Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82eaf68cb2b7738118e0fe2db0a695219566f54d44c7b0fbaf0cb57dee99cf8d
+oid sha256:f9fcd044e2ddad170d233979bd4bdab2495251d8cd3812f952c7daf8b91113e4
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1bcfe34c8daeff7460447a9d3a8946825d8dab5df0c066b20d6d05d485cdbf
+oid sha256:e2d36459786224f6a447682dbdaec705b7f2f43b0ee34f38de2e41c7d7e1d66b
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4555e4c65e128e3c73410113c546065354d2476ccf2887955b4785922a9a9a7c
+oid sha256:6da1aa8fbed2d56b3fe060e26ad98e0b41d6a445606ee727563e23a153c55c65
 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": 0.020080321285140562,
+  "epoch": 0.030120481927710843,
   "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": 8.72,
       "eval_steps_per_second": 4.36,
       "step": 10
+    },
+    {
+      "epoch": 0.02208835341365462,
+      "grad_norm": 1.0076066255569458,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.7772,
+      "step": 11
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 1.1053738594055176,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.7395,
+      "step": 12
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "eval_loss": 1.465615153312683,
+      "eval_runtime": 24.3564,
+      "eval_samples_per_second": 8.622,
+      "eval_steps_per_second": 4.311,
+      "step": 12
+    },
+    {
+      "epoch": 0.02610441767068273,
+      "grad_norm": 1.1769044399261475,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.7144,
+      "step": 13
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "grad_norm": 1.0415147542953491,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 5.9251,
+      "step": 14
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "eval_loss": 1.4606515169143677,
+      "eval_runtime": 24.087,
+      "eval_samples_per_second": 8.718,
+      "eval_steps_per_second": 4.359,
+      "step": 14
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 1.0108901262283325,
+      "learning_rate": 0.0,
+      "loss": 6.6035,
+      "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": 3501810870386688.0,
+  "total_flos": 5130560112427008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null