Training in progress, step 35200, checkpoint

last-checkpoint/README.md

@@ -1217,6 +1217,10 @@ You can finetune this model on your own dataset.
 | 0.6167 | 34900 | 0.3015        |
 | 0.6176 | 34950 | 0.3291        |
 | 0.6185 | 35000 | 0.2634        |
+| 0.6194 | 35050 | 0.3212        |
+| 0.6202 | 35100 | 0.2965        |
+| 0.6211 | 35150 | 0.3557        |
+| 0.6220 | 35200 | 0.3535        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d79a423fd264f8aac56fd95502b2264a968c0f7cf7b4c2a1c6541772551d3d3
+oid sha256:a73726096d96dbbbaa9a481dfff6e52b1ea1d694b55f2edc2f1405af8895110b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a70db7a09d43a45af8ba846e6b88322513995922a372c0450b6f22318eba386
+oid sha256:d8b3f57d97ffd57e518f40f15d12ad037a0066d481b15f01ac0c5cd7db8dcb47
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5dbdbbf596351fb268b717a3c2006112ba85ad19e4243b93a29f0071121e106
+oid sha256:ca63325ac742a792a3bcdc1dc21baa9c1c96f6a59934e63bc8a87c6b8f66e093
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33dd792f68c210603692aedada855793ed50b3aa941307b551dc822363f2d043
+oid sha256:6f6bf385710f1d1a6f64e5b03c0c6f98497de21222ff381a7961ac0b45b93ddc
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba7705125f055257ca9fb00bd8484394e209b5a6e280efe9550fda932420046
+oid sha256:f345579e836e5dec04f17da3b053acb614c611f3b7c11559a8cdc45e09194e58
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.618472902051563,
+  "epoch": 0.622007032920429,
   "eval_steps": 500,
-  "global_step": 35000,
+  "global_step": 35200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4908,6 +4908,34 @@
       "learning_rate": 2.120908680371483e-05,
       "loss": 0.2634,
       "step": 35000
+    },
+    {
+      "epoch": 0.6193564347687794,
+      "grad_norm": 1.4780889749526978,
+      "learning_rate": 2.1160000785376295e-05,
+      "loss": 0.3212,
+      "step": 35050
+    },
+    {
+      "epoch": 0.620239967485996,
+      "grad_norm": 1.699916124343872,
+      "learning_rate": 2.1110914767037756e-05,
+      "loss": 0.2965,
+      "step": 35100
+    },
+    {
+      "epoch": 0.6211235002032125,
+      "grad_norm": 1.6198956966400146,
+      "learning_rate": 2.106182874869922e-05,
+      "loss": 0.3557,
+      "step": 35150
+    },
+    {
+      "epoch": 0.622007032920429,
+      "grad_norm": 1.2697581052780151,
+      "learning_rate": 2.1012742730360685e-05,
+      "loss": 0.3535,
+      "step": 35200
     }
   ],
   "logging_steps": 50,