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:b01b9daafcad04673491c04108f39a3f596eb23e03eaf535a3a764a4c5b30340
+oid sha256:73810805725027a88dd4eac83505229506f0bda4afe4ba15bc463ef99b6a71f6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd9bc3929008086d5d653a1031c116e96d55c2480dfc55f7f06c0052ab1f4b7
+oid sha256:8f01a15685949dbc93d1d62fef5369065bdb9efd6ec4fdde98cad25e6e26e050
 size 43122580

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": 0.12779552715654952,
+  "epoch": 0.1703940362087327,
   "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": 40.616,
       "eval_steps_per_second": 20.308,
       "step": 15
+    },
+    {
+      "epoch": 0.13631522896698617,
+      "grad_norm": 1.5528202056884766,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.2339,
+      "step": 16
+    },
+    {
+      "epoch": 0.1448349307774228,
+      "grad_norm": 1.3524258136749268,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1078,
+      "step": 17
+    },
+    {
+      "epoch": 0.15335463258785942,
+      "grad_norm": 1.4117428064346313,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.308,
+      "step": 18
+    },
+    {
+      "epoch": 0.16187433439829607,
+      "grad_norm": 1.2998523712158203,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2141,
+      "step": 19
+    },
+    {
+      "epoch": 0.1703940362087327,
+      "grad_norm": 1.366175889968872,
+      "learning_rate": 0.0,
+      "loss": 2.3305,
+      "step": 20
+    },
+    {
+      "epoch": 0.1703940362087327,
+      "eval_loss": 2.2778968811035156,
+      "eval_runtime": 4.8743,
+      "eval_samples_per_second": 40.621,
+      "eval_steps_per_second": 20.311,
+      "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": 1.1236102807486464e+16,
+  "total_flos": 1.4935231303778304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null