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:f448fa946f5aa0415f701fd50a7c0aec73f2f77f36a4dba4a72b05fbccf700f3
+oid sha256:488a645e9bb4278e153598b31d64d9f6a1b3c5c1d4703838f6e637855bc037b4
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c02f1c41f3d6daa1969eabc4cd77de4b0629cb8caffd30c3700c3b8bcb4fcbe
+oid sha256:8805f117ea27d62e37d6cb1ace7ca1d36924fd5e9faee231bc31f9418dd233ce
 size 161810282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf0878306dfabad22df73aa5835c9e34d3f3302f1c21c247c88f8c2ea4fd50f
+oid sha256:f4ec00b30112630c8f1ec8713a30a710bbb4005a9dadcacf4fed633d77dd07cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003993158388627485,
+  "epoch": 0.000798631677725497,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 12.935,
       "eval_steps_per_second": 6.468,
       "step": 15
+    },
+    {
+      "epoch": 0.0004791790066352982,
+      "grad_norm": 0.5660752058029175,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.7645,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005324211184836647,
+      "eval_loss": 2.8858046531677246,
+      "eval_runtime": 1223.6712,
+      "eval_samples_per_second": 12.926,
+      "eval_steps_per_second": 6.463,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005590421744078479,
+      "grad_norm": 0.47273609042167664,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8185,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006389053421803976,
+      "grad_norm": 0.5204505324363708,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.986,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006655263981045808,
+      "eval_loss": 2.8752849102020264,
+      "eval_runtime": 1223.8917,
+      "eval_samples_per_second": 12.924,
+      "eval_steps_per_second": 6.462,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007187685099529473,
+      "grad_norm": 0.43472805619239807,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.7946,
+      "step": 27
+    },
+    {
+      "epoch": 0.000798631677725497,
+      "grad_norm": 0.49167361855506897,
+      "learning_rate": 0.0,
+      "loss": 2.9968,
+      "step": 30
+    },
+    {
+      "epoch": 0.000798631677725497,
+      "eval_loss": 2.871952533721924,
+      "eval_runtime": 1224.3929,
+      "eval_samples_per_second": 12.918,
+      "eval_steps_per_second": 6.46,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5227908138270720.0,
+  "total_flos": 1.045581627654144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null