Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9dcbc40162be0164467bbc8b5e807c866f2f72ff307498d2a43c2c19d6cde5f
+oid sha256:ff1659573be9832300f4f4efea5a2cf7e4b44363f06622e7e55214c46e1143b5
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4162b80d1e9112a887d3befe658a83ba1222e00f3cc9b381daff32e81f3858
+oid sha256:1b2fab67c049fb2be004c11732675fa014bc78c5e94282c5a42a91db5f153a03
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b9c1be8d8bae4df98ae1a27353c07078eed013c40757a6521cd0fbfb3c8fb9
+oid sha256:7e90410ed8d75deee232d46a71672a78439ef812c0e8c37ade4c255c49bee23b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:cc8ae5b9632b883900417a4b328f111a055e2a3387d176daa619ce2ea248142d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.880952380952381,
+  "epoch": 2.3333333333333335,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 0.0001,
       "loss": 1.2649,
       "step": 20
+    },
+    {
+      "epoch": 1.9761904761904763,
+      "grad_norm": 0.17005658149719238,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1879,
+      "step": 21
+    },
+    {
+      "epoch": 1.9761904761904763,
+      "eval_loss": 1.1423633098602295,
+      "eval_runtime": 6.4505,
+      "eval_samples_per_second": 15.503,
+      "eval_steps_per_second": 7.751,
+      "step": 21
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 0.20884154736995697,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.1346,
+      "step": 22
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.1699027419090271,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.1203,
+      "step": 23
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 0.16104689240455627,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.198,
+      "step": 24
+    },
+    {
+      "epoch": 2.238095238095238,
+      "eval_loss": 1.141262173652649,
+      "eval_runtime": 6.2986,
+      "eval_samples_per_second": 15.876,
+      "eval_steps_per_second": 7.938,
+      "step": 24
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.16542628407478333,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.1115,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -222,7 +273,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3791128769593344.0,
+  "total_flos": 4707063061020672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null