| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5333333333333333, | |
| "eval_steps": 25, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.3797595190380762e-05, | |
| "loss": 3.5104, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 2.643505334854126, | |
| "eval_runtime": 13.8992, | |
| "eval_samples_per_second": 17.987, | |
| "eval_steps_per_second": 2.302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 2.2052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.966366171836853, | |
| "eval_runtime": 13.6092, | |
| "eval_samples_per_second": 18.37, | |
| "eval_steps_per_second": 2.351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.1292585170340683e-05, | |
| "loss": 1.81, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.8134992122650146, | |
| "eval_runtime": 13.5125, | |
| "eval_samples_per_second": 18.501, | |
| "eval_steps_per_second": 2.368, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.0040080160320643e-05, | |
| "loss": 1.705, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7801309823989868, | |
| "eval_runtime": 13.4868, | |
| "eval_samples_per_second": 18.537, | |
| "eval_steps_per_second": 2.373, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.87875751503006e-05, | |
| "loss": 1.6288, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.7698311805725098, | |
| "eval_runtime": 13.6256, | |
| "eval_samples_per_second": 18.348, | |
| "eval_steps_per_second": 2.349, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.7535070140280564e-05, | |
| "loss": 1.7262, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.7579054832458496, | |
| "eval_runtime": 13.6761, | |
| "eval_samples_per_second": 18.28, | |
| "eval_steps_per_second": 2.34, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.628256513026052e-05, | |
| "loss": 1.6657, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.7578012943267822, | |
| "eval_runtime": 13.4284, | |
| "eval_samples_per_second": 18.617, | |
| "eval_steps_per_second": 2.383, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5030060120240483e-05, | |
| "loss": 1.6197, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.7506276369094849, | |
| "eval_runtime": 13.5018, | |
| "eval_samples_per_second": 18.516, | |
| "eval_steps_per_second": 2.37, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.3777555110220442e-05, | |
| "loss": 1.7643, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.745801568031311, | |
| "eval_runtime": 13.5003, | |
| "eval_samples_per_second": 18.518, | |
| "eval_steps_per_second": 2.37, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.25250501002004e-05, | |
| "loss": 1.6707, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.7450388669967651, | |
| "eval_runtime": 13.3223, | |
| "eval_samples_per_second": 18.765, | |
| "eval_steps_per_second": 2.402, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.1272545090180361e-05, | |
| "loss": 1.6439, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.7427024841308594, | |
| "eval_runtime": 13.3162, | |
| "eval_samples_per_second": 18.774, | |
| "eval_steps_per_second": 2.403, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.0020040080160322e-05, | |
| "loss": 1.5697, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.7423481941223145, | |
| "eval_runtime": 13.6598, | |
| "eval_samples_per_second": 18.302, | |
| "eval_steps_per_second": 2.343, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.767535070140282e-06, | |
| "loss": 1.6362, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.7418254613876343, | |
| "eval_runtime": 13.299, | |
| "eval_samples_per_second": 18.798, | |
| "eval_steps_per_second": 2.406, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.515030060120242e-06, | |
| "loss": 1.607, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.738572120666504, | |
| "eval_runtime": 13.7472, | |
| "eval_samples_per_second": 18.186, | |
| "eval_steps_per_second": 2.328, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.2625250501002e-06, | |
| "loss": 1.5168, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.7354249954223633, | |
| "eval_runtime": 13.5456, | |
| "eval_samples_per_second": 18.456, | |
| "eval_steps_per_second": 2.362, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.010020040080161e-06, | |
| "loss": 1.6947, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.7342841625213623, | |
| "eval_runtime": 13.8125, | |
| "eval_samples_per_second": 18.1, | |
| "eval_steps_per_second": 2.317, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 6573652967424000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |