Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565694a02d1a680ad13e6d5c287bf364d75ba1df1968e700df48d5b139619be8
+oid sha256:63c18d76db1e3cd8d5cc921c7e93be2640e56d8b14a306c7c8e949d34868342b
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d201213f522b4297793e9cae51caef747a5e3fa1fe3af92f0f21681c0637437
+oid sha256:314184f3d06784e0cc34a5b175d52a5b8426ce9f07b403a27c1c5b225289b3b6
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8da9606d70da26debcc91dc4a0b0ee52744429e41e4aaa27c50a18cdc492729
+oid sha256:439c4a24223d3d55c2f985cccc136d3d4af92525abe9b6d7f861e5a65fc1979e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3686b687745fcb51a0130846462af73ebb73b22def0cd1248dd8c0cf83e372
+oid sha256:0650d632b373768646c0172b27f51c428a8afa6a9791ff3bb91beb85b6249929
 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": 0.052890320393287,
+  "epoch": 0.06780810306831667,
   "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": 18.591,
       "eval_steps_per_second": 4.648,
       "step": 39
+    },
+    {
+      "epoch": 0.054246482454653334,
+      "grad_norm": 0.31619793176651,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.239,
+      "step": 40
+    },
+    {
+      "epoch": 0.055602644516019664,
+      "grad_norm": 0.33402693271636963,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2204,
+      "step": 41
+    },
+    {
+      "epoch": 0.056958806577386,
+      "grad_norm": 0.3335304260253906,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1981,
+      "step": 42
+    },
+    {
+      "epoch": 0.05831496863875233,
+      "grad_norm": 0.3046887218952179,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2376,
+      "step": 43
+    },
+    {
+      "epoch": 0.05967113070011867,
+      "grad_norm": 0.3035743534564972,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2419,
+      "step": 44
+    },
+    {
+      "epoch": 0.061027292761485,
+      "grad_norm": 0.3044282793998718,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2429,
+      "step": 45
+    },
+    {
+      "epoch": 0.062383454822851334,
+      "grad_norm": 0.3118952512741089,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2389,
+      "step": 46
+    },
+    {
+      "epoch": 0.06373961688421767,
+      "grad_norm": 0.3790152370929718,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2521,
+      "step": 47
+    },
+    {
+      "epoch": 0.06509577894558399,
+      "grad_norm": 0.3012060523033142,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2164,
+      "step": 48
+    },
+    {
+      "epoch": 0.06645194100695033,
+      "grad_norm": 0.3109649419784546,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2321,
+      "step": 49
+    },
+    {
+      "epoch": 0.06780810306831667,
+      "grad_norm": 0.32313668727874756,
+      "learning_rate": 0.0,
+      "loss": 1.2133,
+      "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": 2.5092246378381312e+17,
+  "total_flos": 3.21695466389504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null