| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 85, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 11.891107559204102, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 3.299, | |
| "mean_token_accuracy": 0.4547618865966797, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 3.044015884399414, | |
| "learning_rate": 1.999145758387301e-05, | |
| "loss": 2.3198, | |
| "mean_token_accuracy": 0.5092985607683659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 1.4847815036773682, | |
| "learning_rate": 1.9694002659393306e-05, | |
| "loss": 1.7828, | |
| "mean_token_accuracy": 0.5745997056365013, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.9522435069084167, | |
| "learning_rate": 1.898390981891979e-05, | |
| "loss": 1.4, | |
| "mean_token_accuracy": 0.6392715856432915, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.6069338321685791, | |
| "learning_rate": 1.789140509396394e-05, | |
| "loss": 1.1739, | |
| "mean_token_accuracy": 0.6828911945223808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.5275129079818726, | |
| "learning_rate": 1.646299237860941e-05, | |
| "loss": 1.0771, | |
| "mean_token_accuracy": 0.7027453184127808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4117647058823529, | |
| "grad_norm": 0.6234576106071472, | |
| "learning_rate": 1.4759473930370738e-05, | |
| "loss": 1.0115, | |
| "mean_token_accuracy": 0.7170437932014465, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.3768845498561859, | |
| "learning_rate": 1.2853362242491054e-05, | |
| "loss": 0.9793, | |
| "mean_token_accuracy": 0.7235300198197365, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5294117647058824, | |
| "grad_norm": 0.5602439045906067, | |
| "learning_rate": 1.0825793454723325e-05, | |
| "loss": 0.9547, | |
| "mean_token_accuracy": 0.7290156945586205, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.601157784461975, | |
| "learning_rate": 8.763073687306523e-06, | |
| "loss": 0.9258, | |
| "mean_token_accuracy": 0.7356743782758712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6470588235294118, | |
| "grad_norm": 0.3758750259876251, | |
| "learning_rate": 6.7530053079531664e-06, | |
| "loss": 0.9166, | |
| "mean_token_accuracy": 0.7379220128059387, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.2922804057598114, | |
| "learning_rate": 4.881149509103993e-06, | |
| "loss": 0.9147, | |
| "mean_token_accuracy": 0.7374181285500526, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7647058823529411, | |
| "grad_norm": 0.322323203086853, | |
| "learning_rate": 3.2271842837425917e-06, | |
| "loss": 0.9176, | |
| "mean_token_accuracy": 0.7366804420948029, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.2906600832939148, | |
| "learning_rate": 1.861512827298051e-06, | |
| "loss": 0.9045, | |
| "mean_token_accuracy": 0.7401018545031548, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.33901330828666687, | |
| "learning_rate": 8.42266733449425e-07, | |
| "loss": 0.8977, | |
| "mean_token_accuracy": 0.7416183516383171, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.2457120567560196, | |
| "learning_rate": 2.1283154672645522e-07, | |
| "loss": 0.9017, | |
| "mean_token_accuracy": 0.7403849691152573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3804878890514374, | |
| "learning_rate": 0.0, | |
| "loss": 0.9078, | |
| "mean_token_accuracy": 0.7387076124548912, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 85, | |
| "total_flos": 71084393103360.0, | |
| "train_loss": 1.2520353261162254, | |
| "train_runtime": 7437.5066, | |
| "train_samples_per_second": 1.463, | |
| "train_steps_per_second": 0.011 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 85, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 71084393103360.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |