Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aed67bbda57ad52d7af3cf95a925d3d69371b55a139a98ae2bf8ccb66b77464
+oid sha256:6e2b812e05447f98b95e53fb3e4585a3e613229237e8495a2774ff9ca0c940ad
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eff64625a020557fdc8457ce1732a35acfce3b8b82a831886bfe724c9785240
+oid sha256:3775378072cc4284bd66d7d6e0eaa64bc09c4d70be8a8e2a69826dbacaa62172
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7271133a69aed95a478dd38ae5679559b36062adb67fb034600999504bac978
+oid sha256:32a915e7b85a4b698fd56615d329d8d966599d83261320ff42a3c81047982dc8
 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": 0.15204678362573099,
+  "epoch": 0.1949317738791423,
   "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": 2.5355,
       "step": 35
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "grad_norm": 3.544443130493164,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3278,
+      "step": 40
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "eval_loss": 0.6018404364585876,
+      "eval_runtime": 13.4265,
+      "eval_samples_per_second": 8.044,
+      "eval_steps_per_second": 4.022,
+      "step": 40
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 3.317370653152466,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3523,
+      "step": 45
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "grad_norm": 3.9417917728424072,
+      "learning_rate": 0.0,
+      "loss": 2.5454,
+      "step": 50
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "eval_loss": 0.6009447574615479,
+      "eval_runtime": 13.3322,
+      "eval_samples_per_second": 8.101,
+      "eval_steps_per_second": 4.05,
+      "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": 1.358320644390912e+16,
+  "total_flos": 1.7439084402180096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null