Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335cb31cbb4f422864d2b05106af654fc50279e92bc67bd1006de6bb8d914df7
+oid sha256:efe715dfc3c6655975b4c0cb344e7c945494e1463e96c18bf9c77000e7066604
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7fe6e9dd385d88d37e6100bc6ead9650910c40bd8e9f5e0c841df05366de41
+oid sha256:fa28aca63d30e6a77fca80f9f9286ec5bb1020314276276e1f34a85650641b30
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
+oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:541ccba4d24c3fd7a3a1bd1b7c1a8ef18368821282014bf91f536020daf3aafe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28486646884273,
+  "epoch": 0.56973293768546,
   "eval_steps": 6,
-  "global_step": 6,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 480.233,
       "eval_steps_per_second": 240.117,
       "step": 6
+    },
+    {
+      "epoch": 0.3323442136498516,
+      "grad_norm": 0.10505552589893341,
+      "learning_rate": 7e-05,
+      "loss": 10.3793,
+      "step": 7
+    },
+    {
+      "epoch": 0.3798219584569733,
+      "grad_norm": 0.10710933804512024,
+      "learning_rate": 8e-05,
+      "loss": 10.3793,
+      "step": 8
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "grad_norm": 0.104378342628479,
+      "learning_rate": 9e-05,
+      "loss": 10.3886,
+      "step": 9
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 0.1055062860250473,
+      "learning_rate": 0.0001,
+      "loss": 10.3806,
+      "step": 10
+    },
+    {
+      "epoch": 0.5222551928783383,
+      "grad_norm": 0.11344417184591293,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 10.3823,
+      "step": 11
+    },
+    {
+      "epoch": 0.56973293768546,
+      "grad_norm": 0.10140898078680038,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 10.3856,
+      "step": 12
+    },
+    {
+      "epoch": 0.56973293768546,
+      "eval_loss": 10.380664825439453,
+      "eval_runtime": 0.0723,
+      "eval_samples_per_second": 497.765,
+      "eval_steps_per_second": 248.882,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 481676328960.0,
+  "total_flos": 966585384960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null