Training in progress, step 32400, checkpoint

last-checkpoint/README.md

@@ -1307,6 +1307,10 @@ You can finetune this model on your own dataset.
 | 0.5672 | 32100 | 0.2491        |
 | 0.5681 | 32150 | 0.2663        |
 | 0.5690 | 32200 | 0.3433        |
+| 0.5699 | 32250 | 0.3375        |
+| 0.5708 | 32300 | 0.2891        |
+| 0.5716 | 32350 | 0.296         |
+| 0.5725 | 32400 | 0.2478        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059e5ea13c385fd2b7824c1ae9f5d7517f93ed2064e18f707d204b5f00551fcf
+oid sha256:ae7029cc4a936db82aecdfc345ae4f6be581e777c25d3e011d86f49807e6bd27
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3628f48729b03521592b21ba8e241dd8f7b12c27ab2d17f87975f425eeac02df
+oid sha256:ffb5e77212890ce43c0fc7a397665bcd4da432ff88fa93a14b948bcf16b02cdd
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d8e0757ed6c29dd6ad40d6348476d9c45a6c913dbe6d558683a2aff7f6eeaa
+oid sha256:aa682a307fc96e53a68118cb34dd8ebd33bebc1ee7d8a07cfe20e4ef67c0641e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d2345a7bbddb12fb6a365e62bd73e47296785a601a5379725821a73d3794f3
+oid sha256:e7d183fbaa9612fc768da7cf7cefd13466b61ea27398ff0fc8e2f5977752f4ef
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe5ee6b9c7e51d497fade31af9f8cbe420701d187e60d0b9c360cfa22b492c4
+oid sha256:71836e8eeb9479ebd5deabd14069458b8ae082f80c2be8da5292f909ebf1971a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.568995069887438,
+  "epoch": 0.572529200756304,
   "eval_steps": 500,
-  "global_step": 32200,
+  "global_step": 32400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4516,6 +4516,34 @@
       "learning_rate": 2.395594038993933e-05,
       "loss": 0.3433,
       "step": 32200
+    },
+    {
+      "epoch": 0.5698786026046545,
+      "grad_norm": 1.4697036743164062,
+      "learning_rate": 2.3906854371600795e-05,
+      "loss": 0.3375,
+      "step": 32250
+    },
+    {
+      "epoch": 0.5707621353218709,
+      "grad_norm": 2.39277720451355,
+      "learning_rate": 2.385776835326226e-05,
+      "loss": 0.2891,
+      "step": 32300
+    },
+    {
+      "epoch": 0.5716456680390875,
+      "grad_norm": 1.5755674839019775,
+      "learning_rate": 2.380868233492372e-05,
+      "loss": 0.296,
+      "step": 32350
+    },
+    {
+      "epoch": 0.572529200756304,
+      "grad_norm": 1.5802369117736816,
+      "learning_rate": 2.3759596316585182e-05,
+      "loss": 0.2478,
+      "step": 32400
     }
   ],
   "logging_steps": 50,