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:f6f04ec9ba4560bceae3be359e3815743a83fefc0d532861dc7585888b96fd09
+oid sha256:de45c8a921be72453ae8017ff551652b015af529680ef25d86bd5532787499a5
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67c6c0c9604ed2371d2e630c2dfd000b08ead405cc0e0819c317c0d6cd8b7bf
+oid sha256:b91f39d1587b2a556b4eb7fcab97950148cc7c53189d472ec33fee8d8a423e09
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02165d4c69622fcfc766b69f9ff93ab491b56d69b5e1c404e98df0ba367c4740
+oid sha256:bc815ac006f84205e1a46c9f874750bf2e86b13d6a4fe2f474151cb4ed03338a
 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": 0.00306044376434583,
+  "epoch": 0.003923645851725424,
   "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": 0.6068,
       "step": 35
+    },
+    {
+      "epoch": 0.0031389166813803387,
+      "grad_norm": 7.56188440322876,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5115,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031389166813803387,
+      "eval_loss": 0.5395087599754333,
+      "eval_runtime": 179.6605,
+      "eval_samples_per_second": 29.867,
+      "eval_steps_per_second": 14.934,
+      "step": 40
+    },
+    {
+      "epoch": 0.0035312812665528807,
+      "grad_norm": 9.424992561340332,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.507,
+      "step": 45
+    },
+    {
+      "epoch": 0.003923645851725424,
+      "grad_norm": 10.194769859313965,
+      "learning_rate": 0.0,
+      "loss": 0.5211,
+      "step": 50
+    },
+    {
+      "epoch": 0.003923645851725424,
+      "eval_loss": 0.5438435077667236,
+      "eval_runtime": 179.8406,
+      "eval_samples_per_second": 29.838,
+      "eval_steps_per_second": 14.919,
+      "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": 938127510208512.0,
+  "total_flos": 1202727577190400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null