Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55fab431b1d345efce24912784ed7469e7449bc2ca5debd3133695e8613fa3ff
+oid sha256:4f3579f324fc958fafdb93fdb7d379bf500a642439998bd7dd9d836b7c1c9091
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614a8f2168f65aadab7912711e8346ffd8f3e7818efd269ad6e4cdfe24bc3ca0
+oid sha256:53516703d1aac2b00e5054d3bc0723b395472978530e3dce10b650eaf94b5b12
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ef401f25b7d760f23004c6a5482ad76a2b97d0da55c4512010973cc4688c8c
+oid sha256:ca2d929880be21a07e213ae10887a4c406f4ec23e6e0e3e33fddf6209872b66f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05672417868116285,
+  "epoch": 0.07563223824155046,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 226.194,
       "eval_steps_per_second": 113.097,
       "step": 15
+    },
+    {
+      "epoch": 0.06050579059324037,
+      "grad_norm": 13.019819259643555,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 39.8672,
+      "step": 16
+    },
+    {
+      "epoch": 0.06428740250531789,
+      "grad_norm": 11.753969192504883,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 40.9531,
+      "step": 17
+    },
+    {
+      "epoch": 0.06806901441739542,
+      "grad_norm": 12.145090103149414,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 39.6641,
+      "step": 18
+    },
+    {
+      "epoch": 0.07185062632947294,
+      "grad_norm": 13.901262283325195,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 42.9062,
+      "step": 19
+    },
+    {
+      "epoch": 0.07563223824155046,
+      "grad_norm": 11.688858032226562,
+      "learning_rate": 0.0,
+      "loss": 38.2188,
+      "step": 20
+    },
+    {
+      "epoch": 0.07563223824155046,
+      "eval_loss": 2.5669143199920654,
+      "eval_runtime": 1.9736,
+      "eval_samples_per_second": 225.985,
+      "eval_steps_per_second": 112.992,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 127377069834240.0,
+  "total_flos": 169836093112320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null