Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422f8bb10cd574f04f213cd9afa60f650b2039ef4521d8cba8e73881d12a2478
+oid sha256:565726573f0a20793412e24f298b9b92a46f811930294cc15b08e358eceaff2b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106c4966af54123c71433699aefbc267a05f9db84570c5f2478bb025cc9b93ec
+oid sha256:aa16239a9c177114d4c75ede08b3e82dd39706c14e1f71ca9d8224605d9ca26c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbd1aa4b70237b5c3c547fb649a60cb477a57c22993e1c9204b5617c9693660
+oid sha256:b9cbf399d2e32da746fe2d391986409acf722afe3eae7d8e75807e1038dab9b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024612579762989972,
+  "epoch": 0.032816773017319965,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 4.524,
       "eval_steps_per_second": 0.566,
       "step": 27
+    },
+    {
+      "epoch": 0.027347310847766638,
+      "grad_norm": 10.839764595031738,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 5.6314,
+      "step": 30
+    },
+    {
+      "epoch": 0.0300820419325433,
+      "grad_norm": 9.605040550231934,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 5.397,
+      "step": 33
+    },
+    {
+      "epoch": 0.032816773017319965,
+      "grad_norm": 12.7434720993042,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 4.4798,
+      "step": 36
+    },
+    {
+      "epoch": 0.032816773017319965,
+      "eval_loss": 1.2467855215072632,
+      "eval_runtime": 408.5454,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.565,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.03129498681344e+16,
+  "total_flos": 9.527404707132211e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null