Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad5b9c630b97cc8fc81c14436b52dfb1411ec86a786f53a1e94e11d5cac8282
+oid sha256:ae891f568a1c1323371f421df7e8497a947dd98ea827fd84d28c311cf81ab3c6
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a3a49c7d115993f093a1de1b1ff5e8c6fd6e8253564ed1d573f0dd24b4d130
+oid sha256:ce87d02da495ac41367a2a1cb96c12826c15e106327ab62939bdfad16a2f3aab
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cdb3fd225732740970359ffdd1418685448d0cd4c88e65a8e97b2d91f96913
+oid sha256:147a294f9a33d16934a9eb60b9f9bedc7178384ab62a9efc5e72db5352813f0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000497840616326683,
+  "epoch": 0.000995681232653366,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 8.049,
       "eval_steps_per_second": 4.024,
       "step": 10
+    },
+    {
+      "epoch": 0.0005974087395920196,
+      "grad_norm": 0.7066208720207214,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.7109,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007467609244900245,
+      "grad_norm": 0.9704435467720032,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.3098,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007467609244900245,
+      "eval_loss": 1.6141732931137085,
+      "eval_runtime": 1051.2981,
+      "eval_samples_per_second": 8.045,
+      "eval_steps_per_second": 4.023,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008961131093880294,
+      "grad_norm": 1.287255048751831,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4166,
+      "step": 18
+    },
+    {
+      "epoch": 0.000995681232653366,
+      "eval_loss": 1.5906931161880493,
+      "eval_runtime": 1051.8387,
+      "eval_samples_per_second": 8.041,
+      "eval_steps_per_second": 4.021,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.285435567374336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null