| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.4154589371980677, | |
| "eval_steps": 25, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24154589371980675, | |
| "grad_norm": 0.24812498688697815, | |
| "learning_rate": 0.000493936638139193, | |
| "loss": 1.1502, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24154589371980675, | |
| "eval_loss": 0.9789943099021912, | |
| "eval_runtime": 52.5341, | |
| "eval_samples_per_second": 3.94, | |
| "eval_steps_per_second": 0.495, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "grad_norm": 0.35792288184165955, | |
| "learning_rate": 0.000463751348237005, | |
| "loss": 0.9241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "eval_loss": 0.9137127995491028, | |
| "eval_runtime": 52.1664, | |
| "eval_samples_per_second": 3.968, | |
| "eval_steps_per_second": 0.498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 0.1500280201435089, | |
| "learning_rate": 0.000411248712216741, | |
| "loss": 0.8907, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "eval_loss": 0.871120274066925, | |
| "eval_runtime": 52.6024, | |
| "eval_samples_per_second": 3.935, | |
| "eval_steps_per_second": 0.494, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 0.17570209503173828, | |
| "learning_rate": 0.00034191042415818, | |
| "loss": 0.8684, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_loss": 0.8509008288383484, | |
| "eval_runtime": 52.4802, | |
| "eval_samples_per_second": 3.944, | |
| "eval_steps_per_second": 0.495, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "grad_norm": 0.12721501290798187, | |
| "learning_rate": 0.00026297595453297494, | |
| "loss": 0.8553, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "eval_loss": 0.8410875201225281, | |
| "eval_runtime": 52.6568, | |
| "eval_samples_per_second": 3.931, | |
| "eval_steps_per_second": 0.494, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "grad_norm": 0.14220421016216278, | |
| "learning_rate": 0.00018268669172909137, | |
| "loss": 0.8527, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "eval_loss": 0.8425164818763733, | |
| "eval_runtime": 52.5225, | |
| "eval_samples_per_second": 3.941, | |
| "eval_steps_per_second": 0.495, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "grad_norm": 0.13018099963665009, | |
| "learning_rate": 0.00010942547535123056, | |
| "loss": 0.8532, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "eval_loss": 0.83249831199646, | |
| "eval_runtime": 52.6913, | |
| "eval_samples_per_second": 3.929, | |
| "eval_steps_per_second": 0.493, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "grad_norm": 0.1186065599322319, | |
| "learning_rate": 5.0841360885691e-05, | |
| "loss": 0.8463, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "eval_loss": 0.8275504112243652, | |
| "eval_runtime": 52.8803, | |
| "eval_samples_per_second": 3.915, | |
| "eval_steps_per_second": 0.492, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 0.11684705317020416, | |
| "learning_rate": 1.305099728150655e-05, | |
| "loss": 0.8363, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "eval_loss": 0.8260972499847412, | |
| "eval_runtime": 52.8873, | |
| "eval_samples_per_second": 3.914, | |
| "eval_steps_per_second": 0.492, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "grad_norm": 0.12228501588106155, | |
| "learning_rate": 0.0, | |
| "loss": 0.8416, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "eval_loss": 0.8257294297218323, | |
| "eval_runtime": 52.5215, | |
| "eval_samples_per_second": 3.941, | |
| "eval_steps_per_second": 0.495, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9398176774774784e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |