| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8461538461538463, | |
| "eval_steps": 500, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 6.456618785858154, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.9054, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 6.547460556030273, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.9154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 5.908721923828125, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8793, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 2.536839008331299, | |
| "learning_rate": 9.944154131125643e-06, | |
| "loss": 0.8316, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 4.8492865562438965, | |
| "learning_rate": 9.777864028930705e-06, | |
| "loss": 0.8177, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 5.343000411987305, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.8852, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 5.4906439781188965, | |
| "learning_rate": 9.131193871579975e-06, | |
| "loss": 0.8383, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 3.948390245437622, | |
| "learning_rate": 8.665259359149132e-06, | |
| "loss": 0.7625, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 4.181735992431641, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 1.2059, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.1923076923076923, | |
| "grad_norm": 1.8489601612091064, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.7324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 1.8061974048614502, | |
| "learning_rate": 6.8267051218319766e-06, | |
| "loss": 0.7359, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.4230769230769231, | |
| "grad_norm": 1.7004175186157227, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.7131, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.1723263263702393, | |
| "learning_rate": 5.373650467932122e-06, | |
| "loss": 0.6444, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.6538461538461537, | |
| "grad_norm": 1.2155582904815674, | |
| "learning_rate": 4.626349532067879e-06, | |
| "loss": 0.7125, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.7692307692307692, | |
| "grad_norm": 0.947443425655365, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.6467, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.8846153846153846, | |
| "grad_norm": 0.8171675801277161, | |
| "learning_rate": 3.173294878168025e-06, | |
| "loss": 0.6705, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.0384615384615383, | |
| "grad_norm": 1.1855154037475586, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.0619, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.6295896172523499, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.6591, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.269230769230769, | |
| "grad_norm": 0.5844054222106934, | |
| "learning_rate": 1.3347406408508695e-06, | |
| "loss": 0.5755, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.3846153846153846, | |
| "grad_norm": 0.5806536078453064, | |
| "learning_rate": 8.688061284200266e-07, | |
| "loss": 0.6509, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.5342062711715698, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.6663, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.6153846153846154, | |
| "grad_norm": 0.4949410855770111, | |
| "learning_rate": 2.2213597106929608e-07, | |
| "loss": 0.6374, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.730769230769231, | |
| "grad_norm": 0.5183479189872742, | |
| "learning_rate": 5.584586887435739e-08, | |
| "loss": 0.6574, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.8461538461538463, | |
| "grad_norm": 0.4780174195766449, | |
| "learning_rate": 0.0, | |
| "loss": 0.6619, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.8461538461538463, | |
| "step": 24, | |
| "total_flos": 31498096181248.0, | |
| "train_loss": 0.769462858637174, | |
| "train_runtime": 692.903, | |
| "train_samples_per_second": 3.537, | |
| "train_steps_per_second": 0.035 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 31498096181248.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |