Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7490742c318434f985399c767a1c602f55fb6a0dfe00dcfd110170199aad847e
+oid sha256:6240728159d513faa05abf6b5d7ed2406f17cba8a6ca15979a18ce62688bde0f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae79ea085872aedd87bc5a62cb5c44bd8029427fd8eebd823d147f0676a7f312
+oid sha256:e3647ec73c1e57bf25af24da7e11057a0a6dc36496110229d4e9f1d78ece690b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
+oid sha256:a9273107ed22f2b0460ae677b61e5921af160c5c9d230441f93d948a850671aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002395388876412905,
+  "epoch": 0.003593083314619358,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 8.267,
       "eval_steps_per_second": 8.267,
       "step": 8
+    },
+    {
+      "epoch": 0.002694812485964518,
+      "grad_norm": 12.036263465881348,
+      "learning_rate": 0.00018,
+      "loss": 7.8039,
+      "step": 9
+    },
+    {
+      "epoch": 0.0029942360955161314,
+      "grad_norm": 13.046463012695312,
+      "learning_rate": 0.0002,
+      "loss": 7.8042,
+      "step": 10
+    },
+    {
+      "epoch": 0.0032936597050677446,
+      "grad_norm": 24.538808822631836,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 8.7757,
+      "step": 11
+    },
+    {
+      "epoch": 0.003593083314619358,
+      "grad_norm": 26.114961624145508,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 5.6577,
+      "step": 12
+    },
+    {
+      "epoch": 0.003593083314619358,
+      "eval_loss": 5.31056022644043,
+      "eval_runtime": 85.1933,
+      "eval_samples_per_second": 8.264,
+      "eval_steps_per_second": 8.264,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2967549134241792.0,
+  "total_flos": 4451323701362688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null