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:d847ebcfcc53f0ef1124e6aca7279725f9aca50186e00f793d1db9769ce766e6
+oid sha256:8795e5aff2cff6cb823acdce516f8bbfed86d99b5854bdda90ebd404761b3701
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2142d3692f1d3dccfc9b0a79467dada72aa55509229ec94d32f11279fbd3b992
+oid sha256:d7903b8b6b5687848f35be8fc8be652fb4a2ea675fa00e97847db8107b5982b9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e541f7aee48cc7ed448f7f7a74ac3c336f54829308a589e6265d77e6e70e6da
+oid sha256:75b46e3a1ff6f846edcd4695cb2c6c0e33a8907340ebcb71b83de879b2908864
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:2e5ade5af8511e8b306c6fe7ab74482129adcb22f8d53a32a67703220fa1fc83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
+  "epoch": 0.96,
   "eval_steps": 3,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,29 @@
       "eval_samples_per_second": 14.361,
       "eval_steps_per_second": 7.18,
       "step": 6
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 3.5568253993988037,
+      "eval_runtime": 0.3981,
+      "eval_samples_per_second": 15.072,
+      "eval_steps_per_second": 7.536,
+      "step": 9
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.7051615715026855,
+      "learning_rate": 0.0001,
+      "loss": 4.2865,
+      "step": 10
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 2.183289051055908,
+      "eval_runtime": 0.4018,
+      "eval_samples_per_second": 14.934,
+      "eval_steps_per_second": 7.467,
+      "step": 12
     }
   ],
   "logging_steps": 5,
@@ -57,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1479651398516736.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null