Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800d99bb42b7733e2d0445567490e2b246aec925dd0a40d19c6c6503d0c7b0c5
+oid sha256:0fd56f78283954fd90f07fea9c85878c7b082532d16ac2b48c43da6a36ffc948
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:201fe6f4bfd65c8a50b6c8fd3bda57545b66c054501f54c0f49edbaa1f255e79
+oid sha256:0cca486d77b5bd5033e21cc52ddb2df75eb7e53ce072ccba14d8622cae5871de
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
+oid sha256:eb6860fb662996e06408f7395eb95e33608243e10060296406b09d21d33362d5
 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": 0.7858942065491183,
+  "epoch": 1.0151133501259446,
   "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": 718.869,
       "eval_steps_per_second": 359.435,
       "step": 39
+    },
+    {
+      "epoch": 0.8060453400503779,
+      "grad_norm": 0.089471235871315,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7712,
+      "step": 40
+    },
+    {
+      "epoch": 0.8261964735516373,
+      "grad_norm": 0.07347529381513596,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 11.7802,
+      "step": 41
+    },
+    {
+      "epoch": 0.8463476070528967,
+      "grad_norm": 0.08484639972448349,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7664,
+      "step": 42
+    },
+    {
+      "epoch": 0.8664987405541562,
+      "grad_norm": 0.07450371980667114,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 11.7729,
+      "step": 43
+    },
+    {
+      "epoch": 0.8866498740554156,
+      "grad_norm": 0.07436664402484894,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.7682,
+      "step": 44
+    },
+    {
+      "epoch": 0.906801007556675,
+      "grad_norm": 0.06699005514383316,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7737,
+      "step": 45
+    },
+    {
+      "epoch": 0.9269521410579346,
+      "grad_norm": 0.06120536848902702,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.7755,
+      "step": 46
+    },
+    {
+      "epoch": 0.947103274559194,
+      "grad_norm": 0.07080995291471481,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 11.7769,
+      "step": 47
+    },
+    {
+      "epoch": 0.9672544080604534,
+      "grad_norm": 0.05604703351855278,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.7804,
+      "step": 48
+    },
+    {
+      "epoch": 0.9874055415617129,
+      "grad_norm": 0.07272876054048538,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 11.7743,
+      "step": 49
+    },
+    {
+      "epoch": 1.0151133501259446,
+      "grad_norm": 0.11772315204143524,
+      "learning_rate": 0.0,
+      "loss": 21.2567,
+      "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": 7921727963136.0,
+  "total_flos": 10156061491200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null