Training in progress, step 16200, checkpoint

last-checkpoint/README.md

@@ -1347,6 +1347,10 @@ You can finetune this model on your own dataset.
 | 0.2810 | 15900 | 0.348         |
 | 0.2818 | 15950 | 0.367         |
 | 0.2827 | 16000 | 0.3427        |
+| 0.2836 | 16050 | 0.3637        |
+| 0.2845 | 16100 | 0.3489        |
+| 0.2854 | 16150 | 0.4209        |
+| 0.2863 | 16200 | 0.2984        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd95a7943e2d7fca893eb5bdbe9b3d01703e4d80ed047d04c1a67e2b9b33397
+oid sha256:f4d75f43e43417714c9eb673b4140e3bc3180d809cd3703e268b196479d4e674
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f4813f7d86633bd1ed04417d2d1313c405edfb90b56a8c930cfc1d1cf2addb
+oid sha256:1f5b8a814f3aeefa5d532770d34674995a259b1d0de80bb9f90ec6188099e03c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f746250cbdbcfc4b3753e05fc3f2d0b47904bb4b557a3820295b22d838b42f6
+oid sha256:47f7e685ed786d075ed1cbf16f75ee06ff18af8652d59bebd10628b722f2e5f2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218ae04f7dbf6951d970ca21a27b311e58e61f1cd335681a08b187b9413a828c
+oid sha256:c70ce39dc0484a07cf26175c01edd45d7187b33cf3b7426ec3e7187e560fe7f9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56b223eeb93b57918d558b5af382f71a700beb8d1cf640c27db1796abbd5d2f
+oid sha256:198e9c5abe5151f1b8f98a22fd77ae2770a4aa017bd01877ffccc20b1cae28be
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28273046950928593,
+  "epoch": 0.286264600378152,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2248,6 +2248,34 @@
       "learning_rate": 3.985293828905775e-05,
       "loss": 0.3427,
       "step": 16000
+    },
+    {
+      "epoch": 0.28361400222650246,
+      "grad_norm": 3.725020170211792,
+      "learning_rate": 3.980385227071921e-05,
+      "loss": 0.3637,
+      "step": 16050
+    },
+    {
+      "epoch": 0.284497534943719,
+      "grad_norm": 1.5958735942840576,
+      "learning_rate": 3.975476625238068e-05,
+      "loss": 0.3489,
+      "step": 16100
+    },
+    {
+      "epoch": 0.28538106766093546,
+      "grad_norm": 1.3779951333999634,
+      "learning_rate": 3.9705680234042136e-05,
+      "loss": 0.4209,
+      "step": 16150
+    },
+    {
+      "epoch": 0.286264600378152,
+      "grad_norm": 1.6636724472045898,
+      "learning_rate": 3.96565942157036e-05,
+      "loss": 0.2984,
+      "step": 16200
     }
   ],
   "logging_steps": 50,