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:ef1a0332c890ed2038fc60aa4b95955d9fb0bca497a54bf8d3eba1eb81cd9b3a
+oid sha256:76335c71e05c52620d37bbddc8a79a181232d4f33e33a5385b46be893a44a60e
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083e332a7f098f3b38515c3a22cdffa0842eba38a095a1814c601173d6daacb7
+oid sha256:7172e88647e6b42e132f888f4e66eb3e75429e4beff3f537cd2417aab063f915
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de67efb49eeb0cd60dd9f379af798cd40c1503e02cb34d3293f97d54c2e636a7
+oid sha256:c08cb012f68d5fb209b1b3dd6f8f55841816cbeb8f6f20b824d9cf9376e11d91
 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": 0.0005574394945881915,
+  "epoch": 0.0008361592418822874,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 38.245,
       "eval_steps_per_second": 19.122,
       "step": 6
+    },
+    {
+      "epoch": 0.0006503460770195569,
+      "grad_norm": 44.13718032836914,
+      "learning_rate": 0.00014,
+      "loss": 13.328,
+      "step": 7
+    },
+    {
+      "epoch": 0.0007432526594509221,
+      "grad_norm": 52.688873291015625,
+      "learning_rate": 0.00016,
+      "loss": 13.0226,
+      "step": 8
+    },
+    {
+      "epoch": 0.0008361592418822874,
+      "grad_norm": 60.45896911621094,
+      "learning_rate": 0.00018,
+      "loss": 13.8277,
+      "step": 9
+    },
+    {
+      "epoch": 0.0008361592418822874,
+      "eval_loss": 3.415884494781494,
+      "eval_runtime": 116.4689,
+      "eval_samples_per_second": 38.912,
+      "eval_steps_per_second": 19.456,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 54830353612800.0,
+  "total_flos": 83342137491456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null