Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da71344aa1ff97eea0246faca6940d1fb746f997d77b368665852028a6c73a3
+oid sha256:3eabb41f5072154ea5542da9bea138c4fe8224085b1e107fe9607d0d40ac28c6
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c79322c66fa7684df4904cef6074168257778a516aa21813594de4e09a524a6
+oid sha256:a29fa2ba30d9bd7d4be5232904728f021f86705a73f9d711a9f2b30029ebab24
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3874d81c68d237eff7165dcf48e6973ab7998fdec16147e742b36a46a13a76c
+oid sha256:542df61d1c6148ada1c376ebc8f1739c398348ac99a9391e7ce94e1944cf227c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013686911890504706,
+  "epoch": 0.002053036783575706,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 52.059,
       "eval_steps_per_second": 26.034,
       "step": 20
+    },
+    {
+      "epoch": 0.001437125748502994,
+      "grad_norm": 4.836862087249756,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 12.4417,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016424294268605646,
+      "grad_norm": 6.216834545135498,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.7135,
+      "step": 24
+    },
+    {
+      "epoch": 0.001710863986313088,
+      "eval_loss": 3.0287530422210693,
+      "eval_runtime": 118.1814,
+      "eval_samples_per_second": 52.064,
+      "eval_steps_per_second": 26.036,
+      "step": 25
+    },
+    {
+      "epoch": 0.0018477331052181353,
+      "grad_norm": 5.625243663787842,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.8553,
+      "step": 27
+    },
+    {
+      "epoch": 0.002053036783575706,
+      "grad_norm": 4.978127479553223,
+      "learning_rate": 0.0,
+      "loss": 11.1414,
+      "step": 30
+    },
+    {
+      "epoch": 0.002053036783575706,
+      "eval_loss": 3.01611328125,
+      "eval_runtime": 118.2006,
+      "eval_samples_per_second": 52.056,
+      "eval_steps_per_second": 26.032,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 303370988421120.0,
+  "total_flos": 455056482631680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null