Training in progress, step 38600, checkpoint

last-checkpoint/README.md

@@ -1285,6 +1285,10 @@ You can finetune this model on your own dataset.
 | 0.6768 | 38300 | 0.3098        |
 | 0.6777 | 38350 | 0.2837        |
 | 0.6786 | 38400 | 0.2998        |
+| 0.6794 | 38450 | 0.2477        |
+| 0.6803 | 38500 | 0.3343        |
+| 0.6812 | 38550 | 0.2411        |
+| 0.6821 | 38600 | 0.2641        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c033e355f6e42ff78f502c063b5b2db3a52df78665c5ff9bb6479d0c624edc
+oid sha256:9411645577be70106bcbbb74c24716149dda56d2f3e7a581b79fdcdc3ed41249
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd783dda3b4095b4bde6c3534ce452f7dd91f5cc8116eb11d93f25b3ce7530c
+oid sha256:b3e25051f1943dbef57f8ebb6e352941619afea10b29f67080e5c0e931b5bcec
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8142ca4f7ed2fe593cefee908aecc5f50a35392fb476fa2ad8c3ba0e7ec834c
+oid sha256:383863d97b21487295b0694693e6eddac2a40d27317755b362907c5201542167
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcf7219057595bd52b15bf2951670512df99f3f40268de42603fbc194d2d20b
+oid sha256:1c584d258d651b75cc67fda371e341a5dcb6a64a5f3ef27cdd2725022fe4132e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ca8a4ad9f574d1ca2310145c441ff394dd14227f12775f4424e4ebe7c06f50
+oid sha256:10f4be9189e6431a4a4fa709ab0080899a72a8630fa75a31259beca939bff08e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6785531268222862,
+  "epoch": 0.6820872576911523,
   "eval_steps": 500,
-  "global_step": 38400,
+  "global_step": 38600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5384,6 +5384,34 @@
       "learning_rate": 1.7872219277061123e-05,
       "loss": 0.2998,
       "step": 38400
+    },
+    {
+      "epoch": 0.6794366595395027,
+      "grad_norm": 1.5092830657958984,
+      "learning_rate": 1.7823133258722584e-05,
+      "loss": 0.2477,
+      "step": 38450
+    },
+    {
+      "epoch": 0.6803201922567192,
+      "grad_norm": 1.4017945528030396,
+      "learning_rate": 1.7774047240384052e-05,
+      "loss": 0.3343,
+      "step": 38500
+    },
+    {
+      "epoch": 0.6812037249739358,
+      "grad_norm": 1.5817060470581055,
+      "learning_rate": 1.7724961222045513e-05,
+      "loss": 0.2411,
+      "step": 38550
+    },
+    {
+      "epoch": 0.6820872576911523,
+      "grad_norm": 1.4471608400344849,
+      "learning_rate": 1.7675875203706975e-05,
+      "loss": 0.2641,
+      "step": 38600
     }
   ],
   "logging_steps": 50,