Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f256054f75ca529de3de3d31d968831168d96bd93b26db8cfb78737f117fa5f
+oid sha256:196dba7b25c0a4c68d7a023c577d7e08c52e76d0408d8bc30c27ca039dbe9a92
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e19a66b263f1d6b622f520ca1c19416aeecac18d947e4eebc62fbd930353fd
+oid sha256:68c232c70d72ff63954a64510b19045d431ee3cf56e8201d12f051c97760d891
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5247c071411b90e6abc28dfd3094729155dc46bfcf927ecdb927c420369d449
+oid sha256:20c9aaea8c26c5e4232cacfa8dd7d43278b636bf8b016e620006628dcd43298e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.380071763731714,
+  "epoch": 1.6560861164780567,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,41 @@
       "learning_rate": 9.08526023432446e-05,
       "loss": 0.3113,
       "step": 2500
+    },
+    {
+      "epoch": 1.4352746342809826,
+      "grad_norm": 1.3542137145996094,
+      "learning_rate": 8.971114170929969e-05,
+      "loss": 0.2965,
+      "step": 2600
+    },
+    {
+      "epoch": 1.4904775048302512,
+      "grad_norm": 1.0694419145584106,
+      "learning_rate": 8.851066780355073e-05,
+      "loss": 0.2907,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5456803753795199,
+      "grad_norm": 1.2589095830917358,
+      "learning_rate": 8.72529646062573e-05,
+      "loss": 0.2881,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6008832459287883,
+      "grad_norm": 0.9907445311546326,
+      "learning_rate": 8.593990114403092e-05,
+      "loss": 0.2833,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6560861164780567,
+      "grad_norm": 1.1165964603424072,
+      "learning_rate": 8.45734287123433e-05,
+      "loss": 0.279,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -201,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3266286871642112e+18,
+  "total_flos": 1.5884360163671409e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null