Training in progress, step 47800, checkpoint

last-checkpoint/README.md

@@ -1245,6 +1245,10 @@ You can finetune this model on your own dataset.
 | 0.8394 | 47500 | 0.2681        |
 | 0.8402 | 47550 | 0.2764        |
 | 0.8411 | 47600 | 0.3211        |
+| 0.8420 | 47650 | 0.3081        |
+| 0.8429 | 47700 | 0.2929        |
+| 0.8438 | 47750 | 0.3466        |
+| 0.8447 | 47800 | 0.3012        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb571cf1016cc58baf3a7817dee516595d05a1b71fc7e2bc74f8a0f087b67ab
+oid sha256:fce1f6af6d2a72f031e3c0de240f823edc94a245e95fb7a33a39dc0ad38f9ec0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a0556ded0b57b07366c16a857e404e3a6ed590b3f36f4eb437f7d0466a1f1f3
+oid sha256:310b5e6c85d4fa71697a913a5e8eb1baf2af955a83f82ffe53be481221938fc4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5553d76033a44cec5e8d74f3dd5d950d64ab61bcadfeb096978618edc47ea5ab
+oid sha256:6664f2f42fe11eba3d15efd3cef84351c1ed700ca012feeaaba10e813a674fd6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc906030957a3fd71ac5d5f065e62c1d0ee722af605316e3fb4aeb71bb2da6d9
+oid sha256:8d8621fe1648dc96d7d6a12a9e96d1ea20e9a16f5271880935750dfe7f0b53b1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04207c7c463cb091778bcde4ddbf6fbbaa052a080cecf59df48a2d3acdd2924
+oid sha256:785cadb5b905b280e8fff12125b530dd86b352b15f0eb2d7c104357be9261774
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8411231467901257,
+  "epoch": 0.8446572776589917,
   "eval_steps": 500,
-  "global_step": 47600,
+  "global_step": 47800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6672,6 +6672,34 @@
       "learning_rate": 8.845300504604269e-06,
       "loss": 0.3211,
       "step": 47600
+    },
+    {
+      "epoch": 0.8420066795073422,
+      "grad_norm": 1.5162594318389893,
+      "learning_rate": 8.796214486265734e-06,
+      "loss": 0.3081,
+      "step": 47650
+    },
+    {
+      "epoch": 0.8428902122245586,
+      "grad_norm": 1.3636444807052612,
+      "learning_rate": 8.747128467927197e-06,
+      "loss": 0.2929,
+      "step": 47700
+    },
+    {
+      "epoch": 0.8437737449417752,
+      "grad_norm": 1.2207202911376953,
+      "learning_rate": 8.69804244958866e-06,
+      "loss": 0.3466,
+      "step": 47750
+    },
+    {
+      "epoch": 0.8446572776589917,
+      "grad_norm": 1.294301152229309,
+      "learning_rate": 8.648956431250123e-06,
+      "loss": 0.3012,
+      "step": 47800
     }
   ],
   "logging_steps": 50,