Saiga-7b-lora / trainer_log.jsonl
SouthMemphis's picture
Upload 13 files
38f54d5 verified
raw
history blame
3.19 kB
{"current_steps": 10, "total_steps": 125, "loss": 1.1006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:07:39", "remaining_time": "1:28:05"}
{"current_steps": 20, "total_steps": 125, "loss": 1.049, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.690766700109659e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:15:35", "remaining_time": "1:21:52"}
{"current_steps": 30, "total_steps": 125, "loss": 1.0269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3224215685535294e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:23:16", "remaining_time": "1:13:41"}
{"current_steps": 40, "total_steps": 125, "loss": 0.9896, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8395669874474915e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:30:51", "remaining_time": "1:05:35"}
{"current_steps": 50, "total_steps": 125, "loss": 1.0179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.272542485937369e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:38:41", "remaining_time": "0:58:01"}
{"current_steps": 60, "total_steps": 125, "loss": 0.9636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.656976298823284e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:46:22", "remaining_time": "0:50:14"}
{"current_steps": 70, "total_steps": 125, "loss": 1.0151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.031546713535688e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:53:53", "remaining_time": "0:42:20"}
{"current_steps": 80, "total_steps": 125, "loss": 1.0039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4355517710873184e-05, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "1:01:41", "remaining_time": "0:34:42"}
{"current_steps": 90, "total_steps": 125, "loss": 0.9773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.064400256282757e-06, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "1:09:26", "remaining_time": "0:27:00"}
{"current_steps": 100, "total_steps": 125, "loss": 0.9578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7745751406263165e-06, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "1:17:13", "remaining_time": "0:19:18"}
{"current_steps": 110, "total_steps": 125, "loss": 0.9773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7555878527937164e-06, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "1:25:03", "remaining_time": "0:11:35"}
{"current_steps": 120, "total_steps": 125, "loss": 1.0422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9713246713805588e-07, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "1:32:57", "remaining_time": "0:03:52"}
{"current_steps": 125, "total_steps": 125, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:36:53", "remaining_time": "0:00:00"}