Training in progress, step 11800, checkpoint

last-checkpoint/README.md

@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
 | 0.2032 | 11500 | 0.4133        |
 | 0.2041 | 11550 | 0.4255        |
 | 0.2050 | 11600 | 0.3766        |
+| 0.2059 | 11650 | 0.3651        |
+| 0.2067 | 11700 | 0.4562        |
+| 0.2076 | 11750 | 0.3946        |
+| 0.2085 | 11800 | 0.4075        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ffbfcafcc9fe0626ad95a757161650ebd608dc792a3be66dc280648638250c0
+oid sha256:1b862a23d12f1864e02fd89ff20938a5a8d57d9e45b50fd7ba8fb62a812ed9c4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54acb4c4ed26eb791b88eae901790e10103feef91580aec05ddfaf448cbfd85f
+oid sha256:e03a1731cf97a2713699785dde7889737564cf64dda094167f6bf39225f51425
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30da9f4d62258aeaf62aeb9ec9e5016819eb36a85d257e4973896ca659746a7b
+oid sha256:723b9765e6117e22f09f68846aa63411b573b1386212c3de8a3659e8a2bc457a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af444b90e8c6af59e605b8e6c36eed3028670ac5414ccb3c62069b581f1e100f
+oid sha256:32596f6769c071a4397e5c0daafd0033f8ee8c8e6a4611bee1a368898a86e488
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106144745ca94d3699bc51480a1ded383a9cde9abbc3f32cdef1f9281aa6d035
+oid sha256:a48af0c514adaca9b905e2d835164b19c1d65658838747141fac1c271772baaa
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2049795903942323,
+  "epoch": 0.20851372126309836,
   "eval_steps": 500,
-  "global_step": 11600,
+  "global_step": 11800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1632,6 +1632,34 @@
       "learning_rate": 4.417054446211541e-05,
       "loss": 0.3766,
       "step": 11600
+    },
+    {
+      "epoch": 0.2058631231114488,
+      "grad_norm": 2.006748676300049,
+      "learning_rate": 4.412145844377688e-05,
+      "loss": 0.3651,
+      "step": 11650
+    },
+    {
+      "epoch": 0.20674665582866533,
+      "grad_norm": 1.5192091464996338,
+      "learning_rate": 4.407237242543834e-05,
+      "loss": 0.4562,
+      "step": 11700
+    },
+    {
+      "epoch": 0.20763018854588186,
+      "grad_norm": 1.820331335067749,
+      "learning_rate": 4.402328640709981e-05,
+      "loss": 0.3946,
+      "step": 11750
+    },
+    {
+      "epoch": 0.20851372126309836,
+      "grad_norm": 3.302582025527954,
+      "learning_rate": 4.3974200388761265e-05,
+      "loss": 0.4075,
+      "step": 11800
     }
   ],
   "logging_steps": 50,