Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bcdec891e2f17bbf4fc48a2ca1973e977b81e6a3c93c0ef1a639895a18f688
+oid sha256:7d5c7206a327c0d58a2608d792a361bd9335e66f12b6f2d1df6895258b3c2ec1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038c1d8ae8fdd7fb024db761bf783e95fa8749a9c272b282da111c76ae99b1ec
+oid sha256:10d2e8f100ead6ae962104dc9b75ffa54bb39ea20b8a02c20fd18112382a743b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0a6bdbfc1285a5f5c8ad50849b4a9ce2b97dd015708be30087e5e5a5d5d9fca
+oid sha256:c6ecbff1c74cc1d427d1d52d812c3fa4ecd63e0194b840964d71abf4d057b60e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007230196703880914,
+  "epoch": 0.014035087719298246,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 3.327,
       "eval_steps_per_second": 1.664,
       "step": 15
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 4.361161231994629,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 8.175,
+      "step": 18
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 2.126591205596924,
+      "eval_runtime": 297.8187,
+      "eval_samples_per_second": 3.324,
+      "eval_steps_per_second": 1.662,
+      "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 4.228249549865723,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 8.1639,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 3.8976006507873535,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 8.1004,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 2.1243057250976562,
+      "eval_runtime": 298.0859,
+      "eval_samples_per_second": 3.321,
+      "eval_steps_per_second": 1.661,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 4.909876346588135,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 8.4362,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 3.950687885284424,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 8.2356,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 2.118710994720459,
+      "eval_runtime": 298.1844,
+      "eval_samples_per_second": 3.32,
+      "eval_steps_per_second": 1.66,
+      "step": 30
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 4.570465564727783,
+      "learning_rate": 0.0,
+      "loss": 7.8479,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.054694248022016e+16,
+  "total_flos": 2.065442902376448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null