Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c348459b49b48817d0ca297d08843dd72c2900975fb232b18deae11d7bffb2
+oid sha256:d2d3118c4d060cf9973780e2aaa84708a2b65970aa9b83884c8b17fc95d8c09f
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecd02fcdd95b18cd5ce74122dbffe370ea1f17686d8388742d28e85a6e72664
+oid sha256:2dd7933ef5b6172011e67d1944b09f9a08346a3d06c75e82774c4fb60f4d1e51
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403802fc1b17803d2d916cdfd1de8f3b120b98330ad584b12b18aba37539dfd1
+oid sha256:02ffb444460cec0593644f90f5f44566acef22e7acc3140154ec101ab0bf695d
 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": 0.021069265209375822,
+  "epoch": 0.03160389781406373,
   "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": 2.9711,
       "step": 18
+    },
+    {
+      "epoch": 0.022122728469844616,
+      "grad_norm": 5.256614685058594,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.7517,
+      "step": 21
+    },
+    {
+      "epoch": 0.02528311825125099,
+      "grad_norm": 4.054143905639648,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.6012,
+      "step": 24
+    },
+    {
+      "epoch": 0.02528311825125099,
+      "eval_loss": 2.638476610183716,
+      "eval_runtime": 15.3056,
+      "eval_samples_per_second": 26.134,
+      "eval_steps_per_second": 13.067,
+      "step": 24
+    },
+    {
+      "epoch": 0.028443508032657362,
+      "grad_norm": 3.4772584438323975,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.6977,
+      "step": 27
+    },
+    {
+      "epoch": 0.03160389781406373,
+      "grad_norm": 3.0739574432373047,
+      "learning_rate": 0.0,
+      "loss": 2.3018,
+      "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": 1967550690754560.0,
+  "total_flos": 2951326036131840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null