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:a63853ec1318d55cbc389f5973b7328f14abbe1339a6a1001b4a9b7ab67814eb
+oid sha256:684145367e7e51b479b8d7f47b8541e3fbb1ebdf8ae112e0a4c320777a826d24
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb0f217ba647d69e8b87e12f10d698b3b6e92c985f41975d27b0c9af8e75c33
+oid sha256:bee52cd5fa1d851899c893a372e43297d580ecde6b33d913830c61172d61eda1
 size 335922386

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": 0.01238390092879257,
+  "epoch": 0.02476780185758514,
   "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": 9.359,
       "eval_steps_per_second": 4.68,
       "step": 10
+    },
+    {
+      "epoch": 0.014860681114551083,
+      "grad_norm": 2.586092710494995,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.3273,
+      "step": 12
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": 1.8593789339065552,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.126,
+      "step": 15
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "eval_loss": 0.9424641132354736,
+      "eval_runtime": 61.7521,
+      "eval_samples_per_second": 5.506,
+      "eval_steps_per_second": 2.753,
+      "step": 15
+    },
+    {
+      "epoch": 0.022291021671826627,
+      "grad_norm": 1.9731193780899048,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8594,
+      "step": 18
+    },
+    {
+      "epoch": 0.02476780185758514,
+      "eval_loss": 0.8208107352256775,
+      "eval_runtime": 61.9509,
+      "eval_samples_per_second": 5.488,
+      "eval_steps_per_second": 2.744,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null