Training in progress, step 30400, checkpoint

last-checkpoint/README.md

@@ -1265,6 +1265,10 @@ You can finetune this model on your own dataset.
 | 0.5319 | 30100 | 0.3204        |
 | 0.5328 | 30150 | 0.2496        |
 | 0.5337 | 30200 | 0.4147        |
+| 0.5345 | 30250 | 0.3021        |
+| 0.5354 | 30300 | 0.2758        |
+| 0.5363 | 30350 | 0.3166        |
+| 0.5372 | 30400 | 0.35          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fdaa72a1273993224fa25cd6ae828434957eb8fe61239c1e320466c47d9b825
+oid sha256:cf79ddb807641f21ab4f124fe2a7f27110c30ccaaa038e866819c2a6c3894db3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f37496e89883f6fc386020ad2e2737fb211e26fa5f09d8c0b7ba33fa265d290
+oid sha256:ceffaa43e4f0c60b5feed0fbc2c3565eef53e3ad867186e6797fe95254c2affe
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81da5af6afb90a5f448879aab382d7c289ea5663dd55fc76a78e2ffba833506d
+oid sha256:80122c84195c17eb984e073adfb25182010304afad0586ccdcb1a261a3a0f848
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333f0c5d2657a0d36f7c5d0a5d113f16688fb194846ffda2f04f57fa9aad9a8b
+oid sha256:528a5407336a16734f58a4f46d586ee071f6f4a258839c4070d301e8f708f0a5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:556d068be039654c814d6bf835c59f969aab843389d89f79ddf0f3729b9c071a
+oid sha256:ba2e19f20627e37fe99b4ad87f03b959017a779a9fc1b80f764c9a8c0220d435
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5336537611987772,
+  "epoch": 0.5371878920676433,
   "eval_steps": 500,
-  "global_step": 30200,
+  "global_step": 30400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4236,6 +4236,34 @@
       "learning_rate": 2.5918399403114018e-05,
       "loss": 0.4147,
       "step": 30200
+    },
+    {
+      "epoch": 0.5345372939159937,
+      "grad_norm": 1.886425495147705,
+      "learning_rate": 2.5869313384775486e-05,
+      "loss": 0.3021,
+      "step": 30250
+    },
+    {
+      "epoch": 0.5354208266332102,
+      "grad_norm": 1.6316314935684204,
+      "learning_rate": 2.5820227366436944e-05,
+      "loss": 0.2758,
+      "step": 30300
+    },
+    {
+      "epoch": 0.5363043593504268,
+      "grad_norm": 1.3990044593811035,
+      "learning_rate": 2.577114134809841e-05,
+      "loss": 0.3166,
+      "step": 30350
+    },
+    {
+      "epoch": 0.5371878920676433,
+      "grad_norm": 2.1562857627868652,
+      "learning_rate": 2.572205532975987e-05,
+      "loss": 0.35,
+      "step": 30400
     }
   ],
   "logging_steps": 50,