| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014702098724592935, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014702098724592936, | |
| "grad_norm": 0.0067909229546785355, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014702098724592936, | |
| "eval_loss": 11.93165397644043, | |
| "eval_runtime": 14.724, | |
| "eval_samples_per_second": 194.513, | |
| "eval_steps_per_second": 97.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002940419744918587, | |
| "grad_norm": 0.010844946838915348, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9333, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004410629617377881, | |
| "grad_norm": 0.025482863187789917, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9264, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004410629617377881, | |
| "eval_loss": 11.93165111541748, | |
| "eval_runtime": 14.7567, | |
| "eval_samples_per_second": 194.081, | |
| "eval_steps_per_second": 97.041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005880839489837174, | |
| "grad_norm": 0.008563072420656681, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9317, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007351049362296467, | |
| "grad_norm": 0.008178934454917908, | |
| "learning_rate": 0.0001, | |
| "loss": 11.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008821259234755762, | |
| "grad_norm": 0.01497261505573988, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008821259234755762, | |
| "eval_loss": 11.931640625, | |
| "eval_runtime": 14.8958, | |
| "eval_samples_per_second": 192.269, | |
| "eval_steps_per_second": 96.134, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010291469107215055, | |
| "grad_norm": 0.007469069678336382, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9306, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011761678979674349, | |
| "grad_norm": 0.007874428294599056, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9309, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013231888852133643, | |
| "grad_norm": 0.007859715260565281, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9301, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013231888852133643, | |
| "eval_loss": 11.931620597839355, | |
| "eval_runtime": 14.8569, | |
| "eval_samples_per_second": 192.773, | |
| "eval_steps_per_second": 96.386, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014702098724592935, | |
| "grad_norm": 0.009588047862052917, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9322, | |
| "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": 1713340416.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |