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:a2f746929b0766a9a8c55c85358e466c997fe6c51aaac178a726d4e656307d5d
+oid sha256:742b0e8f5cc97c411bc18e53a22d60b2d36e1e8fd634a696be2134986fe17862
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cdfb49f4f045bd7e2dd4cd6a9445f34715a8e3070fd1fdc9824a9c05c05faa0
+oid sha256:a79e11c8d8ceb98aadfb295c89c7f267628be3114000b49d49913734e17e98e7
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10478589420654912,
+  "epoch": 0.1343408900083963,
   "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": 39.064,
       "eval_steps_per_second": 19.563,
       "step": 39
+    },
+    {
+      "epoch": 0.10747271200671704,
+      "grad_norm": 1.1191169023513794,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2467,
+      "step": 40
+    },
+    {
+      "epoch": 0.11015952980688497,
+      "grad_norm": 1.0125330686569214,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.1799,
+      "step": 41
+    },
+    {
+      "epoch": 0.1128463476070529,
+      "grad_norm": 1.3123078346252441,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2992,
+      "step": 42
+    },
+    {
+      "epoch": 0.11553316540722082,
+      "grad_norm": 1.011380672454834,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.2407,
+      "step": 43
+    },
+    {
+      "epoch": 0.11821998320738875,
+      "grad_norm": 1.1584933996200562,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.3031,
+      "step": 44
+    },
+    {
+      "epoch": 0.12090680100755667,
+      "grad_norm": 1.1705843210220337,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2667,
+      "step": 45
+    },
+    {
+      "epoch": 0.1235936188077246,
+      "grad_norm": 1.0741093158721924,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2942,
+      "step": 46
+    },
+    {
+      "epoch": 0.12628043660789254,
+      "grad_norm": 1.0633755922317505,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.3064,
+      "step": 47
+    },
+    {
+      "epoch": 0.12896725440806045,
+      "grad_norm": 1.2350645065307617,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.2901,
+      "step": 48
+    },
+    {
+      "epoch": 0.1316540722082284,
+      "grad_norm": 1.0202724933624268,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.187,
+      "step": 49
+    },
+    {
+      "epoch": 0.1343408900083963,
+      "grad_norm": 1.1233915090560913,
+      "learning_rate": 0.0,
+      "loss": 2.2938,
+      "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": 2.981302609379328e+16,
+  "total_flos": 3.8221828325376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null