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:d018ef538c0304abf2cbc034e4a27d33f0ace4dbb0a7ed3d6bf1ba98d7e8c26d
+oid sha256:d96133d9c368d9d7bc340544bea979f22f630556481ad1272ac2e060811bb2ae
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708aacd2eab3f30c4ce73e46665401a347007898f0f52f8e3e3bd93d8a62deb8
+oid sha256:e0057246d1ec258249f538dc4bb800714349daf2d385ef66bc6794e0201bf2e4
 size 6614970

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": 0.013377180759155009,
+  "epoch": 0.017836241012206676,
   "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": 81.648,
       "eval_steps_per_second": 40.845,
       "step": 15
+    },
+    {
+      "epoch": 0.014268992809765343,
+      "grad_norm": 4.43351411819458,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.0361,
+      "step": 16
+    },
+    {
+      "epoch": 0.015160804860375675,
+      "grad_norm": 5.088730335235596,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.0811,
+      "step": 17
+    },
+    {
+      "epoch": 0.01605261691098601,
+      "grad_norm": 3.823406934738159,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.7383,
+      "step": 18
+    },
+    {
+      "epoch": 0.016944428961596345,
+      "grad_norm": 4.265321731567383,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 8.0918,
+      "step": 19
+    },
+    {
+      "epoch": 0.017836241012206676,
+      "grad_norm": 3.346766710281372,
+      "learning_rate": 0.0,
+      "loss": 4.5464,
+      "step": 20
+    },
+    {
+      "epoch": 0.017836241012206676,
+      "eval_loss": 0.4048779606819153,
+      "eval_runtime": 23.1311,
+      "eval_samples_per_second": 81.665,
+      "eval_steps_per_second": 40.854,
+      "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": 893328870604800.0,
+  "total_flos": 1187977258598400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null