| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.603550295857988, | |
| "eval_steps": 5, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11834319526627218, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.6428, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11834319526627218, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.5284, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.153, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.992981096013517e-05, | |
| "loss": 2.6411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7203, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35502958579881655, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.964635581908359e-05, | |
| "loss": 2.6552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.35502958579881655, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7242, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9151456172430186e-05, | |
| "loss": 2.6293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.967, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.845596003501826e-05, | |
| "loss": 2.6225, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 268.4624, | |
| "eval_samples_per_second": 0.603, | |
| "eval_steps_per_second": 0.153, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7575112421616203e-05, | |
| "loss": 2.6365, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.8379, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8284023668639053, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.6528221181905217e-05, | |
| "loss": 2.6304, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8284023668639053, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.5669, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.533823377964791e-05, | |
| "loss": 2.6426, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.4996, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.153, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0650887573964498, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4031234292879726e-05, | |
| "loss": 2.6404, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0650887573964498, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7725, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.183431952662722, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2635871660690677e-05, | |
| "loss": 2.6214, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.183431952662722, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7285, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.301775147928994, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1182731709213658e-05, | |
| "loss": 2.636, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.301775147928994, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.906, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.4201183431952662, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.703666721774403e-06, | |
| "loss": 2.6574, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4201183431952662, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.4678, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.153, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.231097248774273e-06, | |
| "loss": 2.6211, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.8967, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.6568047337278107, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.797301461371626e-06, | |
| "loss": 2.6171, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6568047337278107, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.422, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.153, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7751479289940828, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.43370762606287e-06, | |
| "loss": 2.6375, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.7751479289940828, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 268.3368, | |
| "eval_samples_per_second": 0.604, | |
| "eval_steps_per_second": 0.153, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.893491124260355, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.170205208855281e-06, | |
| "loss": 2.6548, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.893491124260355, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.6946, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0118343195266273, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.0344897093700333e-06, | |
| "loss": 2.6684, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.0118343195266273, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.6543, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.1301775147928996, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.0514555858664663e-06, | |
| "loss": 2.6305, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.1301775147928996, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.8601, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.2485207100591715, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2426505780436326e-06, | |
| "loss": 2.6421, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.2485207100591715, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7705, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.366863905325444, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.258033886587911e-07, | |
| "loss": 2.6469, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.366863905325444, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.5145, | |
| "eval_samples_per_second": 0.606, | |
| "eval_steps_per_second": 0.153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.485207100591716, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.1443507700495968e-07, | |
| "loss": 2.6275, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.485207100591716, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.7646, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.603550295857988, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7562682356786488e-08, | |
| "loss": 2.6352, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.603550295857988, | |
| "eval_loss": 2.5045294761657715, | |
| "eval_runtime": 267.6496, | |
| "eval_samples_per_second": 0.605, | |
| "eval_steps_per_second": 0.153, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 5, | |
| "total_flos": 5.736198700007424e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |