Training in progress, step 49800, checkpoint

last-checkpoint/README.md

@@ -1285,6 +1285,10 @@ You can finetune this model on your own dataset.
 | 0.8747 | 49500 | 0.3182        |
 | 0.8756 | 49550 | 0.3063        |
 | 0.8765 | 49600 | 0.2385        |
+| 0.8773 | 49650 | 0.3152        |
+| 0.8782 | 49700 | 0.267         |
+| 0.8791 | 49750 | 0.2599        |
+| 0.8800 | 49800 | 0.3226        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8131e17a996f8828e5a4d3b270f9fd8ff6e941e36a00908536ef7a5e8550aaba
+oid sha256:ed2d369eb5785f37e695387aeb0f0e1b88aba7649dea47063848b806090ff91f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1ac75d8f0e3ef9befe27d47520e773ab09b8e31d1344e3def76ce5cd49eb10
+oid sha256:7c88873a80431132be5b9a6198db1d2eb68145fe27f94342674f074b433cbd62
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:281a95f6afaa2c9511c5ed8a9ce2381872188baca75f43c1972f2ab2f8eef316
+oid sha256:a0c031c47895ee65720a29aa486037b758096a0c008e8c7d3bf0a06b848dd598
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cac657ef6092bde192981138bb915fe2e134b5e72b8ef8fc2e6cf2847fb45f5
+oid sha256:98ce6fbeef0ab2e0cecf23435bfa5221dc56a6ce59fe8d9b84d1e42bcc5d69c4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81093c41fdabf9a6d7f304a197f461407189d93225316dffdaf89ead0f00b3f5
+oid sha256:1cd200196e0f200dd4627f60d44a82669aaadc601edaa64b9c6e1ddba3c662c9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8764644554787864,
+  "epoch": 0.8799985863476525,
   "eval_steps": 500,
-  "global_step": 49600,
+  "global_step": 49800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6952,6 +6952,34 @@
       "learning_rate": 6.8828414914295815e-06,
       "loss": 0.2385,
       "step": 49600
+    },
+    {
+      "epoch": 0.8773479881960029,
+      "grad_norm": 1.3927173614501953,
+      "learning_rate": 6.833755473091045e-06,
+      "loss": 0.3152,
+      "step": 49650
+    },
+    {
+      "epoch": 0.8782315209132194,
+      "grad_norm": 1.4090054035186768,
+      "learning_rate": 6.784669454752508e-06,
+      "loss": 0.267,
+      "step": 49700
+    },
+    {
+      "epoch": 0.879115053630436,
+      "grad_norm": 1.5765697956085205,
+      "learning_rate": 6.735583436413972e-06,
+      "loss": 0.2599,
+      "step": 49750
+    },
+    {
+      "epoch": 0.8799985863476525,
+      "grad_norm": 1.617443323135376,
+      "learning_rate": 6.686497418075435e-06,
+      "loss": 0.3226,
+      "step": 49800
     }
   ],
   "logging_steps": 50,