Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e4b52b9fe6cc2a78ead3c1c7537ca8a77a44a7344333aff5edd0324a58aa74
+oid sha256:d1607c3773e9cf43a96a6984de544fef318ed4bb3563d2bee65f4fdefd6058c0
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84cf684423491f57bfd2ab05597f6c86f81fbe3f5935e474266fdc55c48a6ad9
+oid sha256:46ff772245c4d145ab3ec194669f342ef176d118dc4dfbac4f23ba07b1c592a4
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8d766a2c89ca827fd88604c04645a44e7deecf9ec62a527d0adcbef8aac440
+oid sha256:2653fa26103127586994025063275770d818265c4b9d4080b9f9aa5f4ade624d
 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": 0.02908819690471751,
+  "epoch": 0.037292560134253215,
   "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": 1.2815,
       "step": 35
+    },
+    {
+      "epoch": 0.029834048107402575,
+      "grad_norm": 2.789149045944214,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4079,
+      "step": 40
+    },
+    {
+      "epoch": 0.029834048107402575,
+      "eval_loss": 1.2403818368911743,
+      "eval_runtime": 55.4301,
+      "eval_samples_per_second": 10.193,
+      "eval_steps_per_second": 5.106,
+      "step": 40
+    },
+    {
+      "epoch": 0.03356330412082789,
+      "grad_norm": 1.9482420682907104,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3194,
+      "step": 45
+    },
+    {
+      "epoch": 0.037292560134253215,
+      "grad_norm": 1.8774888515472412,
+      "learning_rate": 0.0,
+      "loss": 1.2773,
+      "step": 50
+    },
+    {
+      "epoch": 0.037292560134253215,
+      "eval_loss": 1.233705759048462,
+      "eval_runtime": 55.4467,
+      "eval_samples_per_second": 10.19,
+      "eval_steps_per_second": 5.104,
+      "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": 8004335107571712.0,
+  "total_flos": 1.0313277927063552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null