| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.020408163265306, | |
| "eval_steps": 4, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08163265306122448, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0529, | |
| "eval_samples_per_second": 10.23, | |
| "eval_steps_per_second": 1.461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5097, | |
| "eval_samples_per_second": 13.91, | |
| "eval_steps_per_second": 1.987, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5152, | |
| "eval_samples_per_second": 13.86, | |
| "eval_steps_per_second": 1.98, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.865224352899119e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5288, | |
| "eval_samples_per_second": 13.736, | |
| "eval_steps_per_second": 1.962, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.177439057064683e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5277, | |
| "eval_samples_per_second": 13.746, | |
| "eval_steps_per_second": 1.964, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.985792958513931e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5287, | |
| "eval_samples_per_second": 13.738, | |
| "eval_steps_per_second": 1.963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.434016163555452e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.709275855447621e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5298, | |
| "eval_samples_per_second": 13.727, | |
| "eval_steps_per_second": 1.961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019601169804216e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5263, | |
| "eval_samples_per_second": 13.759, | |
| "eval_steps_per_second": 1.966, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5687918106563326e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5277, | |
| "eval_samples_per_second": 13.746, | |
| "eval_steps_per_second": 1.964, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.693877551020408, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.318367983829392e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.380821129028489e-07, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5295, | |
| "eval_samples_per_second": 13.73, | |
| "eval_steps_per_second": 1.961, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 37, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.48250403775447e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |