Training in progress, step 6800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ecbd17698411abba08f800223d4f97c20ce6694fc5497eae762462f06c3ee3
+oid sha256:47fb5b2e87c858b356a497af5a368276e3f58a5b8eb72b8afd457002cb20edd9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e240a4ccbdf1ba5b7269029cb4c7fbd098170a36530fb8a7924ca7a51629862
+oid sha256:359bfa99d36cf98378251b4b3e7fbc9f02cda5213fa14831cd11bb03b49f087c
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcac68827b9f46f3ac71f10fc39a641a04d0ffa77754feb125895a9297c3035
+oid sha256:9b1c9b6d56495163f90ed52427fdb2571b9bad67126fc94f02c5944a1a78d778
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5a6b913ef84b8f56bbbc750706d31053f1c2d4afa8b1e983e030aad31a2507
+oid sha256:4052ec18fc2afb5774bb3660c8960b211e377d97915cd96a50052364ba383943
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004908176203525707,
+  "epoch": 0.0050569088157537585,
   "eval_steps": 2000,
-  "global_step": 6600,
+  "global_step": 6800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,13 @@
       "learning_rate": 1.9999952606205736e-05,
       "loss": 1.6222,
       "step": 6600
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.0667927265167236,
+      "learning_rate": 1.999994968539587e-05,
+      "loss": 1.5443,
+      "step": 6800
     }
   ],
   "logging_steps": 200,
@@ -245,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 8.670264252137472e+16,
+  "total_flos": 8.931527756085658e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null