Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9902b37fdf30bd898e72e062032368ce7d3124d27defa06d740efe280dc41d
+oid sha256:6627017b96013b48702bf5ee0f807115db92fcb515cf1d25f8dc1bb09872b0ea
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fe13c1088b03e11a3d5905d908bcc33c1f9e0792d459d74980c963162b3a66
+oid sha256:a344b26925272a6d748c47bd316256cfa8b69605679d0a6120fd84509c44e8f0
 size 70922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
+oid sha256:8a09ad7e826d10efce700906e00267beeb0fde82aeff880f7721e7c0c6d184a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006837606837606838,
+  "epoch": 0.010256410256410256,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,57 @@
       "eval_samples_per_second": 172.744,
       "eval_steps_per_second": 86.372,
       "step": 10
+    },
+    {
+      "epoch": 0.007521367521367521,
+      "grad_norm": 0.01218665111809969,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3796,
+      "step": 11
+    },
+    {
+      "epoch": 0.008205128205128205,
+      "grad_norm": 0.014596718363463879,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3781,
+      "step": 12
+    },
+    {
+      "epoch": 0.008205128205128205,
+      "eval_loss": 10.378983497619629,
+      "eval_runtime": 3.7412,
+      "eval_samples_per_second": 164.654,
+      "eval_steps_per_second": 82.327,
+      "step": 12
+    },
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 0.016098329797387123,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3813,
+      "step": 13
+    },
+    {
+      "epoch": 0.009572649572649573,
+      "grad_norm": 0.0119888074696064,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3783,
+      "step": 14
+    },
+    {
+      "epoch": 0.009572649572649573,
+      "eval_loss": 10.378974914550781,
+      "eval_runtime": 3.5778,
+      "eval_samples_per_second": 172.173,
+      "eval_steps_per_second": 86.086,
+      "step": 14
+    },
+    {
+      "epoch": 0.010256410256410256,
+      "grad_norm": 0.015922540798783302,
+      "learning_rate": 0.0,
+      "loss": 10.3789,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -139,12 +190,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 517236326400.0,
+  "total_flos": 775854489600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null