Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43068dc3deb6eb813d6a28edf7e0215a7f6477f84e786a4a628dab741824630c
+oid sha256:208499bcf727f8b083a7b514a6106316a836d4a1cb4578473e22f620b0608e46
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107df24863016d74c03b4fb78999b377a162010202a5636d458667e96285852e
+oid sha256:a93d97e38917c3dcaf7eb8e2df76373e688dd52f0af073be6d167c19d56d51f9
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156e1688439d5c56c4b456fff105e4b11da885d5d5465581856864395f905df9
+oid sha256:c6afa12c7f6dfef3a4c050c66fe0d6eeafd92164312401416d48b422a8e0b1a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005963918294319368,
+  "epoch": 0.011927836588638736,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,116 @@
       "eval_samples_per_second": 9.221,
       "eval_steps_per_second": 4.61,
       "step": 10
+    },
+    {
+      "epoch": 0.006560310123751305,
+      "grad_norm": 1.0968209505081177,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.5539,
+      "step": 11
+    },
+    {
+      "epoch": 0.007156701953183241,
+      "grad_norm": 0.8019706010818481,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2537,
+      "step": 12
+    },
+    {
+      "epoch": 0.007156701953183241,
+      "eval_loss": 0.24521681666374207,
+      "eval_runtime": 76.5378,
+      "eval_samples_per_second": 9.224,
+      "eval_steps_per_second": 4.612,
+      "step": 12
+    },
+    {
+      "epoch": 0.007753093782615178,
+      "grad_norm": 0.8972131609916687,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.188,
+      "step": 13
+    },
+    {
+      "epoch": 0.008349485612047115,
+      "grad_norm": 1.388610601425171,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2539,
+      "step": 14
+    },
+    {
+      "epoch": 0.008349485612047115,
+      "eval_loss": 0.20003721117973328,
+      "eval_runtime": 76.5695,
+      "eval_samples_per_second": 9.22,
+      "eval_steps_per_second": 4.61,
+      "step": 14
+    },
+    {
+      "epoch": 0.008945877441479051,
+      "grad_norm": 1.2546236515045166,
+      "learning_rate": 0.0001,
+      "loss": 0.2859,
+      "step": 15
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "grad_norm": 1.2586054801940918,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2893,
+      "step": 16
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "eval_loss": 0.17982345819473267,
+      "eval_runtime": 76.5392,
+      "eval_samples_per_second": 9.224,
+      "eval_steps_per_second": 4.612,
+      "step": 16
+    },
+    {
+      "epoch": 0.010138661100342925,
+      "grad_norm": 1.4489102363586426,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.1875,
+      "step": 17
+    },
+    {
+      "epoch": 0.010735052929774861,
+      "grad_norm": 1.0019066333770752,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0675,
+      "step": 18
+    },
+    {
+      "epoch": 0.010735052929774861,
+      "eval_loss": 0.15851947665214539,
+      "eval_runtime": 76.5776,
+      "eval_samples_per_second": 9.219,
+      "eval_steps_per_second": 4.61,
+      "step": 18
+    },
+    {
+      "epoch": 0.0113314447592068,
+      "grad_norm": 0.7860324382781982,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.1514,
+      "step": 19
+    },
+    {
+      "epoch": 0.011927836588638736,
+      "grad_norm": 0.9038301110267639,
+      "learning_rate": 0.0,
+      "loss": 0.178,
+      "step": 20
+    },
+    {
+      "epoch": 0.011927836588638736,
+      "eval_loss": 0.1537449210882187,
+      "eval_runtime": 76.5787,
+      "eval_samples_per_second": 9.219,
+      "eval_steps_per_second": 4.61,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -139,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6591291693465600.0,
+  "total_flos": 1.31825833869312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null