Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e26e52f2497aee96de237b77f5a9a077a2f6e33e8bfbb953a3c90d72e59526b
+oid sha256:7e572c6efae4f61ab99f0e230e4d35688b9fb69e12bc3675c37ade703f9539dc
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c3e6732a4fd828dd4ad0a357bc9ab6cd2337455f01c4ef1130982123df09ea
+oid sha256:e3c54998cf5baee5a75099f753bce991a597595f093e7be0a921a725a7ed314f
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6f36c43b25c18064047d49091952271bf897fce258fb8ea80c54bf2aca0a65
+oid sha256:a39614d4b29fa4effca5b8905624e76498c3279859dada66534907707918edb5
 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": 0.03513513513513514,
+  "epoch": 0.04504504504504504,
   "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": 1.7043,
       "step": 35
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "grad_norm": 1.6609708070755005,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.674,
+      "step": 40
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "eval_loss": 1.6486310958862305,
+      "eval_runtime": 19.8172,
+      "eval_samples_per_second": 23.616,
+      "eval_steps_per_second": 11.808,
+      "step": 40
+    },
+    {
+      "epoch": 0.04054054054054054,
+      "grad_norm": 1.9326635599136353,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6332,
+      "step": 45
+    },
+    {
+      "epoch": 0.04504504504504504,
+      "grad_norm": 1.9144363403320312,
+      "learning_rate": 0.0,
+      "loss": 1.7412,
+      "step": 50
+    },
+    {
+      "epoch": 0.04504504504504504,
+      "eval_loss": 1.641535997390747,
+      "eval_runtime": 19.9565,
+      "eval_samples_per_second": 23.451,
+      "eval_steps_per_second": 11.725,
+      "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": 2713319878164480.0,
+  "total_flos": 3478615228416000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null