Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddd296d70d9b3b61ea53b45e334f04990034e1561c23a9d5310e615af21d625
+oid sha256:1d86c95965cefd952d5ca27059b33f80c64b6b50fce4dda34b1747e02db21f81
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59d2161e7818ef52d0dedcff1f80a4ff4d3161cac3cfbe9a413303665cb10c1
+oid sha256:13a70a8743b5c2d0bb79fb4dcc70920aea4481b8a9f6fa403ceab3c107ef115e
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93b0856df0781ee689edcb1cf7d2e5a3fef386bea76c4a707f7fab6bcaef139
+oid sha256:f00908dcb63c73e3df9f03fbc0b4e06062fa22233b29723cfa3cb055febf171b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
+oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3873570948217888,
+  "epoch": 0.5810356422326832,
   "eval_steps": 50,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,6 +141,69 @@
       "learning_rate": 0.000135,
       "loss": 40.6851,
       "step": 18
+    },
+    {
+      "epoch": 0.4088769334229993,
+      "grad_norm": 54.74737548828125,
+      "learning_rate": 0.0001425,
+      "loss": 40.0946,
+      "step": 19
+    },
+    {
+      "epoch": 0.43039677202420984,
+      "grad_norm": 113.8772201538086,
+      "learning_rate": 0.00015,
+      "loss": 39.7055,
+      "step": 20
+    },
+    {
+      "epoch": 0.4519166106254203,
+      "grad_norm": 77.01616668701172,
+      "learning_rate": 0.00014994217771805422,
+      "loss": 36.2917,
+      "step": 21
+    },
+    {
+      "epoch": 0.4734364492266308,
+      "grad_norm": 24.734567642211914,
+      "learning_rate": 0.00014976880002998458,
+      "loss": 38.7726,
+      "step": 22
+    },
+    {
+      "epoch": 0.4949562878278413,
+      "grad_norm": 33.39565658569336,
+      "learning_rate": 0.00014948013427161947,
+      "loss": 34.3707,
+      "step": 23
+    },
+    {
+      "epoch": 0.5164761264290518,
+      "grad_norm": 19.322717666625977,
+      "learning_rate": 0.00014907662554463532,
+      "loss": 35.1135,
+      "step": 24
+    },
+    {
+      "epoch": 0.5379959650302623,
+      "grad_norm": 25.940776824951172,
+      "learning_rate": 0.00014855889603024227,
+      "loss": 35.1159,
+      "step": 25
+    },
+    {
+      "epoch": 0.5595158036314728,
+      "grad_norm": 19.108659744262695,
+      "learning_rate": 0.00014792774402982574,
+      "loss": 34.2692,
+      "step": 26
+    },
+    {
+      "epoch": 0.5810356422326832,
+      "grad_norm": 18.458415985107422,
+      "learning_rate": 0.0001471841427340235,
+      "loss": 34.6374,
+      "step": 27
     }
   ],
   "logging_steps": 1,
@@ -160,7 +223,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.466481367790387e+16,
+  "total_flos": 1.419972205168558e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null