| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 10, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.9219, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001292029674220179, | |
| "loss": 0.8431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00020478185834579558, | |
| "loss": 0.8259, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002584059348440358, | |
| "loss": 0.8513, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8157, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8119, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8002, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.743, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.793, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.22686079972512133, | |
| "eval_loss": 0.7526410222053528, | |
| "eval_runtime": 229.5348, | |
| "eval_samples_per_second": 0.157, | |
| "eval_steps_per_second": 0.009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7927, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7881, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7832, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7478, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.741, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7564, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7315, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7531, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7549, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.22750504660052398, | |
| "eval_loss": 0.7324042320251465, | |
| "eval_runtime": 224.0786, | |
| "eval_samples_per_second": 0.161, | |
| "eval_steps_per_second": 0.009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7742, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7763, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6916, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6979, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7256, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7626, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7329, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6927, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6781, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0003, | |
| "loss": 0.672, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_accuracy": 0.2278271700382253, | |
| "eval_loss": 0.7340984344482422, | |
| "eval_runtime": 224.2193, | |
| "eval_samples_per_second": 0.161, | |
| "eval_steps_per_second": 0.009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6875, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7242, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7121, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6614, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6649, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6056, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.656, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6428, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.22737619722544344, | |
| "eval_loss": 0.7448343634605408, | |
| "eval_runtime": 223.9913, | |
| "eval_samples_per_second": 0.161, | |
| "eval_steps_per_second": 0.009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6096, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6172, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5967, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5958, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5921, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6026, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5941, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.612, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6084, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5446, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.22646351415195637, | |
| "eval_loss": 0.7739428281784058, | |
| "eval_runtime": 223.8688, | |
| "eval_samples_per_second": 0.161, | |
| "eval_steps_per_second": 0.009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5375, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5548, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6092, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4286, | |
| "step": 54 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 135, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 68912311697408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |