| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8518518518518519, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009259259259259259, | |
| "eval_loss": 2.1662161350250244, | |
| "eval_runtime": 31.5566, | |
| "eval_samples_per_second": 47.565, | |
| "eval_steps_per_second": 5.958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 1.75, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.857, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.8324, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.866, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.421875, | |
| "learning_rate": 0.00019984815164333163, | |
| "loss": 1.974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 0.00019939306773179497, | |
| "loss": 2.0103, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 2.0427, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6481481481481481, | |
| "grad_norm": 1.3125, | |
| "learning_rate": 0.00019757963826274357, | |
| "loss": 2.0967, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 0.00019622680003092503, | |
| "loss": 2.1174, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 2.109, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "grad_norm": 1.25, | |
| "learning_rate": 0.00019264940672148018, | |
| "loss": 2.1218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0185185185185186, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 0.00019043571606975777, | |
| "loss": 1.8774, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.9755, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2037037037037037, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 0.00018519194088383273, | |
| "loss": 0.9357, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2962962962962963, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 0.0001821777815225245, | |
| "loss": 0.9453, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.9413, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 0.00017541066097768963, | |
| "loss": 0.9678, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.574074074074074, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 0.00017167825131684513, | |
| "loss": 0.9576, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.9958, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7592592592592593, | |
| "grad_norm": 1.1953125, | |
| "learning_rate": 0.00016357237482099684, | |
| "loss": 0.9805, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 0.00015922352526649803, | |
| "loss": 1.0055, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "eval_loss": 2.0688600540161133, | |
| "eval_runtime": 26.9652, | |
| "eval_samples_per_second": 55.664, | |
| "eval_steps_per_second": 6.972, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2990695522435072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |