Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028261641ab6cbb485c1974ef6b683052508e9a0b2ee07b49eaace079456f408
+oid sha256:eddc3911883bf877de0dfcfd58769044c2f83c977f8e6aeb6b47def642e69fb0
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ebdc5441da9b96a9485381511bc341ae823bfecd5064dee95d4c8fdbd8cc24
+oid sha256:7dc63265cc41222a6ed7b3f38f75ed8f521c9b7cc12cae805fddaf4f71460ca5
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3aecb75efdd11c0e1c39b49041e1993d554f3f56394f02961f75e0cc234fa1b
+oid sha256:b0477852d6129f9137d9cb4bd8e504eba435ba453fa1a20cae07fcf8d0c622c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20804953560371517,
+  "epoch": 0.22516183506895582,
   "eval_steps": 42,
-  "global_step": 462,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1181,6 +1181,90 @@
       "eval_samples_per_second": 137.594,
       "eval_steps_per_second": 34.398,
       "step": 462
+    },
+    {
+      "epoch": 0.2094005066141289,
+      "grad_norm": 1.0856338739395142,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 11.4542,
+      "step": 465
+    },
+    {
+      "epoch": 0.21075147762454263,
+      "grad_norm": 0.731679379940033,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 11.4381,
+      "step": 468
+    },
+    {
+      "epoch": 0.21210244863495636,
+      "grad_norm": 1.1720694303512573,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 11.4408,
+      "step": 471
+    },
+    {
+      "epoch": 0.2134534196453701,
+      "grad_norm": 0.8371026515960693,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 11.4373,
+      "step": 474
+    },
+    {
+      "epoch": 0.21480439065578386,
+      "grad_norm": 0.7634724974632263,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 11.4381,
+      "step": 477
+    },
+    {
+      "epoch": 0.2161553616661976,
+      "grad_norm": 1.8316603899002075,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 11.4259,
+      "step": 480
+    },
+    {
+      "epoch": 0.21750633267661132,
+      "grad_norm": 1.1125842332839966,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 11.436,
+      "step": 483
+    },
+    {
+      "epoch": 0.21885730368702505,
+      "grad_norm": 1.068013072013855,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 11.4463,
+      "step": 486
+    },
+    {
+      "epoch": 0.22020827469743878,
+      "grad_norm": 0.86719810962677,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 11.4465,
+      "step": 489
+    },
+    {
+      "epoch": 0.22155924570785251,
+      "grad_norm": 0.8328643441200256,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 11.4497,
+      "step": 492
+    },
+    {
+      "epoch": 0.22291021671826625,
+      "grad_norm": 0.7008333206176758,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 11.4307,
+      "step": 495
+    },
+    {
+      "epoch": 0.22426118772867998,
+      "grad_norm": 0.7325507402420044,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 11.444,
+      "step": 498
     }
   ],
   "logging_steps": 3,
@@ -1195,12 +1279,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 254582636544000.0,
+  "total_flos": 275516669952000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null