Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dcd64ac1109a6ffd90c221f18474578dd42de2ebf9364a95fbd2255f234703c
+oid sha256:af442b82d4602549494cbf3a616f97c58826ea031e491908bc057b4b1b792d29
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fd3d4d3289f305320f7dc528ced94a5bbb778f4c097a64503f53ac90d6cf5b
+oid sha256:107ffa37448f75e8461d12308993250faaedd250300d1143002b80f584d54b52
 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": 0.6999439147504206,
+  "epoch": 0.89736399326977,
   "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": 270.433,
       "eval_steps_per_second": 67.608,
       "step": 39
+    },
+    {
+      "epoch": 0.7178911946158161,
+      "grad_norm": 0.18479208648204803,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3654,
+      "step": 40
+    },
+    {
+      "epoch": 0.7358384744812114,
+      "grad_norm": 0.19193631410598755,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.366,
+      "step": 41
+    },
+    {
+      "epoch": 0.7537857543466069,
+      "grad_norm": 0.19918745756149292,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3647,
+      "step": 42
+    },
+    {
+      "epoch": 0.7717330342120022,
+      "grad_norm": 0.2266952097415924,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3601,
+      "step": 43
+    },
+    {
+      "epoch": 0.7896803140773977,
+      "grad_norm": 0.21075403690338135,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3671,
+      "step": 44
+    },
+    {
+      "epoch": 0.807627593942793,
+      "grad_norm": 0.20477190613746643,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.365,
+      "step": 45
+    },
+    {
+      "epoch": 0.8255748738081884,
+      "grad_norm": 0.1861516535282135,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3645,
+      "step": 46
+    },
+    {
+      "epoch": 0.8435221536735839,
+      "grad_norm": 0.20022974908351898,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3659,
+      "step": 47
+    },
+    {
+      "epoch": 0.8614694335389792,
+      "grad_norm": 0.20338262617588043,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3651,
+      "step": 48
+    },
+    {
+      "epoch": 0.8794167134043747,
+      "grad_norm": 0.20791947841644287,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3679,
+      "step": 49
+    },
+    {
+      "epoch": 0.89736399326977,
+      "grad_norm": 0.22175496816635132,
+      "learning_rate": 0.0,
+      "loss": 10.3645,
+      "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": 68882322161664.0,
+  "total_flos": 88338832293888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null