Training in progress, step 28400, checkpoint

last-checkpoint/README.md

@@ -1225,6 +1225,10 @@ You can finetune this model on your own dataset.
 | 0.4965 | 28100 | 0.3604        |
 | 0.4974 | 28150 | 0.2612        |
 | 0.4983 | 28200 | 0.3593        |
+| 0.4992 | 28250 | 0.2961        |
+| 0.5001 | 28300 | 0.3338        |
+| 0.5010 | 28350 | 0.3109        |
+| 0.5018 | 28400 | 0.3234        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1965a5554a69ff8c5d7634a28c5f04a03c69dd137851c93b70cebbac2f7e99
+oid sha256:63181bf09a1c611c492c8b6ad279006fb56b9805969d0edba71cff3ee723a234
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22731b099d557e9c813459e9016c90f95f238923990688ebd670d8401d82293f
+oid sha256:d1746c035958eb9e0a972414e56f8fa4733c0402b003adb0be00e93e8ce71e93
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49299668d565a8fbf28b1ad8ad6ea4712f5b9b7d3472cc8d598ff75082532ee
+oid sha256:febec73de51eb7db9177092196a53a5124fb83edff44db6d3e9496c1ee972476
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a77e32486116fb80a72650dd1d3f8b1c3fcfe6b44b779b1f8fb0e11f75bb318
+oid sha256:f5147f98e53184b8dd37c8115204cda76018272755476678192eccb1efdd5d07
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be316569338339522180d5bdc62cd0944e9a3d23a5127275cdd38048e9eeda36
+oid sha256:953c76ee5b14f1426684c90829d80bb305b640c5a3e12732ffb64cce4b8f5126
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.49831245251011647,
+  "epoch": 0.5018465833789825,
   "eval_steps": 500,
-  "global_step": 28200,
+  "global_step": 28400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3956,6 +3956,34 @@
       "learning_rate": 2.7881840136655475e-05,
       "loss": 0.3593,
       "step": 28200
+    },
+    {
+      "epoch": 0.499195985227333,
+      "grad_norm": 1.1693766117095947,
+      "learning_rate": 2.783275411831694e-05,
+      "loss": 0.2961,
+      "step": 28250
+    },
+    {
+      "epoch": 0.5000795179445495,
+      "grad_norm": 1.65450918674469,
+      "learning_rate": 2.7783668099978404e-05,
+      "loss": 0.3338,
+      "step": 28300
+    },
+    {
+      "epoch": 0.500963050661766,
+      "grad_norm": 1.438693642616272,
+      "learning_rate": 2.7734582081639866e-05,
+      "loss": 0.3109,
+      "step": 28350
+    },
+    {
+      "epoch": 0.5018465833789825,
+      "grad_norm": 1.5170999765396118,
+      "learning_rate": 2.768549606330133e-05,
+      "loss": 0.3234,
+      "step": 28400
     }
   ],
   "logging_steps": 50,