Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55fb81428939778dab08e7922db21d016e3f504c05107e029c92f5fce46fe882
+oid sha256:ee0f7f6efa259946627904facc17872a7c399f185f2fa3c1cfc100a6322fb601
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a229809403e9c000da99928a1a77232623f005939cd31324d820e5637351f23b
+oid sha256:0539557cdcb1b310091e9a740e6565900f4359018a39a195ddb6d9bc8daf4959
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba198d9667b25aa3e1e3ed428937b84fcb61b09b165df40f8a2db486d218cb8
+oid sha256:dd393a0ba2edec99a3162827022ce552435f0d62f37eef791559e57aae2a12ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3691128148959475,
+  "epoch": 1.642935377875137,
   "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": 9.107512678178223e-05,
       "loss": 1.1572,
       "step": 2500
+    },
+    {
+      "epoch": 1.4238773274917853,
+      "grad_norm": 2.1899495124816895,
+      "learning_rate": 8.99553475612544e-05,
+      "loss": 1.0975,
+      "step": 2600
+    },
+    {
+      "epoch": 1.4786418400876231,
+      "grad_norm": 2.541968822479248,
+      "learning_rate": 8.877717071624055e-05,
+      "loss": 1.1102,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5334063526834611,
+      "grad_norm": 1.9248064756393433,
+      "learning_rate": 8.754231823724187e-05,
+      "loss": 1.1012,
+      "step": 2800
+    },
+    {
+      "epoch": 1.588170865279299,
+      "grad_norm": 2.002230644226074,
+      "learning_rate": 8.62525949502896e-05,
+      "loss": 1.0992,
+      "step": 2900
+    },
+    {
+      "epoch": 1.642935377875137,
+      "grad_norm": 2.2088050842285156,
+      "learning_rate": 8.490988587906137e-05,
+      "loss": 1.1102,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -201,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2070042691739648e+18,
+  "total_flos": 1.4496265837006356e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null