Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee7f5e840e095848c632b0c790cdfe52bc1294755f878817507e5b8cd4e48d5
+oid sha256:235203a9553025a7db99cc8c71efa70bba1f91ab545a7220ef1323ce64582e4b
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345108d0fb2d53cd679c4e5ad030966dbf82d41f851b36f20e18b06099d3fe84
+oid sha256:b2cd57660b15f346d8b18bbe7a8da1fd2c99cf04ef11382550955cf575869030
 size 13685516

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": 0.004300381658872225,
+  "epoch": 0.005733842211829633,
   "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": 112.491,
       "eval_steps_per_second": 56.255,
       "step": 15
+    },
+    {
+      "epoch": 0.004587073769463707,
+      "grad_norm": 1.4125806093215942,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7849,
+      "step": 16
+    },
+    {
+      "epoch": 0.004873765880055188,
+      "grad_norm": 1.3750802278518677,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4638,
+      "step": 17
+    },
+    {
+      "epoch": 0.00516045799064667,
+      "grad_norm": 1.4604270458221436,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4954,
+      "step": 18
+    },
+    {
+      "epoch": 0.005447150101238152,
+      "grad_norm": 1.4208030700683594,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6142,
+      "step": 19
+    },
+    {
+      "epoch": 0.005733842211829633,
+      "grad_norm": 1.3754969835281372,
+      "learning_rate": 0.0,
+      "loss": 1.4593,
+      "step": 20
+    },
+    {
+      "epoch": 0.005733842211829633,
+      "eval_loss": 1.566907286643982,
+      "eval_runtime": 51.1312,
+      "eval_samples_per_second": 114.9,
+      "eval_steps_per_second": 57.46,
+      "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": 1547541468413952.0,
+  "total_flos": 2065520224370688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null