Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b28e929e31402580bc7714ece765bebaf6232a77f1945b6acd6f9edd64c2dbf
+oid sha256:51e8be5e06c2a06f02c41ecb622e9c47147abe64e3952034156af7ed24cb7ce5
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2dd9c2c5c4ed94606f74a8ebe5edae84a5ff2ee2612b72c0fde25ccd64cf9f9
+oid sha256:40bd2bc252edc6b00dc39cfef5f9958a6e9490cf444cd94e33e1341079d530df
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b02cb45f4d7dbcf1f3bbd1da580bee2c1c4946401fd6dcc2d96aa004cddd97d
+oid sha256:9827b398fc968e0b0684f99c11a527546e70ab824cd0ae8d6535c172e2f92b44
 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": 0.028070175438596492,
+  "epoch": 0.042105263157894736,
   "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": 57.042,
       "eval_steps_per_second": 28.521,
       "step": 6
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 0.7844423055648804,
+      "learning_rate": 0.00014,
+      "loss": 2.0469,
+      "step": 7
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 0.9878946542739868,
+      "learning_rate": 0.00016,
+      "loss": 1.9194,
+      "step": 8
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 1.2176491022109985,
+      "learning_rate": 0.00018,
+      "loss": 1.8877,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 1.8432834148406982,
+      "eval_runtime": 1.5791,
+      "eval_samples_per_second": 56.995,
+      "eval_steps_per_second": 28.497,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 264600066981888.0,
+  "total_flos": 408927376244736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null