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:d82de089f452ac6dbcb12ff285dd47fd071ac2871c9e774eb43d7e1a54edc810
+oid sha256:4d6bdb1ff3e4c59cf159616eba9a5ac4e1aebd0a7aacd3a7f7d442651663bb33
 size 28548400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b1e31d9904c74c19ee7c75e85c012b230a9fc37fde42053f140870deee31e9
+oid sha256:4cb5ae4ed015e189294232529633918499c899105c3f2ffd36b2927fa48d5299
 size 57188922

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66af1de9476465628ab35ece9f31ea6723098101b19bf3c8ad33552672acf180
+oid sha256:296c3e519c2d2f8c604a3e10b3fb95559d43dcdd9013219372df4529e7cb4489
 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": 0.03646308113035551,
+  "epoch": 0.054694621695533276,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 8.7594,
       "step": 18
+    },
+    {
+      "epoch": 0.03828623518687329,
+      "grad_norm": 3.9609525203704834,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 8.4288,
+      "step": 21
+    },
+    {
+      "epoch": 0.04375569735642662,
+      "grad_norm": 4.910305023193359,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.5959,
+      "step": 24
+    },
+    {
+      "epoch": 0.04375569735642662,
+      "eval_loss": 2.1110403537750244,
+      "eval_runtime": 4.6822,
+      "eval_samples_per_second": 49.336,
+      "eval_steps_per_second": 24.775,
+      "step": 24
+    },
+    {
+      "epoch": 0.049225159525979945,
+      "grad_norm": 4.449171543121338,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.2751,
+      "step": 27
+    },
+    {
+      "epoch": 0.054694621695533276,
+      "grad_norm": 4.476564407348633,
+      "learning_rate": 0.0,
+      "loss": 8.9483,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 305219166535680.0,
+  "total_flos": 457828749803520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null