| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008518903446748335, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "grad_norm": 2.5001614093780518, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.825, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "eval_loss": 5.655045509338379, | |
| "eval_runtime": 5197.3091, | |
| "eval_samples_per_second": 2.378, | |
| "eval_steps_per_second": 1.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.815122757398668e-05, | |
| "grad_norm": 2.1226208209991455, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.6844, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010222684136098001, | |
| "grad_norm": 2.5686793327331543, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1539, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013630245514797336, | |
| "grad_norm": 4.603909015655518, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 4.0091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001703780689349667, | |
| "grad_norm": 2.2434098720550537, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 1.482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020445368272196002, | |
| "grad_norm": 2.6793839931488037, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.8997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023852929650895337, | |
| "grad_norm": 3.525517463684082, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002726049102959467, | |
| "grad_norm": 4.246636867523193, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 1.3833, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00030668052408294006, | |
| "grad_norm": 5.746326923370361, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1267, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003407561378699334, | |
| "grad_norm": 5.541106700897217, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.8371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003748317516569267, | |
| "grad_norm": 4.492342472076416, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.8644, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00040890736544392005, | |
| "grad_norm": 5.070585250854492, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5652, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004429829792309134, | |
| "grad_norm": 3.305798292160034, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.5209, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00047705859301790674, | |
| "grad_norm": 1.7791708707809448, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.1586, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005111342068049, | |
| "grad_norm": 4.680875301361084, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5646, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005452098205918934, | |
| "grad_norm": 3.8708016872406006, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.431, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005792854343788867, | |
| "grad_norm": 4.305510520935059, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.4888, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006133610481658801, | |
| "grad_norm": 4.049569606781006, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2277, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006474366619528734, | |
| "grad_norm": 3.324610948562622, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.2978, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006815122757398668, | |
| "grad_norm": 3.7074697017669678, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.3028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007155878895268601, | |
| "grad_norm": 1.7295836210250854, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0916, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007496635033138534, | |
| "grad_norm": 2.569653272628784, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.3138, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007837391171008468, | |
| "grad_norm": 2.379580020904541, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.2004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0008178147308878401, | |
| "grad_norm": 2.292313814163208, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1673, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008518903446748335, | |
| "grad_norm": 2.342252731323242, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.2094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008518903446748335, | |
| "eval_loss": 0.17272759974002838, | |
| "eval_runtime": 5196.4661, | |
| "eval_samples_per_second": 2.378, | |
| "eval_steps_per_second": 1.189, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.014178406321357e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |