, | |
| "eval_loss": 0.7191545367240906, | |
| "eval_runtime": 834.4338, | |
| "eval_samples_per_second": 6.912, | |
| "eval_steps_per_second": 3.456, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025551175354066287, | |
| "grad_norm": 0.37949132919311523, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7084, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0029201343261790044, | |
| "grad_norm": 0.43039050698280334, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029201343261790044, | |
| "eval_loss": 0.6962733864784241, | |
| "eval_runtime": 832.6687, | |
| "eval_samples_per_second": 6.927, | |
| "eval_steps_per_second": 3.464, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032851511169513796, | |
| "grad_norm": 0.3372248709201813, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.694, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0036501679077237553, | |
| "grad_norm": 0.3166466951370239, | |
| "learning_rate": 0.0, | |
| "loss": 0.6975, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0036501679077237553, | |
| "eval_loss": 0.6923239231109619, | |
| "eval_runtime": 832.782, | |
| "eval_samples_per_second": 6.926, | |
| "eval_steps_per_second": 3.463, | |
| "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": 1.5404664619008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |