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:bdce6b30f5ea98e4092661b79621841434741a05f260f68390c512093c95a068
+oid sha256:21e5bc3baba045b6adb2ecf16d2af1b10d7ce8191deacf2f43cebd7ad4b8ca77
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca765307b055314fa722a59fdec7efdbf8f9c88a3e6827b0cb61881a3fd8fa3b
+oid sha256:f4308e00e70f990d5c8e4bc074ed30e21a0d7e55f5ec83dfc4c962384e041ee0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a4a3475bbbd37ecdd810d8257811f1364a7006e49ca0ea2393e9b025bf14bc
+oid sha256:201bcb7e4468e1cbf19a98a9b22043458577f3af3827e705acbaa6565416ca4f
 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": 0.002623833151122698,
+  "epoch": 0.00336388865528551,
   "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": 1.2994,
       "step": 35
+    },
+    {
+      "epoch": 0.0026911109242284082,
+      "grad_norm": 4.64229154586792,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2359,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026911109242284082,
+      "eval_loss": 1.182938814163208,
+      "eval_runtime": 718.2201,
+      "eval_samples_per_second": 8.715,
+      "eval_steps_per_second": 4.358,
+      "step": 40
+    },
+    {
+      "epoch": 0.003027499789756959,
+      "grad_norm": 4.52047872543335,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1852,
+      "step": 45
+    },
+    {
+      "epoch": 0.00336388865528551,
+      "grad_norm": 4.517399311065674,
+      "learning_rate": 0.0,
+      "loss": 1.124,
+      "step": 50
+    },
+    {
+      "epoch": 0.00336388865528551,
+      "eval_loss": 1.1775221824645996,
+      "eval_runtime": 713.6593,
+      "eval_samples_per_second": 8.77,
+      "eval_steps_per_second": 4.386,
+      "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": 6352122043957248.0,
+  "total_flos": 8143746210201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null