Training in progress, step 48200, checkpoint

last-checkpoint/README.md

@@ -1253,6 +1253,10 @@ You can finetune this model on your own dataset.
 | 0.8464 | 47900 | 0.2914        |
 | 0.8473 | 47950 | 0.3219        |
 | 0.8482 | 48000 | 0.3104        |
+| 0.8491 | 48050 | 0.3676        |
+| 0.8500 | 48100 | 0.2989        |
+| 0.8508 | 48150 | 0.3259        |
+| 0.8517 | 48200 | 0.2949        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d06b1080b11ff71d438c79d42b856600d8a1837767cc93a0f4b910c0a5b3bbe
+oid sha256:4294436b31337b8f68a1a6e59bc31c1c50d6ea48412e337c4f3f279629185a2b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ed6a39e52c37128938194bb73101a8a9722b0f52ba4f5496c71d280b71e9fc
+oid sha256:3dd725319401ffadaefeead1ad1a2cc0dd183fa2e660298c1a19fdcb910503bc
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddda33f244c8e8c75c77f432ddeb1ecd4a5542f0afaeca6c9a4938180a8390c2
+oid sha256:ab981814c6b01f5ae8f1a22b4a3f98efeff40368e2035bd20d25f06a479e607f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c19235faf86fc7b488d049c5de2dd9270a2ad7d80400a9f4692705e68f0f698f
+oid sha256:3efc050901e150a59e85c2ab742c4d82ce79ba854a2e4dcd71f14091e10af7e2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac25fdb927a745ab43f8015082d3fd4a83655134c52103466f1ab5cd6a68cc3
+oid sha256:8b1d3fc7b5bb4b8d1485e3784ebbc483bfa2d10789ae8506a40f9ef3d604aa52
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8481914085278578,
+  "epoch": 0.8517255393967239,
   "eval_steps": 500,
-  "global_step": 48000,
+  "global_step": 48200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6728,6 +6728,34 @@
       "learning_rate": 8.452612357895976e-06,
       "loss": 0.3104,
       "step": 48000
+    },
+    {
+      "epoch": 0.8490749412450743,
+      "grad_norm": 1.4819157123565674,
+      "learning_rate": 8.403526339557441e-06,
+      "loss": 0.3676,
+      "step": 48050
+    },
+    {
+      "epoch": 0.8499584739622909,
+      "grad_norm": 1.882551670074463,
+      "learning_rate": 8.354440321218904e-06,
+      "loss": 0.2989,
+      "step": 48100
+    },
+    {
+      "epoch": 0.8508420066795074,
+      "grad_norm": 1.3162806034088135,
+      "learning_rate": 8.305354302880369e-06,
+      "loss": 0.3259,
+      "step": 48150
+    },
+    {
+      "epoch": 0.8517255393967239,
+      "grad_norm": 1.8228886127471924,
+      "learning_rate": 8.256268284541832e-06,
+      "loss": 0.2949,
+      "step": 48200
     }
   ],
   "logging_steps": 50,