Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db804d5174d336b6f9629d4f70964a54f0fbb4b06ca277c59a799dac6d2306c
+oid sha256:a1069a79a936ebb1b9a0a4dd3b7725f535bbdec5a22d49a6f7d4ac4fb448937c
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f0be0df0a9bcd16c86c6dc461bb8b70554fa5d76c9eefedc9a36aa0d686186
+oid sha256:c9f46d0aeaf8c2e93fafa1d50c7f1cba8febad13f084bc5b0589dea583559ca2
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a8a9bdd862ce991dd45800936ca731700f83e2a539b63be29d121aacf28815
+oid sha256:54a60ebbcefea7f2668cc430bd7ea8e59180f28cf088ef8235e062aab550c587
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.017667844522968,
+  "epoch": 1.1448763250883391,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 40.037,
       "eval_steps_per_second": 5.005,
       "step": 72
+    },
+    {
+      "epoch": 1.0600706713780919,
+      "grad_norm": 0.05056842789053917,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 2.46,
+      "step": 75
+    },
+    {
+      "epoch": 1.1024734982332156,
+      "grad_norm": 0.0757237896323204,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 2.5239,
+      "step": 78
+    },
+    {
+      "epoch": 1.1448763250883391,
+      "grad_norm": 0.051590222865343094,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 2.4761,
+      "step": 81
+    },
+    {
+      "epoch": 1.1448763250883391,
+      "eval_loss": 2.3426692485809326,
+      "eval_runtime": 3.0085,
+      "eval_samples_per_second": 39.887,
+      "eval_steps_per_second": 4.986,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9153654753853440.0,
+  "total_flos": 1.029786159808512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null