Training in progress, step 14, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20db5a33a39460601b4e9b8ea50e0d58a4f453f6af5b1939af6414d75387220a
+oid sha256:b49dbdc51a749f4586f4bfc5c29f962254bc2481435b9b40b18ff54b41afdeaf
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083281d4de1e4435e06c5c33bbbb4388616de2668bdd8f88ee2823283b636f00
+oid sha256:051d7de4ca8ec489f06051a5cac9473ba046b56d064e63e01d60fef33aa00efb
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65370118f607e09d6381397903a67c7ae938a6fbd645e372609f9bfe9fb51de6
+oid sha256:585fddc4777b08565c6c3d5891526e512f43b18c6849f7dfec648d08d9b7a952
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6974b3faf746b0cd5ad484ee0aa41b3416e51a6dcce41ba35e954232a5c6d57
+oid sha256:b94bcb770032d6a31492d829aa0341ce1de94ff1ad97397c70c01125f6cf0767
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2857142857142857,
+  "epoch": 0.5714285714285714,
   "eval_steps": 5,
-  "global_step": 7,
+  "global_step": 14,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 98.315,
       "eval_steps_per_second": 12.513,
       "step": 5
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.5947085618972778,
+      "learning_rate": 7.300325188655761e-05,
+      "loss": 11.8803,
+      "step": 10
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "eval_loss": 11.870901107788086,
+      "eval_runtime": 1.6553,
+      "eval_samples_per_second": 99.68,
+      "eval_steps_per_second": 12.687,
+      "step": 10
     }
   ],
   "logging_steps": 10,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 27784617394176.0,
+  "total_flos": 55694390722560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null