Training in progress, step 42800, checkpoint

last-checkpoint/README.md

@@ -1371,6 +1371,10 @@ You can finetune this model on your own dataset.
 | 0.7510 | 42500 | 0.3433        |
 | 0.7519 | 42550 | 0.3273        |
 | 0.7528 | 42600 | 0.3123        |
+| 0.7537 | 42650 | 0.29          |
+| 0.7545 | 42700 | 0.3352        |
+| 0.7554 | 42750 | 0.3143        |
+| 0.7563 | 42800 | 0.2833        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff54d76c9ebf490f12ff8e20aef5fa2ede05719c3e5676b2c4b70743a6ddb70
+oid sha256:947ad26bf0a1ea98a40d7847b1d4081968d0ea03f777dd415d118a3341c7d595
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bcc3dd859b5b30a53288025a1e1562aaecb27ca1c5f50de5231f42624b5be4
+oid sha256:fbe6b037eef5d6174a1e64a06f40631b730395d9ff0774dfc1245b870b5a756f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283d0e72fe96a15f8f83fa6413bf75a47c1e9923215c4159761e62486061e4d6
+oid sha256:0a0a70fc822cbf0577f57f474f054d71e07e1660e7791d186284f5053153721d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6825a6ad95d754623a78051fc89a4d4e41f2bf2218e7b695b249c975dc4ba73
+oid sha256:31395f18239b3bc788fb9174ae1acda597a1a3b63f5595848ade3391438691e5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052884290aaf5bd113167914e5b98e8e8eb63821927d0e64cb92a12102bb9c25
+oid sha256:ff01474c5f0e5dbd5aec03f387f08f61e0a9ae8d77c69168920103f17f16f317
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7527698750684738,
+  "epoch": 0.7563040059373398,
   "eval_steps": 500,
-  "global_step": 42600,
+  "global_step": 42800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5972,6 +5972,34 @@
       "learning_rate": 1.3750957177357601e-05,
       "loss": 0.3123,
       "step": 42600
+    },
+    {
+      "epoch": 0.7536534077856903,
+      "grad_norm": 4.600383758544922,
+      "learning_rate": 1.3701871159019066e-05,
+      "loss": 0.29,
+      "step": 42650
+    },
+    {
+      "epoch": 0.7545369405029069,
+      "grad_norm": 4.080932140350342,
+      "learning_rate": 1.3652785140680529e-05,
+      "loss": 0.3352,
+      "step": 42700
+    },
+    {
+      "epoch": 0.7554204732201233,
+      "grad_norm": 1.4026703834533691,
+      "learning_rate": 1.3603699122341992e-05,
+      "loss": 0.3143,
+      "step": 42750
+    },
+    {
+      "epoch": 0.7563040059373398,
+      "grad_norm": 1.4037362337112427,
+      "learning_rate": 1.3555594824370226e-05,
+      "loss": 0.2833,
+      "step": 42800
     }
   ],
   "logging_steps": 50,