Training in progress, step 30200, checkpoint

last-checkpoint/README.md

@@ -1261,6 +1261,10 @@ You can finetune this model on your own dataset.
 | 0.5284 | 29900 | 0.3775        |
 | 0.5292 | 29950 | 0.3114        |
 | 0.5301 | 30000 | 0.2383        |
+| 0.5310 | 30050 | 0.3798        |
+| 0.5319 | 30100 | 0.3204        |
+| 0.5328 | 30150 | 0.2496        |
+| 0.5337 | 30200 | 0.4147        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb95ae4ccdc1225fa61fa51177153a06dac70457a68aef666cd0a1eed08ba1a
+oid sha256:7fdaa72a1273993224fa25cd6ae828434957eb8fe61239c1e320466c47d9b825
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a7aa1c487fa54454696db788c6e152307a22042949edfa76090e98becd066e
+oid sha256:3f37496e89883f6fc386020ad2e2737fb211e26fa5f09d8c0b7ba33fa265d290
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7e98986a27a407adbceaabeb5013a890ed1e6ec34d83926bcddbcf669ec678
+oid sha256:81da5af6afb90a5f448879aab382d7c289ea5663dd55fc76a78e2ffba833506d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:571d19b834362983e79e52affef058f87dcf5429e544d22e5fa9121931e62b84
+oid sha256:333f0c5d2657a0d36f7c5d0a5d113f16688fb194846ffda2f04f57fa9aad9a8b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f6718e4a878b8d1ac645f468a8f963dffffaa70e597cacccbc9fdb9c7011a3
+oid sha256:556d068be039654c814d6bf835c59f969aab843389d89f79ddf0f3729b9c071a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5301196303299112,
+  "epoch": 0.5336537611987772,
   "eval_steps": 500,
-  "global_step": 30000,
+  "global_step": 30200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4208,6 +4208,34 @@
       "learning_rate": 2.6114743476468162e-05,
       "loss": 0.2383,
       "step": 30000
+    },
+    {
+      "epoch": 0.5310031630471276,
+      "grad_norm": 1.6281217336654663,
+      "learning_rate": 2.6065657458129627e-05,
+      "loss": 0.3798,
+      "step": 30050
+    },
+    {
+      "epoch": 0.5318866957643441,
+      "grad_norm": 1.1688692569732666,
+      "learning_rate": 2.6016571439791092e-05,
+      "loss": 0.3204,
+      "step": 30100
+    },
+    {
+      "epoch": 0.5327702284815606,
+      "grad_norm": 1.354048490524292,
+      "learning_rate": 2.5967485421452553e-05,
+      "loss": 0.2496,
+      "step": 30150
+    },
+    {
+      "epoch": 0.5336537611987772,
+      "grad_norm": 2.8124821186065674,
+      "learning_rate": 2.5918399403114018e-05,
+      "loss": 0.4147,
+      "step": 30200
     }
   ],
   "logging_steps": 50,