Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c1e8afc5d6e724647aa6282eea420a5674252560cfe3ca227d9079c5ab3503
+oid sha256:a5e8881aad18812c596776b42467ea44ba6e2019208cb5f8c45d0a376536107b
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925357869e6ba85e6c835b49837b1223de96991a316b48a2f12c8541300e39be
+oid sha256:e24b1cb4126b6578f8ef42b1cfb376b96e018a237e5ea0f12de0ee1e45f85a0d
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8062f178cdbb1c5d808c1d4d26e9f0f29c4b409a65e50547129df87250075971
+oid sha256:0527c0935311c8a923a2d690cf85dc65fa8804853ac1e460d104fb7d5f70ed76
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5505092210294522,
+  "epoch": 0.8257638315441783,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,41 @@
       "learning_rate": 4.9903868093081854e-05,
       "loss": 1.3367,
       "step": 1000
+    },
+    {
+      "epoch": 0.6055601431323975,
+      "grad_norm": 1.8014689683914185,
+      "learning_rate": 4.0351577053958396e-05,
+      "loss": 1.2852,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6606110652353427,
+      "grad_norm": 1.8801296949386597,
+      "learning_rate": 3.1154846703215746e-05,
+      "loss": 1.229,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7156619873382879,
+      "grad_norm": 1.738985538482666,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 1.2434,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7707129094412332,
+      "grad_norm": 2.303053379058838,
+      "learning_rate": 1.5158135674454127e-05,
+      "loss": 1.2021,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257638315441783,
+      "grad_norm": 1.6559442281723022,
+      "learning_rate": 8.947660827286925e-06,
+      "loss": 1.1831,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -96,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.293567140023501e+17,
+  "total_flos": 7.96786646670508e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null