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:a9bcad8bdceb953e4041a2446f3ca0ac69dfd62bdc88a7053d8ccd908a1a7274
+oid sha256:6c6338372961508d0e6e53f4b425dedb3b1d009925d6beed6c8fe137d15a8822
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90c81f387e715b9f6d842a12d0ffcc53c28bfdd7183a5b426bb29a014eb37be
+oid sha256:c43bc5142208879f6c21142d760abc96f24db666fb369b9d6d73834b699e85a2
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9912bf78e7cc968894815632c1e4fcd3ff686a58ca2e14070632815f6c275f7f
+oid sha256:ca4ef0be595a40805daa15596cdef4ec088c37a282b79824e24568848d376f7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001693870939738424,
+  "epoch": 0.0003387741879476848,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 9.669,
       "eval_steps_per_second": 4.835,
       "step": 10
+    },
+    {
+      "epoch": 0.00018632580337122663,
+      "grad_norm": 23.243389129638672,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 17.2822,
+      "step": 11
+    },
+    {
+      "epoch": 0.00020326451276861087,
+      "grad_norm": 23.551620483398438,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 16.8668,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002202032221659951,
+      "grad_norm": 17.5562686920166,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 15.4958,
+      "step": 13
+    },
+    {
+      "epoch": 0.00023714193156337935,
+      "grad_norm": 25.39556312561035,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 17.6328,
+      "step": 14
+    },
+    {
+      "epoch": 0.0002540806409607636,
+      "grad_norm": 17.877641677856445,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 15.1113,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002540806409607636,
+      "eval_loss": 2.129117488861084,
+      "eval_runtime": 5125.7738,
+      "eval_samples_per_second": 9.699,
+      "eval_steps_per_second": 4.85,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002710193503581478,
+      "grad_norm": 30.318897247314453,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 17.8594,
+      "step": 16
+    },
+    {
+      "epoch": 0.00028795805975553206,
+      "grad_norm": 15.739501953125,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 17.0346,
+      "step": 17
+    },
+    {
+      "epoch": 0.0003048967691529163,
+      "grad_norm": 24.859498977661133,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 18.724,
+      "step": 18
+    },
+    {
+      "epoch": 0.00032183547855030054,
+      "grad_norm": 16.235403060913086,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 15.4015,
+      "step": 19
+    },
+    {
+      "epoch": 0.0003387741879476848,
+      "grad_norm": 15.718273162841797,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 17.4672,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003387741879476848,
+      "eval_loss": 2.085993766784668,
+      "eval_runtime": 5126.7679,
+      "eval_samples_per_second": 9.697,
+      "eval_steps_per_second": 4.849,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -120,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.402135828758528e+16,
+  "total_flos": 2.804271657517056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null