Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b776cef4a8b110f29f03f1f2a505ab26816d15755d261cab864eced6635967f
+oid sha256:020c0fb13a58b5560f02c8bc234c279da102ee2eb7f298e1a83031fe8ed77a9d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7cd6507b3e6336497c085dcdbab5771e4bc873fa652e44ade43922d4c8c091
+oid sha256:10233c45644298c18560fe20a01ae5677c0810ffb56603956549cd685a5b636e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24904fc57fd2178e69b645251775fb3fd05ea113003861d10791be78a06f1a9
+oid sha256:3d2ed7bb47263863992b4cee8254a6b09097065ba424f1725823e1454e5ac93b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
+oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03230148048452221,
+  "epoch": 0.04306864064602961,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 7.844,
       "eval_steps_per_second": 7.844,
       "step": 12
+    },
+    {
+      "epoch": 0.034993270524899055,
+      "grad_norm": 1.4582064151763916,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.3575,
+      "step": 13
+    },
+    {
+      "epoch": 0.03768506056527591,
+      "grad_norm": 1.6408145427703857,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.4609,
+      "step": 14
+    },
+    {
+      "epoch": 0.040376850605652756,
+      "grad_norm": 1.7364938259124756,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.4607,
+      "step": 15
+    },
+    {
+      "epoch": 0.04306864064602961,
+      "grad_norm": 2.5827343463897705,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.5915,
+      "step": 16
+    },
+    {
+      "epoch": 0.04306864064602961,
+      "eval_loss": 0.29014351963996887,
+      "eval_runtime": 10.1162,
+      "eval_samples_per_second": 7.809,
+      "eval_steps_per_second": 7.809,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -142,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5007739164033024.0,
+  "total_flos": 6584249641598976.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null