Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf3a082b3b5771cde54751caa77f09f0ac4d7f3d687469fcd6e9b7696f4a495
+oid sha256:851cdfe1125015a709eaf9fab0267b83600ce306225cf9cd820e9cc7fdc203ef
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62dbf908ef0b086a0e16946877f43a0cfb62b1c92a6c86289364af28379920f
+oid sha256:bf23282483cf5bb04bc0c4249afc594597166999e0ef36987e550627a6fea884
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c5fa2407d16d691efc64965c095a88cbd3aca96aefe47eb8a1e50f4bcded56
+oid sha256:dabb3c45f0b97aec794ee853d6f7a1b873def80a59432ea58a4d496de18a38cc
 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": 0.004491017964071856,
+  "epoch": 0.006736526946107785,
   "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": 2.573,
       "eval_steps_per_second": 1.289,
       "step": 6
+    },
+    {
+      "epoch": 0.005239520958083832,
+      "grad_norm": 12.0173978805542,
+      "learning_rate": 0.00014,
+      "loss": 0.6145,
+      "step": 7
+    },
+    {
+      "epoch": 0.005988023952095809,
+      "grad_norm": 6.952859401702881,
+      "learning_rate": 0.00016,
+      "loss": 0.4532,
+      "step": 8
+    },
+    {
+      "epoch": 0.006736526946107785,
+      "grad_norm": 2.8368070125579834,
+      "learning_rate": 0.00018,
+      "loss": 0.2738,
+      "step": 9
+    },
+    {
+      "epoch": 0.006736526946107785,
+      "eval_loss": 0.3004415035247803,
+      "eval_runtime": 216.9304,
+      "eval_samples_per_second": 2.595,
+      "eval_steps_per_second": 1.3,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 432572580495360.0,
+  "total_flos": 648858870743040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null