Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3558b5f17b9fff7e7424e90889b82673f72fba63ca6ce02b3d2f53c8dd6db8dd
+oid sha256:a9452f8b9dfac05067c81a5ce4311e08d2e7f2c9627cc23c651e223d7792566c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a41e532f7dca479b1520e59da012bffa26af3383bab43d02f08f0aa683fd512
+oid sha256:6837756df16d4b861371d6ae7755d2c5a377b47c1258b2d95da10db2ac011be7
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2972d332e3d5fa4abdd6b0429885a3ecc36eabdf15f91d3aebed7cea929537a
+oid sha256:b34fe06338d52b135f06f73901cbbeeea2e9a59fb363b8294881aaf807d72655
 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": 4.298,
       "eval_steps_per_second": 2.149,
       "step": 10
+    },
+    {
+      "epoch": 0.006560310123751305,
+      "grad_norm": 1.138580083847046,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.5474,
+      "step": 11
+    },
+    {
+      "epoch": 0.007156701953183241,
+      "grad_norm": 0.8171162605285645,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2495,
+      "step": 12
+    },
+    {
+      "epoch": 0.007156701953183241,
+      "eval_loss": 0.24059152603149414,
+      "eval_runtime": 164.1937,
+      "eval_samples_per_second": 4.3,
+      "eval_steps_per_second": 2.15,
+      "step": 12
+    },
+    {
+      "epoch": 0.007753093782615178,
+      "grad_norm": 0.9625129103660583,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.1852,
+      "step": 13
+    },
+    {
+      "epoch": 0.008349485612047115,
+      "grad_norm": 1.333743929862976,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2489,
+      "step": 14
+    },
+    {
+      "epoch": 0.008349485612047115,
+      "eval_loss": 0.19883611798286438,
+      "eval_runtime": 164.7477,
+      "eval_samples_per_second": 4.285,
+      "eval_steps_per_second": 2.143,
+      "step": 14
+    },
+    {
+      "epoch": 0.008945877441479051,
+      "grad_norm": 1.2359386682510376,
+      "learning_rate": 0.0001,
+      "loss": 0.2844,
+      "step": 15
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "grad_norm": 1.2958358526229858,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2865,
+      "step": 16
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "eval_loss": 0.17618103325366974,
+      "eval_runtime": 164.6292,
+      "eval_samples_per_second": 4.288,
+      "eval_steps_per_second": 2.144,
+      "step": 16
+    },
+    {
+      "epoch": 0.010138661100342925,
+      "grad_norm": 1.5453649759292603,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.1897,
+      "step": 17
+    },
+    {
+      "epoch": 0.010735052929774861,
+      "grad_norm": 1.1022392511367798,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0626,
+      "step": 18
+    },
+    {
+      "epoch": 0.010735052929774861,
+      "eval_loss": 0.15503820776939392,
+      "eval_runtime": 164.3594,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.148,
+      "step": 18
+    },
+    {
+      "epoch": 0.0113314447592068,
+      "grad_norm": 0.8071819543838501,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.149,
+      "step": 19
+    },
+    {
+      "epoch": 0.011927836588638736,
+      "grad_norm": 0.8944453597068787,
+      "learning_rate": 0.0,
+      "loss": 0.1737,
+      "step": 20
+    },
+    {
+      "epoch": 0.011927836588638736,
+      "eval_loss": 0.15017978847026825,
+      "eval_runtime": 164.4532,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 2.147,
+      "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