Training in progress, step 42400, checkpoint

last-checkpoint/README.md

@@ -1363,6 +1363,10 @@ You can finetune this model on your own dataset.
 | 0.7439 | 42100 | 0.3288        |
 | 0.7448 | 42150 | 0.3333        |
 | 0.7457 | 42200 | 0.3602        |
+| 0.7466 | 42250 | 0.3631        |
+| 0.7475 | 42300 | 0.2374        |
+| 0.7484 | 42350 | 0.3347        |
+| 0.7492 | 42400 | 0.3031        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83afd304da9ec0fb20d98a2d12c9411b67ec3d42591e5ff6ab887eab75060bc9
+oid sha256:6aa92be7deea9d9fa0443a8e7ac43099edac64700ac1948c996c7d56587f9eab
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3baaf946db368404b08114c9679bf96f88de1ac7c8c80c8a46d8a2e2273b4cf
+oid sha256:87b7fd53fc83dc52997172f5fd46299f5a9cb53791e47663db9b33ca688d8e9d
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d763d9ca70425fdf40bf2c310ee3aa99e16879e3dcca91b65438c05121dc800c
+oid sha256:c78cdd0913fe6a8bd516be3fa927565353e6ccb7f2abf432b224a447c2067b40
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc5774e283703e787806fc20a7b89a411d313a132b63638672a2da2a5ead08e
+oid sha256:36ad923444303f7830b2be707d7167336797f0569cde414d2b04df5898c738d4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96b3ee97617878f5775584f3569298deaaee2c710b13a42dfd4b9c9b2808a60
+oid sha256:0c406d8129b27e63cb0cbf299bbeba9e703c540df5033871f11031330a77f043
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7457016133307416,
+  "epoch": 0.7492357441996077,
   "eval_steps": 500,
-  "global_step": 42200,
+  "global_step": 42400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5916,6 +5916,34 @@
       "learning_rate": 1.4143645324065894e-05,
       "loss": 0.3602,
       "step": 42200
+    },
+    {
+      "epoch": 0.7465851460479581,
+      "grad_norm": 1.546533226966858,
+      "learning_rate": 1.4094559305727355e-05,
+      "loss": 0.3631,
+      "step": 42250
+    },
+    {
+      "epoch": 0.7474686787651746,
+      "grad_norm": 1.3664302825927734,
+      "learning_rate": 1.4045473287388822e-05,
+      "loss": 0.2374,
+      "step": 42300
+    },
+    {
+      "epoch": 0.7483522114823912,
+      "grad_norm": 4.161416053771973,
+      "learning_rate": 1.3996387269050285e-05,
+      "loss": 0.3347,
+      "step": 42350
+    },
+    {
+      "epoch": 0.7492357441996077,
+      "grad_norm": 1.3883721828460693,
+      "learning_rate": 1.3947301250711748e-05,
+      "loss": 0.3031,
+      "step": 42400
     }
   ],
   "logging_steps": 50,