Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11d35ac3eaf8a4a3e7440183fca25b4732d174ee206dc800eea3f18343a83b3
+oid sha256:785dc97ea3b8a3e65c2659f391b19cc52c95ece42aaaa13931ac114af57ecc01
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f91301a897fb6c46a697999e93d02dca95b1a5bd7135c5fd37ae8fec052d82
+oid sha256:b84cb35aadce24c0ea1d16952ae19c78dacd8ca2af8f98a0cd2b4b8b4ca397ae
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7e8c0f7bb988751ccd9907b573ddb354edc6c4d1478341caae7f6c4a40c442
+oid sha256:8e4d249624bc8de793916f023beebfa62202a9083f1d5be34ff57cd42f702095
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.043272481406355645,
+  "epoch": 0.06490872210953347,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 8.957,
       "eval_steps_per_second": 4.478,
       "step": 18
+    },
+    {
+      "epoch": 0.05048456164074825,
+      "grad_norm": 0.9527170062065125,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 1.5801,
+      "step": 21
+    },
+    {
+      "epoch": 0.05769664187514086,
+      "grad_norm": 0.9741354584693909,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 1.6089,
+      "step": 24
+    },
+    {
+      "epoch": 0.06490872210953347,
+      "grad_norm": 0.8610622882843018,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 1.5059,
+      "step": 27
+    },
+    {
+      "epoch": 0.06490872210953347,
+      "eval_loss": 1.3450061082839966,
+      "eval_runtime": 156.5047,
+      "eval_samples_per_second": 8.958,
+      "eval_steps_per_second": 4.479,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0742550511170355e+17,
+  "total_flos": 1.6113825766755533e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null