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:f205188dff42985227d31f6aac72d0ae305c1323e80bbdeea9109c554d0a2515
+oid sha256:e19dd53ac2fe07478fb3f7ff06cd8453289ac38de2e6253a5ffc4ef4c9125468
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e581caa11338fb46cfe658131b1ceaa112775feddab6b604064a612db02246
+oid sha256:12cbed420f150e1cebeb2852191ce060d576920c45eab0e292f9d9eb4790953a
 size 173094

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": 0.26578073089701,
+  "epoch": 0.35437430786268,
   "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": 137.818,
       "eval_steps_per_second": 69.635,
       "step": 15
+    },
+    {
+      "epoch": 0.28349944629014395,
+      "grad_norm": 0.12062043696641922,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.8331,
+      "step": 16
+    },
+    {
+      "epoch": 0.301218161683278,
+      "grad_norm": 0.12629450857639313,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.837,
+      "step": 17
+    },
+    {
+      "epoch": 0.31893687707641194,
+      "grad_norm": 0.13337388634681702,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.8319,
+      "step": 18
+    },
+    {
+      "epoch": 0.33665559246954596,
+      "grad_norm": 0.12452352792024612,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.8309,
+      "step": 19
+    },
+    {
+      "epoch": 0.35437430786268,
+      "grad_norm": 0.12699002027511597,
+      "learning_rate": 0.0,
+      "loss": 10.8314,
+      "step": 20
+    },
+    {
+      "epoch": 0.35437430786268,
+      "eval_loss": 10.833288192749023,
+      "eval_runtime": 0.6024,
+      "eval_samples_per_second": 157.699,
+      "eval_steps_per_second": 79.679,
+      "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": 4962789359616.0,
+  "total_flos": 6603380883456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null