Training in progress, step 34800, checkpoint

last-checkpoint/README.md

@@ -1209,6 +1209,10 @@ You can finetune this model on your own dataset.
 | 0.6096 | 34500 | 0.4175        |
 | 0.6105 | 34550 | 0.3104        |
 | 0.6114 | 34600 | 0.3305        |
+| 0.6123 | 34650 | 0.2832        |
+| 0.6132 | 34700 | 0.3007        |
+| 0.6141 | 34750 | 0.3932        |
+| 0.6149 | 34800 | 0.3           |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba077d6325305d731409aa162830a3c5d5397210799b60591392b1d61570f746
+oid sha256:78346a0c56430d22fa1490f284416b4aeee8fb9539989a398220c805d75e2e61
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726943ff9dec97794faedec459447bcaa417b775d59a98d695e669bfe25957b1
+oid sha256:332311a89c1a8130797191a2ad7878850bf8a5f8687fb07aa8ce26dd6bf3aca2
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0770796c8b6d34fe12dcd97fff6f962f270b4c06153537e6c3ceff010a085b43
+oid sha256:663998c1aaed54adecb3878007dbade857c46ba6a1c5eaffb67717a822135458
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548fc86584eafaf1a293dbece88e9fbb1e4a6c458e2f0be88ff6b690236f0848
+oid sha256:480efcc1d108b2db853c5d91deb1ed2fd305f7b9cbbdf50854f3a85cc79a1117
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381bbbc1437f4c979ed33526acec9652454aa2f2944f4ad7e6a6f3b151477146
+oid sha256:e917b101e0be67dbb3890bb4d8dceac22ecd3870c266a2b20cb6488727437a58
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6114046403138308,
+  "epoch": 0.6149387711826969,
   "eval_steps": 500,
-  "global_step": 34600,
+  "global_step": 34800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4852,6 +4852,34 @@
       "learning_rate": 2.1601774950423123e-05,
       "loss": 0.3305,
       "step": 34600
+    },
+    {
+      "epoch": 0.6122881730310473,
+      "grad_norm": 1.416923999786377,
+      "learning_rate": 2.1552688932084584e-05,
+      "loss": 0.2832,
+      "step": 34650
+    },
+    {
+      "epoch": 0.6131717057482639,
+      "grad_norm": 1.7992863655090332,
+      "learning_rate": 2.150360291374605e-05,
+      "loss": 0.3007,
+      "step": 34700
+    },
+    {
+      "epoch": 0.6140552384654804,
+      "grad_norm": 1.3988946676254272,
+      "learning_rate": 2.1454516895407514e-05,
+      "loss": 0.3932,
+      "step": 34750
+    },
+    {
+      "epoch": 0.6149387711826969,
+      "grad_norm": 1.7125048637390137,
+      "learning_rate": 2.1405430877068978e-05,
+      "loss": 0.3,
+      "step": 34800
     }
   ],
   "logging_steps": 50,