Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee7d366875b417f3ca64f9089a87393df68797927bded8494f4192babdb94f2
+oid sha256:0b0700fba4678cfdca0719cad738c0a058bdede63477172c29d1a2b4eeeef870
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e5fcdd08d401c36422b1730c15b858be7da59adb4bbb209ecc4987defa613a
+oid sha256:88d95bb6666f64d6ff3f741a7e24f0a0a1a18e5af6026b46bae41b6af6cb9067
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07604562737642585,
+  "epoch": 0.11406844106463879,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 11.9334,
       "step": 18
+    },
+    {
+      "epoch": 0.07984790874524715,
+      "grad_norm": 0.07278630882501602,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9331,
+      "step": 21
+    },
+    {
+      "epoch": 0.09125475285171103,
+      "grad_norm": 0.07088412344455719,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.9331,
+      "step": 24
+    },
+    {
+      "epoch": 0.09125475285171103,
+      "eval_loss": 11.93262004852295,
+      "eval_runtime": 0.8978,
+      "eval_samples_per_second": 123.632,
+      "eval_steps_per_second": 62.373,
+      "step": 24
+    },
+    {
+      "epoch": 0.10266159695817491,
+      "grad_norm": 0.06771118193864822,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9278,
+      "step": 27
+    },
+    {
+      "epoch": 0.11406844106463879,
+      "grad_norm": 0.07984782755374908,
+      "learning_rate": 0.0,
+      "loss": 11.9317,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7494696960.0,
+  "total_flos": 11242045440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null