Training in progress, step 48400, checkpoint

last-checkpoint/README.md

@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
 | 0.8500 | 48100 | 0.2989        |
 | 0.8508 | 48150 | 0.3259        |
 | 0.8517 | 48200 | 0.2949        |
+| 0.8526 | 48250 | 0.3914        |
+| 0.8535 | 48300 | 0.2645        |
+| 0.8544 | 48350 | 0.3358        |
+| 0.8553 | 48400 | 0.2939        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4294436b31337b8f68a1a6e59bc31c1c50d6ea48412e337c4f3f279629185a2b
+oid sha256:1b3690fa2a143ecb0d4643a209624dc7188c601389b80bc7eadb77baedd884c8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd725319401ffadaefeead1ad1a2cc0dd183fa2e660298c1a19fdcb910503bc
+oid sha256:b68bdb8f5b522fdce4d5c267f15db43e12a7fbffda0d7ac355cca5fe6e2293a9
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab981814c6b01f5ae8f1a22b4a3f98efeff40368e2035bd20d25f06a479e607f
+oid sha256:1337b9c73878b431640eabbf713a3fc3ffa1889559f5fe2e1f50b06fa34639d6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efc050901e150a59e85c2ab742c4d82ce79ba854a2e4dcd71f14091e10af7e2
+oid sha256:b78f9ce48aa6920e09eb307b60e2b49742b779f95ad33075f31c6652ec108e55
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1d3fc7b5bb4b8d1485e3784ebbc483bfa2d10789ae8506a40f9ef3d604aa52
+oid sha256:0bd8a22cf09f7fa5f8eaecff8876d6b0aa930d2f190895e8ce37c95ed1dd7a48
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8517255393967239,
+  "epoch": 0.8552596702655899,
   "eval_steps": 500,
-  "global_step": 48200,
+  "global_step": 48400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6756,6 +6756,34 @@
       "learning_rate": 8.256268284541832e-06,
       "loss": 0.2949,
       "step": 48200
+    },
+    {
+      "epoch": 0.8526090721139403,
+      "grad_norm": 1.490918517112732,
+      "learning_rate": 8.207182266203294e-06,
+      "loss": 0.3914,
+      "step": 48250
+    },
+    {
+      "epoch": 0.8534926048311569,
+      "grad_norm": 1.5268231630325317,
+      "learning_rate": 8.158096247864759e-06,
+      "loss": 0.2645,
+      "step": 48300
+    },
+    {
+      "epoch": 0.8543761375483734,
+      "grad_norm": 1.9607213735580444,
+      "learning_rate": 8.109010229526222e-06,
+      "loss": 0.3358,
+      "step": 48350
+    },
+    {
+      "epoch": 0.8552596702655899,
+      "grad_norm": 1.4697561264038086,
+      "learning_rate": 8.059924211187687e-06,
+      "loss": 0.2939,
+      "step": 48400
     }
   ],
   "logging_steps": 50,