| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10816657652785289, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01081665765278529, | |
| "eval_accuracy": 0.7290303584415322, | |
| "eval_loss": 1.2268004417419434, | |
| "eval_runtime": 456.6189, | |
| "eval_samples_per_second": 34.25, | |
| "eval_steps_per_second": 1.071, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02163331530557058, | |
| "eval_accuracy": 0.7563876376099345, | |
| "eval_loss": 1.078468918800354, | |
| "eval_runtime": 456.7154, | |
| "eval_samples_per_second": 34.242, | |
| "eval_steps_per_second": 1.071, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03244997295835587, | |
| "eval_accuracy": 0.7668799267017361, | |
| "eval_loss": 1.0238652229309082, | |
| "eval_runtime": 456.7597, | |
| "eval_samples_per_second": 34.239, | |
| "eval_steps_per_second": 1.071, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04326663061114116, | |
| "eval_accuracy": 0.7730476325324204, | |
| "eval_loss": 0.9894265532493591, | |
| "eval_runtime": 456.7371, | |
| "eval_samples_per_second": 34.241, | |
| "eval_steps_per_second": 1.071, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05408328826392644, | |
| "grad_norm": 2.1639328002929688, | |
| "learning_rate": 4.909861186226789e-05, | |
| "loss": 1.2276, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05408328826392644, | |
| "eval_accuracy": 0.7784154459204475, | |
| "eval_loss": 0.9612082839012146, | |
| "eval_runtime": 456.6452, | |
| "eval_samples_per_second": 34.248, | |
| "eval_steps_per_second": 1.071, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06489994591671173, | |
| "eval_accuracy": 0.782137070411325, | |
| "eval_loss": 0.9466578960418701, | |
| "eval_runtime": 456.6288, | |
| "eval_samples_per_second": 34.249, | |
| "eval_steps_per_second": 1.071, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07571660356949703, | |
| "eval_accuracy": 0.7840395143262153, | |
| "eval_loss": 0.930482804775238, | |
| "eval_runtime": 456.4891, | |
| "eval_samples_per_second": 34.259, | |
| "eval_steps_per_second": 1.071, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.08653326122228232, | |
| "eval_accuracy": 0.7867131143188731, | |
| "eval_loss": 0.9141340851783752, | |
| "eval_runtime": 456.5273, | |
| "eval_samples_per_second": 34.256, | |
| "eval_steps_per_second": 1.071, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.09734991887506761, | |
| "eval_accuracy": 0.7895170312687647, | |
| "eval_loss": 0.9005721211433411, | |
| "eval_runtime": 456.6578, | |
| "eval_samples_per_second": 34.247, | |
| "eval_steps_per_second": 1.071, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.10816657652785289, | |
| "grad_norm": 1.771813154220581, | |
| "learning_rate": 4.819722372453579e-05, | |
| "loss": 0.9226, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10816657652785289, | |
| "eval_accuracy": 0.7909631562396202, | |
| "eval_loss": 0.896154522895813, | |
| "eval_runtime": 456.9174, | |
| "eval_samples_per_second": 34.227, | |
| "eval_steps_per_second": 1.07, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27735, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 7.41887283560448e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |