| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9647058823529413, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 7.926609856300782, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 1.3952, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.8405266678960521, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.7195, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.9213360863093222, | |
| "learning_rate": 4.99613632163459e-05, | |
| "loss": 0.4751, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.5013556648810926, | |
| "learning_rate": 4.952806974561518e-05, | |
| "loss": 0.3764, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.36651550460940663, | |
| "learning_rate": 4.862157403595598e-05, | |
| "loss": 0.3376, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.2990382699652553, | |
| "learning_rate": 4.7259364450857096e-05, | |
| "loss": 0.319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.3237256028681643, | |
| "learning_rate": 4.5467721110696685e-05, | |
| "loss": 0.3004, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.279108419607827, | |
| "learning_rate": 4.3281208889462715e-05, | |
| "loss": 0.2876, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.2913644070197406, | |
| "learning_rate": 4.0742010579737855e-05, | |
| "loss": 0.2781, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.31192283061108456, | |
| "learning_rate": 3.7899113090712526e-05, | |
| "loss": 0.2299, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.26219335707946045, | |
| "learning_rate": 3.4807362379317025e-05, | |
| "loss": 0.2162, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.29615778350655847, | |
| "learning_rate": 3.1526405346999946e-05, | |
| "loss": 0.2084, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.28688518177379235, | |
| "learning_rate": 2.8119539115370218e-05, | |
| "loss": 0.2001, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2521941986482173, | |
| "learning_rate": 2.4652489880792128e-05, | |
| "loss": 0.1928, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.23146994181766112, | |
| "learning_rate": 2.1192144906604876e-05, | |
| "loss": 0.1901, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.24231550036213442, | |
| "learning_rate": 1.780526211572016e-05, | |
| "loss": 0.1842, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.39003765031270565, | |
| "learning_rate": 1.4557182178490636e-05, | |
| "loss": 0.1977, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.30306479354663846, | |
| "learning_rate": 1.151056794260289e-05, | |
| "loss": 0.134, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.28623172192127194, | |
| "learning_rate": 8.724195524258688e-06, | |
| "loss": 0.1285, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.24645273464562403, | |
| "learning_rate": 6.25182038324447e-06, | |
| "loss": 0.1293, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.23945572748242794, | |
| "learning_rate": 4.14114025787932e-06, | |
| "loss": 0.1239, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.2367978149293599, | |
| "learning_rate": 2.4328749671846116e-06, | |
| "loss": 0.1256, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.24102969031047347, | |
| "learning_rate": 1.1599808329836177e-06, | |
| "loss": 0.1245, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.22666386671902916, | |
| "learning_rate": 3.470148775153448e-07, | |
| "loss": 0.1242, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.21907314464708774, | |
| "learning_rate": 9.661062636148744e-09, | |
| "loss": 0.121, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.9647058823529413, | |
| "step": 126, | |
| "total_flos": 2.6054191277408256e+16, | |
| "train_loss": 0.28340424479000154, | |
| "train_runtime": 5349.4515, | |
| "train_samples_per_second": 3.033, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 126, | |
| "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": 2.6054191277408256e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |