Training in progress, step 43000, checkpoint

last-checkpoint/README.md

@@ -1375,6 +1375,10 @@ You can finetune this model on your own dataset.
 | 0.7545 | 42700 | 0.3352        |
 | 0.7554 | 42750 | 0.3143        |
 | 0.7563 | 42800 | 0.2833        |
+| 0.7572 | 42850 | 0.2851        |
+| 0.7581 | 42900 | 0.2956        |
+| 0.7590 | 42950 | 0.3038        |
+| 0.7598 | 43000 | 0.2195        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947ad26bf0a1ea98a40d7847b1d4081968d0ea03f777dd415d118a3341c7d595
+oid sha256:75caeec9f53b9b891200013c0a2fd18951ed97d80436096583e4cb1480de71e5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe6b037eef5d6174a1e64a06f40631b730395d9ff0774dfc1245b870b5a756f
+oid sha256:b1f4e8d78cc6baa416d9c6a87aa0b3025829063989d02f0b2a8b88b559ded826
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0a70fc822cbf0577f57f474f054d71e07e1660e7791d186284f5053153721d
+oid sha256:4be9a690b209a02eb17ce8e3f85da6cd14d4dc8a1275cbf619841edc0fbfa444
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31395f18239b3bc788fb9174ae1acda597a1a3b63f5595848ade3391438691e5
+oid sha256:6cac2489bb213d35fe01f779a670cf1cba6053f86765e6ddff3ab2ce908e2308
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff01474c5f0e5dbd5aec03f387f08f61e0a9ae8d77c69168920103f17f16f317
+oid sha256:beb8449b565ba883e76cbff731d0f062ded7c2721b6cab570d00dd75a772df6d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7563040059373398,
+  "epoch": 0.7598381368062059,
   "eval_steps": 500,
-  "global_step": 42800,
+  "global_step": 43000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6000,6 +6000,34 @@
       "learning_rate": 1.3555594824370226e-05,
       "loss": 0.2833,
       "step": 42800
+    },
+    {
+      "epoch": 0.7571875386545563,
+      "grad_norm": 1.5535756349563599,
+      "learning_rate": 1.350650880603169e-05,
+      "loss": 0.2851,
+      "step": 42850
+    },
+    {
+      "epoch": 0.7580710713717729,
+      "grad_norm": 1.3919951915740967,
+      "learning_rate": 1.3457422787693156e-05,
+      "loss": 0.2956,
+      "step": 42900
+    },
+    {
+      "epoch": 0.7589546040889894,
+      "grad_norm": 1.531242847442627,
+      "learning_rate": 1.3408336769354619e-05,
+      "loss": 0.3038,
+      "step": 42950
+    },
+    {
+      "epoch": 0.7598381368062059,
+      "grad_norm": 1.4396170377731323,
+      "learning_rate": 1.335925075101608e-05,
+      "loss": 0.2195,
+      "step": 43000
     }
   ],
   "logging_steps": 50,