Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efdccb3f5614f997c9ffa4562268920ba51100bc8d583307b8265e53b8294a0
+oid sha256:b3cde7bf695645e65d852f1d55be5c04d6a329da827729c837935820970c5bbe
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ec782382280126c6b7cf1c0c690bf8fb7ae6add8c2c39397166e03fe062f65
+oid sha256:e960e946a68209fd592acfc8fa435fa0f817c8bb78d13525dac3b7c04a6aa4fd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da48dd9e7ae748bd2f3fab650d68fffe92a7b3bb2fb003057b108531c68316aa
+oid sha256:4f0c25d3f1898ab75d9af127432199dc02b43b9f44da5dfc8bd50460b463700e
 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": 0.04153354632587859,
+  "epoch": 0.05324813631522897,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.2642,
       "step": 35
+    },
+    {
+      "epoch": 0.042598509052183174,
+      "grad_norm": 0.8788539171218872,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3297,
+      "step": 40
+    },
+    {
+      "epoch": 0.042598509052183174,
+      "eval_loss": 1.3412672281265259,
+      "eval_runtime": 35.3203,
+      "eval_samples_per_second": 11.212,
+      "eval_steps_per_second": 5.606,
+      "step": 40
+    },
+    {
+      "epoch": 0.04792332268370607,
+      "grad_norm": 0.913733959197998,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3858,
+      "step": 45
+    },
+    {
+      "epoch": 0.05324813631522897,
+      "grad_norm": 1.3565720319747925,
+      "learning_rate": 0.0,
+      "loss": 1.3473,
+      "step": 50
+    },
+    {
+      "epoch": 0.05324813631522897,
+      "eval_loss": 1.336426854133606,
+      "eval_runtime": 35.4704,
+      "eval_samples_per_second": 11.164,
+      "eval_steps_per_second": 5.582,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0080125152395264e+16,
+  "total_flos": 1.2577036887392256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null