Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616af754680ea381febd50ed7ff954d4753c612fbf51599540b508bc27e52bc4
+oid sha256:0bd7802ebe2f1feb37b47d9bb2b796b571d19a8401229cf6fd7fea7ef2a33e5e
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c69c95b9655781629ab226636b08734f27060f51acb8884ddb1ec64d929e23
+oid sha256:9b1624608f0890113d88144a872a00c241694ada6be0b8e8f0c76ee08e4d4226
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f51a6c7fb561d4325215873666364c69383bb47cdde09f7c684283da33310f
+oid sha256:9eac3b4aea8c23023b7efac7b6a321ee05a32e93d1dc1b936030320fb1fe800e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 2.4,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -54,6 +54,21 @@
       "eval_samples_per_second": 55.576,
       "eval_steps_per_second": 13.894,
       "step": 5
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4630964994430542,
+      "learning_rate": 6e-05,
+      "loss": 1.2967,
+      "step": 6
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9583229422569275,
+      "eval_runtime": 0.0751,
+      "eval_samples_per_second": 53.27,
+      "eval_steps_per_second": 13.318,
+      "step": 6
     }
   ],
   "logging_steps": 3,
@@ -73,7 +88,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 666882728263680.0,
+  "total_flos": 811073588428800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null