| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9964614295824487, |
| "eval_steps": 250, |
| "global_step": 176, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005661712668082095, |
| "grad_norm": 0.0, |
| "learning_rate": 0, |
| "loss": 4.8338, |
| "mean_token_accuracy": 0.5150225162506104, |
| "num_tokens": 33968.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.11323425336164189, |
| "grad_norm": 6.662907600402832, |
| "learning_rate": 1.8620689655172415e-05, |
| "loss": 2.7196, |
| "mean_token_accuracy": 0.5913833077800902, |
| "num_tokens": 683410.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.22646850672328378, |
| "grad_norm": 6.547586917877197, |
| "learning_rate": 1.632183908045977e-05, |
| "loss": 1.3885, |
| "mean_token_accuracy": 0.667194539308548, |
| "num_tokens": 1359826.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.33970276008492567, |
| "grad_norm": 5.73145055770874, |
| "learning_rate": 1.4022988505747128e-05, |
| "loss": 1.3821, |
| "mean_token_accuracy": 0.6680587850511074, |
| "num_tokens": 2041672.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.45293701344656756, |
| "grad_norm": 5.648466110229492, |
| "learning_rate": 1.1724137931034483e-05, |
| "loss": 1.3702, |
| "mean_token_accuracy": 0.6702538013458252, |
| "num_tokens": 2714035.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5661712668082095, |
| "grad_norm": 5.899498462677002, |
| "learning_rate": 9.42528735632184e-06, |
| "loss": 1.4021, |
| "mean_token_accuracy": 0.6674060389399529, |
| "num_tokens": 3401282.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6794055201698513, |
| "grad_norm": 5.381211280822754, |
| "learning_rate": 7.126436781609196e-06, |
| "loss": 1.3549, |
| "mean_token_accuracy": 0.6747658185660839, |
| "num_tokens": 4086648.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7926397735314933, |
| "grad_norm": 4.983366012573242, |
| "learning_rate": 4.8275862068965525e-06, |
| "loss": 1.3344, |
| "mean_token_accuracy": 0.6785005293786526, |
| "num_tokens": 4760069.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9058740268931351, |
| "grad_norm": 4.462568759918213, |
| "learning_rate": 2.5287356321839083e-06, |
| "loss": 1.3452, |
| "mean_token_accuracy": 0.6764475837349891, |
| "num_tokens": 5438765.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9964614295824487, |
| "mean_token_accuracy": 0.6769746583886445, |
| "num_tokens": 5979364.0, |
| "step": 176, |
| "total_flos": 76379988885504.0, |
| "train_loss": 1.5306899412111803, |
| "train_runtime": 16649.0803, |
| "train_samples_per_second": 1.357, |
| "train_steps_per_second": 0.011 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 176, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 76379988885504.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
