| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 3.199005126953125, | |
| "eval_runtime": 0.8132, | |
| "eval_samples_per_second": 12.297, | |
| "eval_steps_per_second": 1.23, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.8046875, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.8744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.0047969818115234, | |
| "eval_runtime": 0.5075, | |
| "eval_samples_per_second": 19.705, | |
| "eval_steps_per_second": 1.97, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 2.8991804122924805, | |
| "eval_runtime": 0.5408, | |
| "eval_samples_per_second": 18.49, | |
| "eval_steps_per_second": 1.849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.3833, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.823747158050537, | |
| "eval_runtime": 0.5235, | |
| "eval_samples_per_second": 19.103, | |
| "eval_steps_per_second": 1.91, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 2.7889246940612793, | |
| "eval_runtime": 0.5403, | |
| "eval_samples_per_second": 18.509, | |
| "eval_steps_per_second": 1.851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 2.1436, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.7588186264038086, | |
| "eval_runtime": 0.5365, | |
| "eval_samples_per_second": 18.64, | |
| "eval_steps_per_second": 1.864, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 2.7500834465026855, | |
| "eval_runtime": 0.5587, | |
| "eval_samples_per_second": 17.898, | |
| "eval_steps_per_second": 1.79, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 0.0, | |
| "loss": 2.0522, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.7414565086364746, | |
| "eval_runtime": 0.5472, | |
| "eval_samples_per_second": 18.276, | |
| "eval_steps_per_second": 1.828, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 20, | |
| "total_flos": 1.1747466839851008e+16, | |
| "train_loss": 2.369537723064423, | |
| "train_runtime": 116.0943, | |
| "train_samples_per_second": 9.561, | |
| "train_steps_per_second": 0.172 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1747466839851008e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |