Training in progress, step 50400, checkpoint

last-checkpoint/README.md

@@ -1299,6 +1299,10 @@ You can finetune this model on your own dataset.
 | 0.8853 | 50100 | 0.3104        |
 | 0.8862 | 50150 | 0.368         |
 | 0.8871 | 50200 | 0.2848        |
+| 0.8880 | 50250 | 0.4137        |
+| 0.8888 | 50300 | 0.3597        |
+| 0.8897 | 50350 | 0.3246        |
+| 0.8906 | 50400 | 0.2658        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832b902e0fe022fef9cf3e9c3121c2fef0fa24fcbf8488a9cdbb81608e3c7db7
+oid sha256:4402d5595619f726b76f6c11fbb431abe89c0fdd64c6e52d57bdcebda5c57397
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146ff956fa4854ee7e070302bc46d20219774de158993ea087895544f881af40
+oid sha256:68b89f5d87aba4126dddf46cba6f5468fca0adb9ffb6a7c457ba09e31e0cf598
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a89f1ae855fe394d47db931fc0083ae8bdcb1b72bbe34b1c88a5de1f09827b7
+oid sha256:9f76286cc6f7170c117d180053396109205046e24f113f39ebb7eba52374e471
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc8c4b0c63d5380ba075a90ba10318e03e7b9bf88808901ab396ecc55b1ae6b
+oid sha256:7f630d12e96ea581a03c83786f1675e35621e66e28e380551b7eca37b86e7c85
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6400bb8657149255aa24266b64f7fcdf0a428df1c18993fd61a2168a5c57c5d
+oid sha256:56730b1eb2f09afcd359899fa053433fb9b0469fdf6908ef9d55d03c5ac4ee2e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8870668480853846,
+  "epoch": 0.8906009789542507,
   "eval_steps": 500,
-  "global_step": 50200,
+  "global_step": 50400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7036,6 +7036,34 @@
       "learning_rate": 6.293809271367145e-06,
       "loss": 0.2848,
       "step": 50200
+    },
+    {
+      "epoch": 0.8879503808026011,
+      "grad_norm": 1.1558799743652344,
+      "learning_rate": 6.244723253028607e-06,
+      "loss": 0.4137,
+      "step": 50250
+    },
+    {
+      "epoch": 0.8888339135198177,
+      "grad_norm": 1.2852174043655396,
+      "learning_rate": 6.195637234690072e-06,
+      "loss": 0.3597,
+      "step": 50300
+    },
+    {
+      "epoch": 0.8897174462370342,
+      "grad_norm": 2.747140407562256,
+      "learning_rate": 6.146551216351535e-06,
+      "loss": 0.3246,
+      "step": 50350
+    },
+    {
+      "epoch": 0.8906009789542507,
+      "grad_norm": 1.5731008052825928,
+      "learning_rate": 6.097465198012998e-06,
+      "loss": 0.2658,
+      "step": 50400
     }
   ],
   "logging_steps": 50,