Training in progress, step 28800, checkpoint

last-checkpoint/README.md

@@ -1233,6 +1233,10 @@ You can finetune this model on your own dataset.
 | 0.5036 | 28500 | 0.4675        |
 | 0.5045 | 28550 | 0.4318        |
 | 0.5054 | 28600 | 0.3594        |
+| 0.5063 | 28650 | 0.3214        |
+| 0.5071 | 28700 | 0.2856        |
+| 0.5080 | 28750 | 0.3094        |
+| 0.5089 | 28800 | 0.3933        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1974b8b79f821393033413b708b3d76af02ee0630fc769c360d30160ba1e49c
+oid sha256:526b3821cc22dabab82fd7d8615a24774c12cbfff6b5eac716e0f6982df2e75f
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80de25a64d3a7f9b01d3ac384a24ef9565f911507016f6cb2ebb2675cd2fca9a
+oid sha256:ed2e0bba9075cf4efff85ef476d7466568456807cb8d8113da7d9be699bd6395
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104316cbc87d14059ece260dae5c5774e3d91c358c1eb53b1e4cc6f9aa5826ec
+oid sha256:f9bd07dff5dde90cbe325d76b55b63b3e348e3827cc82b9387fe3b76aec8995f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed0a067ae758f61df93eb0349389528a459caaf90517ed5419a4c3a8ab14656
+oid sha256:38258a3d5062f5c88ae31bcccabf324c777da3d611326c6312601c11bdc51857
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c41c0a76cd352649e53d0354e3152b28ade5f9653e46110b22a1db6134af332
+oid sha256:2361ecc3f59af188c2bbc181225eb8037bc343b3fa1989c7fb6e76cff5a21110
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5053807142478486,
+  "epoch": 0.5089148451167147,
   "eval_steps": 500,
-  "global_step": 28600,
+  "global_step": 28800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4012,6 +4012,34 @@
       "learning_rate": 2.7489151989947186e-05,
       "loss": 0.3594,
       "step": 28600
+    },
+    {
+      "epoch": 0.5062642469650651,
+      "grad_norm": 1.109703540802002,
+      "learning_rate": 2.7440065971608647e-05,
+      "loss": 0.3214,
+      "step": 28650
+    },
+    {
+      "epoch": 0.5071477796822816,
+      "grad_norm": 1.9164469242095947,
+      "learning_rate": 2.739097995327011e-05,
+      "loss": 0.2856,
+      "step": 28700
+    },
+    {
+      "epoch": 0.5080313123994982,
+      "grad_norm": 1.3944114446640015,
+      "learning_rate": 2.7341893934931573e-05,
+      "loss": 0.3094,
+      "step": 28750
+    },
+    {
+      "epoch": 0.5089148451167147,
+      "grad_norm": 1.3844256401062012,
+      "learning_rate": 2.7292807916593038e-05,
+      "loss": 0.3933,
+      "step": 28800
     }
   ],
   "logging_steps": 50,