| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009918666931164452, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.918666931164451e-05, | |
| "grad_norm": 1.9503800868988037, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.918666931164451e-05, | |
| "eval_loss": 3.9280550479888916, | |
| "eval_runtime": 85.9639, | |
| "eval_samples_per_second": 49.381, | |
| "eval_steps_per_second": 24.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019837333862328903, | |
| "grad_norm": 1.9433728456497192, | |
| "learning_rate": 4e-05, | |
| "loss": 3.6032, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00029756000793493357, | |
| "grad_norm": 2.1863696575164795, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1764, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029756000793493357, | |
| "eval_loss": 3.918807029724121, | |
| "eval_runtime": 84.9597, | |
| "eval_samples_per_second": 49.965, | |
| "eval_steps_per_second": 24.988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00039674667724657806, | |
| "grad_norm": 1.5799533128738403, | |
| "learning_rate": 8e-05, | |
| "loss": 3.291, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004959333465582226, | |
| "grad_norm": 2.329425811767578, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7845, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005951200158698671, | |
| "grad_norm": 3.523594856262207, | |
| "learning_rate": 0.00012, | |
| "loss": 4.2545, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005951200158698671, | |
| "eval_loss": 3.739866256713867, | |
| "eval_runtime": 85.7733, | |
| "eval_samples_per_second": 49.491, | |
| "eval_steps_per_second": 24.751, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006943066851815116, | |
| "grad_norm": 2.329558849334717, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6807, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007934933544931561, | |
| "grad_norm": 2.337567090988159, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1091, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008926800238048007, | |
| "grad_norm": 3.2499704360961914, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8589, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008926800238048007, | |
| "eval_loss": 3.16778302192688, | |
| "eval_runtime": 84.2737, | |
| "eval_samples_per_second": 50.372, | |
| "eval_steps_per_second": 25.192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009918666931164452, | |
| "grad_norm": 2.997312068939209, | |
| "learning_rate": 0.0002, | |
| "loss": 3.141, | |
| "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": 324298258513920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |