Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd2502ea83d5d366d64130f281c4dc4c51f55959388822860e6132643fa1b6c
+oid sha256:ac497b59fe0dd2f0e40472e46f858bbdb99649d4e9fce2983b94b3c39ae88b57
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:756e1235a09135577c36df1a16bd319d5c02b5e9db73b6bb05c873384f7e2a3d
+oid sha256:8396a332c62fba701e1077afee762c9c5c7d7a254ab5b4d15e66e321049b42a7
 size 7086458

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a638e6bd4189d44eeac1f993292bbad8f48cdfa2af9dfd0362a0525bbf6d848
+oid sha256:574b2f0aac69a88223246e1abbe4d7331cee680c2262f30a429273e330af5c7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03986710963455149,
+  "epoch": 0.07973421926910298,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.865,
       "eval_steps_per_second": 7.432,
       "step": 3
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 1.1863428354263306,
+      "learning_rate": 8e-05,
+      "loss": 1.5754,
+      "step": 4
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 1.072548508644104,
+      "learning_rate": 0.0001,
+      "loss": 1.4127,
+      "step": 5
+    },
+    {
+      "epoch": 0.07973421926910298,
+      "grad_norm": 0.8001244068145752,
+      "learning_rate": 0.00012,
+      "loss": 1.3504,
+      "step": 6
+    },
+    {
+      "epoch": 0.07973421926910298,
+      "eval_loss": 1.3731586933135986,
+      "eval_runtime": 2.161,
+      "eval_samples_per_second": 14.808,
+      "eval_steps_per_second": 7.404,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 83302551650304.0,
+  "total_flos": 166605103300608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null