| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020930354246245617, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020930354246245618, | |
| "grad_norm": 1.814659833908081, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020930354246245618, | |
| "eval_loss": 2.6074929237365723, | |
| "eval_runtime": 74.8612, | |
| "eval_samples_per_second": 26.876, | |
| "eval_steps_per_second": 13.438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041860708492491236, | |
| "grad_norm": 1.9702552556991577, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5943, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006279106273873685, | |
| "grad_norm": 1.8995496034622192, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5512, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006279106273873685, | |
| "eval_loss": 2.5896811485290527, | |
| "eval_runtime": 74.828, | |
| "eval_samples_per_second": 26.888, | |
| "eval_steps_per_second": 13.444, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008372141698498247, | |
| "grad_norm": 1.9130076169967651, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6446, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010465177123122808, | |
| "grad_norm": 1.8720148801803589, | |
| "learning_rate": 0.0001, | |
| "loss": 2.659, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001255821254774737, | |
| "grad_norm": 1.7725203037261963, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4155, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001255821254774737, | |
| "eval_loss": 2.3963053226470947, | |
| "eval_runtime": 74.9235, | |
| "eval_samples_per_second": 26.854, | |
| "eval_steps_per_second": 13.427, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014651247972371933, | |
| "grad_norm": 1.389266014099121, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3148, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016744283396996494, | |
| "grad_norm": 1.2340798377990723, | |
| "learning_rate": 0.00016, | |
| "loss": 2.2516, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018837318821621056, | |
| "grad_norm": 1.129597544670105, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4434, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018837318821621056, | |
| "eval_loss": 2.254772424697876, | |
| "eval_runtime": 74.9283, | |
| "eval_samples_per_second": 26.852, | |
| "eval_steps_per_second": 13.426, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020930354246245617, | |
| "grad_norm": 1.0946333408355713, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2845, | |
| "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": 887672762007552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |