Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7805daf643035164a1fa6da6c2e1a71a5649eecb3446faef4c963c50c0fb75a1
+oid sha256:a69109e2243b746baaa054839e7be57d4cbfe1df99ec05119f327fe75e3442b5
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5da488dbb7936758114806562e1b293b09a3a3f38d9f937addd128b812765
+oid sha256:5fab536024b516737b44da945642d473d6d1df212865171c1c71f241fb314cc2
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc64d5d13a3120771ece3c4a2eb4de07fed7796fc4d888af303e82089a1664f1
+oid sha256:40a41b1cfc2d1d2cac5b4a1a7b6d8de286116a44eea4ee32508ab5c0289c1384
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010416666666666666,
+  "epoch": 0.015625,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.4572,
       "step": 18
+    },
+    {
+      "epoch": 0.0109375,
+      "grad_norm": 2.834351062774658,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.4698,
+      "step": 21
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 2.5578553676605225,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3436,
+      "step": 24
+    },
+    {
+      "epoch": 0.0125,
+      "eval_loss": 2.4004898071289062,
+      "eval_runtime": 76.8553,
+      "eval_samples_per_second": 10.526,
+      "eval_steps_per_second": 5.27,
+      "step": 24
+    },
+    {
+      "epoch": 0.0140625,
+      "grad_norm": 2.488203763961792,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.496,
+      "step": 27
+    },
+    {
+      "epoch": 0.015625,
+      "grad_norm": 2.202345132827759,
+      "learning_rate": 0.0,
+      "loss": 2.3414,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null