Training in progress, step 50600, checkpoint

last-checkpoint/README.md

@@ -1303,6 +1303,10 @@ You can finetune this model on your own dataset.
 | 0.8888 | 50300 | 0.3597        |
 | 0.8897 | 50350 | 0.3246        |
 | 0.8906 | 50400 | 0.2658        |
+| 0.8915 | 50450 | 0.2954        |
+| 0.8924 | 50500 | 0.3035        |
+| 0.8933 | 50550 | 0.2654        |
+| 0.8941 | 50600 | 0.2742        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4402d5595619f726b76f6c11fbb431abe89c0fdd64c6e52d57bdcebda5c57397
+oid sha256:a7c4343fcf9b81ee5a6a389eb06b051ae53e0aa443077eb13f9892dc66deceec
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b89f5d87aba4126dddf46cba6f5468fca0adb9ffb6a7c457ba09e31e0cf598
+oid sha256:4c5af64aade248d58122340358b0197dce309cca03ffce8ae549b8f07d208db3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f76286cc6f7170c117d180053396109205046e24f113f39ebb7eba52374e471
+oid sha256:bd5bc13ec5ce0dc9f4391185df8ee21467fa45863b467072b951e2bda0426e6a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f630d12e96ea581a03c83786f1675e35621e66e28e380551b7eca37b86e7c85
+oid sha256:dbdc3fca57fcb200a77e9e8cef345de9804f9877d6a37468a61a5b2e8c3dd1d5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56730b1eb2f09afcd359899fa053433fb9b0469fdf6908ef9d55d03c5ac4ee2e
+oid sha256:8f9f1c43d41c176471993abe4ddcdbee9a97b13ab57ea41f5ea87ce032c51df5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8906009789542507,
+  "epoch": 0.8941351098231167,
   "eval_steps": 500,
-  "global_step": 50400,
+  "global_step": 50600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7064,6 +7064,34 @@
       "learning_rate": 6.097465198012998e-06,
       "loss": 0.2658,
       "step": 50400
+    },
+    {
+      "epoch": 0.8914845116714671,
+      "grad_norm": 1.7012232542037964,
+      "learning_rate": 6.048379179674462e-06,
+      "loss": 0.2954,
+      "step": 50450
+    },
+    {
+      "epoch": 0.8923680443886837,
+      "grad_norm": 1.2959450483322144,
+      "learning_rate": 5.999293161335925e-06,
+      "loss": 0.3035,
+      "step": 50500
+    },
+    {
+      "epoch": 0.8932515771059002,
+      "grad_norm": 1.6592167615890503,
+      "learning_rate": 5.950207142997389e-06,
+      "loss": 0.2654,
+      "step": 50550
+    },
+    {
+      "epoch": 0.8941351098231167,
+      "grad_norm": 1.2229481935501099,
+      "learning_rate": 5.901121124658853e-06,
+      "loss": 0.2742,
+      "step": 50600
     }
   ],
   "logging_steps": 50,