| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008509733007126901, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.509733007126901e-05, | |
| "grad_norm": 1.2628990411758423, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.509733007126901e-05, | |
| "eval_loss": 2.56070876121521, | |
| "eval_runtime": 243.4177, | |
| "eval_samples_per_second": 20.327, | |
| "eval_steps_per_second": 10.164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017019466014253802, | |
| "grad_norm": 1.4270519018173218, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3577, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025529199021380705, | |
| "grad_norm": 1.4585351943969727, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5578, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025529199021380705, | |
| "eval_loss": 2.5522444248199463, | |
| "eval_runtime": 242.2069, | |
| "eval_samples_per_second": 20.429, | |
| "eval_steps_per_second": 10.214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034038932028507605, | |
| "grad_norm": 1.4806636571884155, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042548665035634504, | |
| "grad_norm": 0.9438812732696533, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9508, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005105839804276141, | |
| "grad_norm": 1.1173439025878906, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9439, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005105839804276141, | |
| "eval_loss": 2.4155304431915283, | |
| "eval_runtime": 241.825, | |
| "eval_samples_per_second": 20.461, | |
| "eval_steps_per_second": 10.231, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005956813104988831, | |
| "grad_norm": 1.9286212921142578, | |
| "learning_rate": 0.00014, | |
| "loss": 2.4062, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006807786405701521, | |
| "grad_norm": 1.8178638219833374, | |
| "learning_rate": 0.00016, | |
| "loss": 2.167, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007658759706414211, | |
| "grad_norm": 1.4230520725250244, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007658759706414211, | |
| "eval_loss": 1.8286491632461548, | |
| "eval_runtime": 242.2217, | |
| "eval_samples_per_second": 20.428, | |
| "eval_steps_per_second": 10.214, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008509733007126901, | |
| "grad_norm": 1.5641324520111084, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0192, | |
| "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": 3166205430988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |