Training in progress, step 12000, checkpoint

last-checkpoint/README.md

@@ -1261,6 +1261,10 @@ You can finetune this model on your own dataset.
 | 0.2067 | 11700 | 0.4562        |
 | 0.2076 | 11750 | 0.3946        |
 | 0.2085 | 11800 | 0.4075        |
+| 0.2094 | 11850 | 0.4304        |
+| 0.2103 | 11900 | 0.3404        |
+| 0.2112 | 11950 | 0.4013        |
+| 0.2120 | 12000 | 0.4278        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b862a23d12f1864e02fd89ff20938a5a8d57d9e45b50fd7ba8fb62a812ed9c4
+oid sha256:70ee7d65436b3c3bdb265a584cb598d21c1152436f7bbe5e5b89abe72d05abfd
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03a1731cf97a2713699785dde7889737564cf64dda094167f6bf39225f51425
+oid sha256:eacbc7b18200a700f9e868dccad3bd885c8a77978e6ef6450cc02303852cb1f4
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:723b9765e6117e22f09f68846aa63411b573b1386212c3de8a3659e8a2bc457a
+oid sha256:2d3ba6287442404e0fa92289c3fc1da4f9e94c42e35bf2cb41249702ce19aede
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32596f6769c071a4397e5c0daafd0033f8ee8c8e6a4611bee1a368898a86e488
+oid sha256:08f76080c54c5059b8f1d78797380cba29afea4aa1d320a9c29f8474a65aad22
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48af0c514adaca9b905e2d835164b19c1d65658838747141fac1c271772baaa
+oid sha256:b9a38922a27408f3b8fdb8e3c0104dbbbeb511c2171a5f4ccac9abbb96798cd4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20851372126309836,
+  "epoch": 0.21204785213196445,
   "eval_steps": 500,
-  "global_step": 11800,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1660,6 +1660,34 @@
       "learning_rate": 4.3974200388761265e-05,
       "loss": 0.4075,
       "step": 11800
+    },
+    {
+      "epoch": 0.2093972539803149,
+      "grad_norm": 2.601897716522217,
+      "learning_rate": 4.392511437042273e-05,
+      "loss": 0.4304,
+      "step": 11850
+    },
+    {
+      "epoch": 0.21028078669753142,
+      "grad_norm": 1.58085036277771,
+      "learning_rate": 4.3876028352084194e-05,
+      "loss": 0.3404,
+      "step": 11900
+    },
+    {
+      "epoch": 0.21116431941474792,
+      "grad_norm": 1.7569571733474731,
+      "learning_rate": 4.382694233374566e-05,
+      "loss": 0.4013,
+      "step": 11950
+    },
+    {
+      "epoch": 0.21204785213196445,
+      "grad_norm": 1.9872467517852783,
+      "learning_rate": 4.3777856315407124e-05,
+      "loss": 0.4278,
+      "step": 12000
     }
   ],
   "logging_steps": 50,