| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012416190712689348, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012416190712689348, | |
| "grad_norm": 1.5310730934143066, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7726, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012416190712689348, | |
| "eval_loss": 1.8528978824615479, | |
| "eval_runtime": 103.4549, | |
| "eval_samples_per_second": 32.787, | |
| "eval_steps_per_second": 16.394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024832381425378696, | |
| "grad_norm": 1.4696600437164307, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7771, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00037248572138068043, | |
| "grad_norm": 1.874938726425171, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00037248572138068043, | |
| "eval_loss": 1.8299616575241089, | |
| "eval_runtime": 102.1593, | |
| "eval_samples_per_second": 33.203, | |
| "eval_steps_per_second": 16.602, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004966476285075739, | |
| "grad_norm": 1.4195663928985596, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7702, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006208095356344674, | |
| "grad_norm": 2.5353384017944336, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8379, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007449714427613609, | |
| "grad_norm": 0.9590808153152466, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7453, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007449714427613609, | |
| "eval_loss": 1.424591064453125, | |
| "eval_runtime": 102.3901, | |
| "eval_samples_per_second": 33.128, | |
| "eval_steps_per_second": 16.564, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008691333498882542, | |
| "grad_norm": 1.308701753616333, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5555, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009932952570151478, | |
| "grad_norm": 1.7601176500320435, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4406, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011174571641420412, | |
| "grad_norm": 1.5814690589904785, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4161, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011174571641420412, | |
| "eval_loss": 1.2501493692398071, | |
| "eval_runtime": 102.2988, | |
| "eval_samples_per_second": 33.158, | |
| "eval_steps_per_second": 16.579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012416190712689348, | |
| "grad_norm": 1.6842873096466064, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1907, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |