Training in progress, step 27000, checkpoint

last-checkpoint/README.md

@@ -1197,6 +1197,10 @@ You can finetune this model on your own dataset.
 | 0.4718 | 26700 | 0.2572        |
 | 0.4727 | 26750 | 0.2821        |
 | 0.4736 | 26800 | 0.2753        |
+| 0.4745 | 26850 | 0.2789        |
+| 0.4753 | 26900 | 0.5175        |
+| 0.4762 | 26950 | 0.3398        |
+| 0.4771 | 27000 | 0.3683        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af9e8fc53f229d8df337a8754e2d3d5b113d4716605b013bad83e9e09dacdb0
+oid sha256:157a36f69c8d6be89b19a5fc2041a6a70bae891ca7bdb6e1f8c5561949e9bafa
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6d4daedba612d713f9144d945bcc7668fddc99a7c572a8a7ecdaadfce55d9f
+oid sha256:3cf3f6a255c756d17edb6da60dbf398937995bd4e9513159583e5e4237f23a63
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd90d4d272f52093bcd166fb2fee1129e8da49cd6cade68a0c1872a9ab44bae6
+oid sha256:77b7843d303f1fcbcb7ded0ee18633ae1a240b93a82ce64b7dc80620210cefa4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9102615210716abefe38c971af7617c4ceba795e3412ef59968e79b6fe53891e
+oid sha256:f721603f06800f16238813b709df823dd021b986d5f3f64a3fdb3ad2473f4313
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca320c82587b083501742caf7cc80ec1a98ca247bf4b8c7cd91053ff97a2d44
+oid sha256:2b9c472a19e7b9448212aaddb68f6d9878d89c838a06487c2d680b2179532b97
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.47357353642805394,
+  "epoch": 0.47710766729692,
   "eval_steps": 500,
-  "global_step": 26800,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3760,6 +3760,34 @@
       "learning_rate": 2.9256248650134498e-05,
       "loss": 0.2753,
       "step": 26800
+    },
+    {
+      "epoch": 0.47445706914527047,
+      "grad_norm": 1.7398908138275146,
+      "learning_rate": 2.920716263179596e-05,
+      "loss": 0.2789,
+      "step": 26850
+    },
+    {
+      "epoch": 0.47534060186248694,
+      "grad_norm": 1.456929087638855,
+      "learning_rate": 2.9158076613457424e-05,
+      "loss": 0.5175,
+      "step": 26900
+    },
+    {
+      "epoch": 0.4762241345797035,
+      "grad_norm": 1.4763001203536987,
+      "learning_rate": 2.910899059511889e-05,
+      "loss": 0.3398,
+      "step": 26950
+    },
+    {
+      "epoch": 0.47710766729692,
+      "grad_norm": 1.3316082954406738,
+      "learning_rate": 2.905990457678035e-05,
+      "loss": 0.3683,
+      "step": 27000
     }
   ],
   "logging_steps": 50,