Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b58cecc3eb1e85b81cbd3ad886f7d18e7ed47da9ae66ca7fe8aa7258ee7e97e
+oid sha256:5dcdfce3185249b041332d706be75bb763e59da7acea3c338606d33740d31787
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5bd60ff14abd7948c10749fafb9b548259f3c7125ff43235cb639ef7e5d632d
+oid sha256:4a616a97a727cf1dda3505af39a8bc1e73d840996ff0268be1ba233bebb20cfa
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1e6991dad8bc748d0e31f4e5e35bbe2e9420c339e4c98abd7035294eef3c2b
+oid sha256:045b4c272e1eb6e89091f4c9d82e18f4b0934375c807b878adae2bc236109356
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14651162790697675,
+  "epoch": 0.16744186046511628,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 36.423,
       "eval_steps_per_second": 4.578,
       "step": 63
+    },
+    {
+      "epoch": 0.15348837209302327,
+      "grad_norm": 2.953460693359375,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 2.3964,
+      "step": 66
+    },
+    {
+      "epoch": 0.16046511627906976,
+      "grad_norm": 2.805899143218994,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 2.4172,
+      "step": 69
+    },
+    {
+      "epoch": 0.16744186046511628,
+      "grad_norm": 3.291818857192993,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 2.522,
+      "step": 72
+    },
+    {
+      "epoch": 0.16744186046511628,
+      "eval_loss": 2.5648176670074463,
+      "eval_runtime": 19.8785,
+      "eval_samples_per_second": 36.421,
+      "eval_steps_per_second": 4.578,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6458987343970304e+16,
+  "total_flos": 1.8810271250251776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null