| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01804402742692169, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036088054853843375, | |
| "eval_loss": 2.960909366607666, | |
| "eval_runtime": 132.2763, | |
| "eval_samples_per_second": 8.822, | |
| "eval_steps_per_second": 4.415, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001804402742692169, | |
| "grad_norm": 3.78476619720459, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7201, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003608805485384338, | |
| "grad_norm": 5.096208095550537, | |
| "learning_rate": 0.0001, | |
| "loss": 11.3326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003608805485384338, | |
| "eval_loss": 2.4844770431518555, | |
| "eval_runtime": 132.2042, | |
| "eval_samples_per_second": 8.827, | |
| "eval_steps_per_second": 4.417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0054132082280765065, | |
| "grad_norm": 7.751808166503906, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.9297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007217610970768676, | |
| "grad_norm": 8.228902816772461, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.1208, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007217610970768676, | |
| "eval_loss": 1.626059651374817, | |
| "eval_runtime": 132.3789, | |
| "eval_samples_per_second": 8.816, | |
| "eval_steps_per_second": 4.412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009022013713460845, | |
| "grad_norm": 7.183887004852295, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.9281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010826416456153013, | |
| "grad_norm": 7.152175426483154, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9957, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010826416456153013, | |
| "eval_loss": 1.387015461921692, | |
| "eval_runtime": 132.1515, | |
| "eval_samples_per_second": 8.831, | |
| "eval_steps_per_second": 4.419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012630819198845183, | |
| "grad_norm": 5.089160442352295, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.4939, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014435221941537351, | |
| "grad_norm": 4.3642168045043945, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.4623, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014435221941537351, | |
| "eval_loss": 1.3095146417617798, | |
| "eval_runtime": 132.2954, | |
| "eval_samples_per_second": 8.821, | |
| "eval_steps_per_second": 4.414, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01623962468422952, | |
| "grad_norm": 7.569018363952637, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.2237, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01804402742692169, | |
| "grad_norm": 4.721866130828857, | |
| "learning_rate": 0.0, | |
| "loss": 5.2091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01804402742692169, | |
| "eval_loss": 1.29438316822052, | |
| "eval_runtime": 132.2444, | |
| "eval_samples_per_second": 8.825, | |
| "eval_steps_per_second": 4.416, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.63247803072512e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |