Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32b5959735aa57b511b7726bfbc2ef5de45ff1ebf9d62c5f60891e02815697b
+oid sha256:09c982744a2e391f73af0e352e0a17f8fbe631dce3317e7eceafc8381ba0953f
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7bb1fceeac45ca2476246b3d206978cdd4cb987a38fb6a0552e774331666a57
-size 243807941
+oid sha256:641da55da61aa12bcdb51eded80a666515608d903c7ddf5cd1bdf125653afb89
+size 243808453

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317b5a305b2a9e21e527e7f85fdb3c6126a0ca02234bcb93021996746c86138a
+oid sha256:b02df20a55610bece1d11ccda94ef741d9490de46861191025bd6f932e04e77c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bf6871cccebbd8019e51a8751deebfdc1a27237b371091ed859a0e2e1ce5c9
+oid sha256:b89d6b7337c8b71ddbff9a2bc80a7133f2055b441080e4bb499fae131f0d3301
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.32,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,146 @@
       "learning_rate": 0.00018841521819342236,
       "loss": 0.8466087341308594,
       "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.33928611874580383,
+      "learning_rate": 0.00018682216046570475,
+      "loss": 0.8981865882873535,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.3191171884536743,
+      "learning_rate": 0.00018513416398022802,
+      "loss": 0.8822257995605469,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.3258090615272522,
+      "learning_rate": 0.0001833530745363661,
+      "loss": 0.8913363456726074,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.3579511046409607,
+      "learning_rate": 0.00018148083972927616,
+      "loss": 0.9036433219909668,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.322074830532074,
+      "learning_rate": 0.00017951950682023191,
+      "loss": 0.8622542381286621,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.3411216735839844,
+      "learning_rate": 0.00017747122049797335,
+      "loss": 0.9023735046386718,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.35992440581321716,
+      "learning_rate": 0.00017533822053352128,
+      "loss": 0.9113937377929687,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.36170879006385803,
+      "learning_rate": 0.00017312283933102038,
+      "loss": 0.8803692817687988,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.3963969349861145,
+      "learning_rate": 0.00017082749937728973,
+      "loss": 0.901433277130127,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.3751416802406311,
+      "learning_rate": 0.00016845471059286887,
+      "loss": 0.859034538269043,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.4061877727508545,
+      "learning_rate": 0.00016600706758745668,
+      "loss": 0.8167524337768555,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.30562642216682434,
+      "learning_rate": 0.00016348724682274353,
+      "loss": 0.8657124519348145,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.3281916677951813,
+      "learning_rate": 0.00016089800368574014,
+      "loss": 0.8574649810791015,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.3317168951034546,
+      "learning_rate": 0.00015824216947580183,
+      "loss": 0.8774423599243164,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3389717638492584,
+      "learning_rate": 0.00015552264830864468,
+      "loss": 0.9006638526916504,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.4187377691268921,
+      "learning_rate": 0.00015274241394073733,
+      "loss": 0.865053367614746,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.33337095379829407,
+      "learning_rate": 0.00014990450651754207,
+      "loss": 0.8772675514221191,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.3234522044658661,
+      "learning_rate": 0.0001470120292491605,
+      "loss": 0.8527763366699219,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.39457225799560547,
+      "learning_rate": 0.00014406814501701857,
+      "loss": 0.8379721641540527,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.317992240190506,
+      "learning_rate": 0.00014107607291530256,
+      "loss": 0.9060126304626465,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -167,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8420601253617664e+16,
+  "total_flos": 5.682222032356147e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null