| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9795918367346939, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 10.881313562892391, | |
| "learning_rate": 1.965925826289068e-06, | |
| "loss": 2.0224, | |
| "num_input_tokens_seen": 1048576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 13.38603350535489, | |
| "learning_rate": 1.8660254037844386e-06, | |
| "loss": 1.9861, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 8.222813240110005, | |
| "learning_rate": 1.7071067811865474e-06, | |
| "loss": 1.9837, | |
| "num_input_tokens_seen": 3145728, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 10.396958079682259, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.9542, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 8.858340282561143, | |
| "learning_rate": 1.2588190451025207e-06, | |
| "loss": 2.0559, | |
| "num_input_tokens_seen": 5242880, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 3.3559993754262956, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8525, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 3.1389545351229113, | |
| "learning_rate": 7.411809548974791e-07, | |
| "loss": 1.8691, | |
| "num_input_tokens_seen": 7340032, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 2.2619715751113194, | |
| "learning_rate": 5.000000000000002e-07, | |
| "loss": 1.8626, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 2.4738597876739514, | |
| "learning_rate": 2.9289321881345254e-07, | |
| "loss": 1.9789, | |
| "num_input_tokens_seen": 9437184, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 2.169239333615782, | |
| "learning_rate": 1.3397459621556128e-07, | |
| "loss": 1.8399, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 2.064624273077457, | |
| "learning_rate": 3.4074173710931796e-08, | |
| "loss": 1.8986, | |
| "num_input_tokens_seen": 11534336, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 2.0479265547550938, | |
| "learning_rate": 0.0, | |
| "loss": 1.8828, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 12, | |
| "total_flos": 19681687633920.0, | |
| "train_loss": 1.9322307407855988, | |
| "train_runtime": 728.4633, | |
| "train_samples_per_second": 0.535, | |
| "train_steps_per_second": 0.016 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 12582912, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 19681687633920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |