| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006167129201356768, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006167129201356768, | |
| "grad_norm": 0.9393113255500793, | |
| "learning_rate": 2e-05, | |
| "loss": 3.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006167129201356768, | |
| "eval_loss": 3.5839953422546387, | |
| "eval_runtime": 28.0514, | |
| "eval_samples_per_second": 24.348, | |
| "eval_steps_per_second": 12.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012334258402713536, | |
| "grad_norm": 0.9207767844200134, | |
| "learning_rate": 4e-05, | |
| "loss": 3.8302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "grad_norm": 0.8743898272514343, | |
| "learning_rate": 6e-05, | |
| "loss": 3.578, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "eval_loss": 3.5698816776275635, | |
| "eval_runtime": 26.0355, | |
| "eval_samples_per_second": 26.233, | |
| "eval_steps_per_second": 13.136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002466851680542707, | |
| "grad_norm": 1.0132392644882202, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5953, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003083564600678384, | |
| "grad_norm": 0.9231270551681519, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1951, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "grad_norm": 1.338451862335205, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "eval_loss": 3.3788719177246094, | |
| "eval_runtime": 26.0925, | |
| "eval_samples_per_second": 26.176, | |
| "eval_steps_per_second": 13.107, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004316990440949738, | |
| "grad_norm": 1.1029199361801147, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4221, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004933703361085414, | |
| "grad_norm": 1.3634976148605347, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "grad_norm": 0.6220034956932068, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1161, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "eval_loss": 3.133355140686035, | |
| "eval_runtime": 26.1216, | |
| "eval_samples_per_second": 26.147, | |
| "eval_steps_per_second": 13.093, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006167129201356768, | |
| "grad_norm": 0.7948748469352722, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3768, | |
| "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": 2483818032267264.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |