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:e00b7fb5b4ed11a0809e466379814a6f3aba3dcce6e0d9a13262794939c1dd25
+oid sha256:3c56d3e77859e372eafe82b695376f6129b266bfa3dafed40ba1b410df6977c2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4f59d8abd93d7e18305b367e02ed29bbdac570dcf1b23b62d750622e59f016
+oid sha256:6cac03ca4d568fb9489ed3dd10a8785ded296f7dea12e6eee2577b715b0684c6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fc1ce580e28a619d9332a6abc08d276d77522f73350afe3c772a2760eb6750
+oid sha256:3c9d20365d985211d2225fedbe36e93295771515206bd7bae67d63469e8d58b4
 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": 0.0003953545836422041,
+  "epoch": 0.0005930318754633062,
   "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": 20.502,
       "eval_steps_per_second": 10.251,
       "step": 6
+    },
+    {
+      "epoch": 0.0004612470142492381,
+      "grad_norm": 0.9536383748054504,
+      "learning_rate": 0.00014,
+      "loss": 2.3776,
+      "step": 7
+    },
+    {
+      "epoch": 0.0005271394448562722,
+      "grad_norm": 0.878818154335022,
+      "learning_rate": 0.00016,
+      "loss": 2.354,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005930318754633062,
+      "grad_norm": 1.0028239488601685,
+      "learning_rate": 0.00018,
+      "loss": 2.3549,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005930318754633062,
+      "eval_loss": 2.153322458267212,
+      "eval_runtime": 311.6939,
+      "eval_samples_per_second": 20.501,
+      "eval_steps_per_second": 10.25,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1803356548890624.0,
+  "total_flos": 2543195133050880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null