Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91270bfed96898597e98a0dc329e749214ec79fc85295ed43e1076f41803c84a
+oid sha256:3e2a11bd08b0ede80777f9f8f3c7437a225c58391a66b01506eb3cece79f6024
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e6c4ca044bb438e090f58ead16e15cbf7d5f67d276507a6456b85d0f6b1746
+oid sha256:27e07579212c22b474078f9b9c9bfd9ca5219d64cd55eabce4922a6cbd24d85f
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b005073ce3487d1a9dc5d2831d6dd25abdac86b29562322c49da0afe478a92
+oid sha256:73fcedd9bdb45aa888b5c9fc0ef207fe6bded7b834698fcaf3cd7d681d79886f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36378947368421055,
+  "epoch": 0.48505263157894735,
   "eval_steps": 50,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,6 +204,69 @@
       "learning_rate": 0.0001471841427340235,
       "loss": 1.5117,
       "step": 27
+    },
+    {
+      "epoch": 0.37726315789473686,
+      "grad_norm": 0.6267299652099609,
+      "learning_rate": 0.00014632923872213652,
+      "loss": 1.383,
+      "step": 28
+    },
+    {
+      "epoch": 0.39073684210526316,
+      "grad_norm": 0.7713648676872253,
+      "learning_rate": 0.0001453643501941863,
+      "loss": 1.4844,
+      "step": 29
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.6838952898979187,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 1.4825,
+      "step": 30
+    },
+    {
+      "epoch": 0.41768421052631577,
+      "grad_norm": 0.71690434217453,
+      "learning_rate": 0.0001431107380368811,
+      "loss": 1.4357,
+      "step": 31
+    },
+    {
+      "epoch": 0.43115789473684213,
+      "grad_norm": 0.6745509505271912,
+      "learning_rate": 0.00014182548931412757,
+      "loss": 1.4733,
+      "step": 32
+    },
+    {
+      "epoch": 0.44463157894736843,
+      "grad_norm": 0.7103040814399719,
+      "learning_rate": 0.0001404372005304598,
+      "loss": 1.3857,
+      "step": 33
+    },
+    {
+      "epoch": 0.45810526315789474,
+      "grad_norm": 0.6221896409988403,
+      "learning_rate": 0.0001389480123265569,
+      "loss": 1.2527,
+      "step": 34
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.562971293926239,
+      "learning_rate": 0.0001373602209226909,
+      "loss": 1.4486,
+      "step": 35
+    },
+    {
+      "epoch": 0.48505263157894735,
+      "grad_norm": 0.5778741240501404,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 1.4134,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -223,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2502242586198016e+16,
+  "total_flos": 3.000299011493069e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null