Training in progress, step 29

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d75631fa28d59b23937f7209eecbe72cf5b2457493a5c10a7d7b2b91b74cd4
+oid sha256:aed37a42eb32c018b99f8a2ea54f2d721d1910bc576a33053a7beb1601e0530a
 size 739322344

logging.jsonl

@@ -20,3 +20,14 @@
 {"loss": 0.21260472, "token_acc": 0.9241944, "grad_norm": 2.05847311, "learning_rate": 3.85e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022284, "epoch": 0.64680851, "global_step/max_steps": "19/29", "percentage": "65.52%", "elapsed_time": "14m 5s", "remaining_time": "7m 25s"}
 {"loss": 0.23483819, "token_acc": 0.90957684, "grad_norm": 1.9506942, "learning_rate": 3.46e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022228, "epoch": 0.68085106, "global_step/max_steps": "20/29", "percentage": "68.97%", "elapsed_time": "14m 52s", "remaining_time": "6m 41s"}
 {"eval_loss": 0.20867875, "eval_token_acc": 0.92511696, "eval_runtime": 13.0105, "eval_samples_per_second": 4.381, "eval_steps_per_second": 0.615, "epoch": 0.68085106, "global_step/max_steps": "20/29", "percentage": "68.97%", "elapsed_time": "15m 5s", "remaining_time": "6m 47s"}
+{"loss": 0.20101674, "token_acc": 0.92574786, "grad_norm": 1.76422858, "learning_rate": 3.08e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.02181, "epoch": 0.71489362, "global_step/max_steps": "21/29", "percentage": "72.41%", "elapsed_time": "15m 55s", "remaining_time": "6m 4s"}
+{"loss": 0.20781831, "token_acc": 0.93246598, "grad_norm": 2.15241098, "learning_rate": 2.69e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.0219, "epoch": 0.74893617, "global_step/max_steps": "22/29", "percentage": "75.86%", "elapsed_time": "16m 37s", "remaining_time": "5m 17s"}
+{"loss": 0.20801759, "token_acc": 0.93892848, "grad_norm": 2.22540712, "learning_rate": 2.31e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.021942, "epoch": 0.78297872, "global_step/max_steps": "23/29", "percentage": "79.31%", "elapsed_time": "17m 21s", "remaining_time": "4m 31s"}
+{"loss": 0.18198422, "token_acc": 0.94633731, "grad_norm": 1.63598311, "learning_rate": 1.92e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.021974, "epoch": 0.81702128, "global_step/max_steps": "24/29", "percentage": "82.76%", "elapsed_time": "18m 5s", "remaining_time": "3m 46s"}
+{"loss": 0.19455627, "token_acc": 0.92534722, "grad_norm": 2.62162328, "learning_rate": 1.54e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.02211, "epoch": 0.85106383, "global_step/max_steps": "25/29", "percentage": "86.21%", "elapsed_time": "18m 43s", "remaining_time": "2m 59s"}
+{"loss": 0.19514789, "token_acc": 0.94586842, "grad_norm": 1.7049104, "learning_rate": 1.15e-06, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022122, "epoch": 0.88510638, "global_step/max_steps": "26/29", "percentage": "89.66%", "elapsed_time": "19m 28s", "remaining_time": "2m 14s"}
+{"loss": 0.19851573, "token_acc": 0.91834848, "grad_norm": 1.9396106, "learning_rate": 7.7e-07, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022067, "epoch": 0.91914894, "global_step/max_steps": "27/29", "percentage": "93.10%", "elapsed_time": "20m 16s", "remaining_time": "1m 30s"}
+{"loss": 0.18254727, "token_acc": 0.93301435, "grad_norm": 1.87893045, "learning_rate": 3.8e-07, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022131, "epoch": 0.95319149, "global_step/max_steps": "28/29", "percentage": "96.55%", "elapsed_time": "20m 58s", "remaining_time": "44s"}
+{"loss": 0.192018, "token_acc": 0.92320897, "grad_norm": 1.8398602, "learning_rate": 0.0, "memory(GiB)": 115.29, "train_speed(iter/s)": 0.022196, "epoch": 0.98723404, "global_step/max_steps": "29/29", "percentage": "100.00%", "elapsed_time": "21m 39s", "remaining_time": "0s"}
+{"eval_loss": 0.19650522, "eval_token_acc": 0.92934145, "eval_runtime": 13.0396, "eval_samples_per_second": 4.371, "eval_steps_per_second": 0.614, "epoch": 0.98723404, "global_step/max_steps": "29/29", "percentage": "100.00%", "elapsed_time": "21m 52s", "remaining_time": "0s"}
+{"train_runtime": 1317.4623, "train_samples_per_second": 1.423, "train_steps_per_second": 0.022, "total_flos": 39523818274816.0, "train_loss": 0.25552522, "epoch": 0.98723404, "global_step/max_steps": "29/29", "percentage": "100.00%", "elapsed_time": "21m 57s", "remaining_time": "0s"}

runs/events.out.tfevents.1744086424.notebook-67532d59-da58-11ef-a92b-d22a634ff48d-0.693841.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f5c081ccef106a51247aec3cb3825d24a2eacb87e3955619ba3c1688b9d96b
-size 15049
+oid sha256:ca8e3d966b43fe948036b57994c19ac76547de92db09c8b65ed3efdc1bd714e4
+size 19117