Training in progress, step 39400, checkpoint

last-checkpoint/README.md

@@ -1303,6 +1303,10 @@ You can finetune this model on your own dataset.
 | 0.6909 | 39100 | 0.3101        |
 | 0.6918 | 39150 | 0.3094        |
 | 0.6927 | 39200 | 0.2485        |
+| 0.6936 | 39250 | 0.2985        |
+| 0.6945 | 39300 | 0.3039        |
+| 0.6953 | 39350 | 0.2616        |
+| 0.6962 | 39400 | 0.2932        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d6820907915018672901efc19cbb352c179cad3ee4118d2b29f0808a0ba1d9
+oid sha256:94767fd5b6dc20de49ba334fd663d49bbab52439b211b34b6edd17e30405b86c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7813cbc30aeb0e33d540e2c0598083ef1f841767e7b1e8f1969f8a6919b6ff34
+oid sha256:2146c07d6c292a2316614d7a7b9fe3a693a9e0eea9764160ec4f5efec7166df8
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a02a223a41a639360f4d62d4f98e6515f2dbf1c87dd6aca13b94f6ef7e4783
+oid sha256:3bf8f818b4d7a0be92e772ae0a75f67d80a9b767e05b6e9aa8f81d57f578b5ec
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a1e2a4a3b1321cbec7e7bb5a73635e20233c2ebb1cea8ca1f3f936291d006b
+oid sha256:94fbce33b74f960529cb34bc94a882a154a6272486e6b5ab9ab677e9a88bdc6d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e6c3ffd695ace5a45f1a39dea8b91d4823676a2ff025905fd82b1c1cf00906
+oid sha256:0a7bfee7ee542a2c30ee052be1eff9c687ace2bd0997831ad2274df374589ca0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6926896502977505,
+  "epoch": 0.6962237811666167,
   "eval_steps": 500,
-  "global_step": 39200,
+  "global_step": 39400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5496,6 +5496,34 @@
       "learning_rate": 1.708782470401131e-05,
       "loss": 0.2485,
       "step": 39200
+    },
+    {
+      "epoch": 0.6935731830149671,
+      "grad_norm": 1.1664527654647827,
+      "learning_rate": 1.703873868567277e-05,
+      "loss": 0.2985,
+      "step": 39250
+    },
+    {
+      "epoch": 0.6944567157321836,
+      "grad_norm": 1.5030759572982788,
+      "learning_rate": 1.698965266733424e-05,
+      "loss": 0.3039,
+      "step": 39300
+    },
+    {
+      "epoch": 0.6953402484494001,
+      "grad_norm": 1.2608274221420288,
+      "learning_rate": 1.69405666489957e-05,
+      "loss": 0.2616,
+      "step": 39350
+    },
+    {
+      "epoch": 0.6962237811666167,
+      "grad_norm": 1.173496961593628,
+      "learning_rate": 1.6891480630657162e-05,
+      "loss": 0.2932,
+      "step": 39400
     }
   ],
   "logging_steps": 50,