Training in progress, step 17200, checkpoint

last-checkpoint/README.md

@@ -1367,6 +1367,10 @@ You can finetune this model on your own dataset.
 | 0.2986 | 16900 | 0.3352        |
 | 0.2995 | 16950 | 0.3812        |
 | 0.3004 | 17000 | 0.3332        |
+| 0.3013 | 17050 | 0.3472        |
+| 0.3022 | 17100 | 0.4207        |
+| 0.3031 | 17150 | 0.3849        |
+| 0.3039 | 17200 | 0.3272        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ad97b260860972b9730f175955e3ce530db8323f7dc5bcf0e90933d6b8fb84
+oid sha256:c8aa8eabf0bd95daa104946b416f3292c9a92c6053a47e54e8098083f61f3874
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd7069f1a068fd2c2876d55655006ec19b8c2319d576c34cff13d207d6cb5d3
+oid sha256:550870691770e56b635695a47badd3d85105a2abddd01d2f68ac682eb4779cfb
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbc5938b66b6b7b1cb7ca970b428c630e6141cd051d14e46bf204d25c3e87c0
+oid sha256:9642b48564b74a9ef3023b3677305007ed89dfb95240067ad9d1be72f7d2692a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa14b4995859788df7ef8bb3ac5bf3bef25e341abeaa5e3ae0de74c72a4065ee
+oid sha256:4c157b3717ebad1d1c4deed2f4a1e630570eeaf89e281bb553ac41881d02a28e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16324e1fa03eb15f85ccd89e40ca9aaf90eafb16b60693a1698d40074577c527
+oid sha256:fcdcffdcd8983b3d6481c27ecbd4b8783b8846e8b39268fee55aae8ba8b88e41
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3004011238536163,
+  "epoch": 0.3039352547224824,
   "eval_steps": 500,
-  "global_step": 17000,
+  "global_step": 17200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2388,6 +2388,34 @@
       "learning_rate": 3.887219964265379e-05,
       "loss": 0.3332,
       "step": 17000
+    },
+    {
+      "epoch": 0.3012846565708328,
+      "grad_norm": 1.9923433065414429,
+      "learning_rate": 3.882311362431525e-05,
+      "loss": 0.3472,
+      "step": 17050
+    },
+    {
+      "epoch": 0.30216818928804934,
+      "grad_norm": 1.5736125707626343,
+      "learning_rate": 3.8774027605976714e-05,
+      "loss": 0.4207,
+      "step": 17100
+    },
+    {
+      "epoch": 0.30305172200526587,
+      "grad_norm": 2.2181496620178223,
+      "learning_rate": 3.872494158763818e-05,
+      "loss": 0.3849,
+      "step": 17150
+    },
+    {
+      "epoch": 0.3039352547224824,
+      "grad_norm": 1.5112169981002808,
+      "learning_rate": 3.867585556929964e-05,
+      "loss": 0.3272,
+      "step": 17200
     }
   ],
   "logging_steps": 50,