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:fc5d734fd21c4ffdd7c639e91c6060f654075be2d83bd4ab28331ca09d6d4f6b
+oid sha256:72b1af5129bdc74d97766b34982f8a20b89d57be4fe6c1cc50547383cb1416d5
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060f68c906acb544160e1c34fcf1ebd64e3c9115231fc8b2ca3bd9df6673f6bb
+oid sha256:c2624611b1ca85bc7b6a3524846205d6acf3ed9a05f095f8837c672b0788f2f1
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328fe9968df7bf20cce6c816bd538e730876deaee486e22d46258667abf17afc
+oid sha256:3531fd590b8fd6fcbddb61e6b46ac1b997cf7cef5113053fb7f5015848c30f35
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba43fdf56448fad0ffc4b3800ab3289204a7137e290f6a13302e4d4c52a37fd
+oid sha256:29bc15d430c252c1243d6e8d1875dc4c35f8e88790da8d78ff009203f04072e9
 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": 0.361844012757321,
+  "epoch": 0.4639025804581038,
   "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": 364.89,
       "eval_steps_per_second": 91.348,
       "step": 39
+    },
+    {
+      "epoch": 0.37112206436648304,
+      "grad_norm": 0.22251972556114197,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3642,
+      "step": 40
+    },
+    {
+      "epoch": 0.3804001159756451,
+      "grad_norm": 0.22692683339118958,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3622,
+      "step": 41
+    },
+    {
+      "epoch": 0.38967816758480717,
+      "grad_norm": 0.23968474566936493,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3702,
+      "step": 42
+    },
+    {
+      "epoch": 0.3989562191939693,
+      "grad_norm": 0.22414839267730713,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3629,
+      "step": 43
+    },
+    {
+      "epoch": 0.40823427080313135,
+      "grad_norm": 0.27029696106910706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3601,
+      "step": 44
+    },
+    {
+      "epoch": 0.4175123224122934,
+      "grad_norm": 0.26507827639579773,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3646,
+      "step": 45
+    },
+    {
+      "epoch": 0.4267903740214555,
+      "grad_norm": 0.23490291833877563,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.358,
+      "step": 46
+    },
+    {
+      "epoch": 0.4360684256306176,
+      "grad_norm": 0.2541787326335907,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.36,
+      "step": 47
+    },
+    {
+      "epoch": 0.44534647723977966,
+      "grad_norm": 0.21563424170017242,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.365,
+      "step": 48
+    },
+    {
+      "epoch": 0.4546245288489417,
+      "grad_norm": 0.24226868152618408,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3748,
+      "step": 49
+    },
+    {
+      "epoch": 0.4639025804581038,
+      "grad_norm": 0.23314820230007172,
+      "learning_rate": 0.0,
+      "loss": 10.3625,
+      "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": 65273453346816.0,
+  "total_flos": 83683914547200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null