Training in progress, step 325, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf7198e8267b3b317d0bfa661e56918b0c602cad0ec4839218b000026dbad83
+oid sha256:f6c120f60dd6a77f9e8cae2805c9b4141450e162dfa65e28c9a540b713a5bacc
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99190bdd777fac27de12589cab5455d8c58569f98b515d3c0aeb3e4773b25a8
+oid sha256:f1e91a886a9320d141bd815bf66c393160cd39c2107702e9017888b495ce1a30
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2d3a921ff2f34dee8d1e2a44b6c868c4f52dd0a9e88a06d804a47ee81494b4
+oid sha256:7414204259a5959267febea726ae52027fe6d00835d10f953fea05f53c913c17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.877914951989026,
+  "epoch": 0.8916323731138546,
   "eval_steps": 500,
-  "global_step": 320,
+  "global_step": 325,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2247,6 +2247,41 @@
       "learning_rate": 3.3333333333333335e-05,
       "loss": 1.1552,
       "step": 320
+    },
+    {
+      "epoch": 0.8806584362139918,
+      "grad_norm": 0.15141616761684418,
+      "learning_rate": 3.257575757575758e-05,
+      "loss": 1.2216,
+      "step": 321
+    },
+    {
+      "epoch": 0.8834019204389575,
+      "grad_norm": 0.18166609108448029,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.1831,
+      "step": 322
+    },
+    {
+      "epoch": 0.8861454046639232,
+      "grad_norm": 0.1654902696609497,
+      "learning_rate": 3.106060606060606e-05,
+      "loss": 1.1447,
+      "step": 323
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.15685853362083435,
+      "learning_rate": 3.0303030303030306e-05,
+      "loss": 1.1643,
+      "step": 324
+    },
+    {
+      "epoch": 0.8916323731138546,
+      "grad_norm": 0.16564173996448517,
+      "learning_rate": 2.954545454545455e-05,
+      "loss": 1.1338,
+      "step": 325
     }
   ],
   "logging_steps": 1,
@@ -2266,7 +2301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9666723522411725e+17,
+  "total_flos": 4.028579259326669e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null