Training in progress, step 36600, checkpoint

last-checkpoint/README.md

@@ -1245,6 +1245,10 @@ You can finetune this model on your own dataset.
 | 0.6414 | 36300 | 0.3015        |
 | 0.6423 | 36350 | 0.3587        |
 | 0.6432 | 36400 | 0.4138        |
+| 0.6441 | 36450 | 0.3785        |
+| 0.6450 | 36500 | 0.3385        |
+| 0.6459 | 36550 | 0.3423        |
+| 0.6467 | 36600 | 0.3793        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6fa930b0dab86162d7efbd96968c6c8ec876ad504bda8baf56c94db0aa7a0fe
+oid sha256:ca7dd164817c500b3b0b3eb309058c161c44231d55e86de5617741cab6d433f6
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac4d3dd23450aee08424612d1db499ef9235974098ad78434fec72fecee4d6d
+oid sha256:cc0cc40d7f31f7445b2755794da94775756808444c54ed79215a2f4ba4587b5d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314b323b3a511d67b15dea57468e46e599190af351ebf5549ffaf80b2c3a5647
+oid sha256:601eaff9ad155807e284a57753f11180748beedbe0867ec2d87c3473c45686f9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccfc3ca931bcded792f304859dd31e568836efb9070c3920cd3b589d1e21087
+oid sha256:96159ff1a27b0e4bf72ec118631397adcea3c517425f37b884cdcd074e28ca52
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c17ed076975a0abe48817667748f3429c8046eb3b0e6862704beb7e23213867
+oid sha256:084dd4771d83f8fe540ab84c096a6087e69ee6b4c24571b41efb4b565bf57160
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6432118181336255,
+  "epoch": 0.6467459490024916,
   "eval_steps": 500,
-  "global_step": 36400,
+  "global_step": 36600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5104,6 +5104,34 @@
       "learning_rate": 1.983467829023581e-05,
       "loss": 0.4138,
       "step": 36400
+    },
+    {
+      "epoch": 0.644095350850842,
+      "grad_norm": 0.9389033317565918,
+      "learning_rate": 1.9785592271897275e-05,
+      "loss": 0.3785,
+      "step": 36450
+    },
+    {
+      "epoch": 0.6449788835680585,
+      "grad_norm": 1.297255516052246,
+      "learning_rate": 1.9736506253558736e-05,
+      "loss": 0.3385,
+      "step": 36500
+    },
+    {
+      "epoch": 0.6458624162852751,
+      "grad_norm": 1.0876415967941284,
+      "learning_rate": 1.96874202352202e-05,
+      "loss": 0.3423,
+      "step": 36550
+    },
+    {
+      "epoch": 0.6467459490024916,
+      "grad_norm": 1.2366421222686768,
+      "learning_rate": 1.9638334216881666e-05,
+      "loss": 0.3793,
+      "step": 36600
     }
   ],
   "logging_steps": 50,