Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3613eb1b993ffed95cd9f1d3369deaafea3fc2c443fde192406856824013e03d
+oid sha256:e6de0294e0e20eda411f9777aa95bc474e9414e975d9e3fe86b9fa14d6212742
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8392a8145b095f8f0e1b8e6e84141acd17c5a7c16241ea55b2136c4199a8ae28
+oid sha256:b7cde417ecd563aec9a52d9af7e37988859a344001a3e3b5eec7485cf85dd3dc
 size 25784826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
+oid sha256:0a016715ccb0112ab1394743f94acfb298ac9ccf9cd4cd745ca6d3b1bffe35a3
 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": 0.010894805761676124,
+  "epoch": 0.013967699694456569,
   "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": 6.784,
       "eval_steps_per_second": 3.392,
       "step": 39
+    },
+    {
+      "epoch": 0.011174159755565256,
+      "grad_norm": 5.941615581512451,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 18.2148,
+      "step": 40
+    },
+    {
+      "epoch": 0.011453513749454386,
+      "grad_norm": 6.788694858551025,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 18.3477,
+      "step": 41
+    },
+    {
+      "epoch": 0.011732867743343518,
+      "grad_norm": 6.989747524261475,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 19.8516,
+      "step": 42
+    },
+    {
+      "epoch": 0.01201222173723265,
+      "grad_norm": 9.784863471984863,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 16.9668,
+      "step": 43
+    },
+    {
+      "epoch": 0.01229157573112178,
+      "grad_norm": 7.244667053222656,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 18.1797,
+      "step": 44
+    },
+    {
+      "epoch": 0.012570929725010912,
+      "grad_norm": 7.783876419067383,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 18.0039,
+      "step": 45
+    },
+    {
+      "epoch": 0.012850283718900044,
+      "grad_norm": 12.166605949401855,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 18.4736,
+      "step": 46
+    },
+    {
+      "epoch": 0.013129637712789174,
+      "grad_norm": 7.943640232086182,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 17.7656,
+      "step": 47
+    },
+    {
+      "epoch": 0.013408991706678306,
+      "grad_norm": 7.052063941955566,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 17.332,
+      "step": 48
+    },
+    {
+      "epoch": 0.013688345700567438,
+      "grad_norm": 7.097042560577393,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 17.2266,
+      "step": 49
+    },
+    {
+      "epoch": 0.013967699694456569,
+      "grad_norm": 9.13848876953125,
+      "learning_rate": 0.0,
+      "loss": 18.5176,
+      "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": 3.961564956721152e+16,
+  "total_flos": 5.072003618832384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null