Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773667611f802cea981e49bac6800d8a739277103b0d4b59212eb8eb74ce967f
+oid sha256:8c51aaeba306deb62511026a4a0c66df368a900ef6aed157a58c5682c89945de
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003174572d3615dfae4b2c99effa0e176e89ce1c8cae243fc24064abc63b74f9
+oid sha256:3993b3119ad00da7f5dac32d08aa72d643b95cf8dac69e854393cf3c3e14fd53
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d4f58351c2eca4a86344893b1042e13cd813a6550f3b9eb6d3acdc66549a9e
+oid sha256:4cfe1d2bf382a2029b4f794726b8bf6e56944106b9765678f8c19dbe3d49ec11
 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": 0.003719546215361726,
+  "epoch": 0.0055793193230425885,
   "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": 8.189,
       "eval_steps_per_second": 4.094,
       "step": 10
+    },
+    {
+      "epoch": 0.004091500836897899,
+      "grad_norm": 53.22500991821289,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 27.342,
+      "step": 11
+    },
+    {
+      "epoch": 0.004463455458434071,
+      "grad_norm": 59.24814224243164,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 18.2533,
+      "step": 12
+    },
+    {
+      "epoch": 0.004463455458434071,
+      "eval_loss": 4.373373985290527,
+      "eval_runtime": 138.3748,
+      "eval_samples_per_second": 8.181,
+      "eval_steps_per_second": 4.09,
+      "step": 12
+    },
+    {
+      "epoch": 0.004835410079970244,
+      "grad_norm": 45.4249153137207,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.9498,
+      "step": 13
+    },
+    {
+      "epoch": 0.005207364701506416,
+      "grad_norm": 51.06169509887695,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 16.3781,
+      "step": 14
+    },
+    {
+      "epoch": 0.005207364701506416,
+      "eval_loss": 4.014023780822754,
+      "eval_runtime": 138.2266,
+      "eval_samples_per_second": 8.189,
+      "eval_steps_per_second": 4.095,
+      "step": 14
+    },
+    {
+      "epoch": 0.0055793193230425885,
+      "grad_norm": 36.74103927612305,
+      "learning_rate": 0.0,
+      "loss": 14.7442,
+      "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": 6332408345395200.0,
+  "total_flos": 9498612518092800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null