| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019071412905625113, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.814282581125023e-05, | |
| "eval_loss": 0.48583489656448364, | |
| "eval_runtime": 1302.4495, | |
| "eval_samples_per_second": 8.476, | |
| "eval_steps_per_second": 4.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019071412905625112, | |
| "grad_norm": 4.917712211608887, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8995, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00038142825811250225, | |
| "grad_norm": 3.281710624694824, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7301, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00038142825811250225, | |
| "eval_loss": 0.3948906362056732, | |
| "eval_runtime": 1302.7836, | |
| "eval_samples_per_second": 8.473, | |
| "eval_steps_per_second": 4.237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005721423871687534, | |
| "grad_norm": 2.8403196334838867, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5185, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007628565162250045, | |
| "grad_norm": 2.8824808597564697, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.355, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007628565162250045, | |
| "eval_loss": 0.3503015637397766, | |
| "eval_runtime": 1306.7155, | |
| "eval_samples_per_second": 8.448, | |
| "eval_steps_per_second": 4.224, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009535706452812557, | |
| "grad_norm": 2.7718515396118164, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4199, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011442847743375068, | |
| "grad_norm": 2.5033485889434814, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011442847743375068, | |
| "eval_loss": 0.33604300022125244, | |
| "eval_runtime": 1303.8889, | |
| "eval_samples_per_second": 8.466, | |
| "eval_steps_per_second": 4.233, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001334998903393758, | |
| "grad_norm": 2.629711627960205, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4143, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001525713032450009, | |
| "grad_norm": 2.8309590816497803, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4284, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001525713032450009, | |
| "eval_loss": 0.33039793372154236, | |
| "eval_runtime": 1298.8442, | |
| "eval_samples_per_second": 8.499, | |
| "eval_steps_per_second": 4.25, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017164271615062602, | |
| "grad_norm": 2.7132301330566406, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3452, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0019071412905625113, | |
| "grad_norm": 2.4782090187072754, | |
| "learning_rate": 0.0, | |
| "loss": 1.2682, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0019071412905625113, | |
| "eval_loss": 0.3293900489807129, | |
| "eval_runtime": 1298.7109, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 4.25, | |
| "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": 1.75266978594816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |