Training in progress, step 985, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9945e31b638334bf494fdbd6bddbd7efb17b80e2cb934406af8bd6e740a52c13
+oid sha256:f6e5b896f8b2107fa474ed7dd4a3e70346065a15ff641a52c3f4f047b8b292b2
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2faad1ff615b4367ac8f493089d35aa61ad18cd058aa6a59301eee8776decdbe
+oid sha256:b1eb16b5bd5f94102e9811db74952e3afddfa0eb03f909b03ec81c889aa909ad
 size 25152884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a563e473225d388aa85a62aecbc6bdee80f72d3795da30b7a19c51113a1af02
+oid sha256:6b712e2c7731e2e06b7c359163b91d5551189c894148dc86f6f8fd62dfef29d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdd00c1b48b23a3fb0db3f88bb5f4c0c6d9b16cd39a52129b3151d7da108592
+oid sha256:708b500eeebd05993112b6d6ad4170e8b50c4b3fed50daf1ac656195272b9044
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7086044830079538,
+  "epoch": 0.7122198120028923,
   "eval_steps": 692,
-  "global_step": 980,
+  "global_step": 985,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6883,6 +6883,41 @@
       "learning_rate": 1.9188404864839465e-05,
       "loss": 1.1212,
       "step": 980
+    },
+    {
+      "epoch": 0.7093275488069414,
+      "grad_norm": 0.453218013048172,
+      "learning_rate": 1.9186584719112724e-05,
+      "loss": 0.9847,
+      "step": 981
+    },
+    {
+      "epoch": 0.7100506146059291,
+      "grad_norm": 0.43997496366500854,
+      "learning_rate": 1.9184762621195897e-05,
+      "loss": 0.9984,
+      "step": 982
+    },
+    {
+      "epoch": 0.7107736804049168,
+      "grad_norm": 0.5103498101234436,
+      "learning_rate": 1.91829385714762e-05,
+      "loss": 1.0727,
+      "step": 983
+    },
+    {
+      "epoch": 0.7114967462039046,
+      "grad_norm": 0.5352555513381958,
+      "learning_rate": 1.918111257034124e-05,
+      "loss": 1.02,
+      "step": 984
+    },
+    {
+      "epoch": 0.7122198120028923,
+      "grad_norm": 0.40594494342803955,
+      "learning_rate": 1.917928461817906e-05,
+      "loss": 1.0947,
+      "step": 985
     }
   ],
   "logging_steps": 1,
@@ -6902,7 +6937,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1817874712625152e+18,
+  "total_flos": 2.1929190399934464e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null