| { | |
| "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": 0.4461756944656372, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.6759, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.310316264629364, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.6698, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.21229001879692078, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.6228, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.1769254058599472, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.6228, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.14216263592243195, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.6104, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.12115108221769333, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6063, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.12172728776931763, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.6236, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.1111619770526886, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.6225, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 0.10374017804861069, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.5952, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.10045181959867477, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.6016, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 0.09922054409980774, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.5926, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.09466025233268738, | |
| "learning_rate": 0.0, | |
| "loss": 0.6137, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 12, | |
| "total_flos": 1.0676277147158446e+18, | |
| "train_loss": 0.6214325428009033, | |
| "train_runtime": 1255.1826, | |
| "train_samples_per_second": 4.987, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 25165824, | |
| "num_train_epochs": 1, | |
| "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": 1.0676277147158446e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |