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:ed6c570913ff6711805790f8b131c4b54bf94c9a20403d6ae0e68983a1a4a167
+oid sha256:49e35fcfb810f4015ef8ffde858fc41b5c2e5a66f51268968be1f02912dbef3d
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be43fe98a4d3f3e7134b2f571b07622db3bb0a6c597a3e2d0b0c26f576d49b4
+oid sha256:4bd9485effd153f06a26519476915b3afde84e0d8fd061c7fd239300cb406d30
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3da36683a47a91a9ad772f7df43342ed45380cacff56c8d7dcb5142c555aaa0
+oid sha256:fcdccc249fee2c1ad1a5096f95a837d69e1cc085a05644f1180a19891ee93076
 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": 0.0022197558268590455,
+  "epoch": 0.003329633740288568,
   "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": 38.844,
       "eval_steps_per_second": 19.439,
       "step": 6
+    },
+    {
+      "epoch": 0.002589715131335553,
+      "grad_norm": 0.3678200840950012,
+      "learning_rate": 0.00014,
+      "loss": 2.5139,
+      "step": 7
+    },
+    {
+      "epoch": 0.0029596744358120607,
+      "grad_norm": 0.49218493700027466,
+      "learning_rate": 0.00016,
+      "loss": 2.5193,
+      "step": 8
+    },
+    {
+      "epoch": 0.003329633740288568,
+      "grad_norm": 0.5838165879249573,
+      "learning_rate": 0.00018,
+      "loss": 2.6137,
+      "step": 9
+    },
+    {
+      "epoch": 0.003329633740288568,
+      "eval_loss": 2.4827823638916016,
+      "eval_runtime": 29.2335,
+      "eval_samples_per_second": 38.962,
+      "eval_steps_per_second": 19.498,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492029198991360.0,
+  "total_flos": 738043798487040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null