| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019803352707613397, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.96067054152268e-05, | |
| "eval_loss": 0.2887181341648102, | |
| "eval_runtime": 1261.1036, | |
| "eval_samples_per_second": 8.43, | |
| "eval_steps_per_second": 4.215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019803352707613398, | |
| "grad_norm": 1.734922170639038, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1269, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00039606705415226796, | |
| "grad_norm": 1.451378345489502, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00039606705415226796, | |
| "eval_loss": 0.2597455680370331, | |
| "eval_runtime": 1258.0453, | |
| "eval_samples_per_second": 8.45, | |
| "eval_steps_per_second": 4.226, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000594100581228402, | |
| "grad_norm": 1.9125475883483887, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007921341083045359, | |
| "grad_norm": 2.3644330501556396, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0579, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007921341083045359, | |
| "eval_loss": 0.22462156414985657, | |
| "eval_runtime": 1262.7065, | |
| "eval_samples_per_second": 8.419, | |
| "eval_steps_per_second": 4.21, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009901676353806699, | |
| "grad_norm": 1.9722180366516113, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001188201162456804, | |
| "grad_norm": 1.2997853755950928, | |
| "learning_rate": 5e-05, | |
| "loss": 0.702, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001188201162456804, | |
| "eval_loss": 0.21118231117725372, | |
| "eval_runtime": 1263.6849, | |
| "eval_samples_per_second": 8.413, | |
| "eval_steps_per_second": 4.207, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001386234689532938, | |
| "grad_norm": 2.2332987785339355, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9282, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0015842682166090718, | |
| "grad_norm": 2.558938503265381, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9566, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0015842682166090718, | |
| "eval_loss": 0.202701136469841, | |
| "eval_runtime": 1263.6515, | |
| "eval_samples_per_second": 8.413, | |
| "eval_steps_per_second": 4.207, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017823017436852059, | |
| "grad_norm": 2.137298345565796, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7827, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0019803352707613397, | |
| "grad_norm": 1.5813252925872803, | |
| "learning_rate": 0.0, | |
| "loss": 1.0114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0019803352707613397, | |
| "eval_loss": 0.20111645758152008, | |
| "eval_runtime": 1262.8516, | |
| "eval_samples_per_second": 8.418, | |
| "eval_steps_per_second": 4.21, | |
| "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 | |
| } | |