Training in progress, step 25

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354d9bc55a0da441ec464af2662101a8a5bcd9e1eb41e440f429de75a19f8b07
+oid sha256:985a59e03c616455184cf4dcf00ba8e95ffe24b639ec01ea8ff6aa571c96d2b4
 size 42002136

logging.jsonl

@@ -17,3 +17,14 @@
 {"loss": 1.72712588, "token_acc": 0.57186544, "grad_norm": 1.11258352, "learning_rate": 0.00013784, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.737209, "epoch": 0.13821138, "global_step/max_steps": "17/369", "percentage": "4.61%", "elapsed_time": "17s", "remaining_time": "6m 1s"}
 {"loss": 1.48443031, "token_acc": 0.67521368, "grad_norm": 0.99743199, "learning_rate": 0.00014595, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.750267, "epoch": 0.14634146, "global_step/max_steps": "18/369", "percentage": "4.88%", "elapsed_time": "18s", "remaining_time": "5m 58s"}
 {"loss": 1.01479948, "token_acc": 0.77894737, "grad_norm": 0.84560066, "learning_rate": 0.00015405, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.76235, "epoch": 0.15447154, "global_step/max_steps": "19/369", "percentage": "5.15%", "elapsed_time": "19s", "remaining_time": "5m 55s"}
+{"loss": 0.96872497, "token_acc": 0.81604697, "grad_norm": 0.63404536, "learning_rate": 0.00016216, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.773341, "epoch": 0.16260163, "global_step/max_steps": "20/369", "percentage": "5.42%", "elapsed_time": "20s", "remaining_time": "5m 53s"}
+{"loss": 1.54066253, "token_acc": 0.64589235, "grad_norm": 1.19960952, "learning_rate": 0.00017027, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.778297, "epoch": 0.17073171, "global_step/max_steps": "21/369", "percentage": "5.69%", "elapsed_time": "21s", "remaining_time": "5m 53s"}
+{"loss": 1.09321463, "token_acc": 0.75870647, "grad_norm": 0.98395354, "learning_rate": 0.00017838, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.788066, "epoch": 0.17886179, "global_step/max_steps": "22/369", "percentage": "5.96%", "elapsed_time": "22s", "remaining_time": "5m 51s"}
+{"loss": 1.52431905, "token_acc": 0.62971698, "grad_norm": 1.01811945, "learning_rate": 0.00018649, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.797395, "epoch": 0.18699187, "global_step/max_steps": "23/369", "percentage": "6.23%", "elapsed_time": "23s", "remaining_time": "5m 49s"}
+{"loss": 1.36404324, "token_acc": 0.68711656, "grad_norm": 1.43212712, "learning_rate": 0.00019459, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.806093, "epoch": 0.19512195, "global_step/max_steps": "24/369", "percentage": "6.50%", "elapsed_time": "24s", "remaining_time": "5m 47s"}
+{"loss": 1.73998666, "token_acc": 0.58227848, "grad_norm": 1.83553851, "learning_rate": 0.0002027, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.813782, "epoch": 0.20325203, "global_step/max_steps": "25/369", "percentage": "6.78%", "elapsed_time": "25s", "remaining_time": "5m 45s"}
+{"loss": 1.37766147, "token_acc": 0.64367816, "grad_norm": 1.23328626, "learning_rate": 0.00021081, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.813136, "epoch": 0.21138211, "global_step/max_steps": "26/369", "percentage": "7.05%", "elapsed_time": "26s", "remaining_time": "5m 47s"}
+{"loss": 1.86809516, "token_acc": 0.5654321, "grad_norm": 1.28665292, "learning_rate": 0.00021892, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.820506, "epoch": 0.2195122, "global_step/max_steps": "27/369", "percentage": "7.32%", "elapsed_time": "27s", "remaining_time": "5m 45s"}
+{"loss": 1.36566472, "token_acc": 0.69902913, "grad_norm": 3.60822392, "learning_rate": 0.00022703, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.827584, "epoch": 0.22764228, "global_step/max_steps": "28/369", "percentage": "7.59%", "elapsed_time": "28s", "remaining_time": "5m 43s"}
+{"loss": 1.76258373, "token_acc": 0.62043796, "grad_norm": 1.86583698, "learning_rate": 0.00023514, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.834279, "epoch": 0.23577236, "global_step/max_steps": "29/369", "percentage": "7.86%", "elapsed_time": "29s", "remaining_time": "5m 41s"}
+{"loss": 1.77485406, "token_acc": 0.5902439, "grad_norm": 1.40830421, "learning_rate": 0.00024324, "memory(GiB)": 9.6, "train_speed(iter/s)": 0.84061, "epoch": 0.24390244, "global_step/max_steps": "30/369", "percentage": "8.13%", "elapsed_time": "30s", "remaining_time": "5m 39s"}