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:fd9ad15d29deb18d7163bbcaaba1f33909384d83d67f8c9f379c9aa241eb789b
+oid sha256:8a0ef261440ce90564f2d2fa757cdbd329781df6eca9ffb0c1b923cffca4e7ff
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c27e39946f3eacdee6bd6c425f1858f6ace622df8d4e7314e81174ca9b2209b
+oid sha256:f1ea2ef1c05efa846f2f9ac6ed278ff0a96097fb93e536888284928f71f3d51b
 size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f36562187cf3b52a09213050f690637853db506cc488d604d4a5bde81a2629d
+oid sha256:7a3e256be1a0d886d12924f27bae3ab668dc46f0fd8fd76aec9bfb6b87068ca6
 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": 0.09684519442406456,
+  "epoch": 0.10481081647626035,
   "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": 48.668,
       "eval_steps_per_second": 6.087,
       "step": 462
+    },
+    {
+      "epoch": 0.09747405932292212,
+      "grad_norm": 0.34824374318122864,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.0597,
+      "step": 465
+    },
+    {
+      "epoch": 0.09810292422177969,
+      "grad_norm": 0.3800143599510193,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 1.0733,
+      "step": 468
+    },
+    {
+      "epoch": 0.09873178912063725,
+      "grad_norm": 0.39402127265930176,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 1.0444,
+      "step": 471
+    },
+    {
+      "epoch": 0.09936065401949482,
+      "grad_norm": 0.3665209114551544,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 1.0652,
+      "step": 474
+    },
+    {
+      "epoch": 0.09998951891835238,
+      "grad_norm": 0.3840101659297943,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 1.0667,
+      "step": 477
+    },
+    {
+      "epoch": 0.10061838381720993,
+      "grad_norm": 0.40634945034980774,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 1.024,
+      "step": 480
+    },
+    {
+      "epoch": 0.1012472487160675,
+      "grad_norm": 0.4399307370185852,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 1.0763,
+      "step": 483
+    },
+    {
+      "epoch": 0.10187611361492506,
+      "grad_norm": 0.3584943115711212,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 1.0044,
+      "step": 486
+    },
+    {
+      "epoch": 0.10250497851378262,
+      "grad_norm": 0.3854651153087616,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 1.0373,
+      "step": 489
+    },
+    {
+      "epoch": 0.10313384341264019,
+      "grad_norm": 0.3579770028591156,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 1.0518,
+      "step": 492
+    },
+    {
+      "epoch": 0.10376270831149775,
+      "grad_norm": 0.38003799319267273,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 1.1002,
+      "step": 495
+    },
+    {
+      "epoch": 0.1043915732103553,
+      "grad_norm": 0.35773521661758423,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 1.062,
+      "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": 9.855143078422118e+16,
+  "total_flos": 1.06657392623616e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null