Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31209ed4f84a9f3fc94215d2a89ecce7d6dc05e72731feb841ee07f66a98f2f9
+oid sha256:7aedaebfce53e736e671aaa3bc297f78e92ec2f60ed18d7b1eb626da7fd90750
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716211ef28fd376a0e4abe44562da715a01a83429812bc77d6b0405dbe575bca
+oid sha256:77965fd920de36e0aee84034bac83dc9b562404b70521492af6252fd5e089f7c
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1f959ea60b750c7c028188fa04a8ff5b2e5620455bc96b506f49b0af84dea2
+oid sha256:df63d4ef88da85b47bc18d13545522ffcf7f76c59ebe865d1f6563f4a6935182
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00411373260738052,
+  "epoch": 0.007985480943738656,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 15.488,
       "eval_steps_per_second": 7.744,
       "step": 15
+    },
+    {
+      "epoch": 0.004355716878402904,
+      "grad_norm": 3.502082586288452,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 6.9885,
+      "step": 18
+    },
+    {
+      "epoch": 0.004839685420447671,
+      "eval_loss": 1.6045597791671753,
+      "eval_runtime": 112.3898,
+      "eval_samples_per_second": 15.482,
+      "eval_steps_per_second": 7.741,
+      "step": 20
+    },
+    {
+      "epoch": 0.005081669691470054,
+      "grad_norm": 4.299140930175781,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.4409,
+      "step": 21
+    },
+    {
+      "epoch": 0.005807622504537205,
+      "grad_norm": 3.838430643081665,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 5.5058,
+      "step": 24
+    },
+    {
+      "epoch": 0.006049606775559589,
+      "eval_loss": 1.5623209476470947,
+      "eval_runtime": 112.5246,
+      "eval_samples_per_second": 15.463,
+      "eval_steps_per_second": 7.732,
+      "step": 25
+    },
+    {
+      "epoch": 0.006533575317604356,
+      "grad_norm": 3.390537977218628,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.1822,
+      "step": 27
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 3.009563684463501,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 5.9296,
+      "step": 30
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "eval_loss": 1.550625205039978,
+      "eval_runtime": 112.422,
+      "eval_samples_per_second": 15.477,
+      "eval_steps_per_second": 7.739,
+      "step": 30
+    },
+    {
+      "epoch": 0.007985480943738656,
+      "grad_norm": 3.4622366428375244,
+      "learning_rate": 0.0,
+      "loss": 6.3164,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1080426806378496.0,
+  "total_flos": 2115835829157888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null