Training in progress, step 36400, checkpoint

last-checkpoint/README.md

@@ -1241,6 +1241,10 @@ You can finetune this model on your own dataset.
 | 0.6379 | 36100 | 0.3065        |
 | 0.6388 | 36150 | 0.3696        |
 | 0.6397 | 36200 | 0.2626        |
+| 0.6406 | 36250 | 0.2681        |
+| 0.6414 | 36300 | 0.3015        |
+| 0.6423 | 36350 | 0.3587        |
+| 0.6432 | 36400 | 0.4138        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9d5f4c75c0e59ead8c90d7f477a6c4f2a76d4f920d64487f7b3f0f977bf04b
+oid sha256:d6fa930b0dab86162d7efbd96968c6c8ec876ad504bda8baf56c94db0aa7a0fe
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af000b0347dc95901909529dc9cfdc24424b2749e401e23c461b99b8dd8404e4
+oid sha256:fac4d3dd23450aee08424612d1db499ef9235974098ad78434fec72fecee4d6d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e48436107029949f024f9a54ee806776f3466bbed0983b649683798572c860
+oid sha256:314b323b3a511d67b15dea57468e46e599190af351ebf5549ffaf80b2c3a5647
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de71f94cd2950bde11e0c308e88441a6d73f11c2bf00a620f09d97b4f7e685a
+oid sha256:9ccfc3ca931bcded792f304859dd31e568836efb9070c3920cd3b589d1e21087
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607bd3d0f644e74e9c8b0820519aa8b98e93f1767aaaa77fb01d3c971b1c38de
+oid sha256:4c17ed076975a0abe48817667748f3429c8046eb3b0e6862704beb7e23213867
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6396776872647594,
+  "epoch": 0.6432118181336255,
   "eval_steps": 500,
-  "global_step": 36200,
+  "global_step": 36400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5076,6 +5076,34 @@
       "learning_rate": 2.0031022363589955e-05,
       "loss": 0.2626,
       "step": 36200
+    },
+    {
+      "epoch": 0.6405612199819759,
+      "grad_norm": 1.4499566555023193,
+      "learning_rate": 1.998193634525142e-05,
+      "loss": 0.2681,
+      "step": 36250
+    },
+    {
+      "epoch": 0.6414447526991924,
+      "grad_norm": 1.7677289247512817,
+      "learning_rate": 1.9932850326912884e-05,
+      "loss": 0.3015,
+      "step": 36300
+    },
+    {
+      "epoch": 0.642328285416409,
+      "grad_norm": 2.6856095790863037,
+      "learning_rate": 1.9883764308574346e-05,
+      "loss": 0.3587,
+      "step": 36350
+    },
+    {
+      "epoch": 0.6432118181336255,
+      "grad_norm": 1.9422292709350586,
+      "learning_rate": 1.983467829023581e-05,
+      "loss": 0.4138,
+      "step": 36400
     }
   ],
   "logging_steps": 50,