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:ada310a0cb94cbae4734f1a4f0bb3ea933f94d775ede6081d7cf65440f074a8a
+oid sha256:0217886443f6fe7c6d89eca636eea483df3efe025187a56f04b8d2cd80882363
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d15b847c34b2ac34c0b1b8220591fcddfa8d760bd2a0d3f638fef9191782ba3
+oid sha256:a8dd28d19ccb89482d6781a1c266089d17d257cc5d214f51e58037fd6b7bdd16
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b76d680e88946aa62382d6662094b505b59578f8ecc27b8777b6d41025edf2b
+oid sha256:6043865080f608c46dc46323e200a9a8606f0801d521ba06c9fa277a73d7fc02
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46221a0bc15c9933d020fd44f518daef244208859bef0a33030be38bcf4d7699
+oid sha256:96c06a6bf750d63b16b1b63011e5e4b8ec1e2c4eda2fb612d28daa31614ac326
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9638a83e00998035c3306a4009cbb4601f701cab3dc9704496c1e291dd48d7fe
+oid sha256:a2528a29ddeca8b52d807d6f4c424b3cb94775a14aec9d1a23a7c4c7e441fd41
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98d98b903e36e91cdce863ddee1a4df0316926794b29ec5e1a7b723feea5eaf
+oid sha256:3156052393e0a3fdcd202f02b651042b4101e63e3463501b15eddc72ac8b15c8
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3978806629c5402c9a771a35781632daf16fe61be6ad66b76eb21cad1169ccf2
+oid sha256:f39cdd1141208d914d89cb8902479069d66725570eee027f0de0b0e47bd74705
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfc50c00b8343aad1e6872f42b496d631dcea255fb8d571acc30edd8ceacdc2
+oid sha256:4620c91d0a5c061ba516bfafacdf660963a14755b7f76df96d58f8743527ff26
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87569e3896fa9f3f64203a5a99efbb535ecb57fdbaf7f612ec18a66d51fc4a8
+oid sha256:026c75bf6107188c4b889c3a461135ef3dec293b17a4687d65de6c7b9f8dbd57
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd7a2bb1ddf85fda6a274bb4464511d512581b7ad1270004ae203ae173d8884
+oid sha256:3ede4241516dbbc7b4545b6b94efb66aa42d8f4d73efd81e9d209f2d5070c287
 size 15984

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": 0.047337278106508875,
+  "epoch": 0.07100591715976332,
   "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": 113.893,
       "eval_steps_per_second": 14.37,
       "step": 6
+    },
+    {
+      "epoch": 0.055226824457593686,
+      "grad_norm": 0.74710613489151,
+      "learning_rate": 0.00014,
+      "loss": 2.4339,
+      "step": 7
+    },
+    {
+      "epoch": 0.0631163708086785,
+      "grad_norm": 0.7509329915046692,
+      "learning_rate": 0.00016,
+      "loss": 2.3672,
+      "step": 8
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.7366978526115417,
+      "learning_rate": 0.00018,
+      "loss": 2.3838,
+      "step": 9
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "eval_loss": 2.343579053878784,
+      "eval_runtime": 1.8762,
+      "eval_samples_per_second": 114.06,
+      "eval_steps_per_second": 14.391,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1730290321981440.0,
+  "total_flos": 2595435482972160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null