Training in progress, step 42600, checkpoint

last-checkpoint/README.md

@@ -1367,6 +1367,10 @@ You can finetune this model on your own dataset.
 | 0.7475 | 42300 | 0.2374        |
 | 0.7484 | 42350 | 0.3347        |
 | 0.7492 | 42400 | 0.3031        |
+| 0.7501 | 42450 | 0.2817        |
+| 0.7510 | 42500 | 0.3433        |
+| 0.7519 | 42550 | 0.3273        |
+| 0.7528 | 42600 | 0.3123        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa92be7deea9d9fa0443a8e7ac43099edac64700ac1948c996c7d56587f9eab
+oid sha256:8ff54d76c9ebf490f12ff8e20aef5fa2ede05719c3e5676b2c4b70743a6ddb70
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b7fd53fc83dc52997172f5fd46299f5a9cb53791e47663db9b33ca688d8e9d
+oid sha256:e1bcc3dd859b5b30a53288025a1e1562aaecb27ca1c5f50de5231f42624b5be4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c78cdd0913fe6a8bd516be3fa927565353e6ccb7f2abf432b224a447c2067b40
+oid sha256:283d0e72fe96a15f8f83fa6413bf75a47c1e9923215c4159761e62486061e4d6
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ad923444303f7830b2be707d7167336797f0569cde414d2b04df5898c738d4
+oid sha256:a6825a6ad95d754623a78051fc89a4d4e41f2bf2218e7b695b249c975dc4ba73
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c406d8129b27e63cb0cbf299bbeba9e703c540df5033871f11031330a77f043
+oid sha256:052884290aaf5bd113167914e5b98e8e8eb63821927d0e64cb92a12102bb9c25
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7492357441996077,
+  "epoch": 0.7527698750684738,
   "eval_steps": 500,
-  "global_step": 42400,
+  "global_step": 42600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5944,6 +5944,34 @@
       "learning_rate": 1.3947301250711748e-05,
       "loss": 0.3031,
       "step": 42400
+    },
+    {
+      "epoch": 0.7501192769168242,
+      "grad_norm": 2.6039016246795654,
+      "learning_rate": 1.389821523237321e-05,
+      "loss": 0.2817,
+      "step": 42450
+    },
+    {
+      "epoch": 0.7510028096340408,
+      "grad_norm": 4.557380676269531,
+      "learning_rate": 1.3849129214034675e-05,
+      "loss": 0.3433,
+      "step": 42500
+    },
+    {
+      "epoch": 0.7518863423512573,
+      "grad_norm": 2.938749074935913,
+      "learning_rate": 1.3800043195696138e-05,
+      "loss": 0.3273,
+      "step": 42550
+    },
+    {
+      "epoch": 0.7527698750684738,
+      "grad_norm": 1.3836658000946045,
+      "learning_rate": 1.3750957177357601e-05,
+      "loss": 0.3123,
+      "step": 42600
     }
   ],
   "logging_steps": 50,