| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004113533525298231, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.227067050596462e-05, | |
| "eval_loss": 3.037961483001709, | |
| "eval_runtime": 144.3978, | |
| "eval_samples_per_second": 35.444, | |
| "eval_steps_per_second": 17.722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041135335252982314, | |
| "grad_norm": 0.8923920392990112, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9514, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008227067050596463, | |
| "grad_norm": 0.9217691421508789, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008227067050596463, | |
| "eval_loss": 3.0199954509735107, | |
| "eval_runtime": 143.0183, | |
| "eval_samples_per_second": 35.786, | |
| "eval_steps_per_second": 17.893, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012340600575894694, | |
| "grad_norm": 1.7913024425506592, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8931, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016454134101192926, | |
| "grad_norm": 1.6517016887664795, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016454134101192926, | |
| "eval_loss": 2.953030586242676, | |
| "eval_runtime": 142.344, | |
| "eval_samples_per_second": 35.955, | |
| "eval_steps_per_second": 17.978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020567667626491155, | |
| "grad_norm": 2.0664424896240234, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9243, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0024681201151789387, | |
| "grad_norm": 1.4436861276626587, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0177, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0024681201151789387, | |
| "eval_loss": 2.9256551265716553, | |
| "eval_runtime": 142.3218, | |
| "eval_samples_per_second": 35.961, | |
| "eval_steps_per_second": 17.98, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002879473467708762, | |
| "grad_norm": 1.4799622297286987, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8244, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003290826820238585, | |
| "grad_norm": 0.8472210168838501, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.0352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003290826820238585, | |
| "eval_loss": 2.9193239212036133, | |
| "eval_runtime": 142.1939, | |
| "eval_samples_per_second": 35.993, | |
| "eval_steps_per_second": 17.997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003702180172768408, | |
| "grad_norm": 1.8832063674926758, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8738, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004113533525298231, | |
| "grad_norm": 1.7079365253448486, | |
| "learning_rate": 0.0, | |
| "loss": 2.9125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004113533525298231, | |
| "eval_loss": 2.917818069458008, | |
| "eval_runtime": 142.7138, | |
| "eval_samples_per_second": 35.862, | |
| "eval_steps_per_second": 17.931, | |
| "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": 1347054886453248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |