Training in progress, step 7000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0409bd80ccd14ddbeb3024bd062d30e291a180d2ca604903df91238170e4c73
+oid sha256:f0f779b104df13d2ef3ff238b794639a37aa0d0cd2cee827abc5589fa06152b0
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68644ea0237312a6dc011ff6674091c2fc2c55988ee98e26d3612f0699d73a35
+oid sha256:8923f264cdf21bc1f05bbec9aea66273c2a073b140852d3ef36be0f3c2033b55
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d723e76d2cab5754253ee0fd79d89a89aad0f0baf1b96ff814454ee845a638e
+oid sha256:41d9009edd34a178308b9e0582a661bb8622860498c029764cf1c8060b2e3cee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5881865857024566,
+  "epoch": 3.8642009384487994,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -462,6 +462,41 @@
       "learning_rate": 2.2356865904013918e-05,
       "loss": 0.1097,
       "step": 6500
+    },
+    {
+      "epoch": 3.6433894562517253,
+      "grad_norm": 0.4998696446418762,
+      "learning_rate": 2.0771592658917193e-05,
+      "loss": 0.1074,
+      "step": 6600
+    },
+    {
+      "epoch": 3.698592326800994,
+      "grad_norm": 0.40012943744659424,
+      "learning_rate": 1.922975467839799e-05,
+      "loss": 0.1078,
+      "step": 6700
+    },
+    {
+      "epoch": 3.753795197350262,
+      "grad_norm": 0.3930221498012543,
+      "learning_rate": 1.773364323135227e-05,
+      "loss": 0.1054,
+      "step": 6800
+    },
+    {
+      "epoch": 3.8089980678995308,
+      "grad_norm": 0.6007972359657288,
+      "learning_rate": 1.6285481634151057e-05,
+      "loss": 0.1068,
+      "step": 6900
+    },
+    {
+      "epoch": 3.8642009384487994,
+      "grad_norm": 0.4134114384651184,
+      "learning_rate": 1.4887421946651437e-05,
+      "loss": 0.1058,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -481,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4474544992722616e+18,
+  "total_flos": 3.711467098590806e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null