Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b8a9001fca8d55ed09205b10f833375837feb80ce371c21c6f020bf5786deb
+oid sha256:c7e76dfb89bdc8bb55f831619666b5aac1cdd95a978bd16de40127f48e40e936
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49dac71c9cd8a6d4b9a6f7d0eee9b542ab258b01e7113c2c1f8153bf567e336c
+oid sha256:a4c32ac7cde8185c1c43ace499072000bb35424ff5291fa36720a3fd3c5d90bb
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1829305e063e707abc232aed8747669a0cbd3f5df8976112390b8cae0ada39
+oid sha256:5de264eb23506e20fe1f20e74d3a6d2bf858564c7b9cdb50edbb337d02d70879
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6debbb9e36081b12b5a18175143dfdcd5bb839da21b79dd3cacf3c9328119485
+oid sha256:e77b9551f71b432639a3069cfe9b15634298ae6574271c13b14ba478962110a3
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05690315520700347,
+  "epoch": 0.07295276308590187,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 40.596,
       "eval_steps_per_second": 10.153,
       "step": 39
+    },
+    {
+      "epoch": 0.058362210468721504,
+      "grad_norm": 0.7893780469894409,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0498,
+      "step": 40
+    },
+    {
+      "epoch": 0.05982126573043954,
+      "grad_norm": 0.7406539916992188,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0363,
+      "step": 41
+    },
+    {
+      "epoch": 0.06128032099215758,
+      "grad_norm": 0.7479976415634155,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1059,
+      "step": 42
+    },
+    {
+      "epoch": 0.06273937625387561,
+      "grad_norm": 0.7913396954536438,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1684,
+      "step": 43
+    },
+    {
+      "epoch": 0.06419843151559365,
+      "grad_norm": 0.7762838006019592,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2163,
+      "step": 44
+    },
+    {
+      "epoch": 0.06565748677731169,
+      "grad_norm": 0.762980043888092,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.075,
+      "step": 45
+    },
+    {
+      "epoch": 0.06711654203902973,
+      "grad_norm": 0.7378513216972351,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1975,
+      "step": 46
+    },
+    {
+      "epoch": 0.06857559730074776,
+      "grad_norm": 0.7755700349807739,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1518,
+      "step": 47
+    },
+    {
+      "epoch": 0.0700346525624658,
+      "grad_norm": 0.7294082045555115,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1671,
+      "step": 48
+    },
+    {
+      "epoch": 0.07149370782418384,
+      "grad_norm": 0.7379075884819031,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1414,
+      "step": 49
+    },
+    {
+      "epoch": 0.07295276308590187,
+      "grad_norm": 0.7766591906547546,
+      "learning_rate": 0.0,
+      "loss": 2.1392,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.509569135306342e+16,
+  "total_flos": 5.780251087785165e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null