Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5cc6bdc71dee79bf87e76cccd7c5f022d94f50f86f182ae3b19cd6f89d1a18
+oid sha256:c29fe4a0133197cda139441a6bba43ba30a0a16566dcea0b7516ede214fd5573
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3d111a59096d88a8938996f72eaa582bdc17c62954716fedb95eaeb752fe76
+oid sha256:c5b38eb68908f60759797c8127974582cae417043d2969c2c60105311ef3ecf1
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb014c34717cc705cc26abab664b6e113f17c41373b9a6cee14bcf66f7b85a9e
+oid sha256:d3492512c1ba7e98d86dc7e3d6cf87a55ddfe936908da4ab0ab28461f25075b9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13245033112582782,
+  "epoch": 0.1490066225165563,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -136,6 +136,20 @@
       "learning_rate": 4.4094922737306846e-05,
       "loss": 0.7668,
       "step": 800
+    },
+    {
+      "epoch": 0.14072847682119205,
+      "grad_norm": 1.9555529356002808,
+      "learning_rate": 4.685430463576159e-05,
+      "loss": 0.7684,
+      "step": 850
+    },
+    {
+      "epoch": 0.1490066225165563,
+      "grad_norm": 2.308894157409668,
+      "learning_rate": 4.961368653421634e-05,
+      "loss": 0.7661,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -155,7 +169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6269184126222336.0,
+  "total_flos": 7039716814749696.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null