Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760ab67e6fe179995f6b64d15703a8de72fd2c27ac74f1667e58cd46333b5c59
+oid sha256:687117264754c089308ffc08924cd3d6a183bd268836411f4d3f67380bff8419
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7a0caf3275a3e9547ddc781f356a280681e3cfc6c27d6d3025de6bb52f1510
+oid sha256:94052967967ab19ba6c22a70ac594d47a04ad7d37f70f07e858b85765bb1d9b6
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e7df98956cbfdbc82d316da9e771635f25d6a42d1941fd1c96e5d31bbffb8a
+oid sha256:53d355765c93bb05ccfd64a6e86d690ee768ea6659b8178416a62a392b9b4bd9
 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": 0.004051211468044771,
+  "epoch": 0.005193860856467655,
   "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": 1.3617,
       "step": 35
+    },
+    {
+      "epoch": 0.004155088685174124,
+      "grad_norm": 1.1504039764404297,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2965,
+      "step": 40
+    },
+    {
+      "epoch": 0.004155088685174124,
+      "eval_loss": 1.3331817388534546,
+      "eval_runtime": 225.5446,
+      "eval_samples_per_second": 17.974,
+      "eval_steps_per_second": 8.987,
+      "step": 40
+    },
+    {
+      "epoch": 0.004674474770820889,
+      "grad_norm": 1.1398301124572754,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4048,
+      "step": 45
+    },
+    {
+      "epoch": 0.005193860856467655,
+      "grad_norm": 1.0534467697143555,
+      "learning_rate": 0.0,
+      "loss": 1.2853,
+      "step": 50
+    },
+    {
+      "epoch": 0.005193860856467655,
+      "eval_loss": 1.3300703763961792,
+      "eval_runtime": 223.1378,
+      "eval_samples_per_second": 18.168,
+      "eval_steps_per_second": 9.084,
+      "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": 1987886889566208.0,
+  "total_flos": 2562998819880960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null