Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de83c0d07e0f9f550dc44b74941e48b7fcc22759ef357edc9493798011bcdd5
+oid sha256:6a134f0a695d079d57bfc5f378a1392d4b53fae4a0c08c80f0bdb5f21597bc97
 size 19593064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56824b41bfb2831ed30774a260d97d90fc2a8dbbacca4d51d743546acb9672e
+oid sha256:d5fa20f88fd6383021f40379c835dde8a31197bfcb2b688e409fbc614fbf9d92
 size 11469420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e66d94e72b9838e0aa2c9488c442c5d774fb1c334a2b9efc81361d4782f51f6
+oid sha256:dc9435c1ef61c5284e23dd20e9b17a96d65178d39f2d8cbad5a8ea1c43ba9408
 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": 0.04108249103358331,
+  "epoch": 0.046951418324095204,
   "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": 72.989,
       "eval_steps_per_second": 9.127,
       "step": 63
+    },
+    {
+      "epoch": 0.04303880013042061,
+      "grad_norm": 0.13522818684577942,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.244,
+      "step": 66
+    },
+    {
+      "epoch": 0.044995109227257905,
+      "grad_norm": 0.1401805877685547,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.3158,
+      "step": 69
+    },
+    {
+      "epoch": 0.046951418324095204,
+      "grad_norm": 0.16507139801979065,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.3923,
+      "step": 72
+    },
+    {
+      "epoch": 0.046951418324095204,
+      "eval_loss": 1.368349313735962,
+      "eval_runtime": 35.4333,
+      "eval_samples_per_second": 72.898,
+      "eval_steps_per_second": 9.116,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2145856332496896.0,
+  "total_flos": 2451627209392128.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null