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:f6a0bbdaee8741456e6019d41435d2497031b447c90ae2e35cc5920e475341be
+oid sha256:f22a1e0c5a8bc6890f006bbd516ed35e58a3f832083390f1bab1349aff734f17
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:479a1059cf803b95f394a914cd1f25cee34ac0286bada3b2b9a0ba41b6e8c288
+oid sha256:a50919e8fe3784439c16b261055797309196a2a89d906b599fc789754da78bd2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185f5a451f9abc72729e973512be4f639b0b150a8950a48ddb47a15c2cc0c531
+oid sha256:1f6c67b9aca20f5df3caeacd4f86d6e96a90915841fe6b6bf98a7b03df3266e5
 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": 0.11247296322999278,
+  "epoch": 0.14419610670511895,
   "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": 2.4343,
       "step": 35
+    },
+    {
+      "epoch": 0.11535688536409516,
+      "grad_norm": 0.8563252687454224,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4361,
+      "step": 40
+    },
+    {
+      "epoch": 0.11535688536409516,
+      "eval_loss": 2.3816773891448975,
+      "eval_runtime": 10.3915,
+      "eval_samples_per_second": 14.05,
+      "eval_steps_per_second": 7.025,
+      "step": 40
+    },
+    {
+      "epoch": 0.12977649603460706,
+      "grad_norm": 0.9579905867576599,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3712,
+      "step": 45
+    },
+    {
+      "epoch": 0.14419610670511895,
+      "grad_norm": 1.130354404449463,
+      "learning_rate": 0.0,
+      "loss": 2.1678,
+      "step": 50
+    },
+    {
+      "epoch": 0.14419610670511895,
+      "eval_loss": 2.3783786296844482,
+      "eval_runtime": 10.1247,
+      "eval_samples_per_second": 14.42,
+      "eval_steps_per_second": 7.21,
+      "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": 7536974311194624.0,
+  "total_flos": 9617734090358784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null