Training in progress, step 47600, checkpoint

last-checkpoint/README.md

@@ -1241,6 +1241,10 @@ You can finetune this model on your own dataset.
 | 0.8358 | 47300 | 0.3043        |
 | 0.8367 | 47350 | 0.2992        |
 | 0.8376 | 47400 | 0.3367        |
+| 0.8385 | 47450 | 0.3135        |
+| 0.8394 | 47500 | 0.2681        |
+| 0.8402 | 47550 | 0.2764        |
+| 0.8411 | 47600 | 0.3211        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fa899c39466858c1bb72384b17719bcb1b30345e9ce76f3b6b83ef15a3594ea
+oid sha256:8eb571cf1016cc58baf3a7817dee516595d05a1b71fc7e2bc74f8a0f087b67ab
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2193950b0b0024f572dc11e3f6e5765584be0f18471c5c13d65ef36051f2d86c
+oid sha256:8a0556ded0b57b07366c16a857e404e3a6ed590b3f36f4eb437f7d0466a1f1f3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb8dcdd8e8b75fd491010fd65bc9f4650cdec68128bc3f93969648db6824c7d
+oid sha256:5553d76033a44cec5e8d74f3dd5d950d64ab61bcadfeb096978618edc47ea5ab
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17b09e37e3cf1eb4e07e5a39443f3088190a89ec52eee73b652e920bd5e3c6d
+oid sha256:fc906030957a3fd71ac5d5f065e62c1d0ee722af605316e3fb4aeb71bb2da6d9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0328ae42c77686bf92831f9769ee36bd90306f1f061a996a4634ff09f38cc121
+oid sha256:f04207c7c463cb091778bcde4ddbf6fbbaa052a080cecf59df48a2d3acdd2924
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8375890159212596,
+  "epoch": 0.8411231467901257,
   "eval_steps": 500,
-  "global_step": 47400,
+  "global_step": 47600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6644,6 +6644,34 @@
       "learning_rate": 9.041644577958415e-06,
       "loss": 0.3367,
       "step": 47400
+    },
+    {
+      "epoch": 0.8384725486384761,
+      "grad_norm": 1.483476996421814,
+      "learning_rate": 8.992558559619878e-06,
+      "loss": 0.3135,
+      "step": 47450
+    },
+    {
+      "epoch": 0.8393560813556926,
+      "grad_norm": 1.5691540241241455,
+      "learning_rate": 8.943472541281341e-06,
+      "loss": 0.2681,
+      "step": 47500
+    },
+    {
+      "epoch": 0.8402396140729091,
+      "grad_norm": 1.2460750341415405,
+      "learning_rate": 8.894386522942804e-06,
+      "loss": 0.2764,
+      "step": 47550
+    },
+    {
+      "epoch": 0.8411231467901257,
+      "grad_norm": 1.3095312118530273,
+      "learning_rate": 8.845300504604269e-06,
+      "loss": 0.3211,
+      "step": 47600
     }
   ],
   "logging_steps": 50,