Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41604847d2c1e693356a408eccfd5c9633466d9f372de7d33cc8cef6f5af8b3d
+oid sha256:f934362ee5136d5df429da19e99a9c393f7424e9b1acffbf562120c395aa611d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6bbe3ed36a820a1f2bad02381b63808abef1b85b396cdf45fef56b46f588eb0
+oid sha256:9a3dc9bb490a94dfeeff37aaa4f0142b8a3a584e8193ccb735c074d0b6c6572c
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da5f91660c06cda34d557a8f46204815d102cca58540e895781ee3ee226c22b
+oid sha256:315787dfb180bc1e94771f58bf52eb8a0da94418e76cb2aa80146590a7df7970
 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": 0.04582776398701547,
+  "epoch": 0.061103685316020624,
   "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": 6.406,
       "eval_steps_per_second": 3.203,
       "step": 15
+    },
+    {
+      "epoch": 0.0488829482528165,
+      "grad_norm": 7.077727317810059,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 19.448,
+      "step": 16
+    },
+    {
+      "epoch": 0.05193813251861753,
+      "grad_norm": 8.61012077331543,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 20.693,
+      "step": 17
+    },
+    {
+      "epoch": 0.05499331678441856,
+      "grad_norm": 7.404054641723633,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 20.7822,
+      "step": 18
+    },
+    {
+      "epoch": 0.058048501050219595,
+      "grad_norm": 7.15053129196167,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 20.0697,
+      "step": 19
+    },
+    {
+      "epoch": 0.061103685316020624,
+      "grad_norm": 7.634872913360596,
+      "learning_rate": 0.0,
+      "loss": 18.9855,
+      "step": 20
+    },
+    {
+      "epoch": 0.061103685316020624,
+      "eval_loss": 1.1719589233398438,
+      "eval_runtime": 73.7275,
+      "eval_samples_per_second": 7.487,
+      "eval_steps_per_second": 3.744,
+      "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": 3.79944500723712e+16,
+  "total_flos": 5.06592667631616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null