Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57bafe229ddc9d396d70b73c5d3f1551beb944434118874bbd2db99ccfa0758
+oid sha256:2b332b6e8afc923724f84413e33299c5790f4ee8cf15f65d6144ba400e36d6c3
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4815fbb30c93a76d04b86b348cb01ba704d445bd57e754c90d9516cc171859c
+oid sha256:8644418b35ffaf32d8aff1eed51b7d29638fabcb22b0cccef0d136903c9d9bb8
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9a25d06c35d5d5739e33f68c959f00eb5b9e3a183683d69b110de9c2694ca6
+oid sha256:d694e0d8a3c8e350e985b3c92970945d2995494a99fcf921d95897d24d690561
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.1073384446878425,
+  "epoch": 4.381161007667032,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,41 @@
       "learning_rate": 9.399114703433688e-06,
       "loss": 0.17,
       "step": 7500
+    },
+    {
+      "epoch": 4.16210295728368,
+      "grad_norm": 0.85968416929245,
+      "learning_rate": 8.313360016700011e-06,
+      "loss": 0.1679,
+      "step": 7600
+    },
+    {
+      "epoch": 4.216867469879518,
+      "grad_norm": 0.9793341159820557,
+      "learning_rate": 7.288533363293959e-06,
+      "loss": 0.1719,
+      "step": 7700
+    },
+    {
+      "epoch": 4.271631982475356,
+      "grad_norm": 0.9244991540908813,
+      "learning_rate": 6.32613260134271e-06,
+      "loss": 0.1718,
+      "step": 7800
+    },
+    {
+      "epoch": 4.326396495071194,
+      "grad_norm": 1.2018598318099976,
+      "learning_rate": 5.427564349027098e-06,
+      "loss": 0.1669,
+      "step": 7900
+    },
+    {
+      "epoch": 4.381161007667032,
+      "grad_norm": 0.9171732664108276,
+      "learning_rate": 4.594141928707629e-06,
+      "loss": 0.1685,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -551,7 +586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.605124734318199e+18,
+  "total_flos": 3.843744149453193e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null