| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007312614259597806, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "grad_norm": 3.6618540287017822, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "eval_loss": 2.5146937370300293, | |
| "eval_runtime": 17.4646, | |
| "eval_samples_per_second": 32.981, | |
| "eval_steps_per_second": 16.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014625228519195613, | |
| "grad_norm": 1.8314112424850464, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0419, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "grad_norm": 1.8840593099594116, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3959, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "eval_loss": 2.5057077407836914, | |
| "eval_runtime": 16.8065, | |
| "eval_samples_per_second": 34.272, | |
| "eval_steps_per_second": 17.136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029250457038391227, | |
| "grad_norm": 2.2732760906219482, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6261, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003656307129798903, | |
| "grad_norm": 3.086693048477173, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2726, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "grad_norm": 2.35554575920105, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8881, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "eval_loss": 2.247176170349121, | |
| "eval_runtime": 16.85, | |
| "eval_samples_per_second": 34.184, | |
| "eval_steps_per_second": 17.092, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005118829981718464, | |
| "grad_norm": 3.5529842376708984, | |
| "learning_rate": 0.00014, | |
| "loss": 2.6279, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005850091407678245, | |
| "grad_norm": 3.266397714614868, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0053, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "grad_norm": 2.460725784301758, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4971, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "eval_loss": 1.427690863609314, | |
| "eval_runtime": 16.8266, | |
| "eval_samples_per_second": 34.231, | |
| "eval_steps_per_second": 17.116, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007312614259597806, | |
| "grad_norm": 3.5861213207244873, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5542, | |
| "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": 1742636046090240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |