| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 1.0085614919662476, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 1.6940793991088867, | |
| "learning_rate": 0.00019487179487179487, | |
| "loss": 3.3236, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 1.1689488887786865, | |
| "learning_rate": 0.00018974358974358974, | |
| "loss": 2.6049, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.2771538496017456, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 2.7969, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 1.1572215557098389, | |
| "learning_rate": 0.0001794871794871795, | |
| "loss": 2.3184, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 1.1674821376800537, | |
| "learning_rate": 0.00017435897435897436, | |
| "loss": 2.2023, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 0.7206246256828308, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 1.6198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.7825830578804016, | |
| "learning_rate": 0.0001641025641025641, | |
| "loss": 2.1556, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.8774120211601257, | |
| "learning_rate": 0.00015897435897435896, | |
| "loss": 1.5896, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.3417644500732422, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 2.2701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 1.579359769821167, | |
| "learning_rate": 0.00014871794871794872, | |
| "loss": 1.9842, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.8545724153518677, | |
| "learning_rate": 0.0001435897435897436, | |
| "loss": 2.537, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9196115732192993, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 2.011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 0.692592203617096, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.6603, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.2092429399490356, | |
| "learning_rate": 0.00012820512820512823, | |
| "loss": 1.7742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 1.0968248844146729, | |
| "learning_rate": 0.0001230769230769231, | |
| "loss": 2.1299, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 1.4401835203170776, | |
| "learning_rate": 0.00011794871794871796, | |
| "loss": 1.6406, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 0.9979494214057922, | |
| "learning_rate": 0.00011282051282051283, | |
| "loss": 1.541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 0.7204625606536865, | |
| "learning_rate": 0.0001076923076923077, | |
| "loss": 1.2973, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.319799542427063, | |
| "learning_rate": 0.00010256410256410256, | |
| "loss": 1.2497, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 0.9326438903808594, | |
| "learning_rate": 9.743589743589744e-05, | |
| "loss": 2.0785, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 1.1567381620407104, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 1.7149, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7692307692307692, | |
| "grad_norm": 1.8623816967010498, | |
| "learning_rate": 8.717948717948718e-05, | |
| "loss": 2.0036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.866828978061676, | |
| "learning_rate": 8.205128205128205e-05, | |
| "loss": 1.6695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 0.9064734578132629, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.5794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6402365565299988, | |
| "learning_rate": 7.17948717948718e-05, | |
| "loss": 1.3953, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.076923076923077, | |
| "grad_norm": 0.7920997738838196, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.5943, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.8890045881271362, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 1.4789, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.230769230769231, | |
| "grad_norm": 0.6904930472373962, | |
| "learning_rate": 5.6410256410256414e-05, | |
| "loss": 1.2727, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.281782627105713, | |
| "learning_rate": 5.128205128205128e-05, | |
| "loss": 0.9979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3846153846153846, | |
| "grad_norm": 0.9640224575996399, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.6476, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.979846179485321, | |
| "learning_rate": 4.1025641025641023e-05, | |
| "loss": 1.2246, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.5384615384615383, | |
| "grad_norm": 1.8661036491394043, | |
| "learning_rate": 3.58974358974359e-05, | |
| "loss": 1.4086, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.6153846153846154, | |
| "grad_norm": 1.186337947845459, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 1.1105, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 0.7501964569091797, | |
| "learning_rate": 2.564102564102564e-05, | |
| "loss": 1.1209, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 1.1312605142593384, | |
| "learning_rate": 2.0512820512820512e-05, | |
| "loss": 0.965, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.8461538461538463, | |
| "grad_norm": 0.7485955953598022, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.7158, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.9230769230769234, | |
| "grad_norm": 1.2738244533538818, | |
| "learning_rate": 1.0256410256410256e-05, | |
| "loss": 1.1139, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.7984910011291504, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 1.5986, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2521659849154560.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |