Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed1d45474cab4980753f156dcad1e1a5e2711a0e628eeec58ac74e365a9e9a8
+oid sha256:ccca63b4be6835a2891c6748c153ae860901f80406b2c094b6c5536d9a1e4d08
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90af40dae5ecdfe2da9383ae97bd71e41228c5a1fbdd6a70561bc286c4d9277d
+oid sha256:536af1b2d60d59ddd1c433fae529b35c670bef4d26688ebccc4ac1a735188428
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa539f6e4688557e287ce87d8b179dfd55b8cad2483d5ba29fc9d6b605bb4a7
+oid sha256:0c174463fbf9d340240780bb1144998996b397ddd619620bc511412aa01252eb
 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": 0.09917355371900827,
+  "epoch": 0.12714558169103624,
   "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": 1.818,
       "step": 35
+    },
+    {
+      "epoch": 0.101716465352829,
+      "grad_norm": 0.628464937210083,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7949,
+      "step": 40
+    },
+    {
+      "epoch": 0.101716465352829,
+      "eval_loss": 1.7145599126815796,
+      "eval_runtime": 10.409,
+      "eval_samples_per_second": 15.948,
+      "eval_steps_per_second": 7.974,
+      "step": 40
+    },
+    {
+      "epoch": 0.11443102352193261,
+      "grad_norm": 0.6162843108177185,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7149,
+      "step": 45
+    },
+    {
+      "epoch": 0.12714558169103624,
+      "grad_norm": 0.6955315470695496,
+      "learning_rate": 0.0,
+      "loss": 1.8294,
+      "step": 50
+    },
+    {
+      "epoch": 0.12714558169103624,
+      "eval_loss": 1.7136833667755127,
+      "eval_runtime": 10.343,
+      "eval_samples_per_second": 16.05,
+      "eval_steps_per_second": 8.025,
+      "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": 2562998819880960.0,
+  "total_flos": 3275637516140544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null