Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cda730a0504543260e181a441e06eb4158f9d93f6ddb200e96fa14982c7f82
+oid sha256:3f8acc8e4583671b90ee55d4dda63885eb7fa29a9a3f70d98501f1851852feb3
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe8bc65229f36bfb76fe4e023d896f5750056569ddf79d6d16fe9e5d13275ed
+oid sha256:3226ae37fb90e8fc8e19c1e5d48d7bffcf5eb041f5cd91967b8bed92ba350dbd
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002796655200380345,
+  "epoch": 0.000559331040076069,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 8.188,
       "eval_steps_per_second": 4.094,
       "step": 10
+    },
+    {
+      "epoch": 0.00033559862404564144,
+      "grad_norm": 0.8673509955406189,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.3144,
+      "step": 12
+    },
+    {
+      "epoch": 0.00041949828005705174,
+      "grad_norm": 0.7220252752304077,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.2095,
+      "step": 15
+    },
+    {
+      "epoch": 0.00041949828005705174,
+      "eval_loss": 1.233842372894287,
+      "eval_runtime": 1838.0633,
+      "eval_samples_per_second": 8.191,
+      "eval_steps_per_second": 4.096,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005033979360684622,
+      "grad_norm": 0.5835627913475037,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2566,
+      "step": 18
+    },
+    {
+      "epoch": 0.000559331040076069,
+      "eval_loss": 1.2087029218673706,
+      "eval_runtime": 1834.2779,
+      "eval_samples_per_second": 8.208,
+      "eval_steps_per_second": 4.104,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3305470584422400.0,
+  "total_flos": 6610941168844800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null