Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f38f63cbb0e9416ed4b2e9a2bd0ab8efc244d26439faa2a8249933883636959
+oid sha256:3083c31e7624313a37661f7cee7d7afdcba6fc9e54839bbb6aed7a4c6a7ff311
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ce0bcb8d328e2d2b372cc45a939b9b9758637bc09766889fc2461643fa99f6
+oid sha256:a0d631d114fdc9fa49d6deb0160925c7d29e3617efab5aed7438ca9a351d9a20
 size 52046596

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d398b0661e80cdd4b290db9637d3a4862993945d935bbf1960dbb0803ec6f9f8
+oid sha256:80f07cf6216070249033266c72356977f28fb9e105b042f5a3ae5146b4bf1b83
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998470fa5c8115b8d249e96e18986f84612a0e6cf47a8a9cd2a28321abea763f
+oid sha256:c72842717b2036b82a63b7b12be12f81cb3652b8a69815f17f509d3428f86bdb
 size 14512

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": 0.004406095098219203,
+  "epoch": 0.006609142647328804,
   "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": 6.722,
       "eval_steps_per_second": 1.682,
       "step": 6
+    },
+    {
+      "epoch": 0.005140444281255737,
+      "grad_norm": 0.5175211429595947,
+      "learning_rate": 0.00014,
+      "loss": 0.4637,
+      "step": 7
+    },
+    {
+      "epoch": 0.005874793464292271,
+      "grad_norm": 0.700370192527771,
+      "learning_rate": 0.00016,
+      "loss": 0.4532,
+      "step": 8
+    },
+    {
+      "epoch": 0.006609142647328804,
+      "grad_norm": 0.6425027847290039,
+      "learning_rate": 0.00018,
+      "loss": 0.4004,
+      "step": 9
+    },
+    {
+      "epoch": 0.006609142647328804,
+      "eval_loss": 0.3521825969219208,
+      "eval_runtime": 170.8063,
+      "eval_samples_per_second": 6.715,
+      "eval_steps_per_second": 1.68,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7902460920201216.0,
+  "total_flos": 1.1853691380301824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null