Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e094428b014b10d14296bc96c79f343649fab50ee7757345d4ad890641dfb8
+oid sha256:cbe6c44aabe032d0ae8403360ec1ed05fc822627c559034f364b9c555c7ee2ae
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025e9c1a87c6b20c4124a8c37258471dfbfd1d35fd46a6532e0e6044a829dd60
+oid sha256:1909c1ba4dc64d7d0fafca4fd0117377c3ac3195919c00e3b64344950908d260
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05e2a7fe5f9efc4996d13bce479f8f30cf4261d161f444cb216569e0ff49c89
+oid sha256:80e0912226767f30058f628d41e26838633adb7576b646df748b130328848c19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04047217537942664,
+  "epoch": 0.045531197301854974,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 18.188,
       "eval_steps_per_second": 2.276,
       "step": 72
+    },
+    {
+      "epoch": 0.04215851602023609,
+      "grad_norm": 0.1585548371076584,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.7453,
+      "step": 75
+    },
+    {
+      "epoch": 0.04384485666104553,
+      "grad_norm": 0.16192683577537537,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7035,
+      "step": 78
+    },
+    {
+      "epoch": 0.045531197301854974,
+      "grad_norm": 0.16156958043575287,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.7299,
+      "step": 81
+    },
+    {
+      "epoch": 0.045531197301854974,
+      "eval_loss": 0.7329394817352295,
+      "eval_runtime": 164.6509,
+      "eval_samples_per_second": 18.202,
+      "eval_steps_per_second": 2.278,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.762054250050355e+16,
+  "total_flos": 4.23231103130665e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null