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:f3b020253dbcb589b71a6536081c7dd2cf7a7ccf9e23e1c6ec07b878d1247696
+oid sha256:587656d4e2a96d3ff50274cf1fed09f531e375eab349de4640acbb9df24677fe
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de84d46b3d310eb10a1e5f6d23a632f00e1bde3a19ac0d891b805abdeb90e7d
+oid sha256:e8b5327cb0a48a2045d740c4a38c1b34613a52f02705386f58cb664ac380c74f
 size 9568884

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": 0.030398986700443317,
+  "epoch": 0.04053198226725776,
   "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": 56.715,
       "eval_steps_per_second": 28.358,
       "step": 15
+    },
+    {
+      "epoch": 0.03242558581380621,
+      "grad_norm": 0.29292696714401245,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2282,
+      "step": 16
+    },
+    {
+      "epoch": 0.034452184927169095,
+      "grad_norm": 0.2874906361103058,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.2546,
+      "step": 17
+    },
+    {
+      "epoch": 0.03647878404053198,
+      "grad_norm": 0.30354994535446167,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.344,
+      "step": 18
+    },
+    {
+      "epoch": 0.03850538315389487,
+      "grad_norm": 0.30029720067977905,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3073,
+      "step": 19
+    },
+    {
+      "epoch": 0.04053198226725776,
+      "grad_norm": 0.29221317172050476,
+      "learning_rate": 0.0,
+      "loss": 2.2997,
+      "step": 20
+    },
+    {
+      "epoch": 0.04053198226725776,
+      "eval_loss": 2.297351837158203,
+      "eval_runtime": 9.2022,
+      "eval_samples_per_second": 90.413,
+      "eval_steps_per_second": 45.206,
+      "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": 1068457965649920.0,
+  "total_flos": 1424610620866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null