Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e80d00284166a15e4f4706c1d8166d58f2a012d736da849699e409d48f65f6
+oid sha256:b0efe2736ccf56a4eb9b3effa5b4ef24fa7f34b2f34c2fb668210e7ba34660b5
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2576802e8f6699fc22ab741a3886d49d1fc7451b22242d88a242dc0cdb7a3c22
+oid sha256:8f0700ab583b86319588093c2dfd0d2e265c99ed973fcc10bced976c5cddb5fe
 size 8671098

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 0.001999650061239283,
+  "epoch": 0.0026662000816523776,
   "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": 196.871,
       "eval_steps_per_second": 98.435,
       "step": 15
+    },
+    {
+      "epoch": 0.002132960065321902,
+      "grad_norm": 20.412412643432617,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 39.3281,
+      "step": 16
+    },
+    {
+      "epoch": 0.0022662700694045207,
+      "grad_norm": 19.470823287963867,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 39.2344,
+      "step": 17
+    },
+    {
+      "epoch": 0.0023995800734871397,
+      "grad_norm": 22.943239212036133,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 36.0312,
+      "step": 18
+    },
+    {
+      "epoch": 0.0025328900775697587,
+      "grad_norm": 18.925182342529297,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 36.0781,
+      "step": 19
+    },
+    {
+      "epoch": 0.0026662000816523776,
+      "grad_norm": 21.876779556274414,
+      "learning_rate": 0.0,
+      "loss": 38.4062,
+      "step": 20
+    },
+    {
+      "epoch": 0.0026662000816523776,
+      "eval_loss": 2.342913866043091,
+      "eval_runtime": 64.0913,
+      "eval_samples_per_second": 197.125,
+      "eval_steps_per_second": 98.563,
+      "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": 1346204482928640.0,
+  "total_flos": 1794939310571520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null