Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87038b788fef736431d9618df829f82ceac193dc61f72ad6e7d5c97738cbc53
+oid sha256:ab8e52ba3206274165270ca889c807bd1a725366029d171c2e7e555c62a4d619
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a458fb4ed2ef3cccfdcbd12bb02c3a70958c37d48cbd2699cd9b195254c7d38e
+oid sha256:598cb2512af7e8188533b45056698859d385c686d0b90b69e581bb986d15eebb
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083b722e8b556bda137ae078b24a5e36ab3e05cf212936fb76f8e8582540a426
+oid sha256:3167b45e8191cbbe1e15b6e4e3e671c26ef8fc1eff2010be5aceabaa71c7c16a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033883947479881405,
+  "epoch": 0.005082592121982211,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 3.521,
       "eval_steps_per_second": 1.76,
       "step": 6
+    },
+    {
+      "epoch": 0.003953127205986164,
+      "grad_norm": 2.7113640308380127,
+      "learning_rate": 0.00014,
+      "loss": 2.2146,
+      "step": 7
+    },
+    {
+      "epoch": 0.004517859663984188,
+      "grad_norm": 2.97259521484375,
+      "learning_rate": 0.00016,
+      "loss": 1.9369,
+      "step": 8
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "grad_norm": 3.431048631668091,
+      "learning_rate": 0.00018,
+      "loss": 1.8664,
+      "step": 9
+    },
+    {
+      "epoch": 0.005082592121982211,
+      "eval_loss": 2.243478536605835,
+      "eval_runtime": 211.702,
+      "eval_samples_per_second": 3.524,
+      "eval_steps_per_second": 1.762,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9202732338511872.0,
+  "total_flos": 1.3804098507767808e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null