Training in progress, step 34400, checkpoint

last-checkpoint/README.md

@@ -1201,6 +1201,10 @@ You can finetune this model on your own dataset.
 | 0.6026 | 34100 | 0.3125        |
 | 0.6035 | 34150 | 0.2738        |
 | 0.6043 | 34200 | 0.3062        |
+| 0.6052 | 34250 | 0.3566        |
+| 0.6061 | 34300 | 0.3466        |
+| 0.6070 | 34350 | 0.2608        |
+| 0.6079 | 34400 | 0.3239        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bdca6c44be34b9e69175940da4b56167b7928c9d214c258d43c5b620bc91b46
+oid sha256:7b5f4ea64897e90b4e4c7c1e0cb94dcb0f1492d916413cce2e66078ccfad6960
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8cce5c0114dfe6db2b221097701d4f63da8b0269ca76f1850aa97156719ebf
+oid sha256:8cf44dfcc82793c060386978756eab303f1fb8ffef4fb86d6d8a80ed57d60773
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed40b835a3a95c0d5caa9e2f9ac60fe5821207cfed755931f0a4c6a4e1bc7f9c
+oid sha256:13dc13fdf2d85fe768a37e80558a7b03bdcb432f2ca4a03fa86e5b8f2373ca60
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c9791c94ed19713d54c258fa73c1747c3a24c92cf2d0108a3b66f313c783e0
+oid sha256:b8efb8d95dab64304b8fe44c3687dc59b22acc22bfbc66f29596f118c5967e9a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67100c483c5008bb6cb432330fcbe9399cb2dfd8372d624a774af533d43e3106
+oid sha256:c62c2049abe02e0f34d9b4894dabef36b68579cab4efe24bc06e5d79c1d79bfd
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6043363785760987,
+  "epoch": 0.6078705094449648,
   "eval_steps": 500,
-  "global_step": 34200,
+  "global_step": 34400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4796,6 +4796,34 @@
       "learning_rate": 2.1993481376764643e-05,
       "loss": 0.3062,
       "step": 34200
+    },
+    {
+      "epoch": 0.6052199112933152,
+      "grad_norm": 1.5402554273605347,
+      "learning_rate": 2.1944395358426107e-05,
+      "loss": 0.3566,
+      "step": 34250
+    },
+    {
+      "epoch": 0.6061034440105317,
+      "grad_norm": 1.7631182670593262,
+      "learning_rate": 2.189530934008757e-05,
+      "loss": 0.3466,
+      "step": 34300
+    },
+    {
+      "epoch": 0.6069869767277483,
+      "grad_norm": 1.2873070240020752,
+      "learning_rate": 2.1846223321749033e-05,
+      "loss": 0.2608,
+      "step": 34350
+    },
+    {
+      "epoch": 0.6078705094449648,
+      "grad_norm": 1.8117417097091675,
+      "learning_rate": 2.1797137303410498e-05,
+      "loss": 0.3239,
+      "step": 34400
     }
   ],
   "logging_steps": 50,