Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e48ac0d65dc32dd608b43cccd66f6e21598cd6b903d180a2101d9697457284d
+oid sha256:298f91c7a5d3b6b89f7e4121dda68b9efc819653e1888fb66dbb1c86dc2ce2f9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf0fded568d97f716b5ef32edc64b73db485ca2bdd43ebefc00f9a3999a96ab
+oid sha256:fe2c6b6c1e3d6b62019e5dd5e0645e56f5e504fa66eaa8042a1d789462f55198
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:73897459790c71e778cc7ceecffb2a8c860a86694620eace0115b8c55bf7b45c
 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": 0.004155346012466038,
+  "epoch": 0.0053273666826487666,
   "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": 2.5179,
       "step": 35
+    },
+    {
+      "epoch": 0.004261893346119014,
+      "grad_norm": 2.1878769397735596,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4348,
+      "step": 40
+    },
+    {
+      "epoch": 0.004261893346119014,
+      "eval_loss": 2.3634743690490723,
+      "eval_runtime": 282.4788,
+      "eval_samples_per_second": 13.99,
+      "eval_steps_per_second": 6.995,
+      "step": 40
+    },
+    {
+      "epoch": 0.00479463001438389,
+      "grad_norm": 1.7152621746063232,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.444,
+      "step": 45
+    },
+    {
+      "epoch": 0.0053273666826487666,
+      "grad_norm": 1.8380874395370483,
+      "learning_rate": 0.0,
+      "loss": 2.2616,
+      "step": 50
+    },
+    {
+      "epoch": 0.0053273666826487666,
+      "eval_loss": 2.3588783740997314,
+      "eval_runtime": 282.7819,
+      "eval_samples_per_second": 13.975,
+      "eval_steps_per_second": 6.988,
+      "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": 7213300567769088.0,
+  "total_flos": 9340299453136896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null