Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadede353f4372c078a32b2bf026892fade378aa258378da7d187d2a68f266de
+oid sha256:9535f32d7d0f7b37947246268347bdf84d78c129478487d755c3231640be7786
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1abe00ee71c544cd30c0812ece91dff81f1d322f97557fa2d29ff51aa062c90
+oid sha256:daa680e1ac8d4a07fc451875af1c4300bd77f4228736cb58c49160f6d66029b2
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7fb8194f244bb999a0fcd4213d2217d37e5555cee829c566323dc715912866
+oid sha256:2536b1d20f7d4b3ed8f236d125ef423bcf25b212a982fab423da846c69098301
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033566433566433566,
+  "epoch": 0.039160839160839164,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 10.044,
       "eval_steps_per_second": 1.256,
       "step": 54
+    },
+    {
+      "epoch": 0.035431235431235435,
+      "grad_norm": 2.1651206016540527,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 3.0361,
+      "step": 57
+    },
+    {
+      "epoch": 0.037296037296037296,
+      "grad_norm": 2.734593629837036,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 3.0934,
+      "step": 60
+    },
+    {
+      "epoch": 0.039160839160839164,
+      "grad_norm": 2.2802178859710693,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 3.0565,
+      "step": 63
+    },
+    {
+      "epoch": 0.039160839160839164,
+      "eval_loss": 3.0123836994171143,
+      "eval_runtime": 269.8579,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 1.256,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0905743068338586e+17,
+  "total_flos": 1.2871744369773773e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null