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:ac51966f4ea7e93943ab2a206c128084e84d0224b1416ceeef88b55b24d95293
+oid sha256:aa0ca24839a2d54c1824b440f15ac95727c6fced68caa90976fe1eb01b8c8c44
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970d663624826c02ddb4e41e5d4320f1dff7efb7baa4041535c4f2fd215789c2
+oid sha256:9376319ea6b9938d46d2a8c32720a3b25f8cd2775ac0a039544ddbabfef79140
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4153372e5441b0ea2e6a8c0a0ff12401521178273f30862f0b9f4725190679f0
+oid sha256:b1fbac2690de67edd93baf8d76b7485f0d1b64a83524d673302021c491150379
 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": 0.11190817790530846,
+  "epoch": 0.14347202295552366,
   "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": 1.8409,
       "step": 35
+    },
+    {
+      "epoch": 0.11477761836441894,
+      "grad_norm": 4.136607646942139,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7918,
+      "step": 40
+    },
+    {
+      "epoch": 0.11477761836441894,
+      "eval_loss": 1.7718225717544556,
+      "eval_runtime": 4.4955,
+      "eval_samples_per_second": 32.7,
+      "eval_steps_per_second": 16.461,
+      "step": 40
+    },
+    {
+      "epoch": 0.1291248206599713,
+      "grad_norm": 3.1386682987213135,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0825,
+      "step": 45
+    },
+    {
+      "epoch": 0.14347202295552366,
+      "grad_norm": 3.5192646980285645,
+      "learning_rate": 0.0,
+      "loss": 1.788,
+      "step": 50
+    },
+    {
+      "epoch": 0.14347202295552366,
+      "eval_loss": 1.7615022659301758,
+      "eval_runtime": 4.4287,
+      "eval_samples_per_second": 33.192,
+      "eval_steps_per_second": 16.709,
+      "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": 347248838836224.0,
+  "total_flos": 445190819020800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null