Training in progress, step 2580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc2136cfbd00690f3783dc17e8800db2dc8ad727fd6fe2cc8c6c953b2599e207
+oid sha256:4b4d9136a9ce0e4ccfef59d92612be6224b1453529c1e6acd828713f37075749
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea2b85354be8b703c4c2920b8b2fb21f3e0e76e72838162be0d20e1b9317205
+oid sha256:fe674b371c6564c8793475ac817ef36331813aeddb6980a9b5b85d709be533a8
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd8571639a832ac3a6bdbe8b83a9d5174ee7552fcb8cdc3d2effb6c405a5866
+oid sha256:fd0207b1251f238352e39cb342463c968aa002551f624c293b10d9e3d04f1f0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a970aca6d8492ea417337203ea2e40d5dcc9a674de898354c4c9743b9beef6
+oid sha256:3ab51e931596bdb995a7ee5081800ce8215a3ea0018197244a214eabc916219f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9981337664165743,
+  "epoch": 0.999683663569395,
   "eval_steps": 500,
-  "global_step": 2576,
+  "global_step": 2580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18039,6 +18039,34 @@
       "learning_rate": 6.177385484029685e-11,
       "loss": 1.3969,
       "step": 2576
+    },
+    {
+      "epoch": 0.9985212407047794,
+      "grad_norm": 0.19256563484668732,
+      "learning_rate": 3.474782465096027e-11,
+      "loss": 1.3432,
+      "step": 2577
+    },
+    {
+      "epoch": 0.9989087149929846,
+      "grad_norm": 0.19377000629901886,
+      "learning_rate": 1.544348756044034e-11,
+      "loss": 1.4043,
+      "step": 2578
+    },
+    {
+      "epoch": 0.9992961892811898,
+      "grad_norm": 0.18626244366168976,
+      "learning_rate": 3.860873380445718e-12,
+      "loss": 1.3605,
+      "step": 2579
+    },
+    {
+      "epoch": 0.999683663569395,
+      "grad_norm": 0.17782603204250336,
+      "learning_rate": 0.0,
+      "loss": 1.3834,
+      "step": 2580
     }
   ],
   "logging_steps": 1.0,
@@ -18053,12 +18081,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.547514766592221e+18,
+  "total_flos": 2.55147909551824e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null