Training in progress, step 51400, checkpoint

last-checkpoint/README.md

@@ -1319,6 +1319,10 @@ You can finetune this model on your own dataset.
 | 0.9030 | 51100 | 0.331         |
 | 0.9039 | 51150 | 0.2881        |
 | 0.9047 | 51200 | 0.3553        |
+| 0.9056 | 51250 | 0.2936        |
+| 0.9065 | 51300 | 0.2987        |
+| 0.9074 | 51350 | 0.3343        |
+| 0.9083 | 51400 | 0.2919        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ad1d70cc9a9203e1932e7a5399b2ea38220c472d491a93ade1e1841ba94da7
+oid sha256:8f6095595fb3007928d93e8e219ea90fc483d7933ff71480f93acc7032b0be18
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c9ea94de1bc6171fc560eb6edc6e3bb30de3a6197d7f6bdc43b28fa6e8b63a
+oid sha256:5528739540379e7472ab0ae207cba54ed4fa2009128623e5cc01b704f91e4334
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697766d9762a48456880b2166b1f5fb91392394ad67b7232020fe661b72f67bd
+oid sha256:00b1d2649da1c33c4c6171910ab9897e0cf291c76124110f095256b857bf610a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f620a353823eb6b71c8ccf047459bfd67f2ce79246e53f2aa937b07f9d71d34
+oid sha256:6ed7436953ae4e16b051c219b7cb3a2e2190d41cf4e564a35d17483bdb596e66
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fadf44129acc4700f11541025d2dded44dc62ab2fdbe50e09f45fc382b24055
+oid sha256:8ac1d7bd261ca287c71b297338a8785cacbd5d9b3b50d5e9d2567d8805ed369c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.904737502429715,
+  "epoch": 0.9082716332985811,
   "eval_steps": 500,
-  "global_step": 51200,
+  "global_step": 51400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7176,6 +7176,34 @@
       "learning_rate": 5.313070624963186e-06,
       "loss": 0.3553,
       "step": 51200
+    },
+    {
+      "epoch": 0.9056210351469315,
+      "grad_norm": 2.317101001739502,
+      "learning_rate": 5.26398460662465e-06,
+      "loss": 0.2936,
+      "step": 51250
+    },
+    {
+      "epoch": 0.906504567864148,
+      "grad_norm": 1.3416547775268555,
+      "learning_rate": 5.214898588286113e-06,
+      "loss": 0.2987,
+      "step": 51300
+    },
+    {
+      "epoch": 0.9073881005813645,
+      "grad_norm": 3.7747082710266113,
+      "learning_rate": 5.1658125699475765e-06,
+      "loss": 0.3343,
+      "step": 51350
+    },
+    {
+      "epoch": 0.9082716332985811,
+      "grad_norm": 1.4777984619140625,
+      "learning_rate": 5.1167265516090395e-06,
+      "loss": 0.2919,
+      "step": 51400
     }
   ],
   "logging_steps": 50,