Training in progress, step 32800, checkpoint

last-checkpoint/README.md

@@ -1315,6 +1315,10 @@ You can finetune this model on your own dataset.
 | 0.5743 | 32500 | 0.2741        |
 | 0.5752 | 32550 | 0.3546        |
 | 0.5761 | 32600 | 0.3927        |
+| 0.5769 | 32650 | 0.2725        |
+| 0.5778 | 32700 | 0.3167        |
+| 0.5787 | 32750 | 0.3249        |
+| 0.5796 | 32800 | 0.2443        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45fd58276a613db39a02b73ae7fb0f916427f84c68306d47cd2dd77d778f740d
+oid sha256:c149da7590ac756041ddcfa88541f8f1672d3db78462e24c5f353c18f8cebb1d
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0c582d327743ee610c3253c0a4bdc5cb41fe46898db21b3b1c785e2413a4e9
+oid sha256:a8e3fdce41c8faa034bc2a86a395da561d04329337006adacae71b20e28f454b
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92457d32429f413543dc4a520ec7ff903eebfb5a9a30773f04a7c15eb4dca6c4
+oid sha256:4dd0555a80b9ec33d03df384178c64ec05cac6166fd02e539edd48eaea584c82
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7b96e3cd8fbcf40fa74eb52caa9f2570529a551c9001ee45b2d2020cedf149
+oid sha256:fd929e14e8b21c3d41ba7c4043d8f146abd5c239c07932d39cf0ff21021e6682
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd2952fde33bc16ddb69c03104a4d42ffc3097dd2a6f3924f62735831aaadce
+oid sha256:14aac029153ded9414487d954464b6a95a9d2baa46bd0202f6e9ea6df2629338
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5760633316251701,
+  "epoch": 0.5795974624940362,
   "eval_steps": 500,
-  "global_step": 32600,
+  "global_step": 32800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4572,6 +4572,34 @@
       "learning_rate": 2.356423396359781e-05,
       "loss": 0.3927,
       "step": 32600
+    },
+    {
+      "epoch": 0.5769468643423866,
+      "grad_norm": 2.3731272220611572,
+      "learning_rate": 2.3515147945259272e-05,
+      "loss": 0.2725,
+      "step": 32650
+    },
+    {
+      "epoch": 0.5778303970596032,
+      "grad_norm": 1.4900075197219849,
+      "learning_rate": 2.3466061926920737e-05,
+      "loss": 0.3167,
+      "step": 32700
+    },
+    {
+      "epoch": 0.5787139297768197,
+      "grad_norm": 1.2145545482635498,
+      "learning_rate": 2.34169759085822e-05,
+      "loss": 0.3249,
+      "step": 32750
+    },
+    {
+      "epoch": 0.5795974624940362,
+      "grad_norm": 1.725298285484314,
+      "learning_rate": 2.3367889890243662e-05,
+      "loss": 0.2443,
+      "step": 32800
     }
   ],
   "logging_steps": 50,