Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64da054c93a16fb6e1ef0847fe0d797ab54982efa19f47494e0b5ae3f2839369
+oid sha256:21a4285568f2d5ad502011794de13ef0828c2888b6d3e6e7599175833877815d
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601b0830993c2ca49af0f1ab3b15f9686870e2555ad211a46250284c590a2b7e
+oid sha256:4b34f5b460e287195d86a6001725574dae0b1d42bc5a00333705517f7b04deea
 size 3633466

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": 0.02566295979469632,
+  "epoch": 0.03421727972626176,
   "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": 198.999,
       "eval_steps_per_second": 99.6,
       "step": 15
+    },
+    {
+      "epoch": 0.02737382378100941,
+      "grad_norm": 1.1695514917373657,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6034,
+      "step": 16
+    },
+    {
+      "epoch": 0.0290846877673225,
+      "grad_norm": 0.8216890096664429,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.668,
+      "step": 17
+    },
+    {
+      "epoch": 0.030795551753635585,
+      "grad_norm": 0.9799723029136658,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6461,
+      "step": 18
+    },
+    {
+      "epoch": 0.032506415739948676,
+      "grad_norm": 0.879396915435791,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4967,
+      "step": 19
+    },
+    {
+      "epoch": 0.03421727972626176,
+      "grad_norm": 0.8300636410713196,
+      "learning_rate": 0.0,
+      "loss": 0.5671,
+      "step": 20
+    },
+    {
+      "epoch": 0.03421727972626176,
+      "eval_loss": 0.6950483322143555,
+      "eval_runtime": 4.8684,
+      "eval_samples_per_second": 202.326,
+      "eval_steps_per_second": 101.266,
+      "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": 304347272970240.0,
+  "total_flos": 404653275611136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null