Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031b86def82a31adeffaa332711bec2066abc6c90d780fe395e1bb5311648164
+oid sha256:bce7e75781ecacb66e0165646e8b468ed9d8d43b4d76b40feb1f0525f730910b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c0378750a2bcd0cb39ca55727ba7a6ecb62a82a4734abdc38a992f444212a4
+oid sha256:92fcb324a85dfb026d35da06dd06c2e681c7702d4fe5e3e125f729cab555afce
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df79124911e0dbd57c3e25b01ed5df65fc4ab25fbd5b0e35bbd332a8451a751
+oid sha256:bd574b2b6cae2e6cda789f12f30f8aef85111dba8a85323388551cfa4755dbff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005431208231674976,
+  "epoch": 0.008146812347512465,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 6.859,
       "eval_steps_per_second": 3.429,
       "step": 16
+    },
+    {
+      "epoch": 0.005770658746154662,
+      "grad_norm": 0.0,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.006110109260634348,
+      "grad_norm": 0.0,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.006449559775114034,
+      "grad_norm": 0.0,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.00678901028959372,
+      "grad_norm": 1.0797548294067383,
+      "learning_rate": 5e-05,
+      "loss": 0.1937,
+      "step": 20
+    },
+    {
+      "epoch": 0.0071284608040734065,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.007467911318553093,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.007807361833032778,
+      "grad_norm": 0.9458051323890686,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0582,
+      "step": 23
+    },
+    {
+      "epoch": 0.008146812347512465,
+      "grad_norm": 0.5507776737213135,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0312,
+      "step": 24
+    },
+    {
+      "epoch": 0.008146812347512465,
+      "eval_loss": NaN,
+      "eval_runtime": 723.0782,
+      "eval_samples_per_second": 6.862,
+      "eval_steps_per_second": 3.431,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.496157229573734e+16,
+  "total_flos": 1.4244235844360602e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null