Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e29fed5d5e788cfe8c52fbb3ab8009e0b771804d981c9c5bb6d15d17c7d48f
+oid sha256:88b3cb325ecec8876d334cd8a9d4e56c4bdfe0043f4b2bd4aad5a744e24339ce
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784bcae49590eed29a36c271116588ef94940c1d86f3340d0b150ff8512f7708
+oid sha256:f73fe7afda83e7c2cae43d0c5465ab24ed2731a9b05ece49930ad5a4be44de80
 size 147950010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be021fdd8df982fc338b86ca131cb94cea4b6c7fd8feb56712e7bdd4631a3d1
+oid sha256:0bdd8990c1a91d4727a2503d3b04a3e49e35b72bf5a65b445da84ad6dd041d3c
 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": 0.029553010712966385,
+  "epoch": 0.04432951606944958,
   "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": 2.076,
       "step": 18
+    },
+    {
+      "epoch": 0.031030661248614703,
+      "grad_norm": 1.156599521636963,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.1467,
+      "step": 21
+    },
+    {
+      "epoch": 0.03546361285555966,
+      "grad_norm": 1.0383951663970947,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0138,
+      "step": 24
+    },
+    {
+      "epoch": 0.03546361285555966,
+      "eval_loss": 2.014021396636963,
+      "eval_runtime": 6.9139,
+      "eval_samples_per_second": 41.221,
+      "eval_steps_per_second": 20.683,
+      "step": 24
+    },
+    {
+      "epoch": 0.03989656446250462,
+      "grad_norm": 0.9691169857978821,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.0115,
+      "step": 27
+    },
+    {
+      "epoch": 0.04432951606944958,
+      "grad_norm": 1.2048197984695435,
+      "learning_rate": 0.0,
+      "loss": 2.0324,
+      "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": 1306268836823040.0,
+  "total_flos": 1959403255234560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null