Training in progress, step 40400, checkpoint

last-checkpoint/README.md

@@ -1323,6 +1323,10 @@ You can finetune this model on your own dataset.
 | 0.7086 | 40100 | 0.2649        |
 | 0.7095 | 40150 | 0.3184        |
 | 0.7104 | 40200 | 0.334         |
+| 0.7112 | 40250 | 0.3609        |
+| 0.7121 | 40300 | 0.306         |
+| 0.7130 | 40350 | 0.2629        |
+| 0.7139 | 40400 | 0.2311        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c11448eab5085dafbe70840b347e552395741208f4c056feba7bdf25c3684b4
+oid sha256:a50f06d6c0fd8326af39a398662f171a8273231c42342726a949dca804e1fec3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176196a55e3283e4494c033b91ec493e6e73b898ba15899622781e50e5276a9c
+oid sha256:a31f8e8daa44a5969c8468131e422d3890bd1b3dfc09e140da75d5ff08dd8929
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c20f027761b73065674875134aab16adfe944ddeaaac5054a42d467120ac3f
+oid sha256:d8789e63d322628b9bf8ef047af43291db3bd5935067320bb834f1fe83567f97
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024951ca35599ed7cd93018ece748744d262ffe3e8da72f14612df6525b8ad2b
+oid sha256:f096ecf59986ddd611fd8ea1bd90586f9039a1554c47a1316352f4e9e8082419
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91554dd52659f1199ca0e07de2f95f60454723c4c5c500a75b5d255aeb95a210
+oid sha256:8fca1118641eb340cc4f5e2369cd22f797bffa655fc6d743b877326b0bf15332
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7103603046420809,
+  "epoch": 0.713894435510947,
   "eval_steps": 500,
-  "global_step": 40200,
+  "global_step": 40400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5636,6 +5636,34 @@
       "learning_rate": 1.6106104337240583e-05,
       "loss": 0.334,
       "step": 40200
+    },
+    {
+      "epoch": 0.7112438373592974,
+      "grad_norm": 1.348560094833374,
+      "learning_rate": 1.6057018318902045e-05,
+      "loss": 0.3609,
+      "step": 40250
+    },
+    {
+      "epoch": 0.7121273700765139,
+      "grad_norm": 0.9920164942741394,
+      "learning_rate": 1.600793230056351e-05,
+      "loss": 0.306,
+      "step": 40300
+    },
+    {
+      "epoch": 0.7130109027937305,
+      "grad_norm": 1.3321669101715088,
+      "learning_rate": 1.595884628222497e-05,
+      "loss": 0.2629,
+      "step": 40350
+    },
+    {
+      "epoch": 0.713894435510947,
+      "grad_norm": 1.257283329963684,
+      "learning_rate": 1.5909760263886435e-05,
+      "loss": 0.2311,
+      "step": 40400
     }
   ],
   "logging_steps": 50,