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:c5f57af9718f06965c4be5632da8c8133b955aafc81521ab701284d43048679b
+oid sha256:f777d88bd2129083ff247242636a36d574d14e847d7d338bc2236c02a58b4192
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d5b8a2424acd9551706bfc509676728d0f05bce7cba6f33a35f80163c10d9b2
+oid sha256:12d26564e2583d9379bb98a64d586d6efe097c43ccbdb6c356c8aa18500ebe1b
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e32cab9f45688a849f1e8df5d4550458cd00b5d51752ffe20c51d4c439a8e38
+oid sha256:984058315d991f8005feb7b2e29f9aa6bbb6189b6b912b694ea5f1c969706c68
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7868852459016393,
+  "epoch": 0.8852459016393442,
   "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": 15.39,
       "eval_steps_per_second": 1.999,
       "step": 72
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 1.3069887161254883,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 7.4671,
+      "step": 75
+    },
+    {
+      "epoch": 0.8524590163934426,
+      "grad_norm": 1.2993086576461792,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 7.5022,
+      "step": 78
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "grad_norm": 1.28661048412323,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 7.0951,
+      "step": 81
+    },
+    {
+      "epoch": 0.8852459016393442,
+      "eval_loss": 1.8206969499588013,
+      "eval_runtime": 10.005,
+      "eval_samples_per_second": 15.392,
+      "eval_steps_per_second": 1.999,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.573162657880474e+16,
+  "total_flos": 1.0782060331401216e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null