| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.984, | |
| "eval_steps": 500, | |
| "global_step": 124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 50.95399475097656, | |
| "learning_rate": 9.959935885253715e-06, | |
| "loss": 5.4476, | |
| "num_input_tokens_seen": 82560, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 406.1771545410156, | |
| "learning_rate": 9.840385594331022e-06, | |
| "loss": 5.3325, | |
| "num_input_tokens_seen": 165120, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 52.38233947753906, | |
| "learning_rate": 9.643264997861312e-06, | |
| "loss": 5.0431, | |
| "num_input_tokens_seen": 247680, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 377.5094909667969, | |
| "learning_rate": 9.371733080722911e-06, | |
| "loss": 4.4316, | |
| "num_input_tokens_seen": 330240, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 42.05713653564453, | |
| "learning_rate": 9.030141317270026e-06, | |
| "loss": 3.253, | |
| "num_input_tokens_seen": 412800, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 346.2967224121094, | |
| "learning_rate": 8.6239639361456e-06, | |
| "loss": 3.1498, | |
| "num_input_tokens_seen": 495360, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 161.69073486328125, | |
| "learning_rate": 8.15971019223152e-06, | |
| "loss": 2.2606, | |
| "num_input_tokens_seen": 577920, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 36.605567932128906, | |
| "learning_rate": 7.644820051634813e-06, | |
| "loss": 1.9825, | |
| "num_input_tokens_seen": 660480, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 73.60350799560547, | |
| "learning_rate": 7.087544961425317e-06, | |
| "loss": 1.4754, | |
| "num_input_tokens_seen": 743040, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 158.03152465820312, | |
| "learning_rate": 6.496815614866792e-06, | |
| "loss": 0.9276, | |
| "num_input_tokens_seen": 825600, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 7.710397720336914, | |
| "learning_rate": 5.882098831289044e-06, | |
| "loss": 0.3203, | |
| "num_input_tokens_seen": 908160, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 15.087837219238281, | |
| "learning_rate": 5.253245844193564e-06, | |
| "loss": 0.3668, | |
| "num_input_tokens_seen": 990720, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 5.742522716522217, | |
| "learning_rate": 4.62033442887377e-06, | |
| "loss": 0.1251, | |
| "num_input_tokens_seen": 1073280, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 3.3580806255340576, | |
| "learning_rate": 3.993507399556699e-06, | |
| "loss": 0.0937, | |
| "num_input_tokens_seen": 1155840, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 14.523807525634766, | |
| "learning_rate": 3.3828100642538097e-06, | |
| "loss": 0.1095, | |
| "num_input_tokens_seen": 1238400, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 4.2941999435424805, | |
| "learning_rate": 2.7980292422118282e-06, | |
| "loss": 0.0431, | |
| "num_input_tokens_seen": 1320960, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 6.715703010559082, | |
| "learning_rate": 2.2485364238130435e-06, | |
| "loss": 0.0373, | |
| "num_input_tokens_seen": 1403520, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 2.378614664077759, | |
| "learning_rate": 1.74313758638889e-06, | |
| "loss": 0.0501, | |
| "num_input_tokens_seen": 1486080, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 3.5217220783233643, | |
| "learning_rate": 1.2899320727454472e-06, | |
| "loss": 0.0309, | |
| "num_input_tokens_seen": 1568640, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 6.760895252227783, | |
| "learning_rate": 8.961827939636198e-07, | |
| "loss": 0.03, | |
| "num_input_tokens_seen": 1651200, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.4529302716255188, | |
| "learning_rate": 5.681998365579594e-07, | |
| "loss": 0.4213, | |
| "num_input_tokens_seen": 1733760, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 22.67563247680664, | |
| "learning_rate": 3.112393392645985e-07, | |
| "loss": 0.0281, | |
| "num_input_tokens_seen": 1816320, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 6.4231414794921875, | |
| "learning_rate": 1.2941926002306536e-07, | |
| "loss": 0.0125, | |
| "num_input_tokens_seen": 1898880, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.6063465476036072, | |
| "learning_rate": 2.5653383040524228e-08, | |
| "loss": 0.0098, | |
| "num_input_tokens_seen": 1981440, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "num_input_tokens_seen": 2047488, | |
| "step": 124, | |
| "total_flos": 2.955998176351027e+16, | |
| "train_loss": 1.4107779081340037, | |
| "train_runtime": 1478.9821, | |
| "train_samples_per_second": 1.352, | |
| "train_steps_per_second": 0.084 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 124, | |
| "num_input_tokens_seen": 2047488, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.955998176351027e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |