Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f85c8bc4ad212684b7993062a23525ac4f791b5229784b4158ac4bce165586
+oid sha256:e28db0f053f0469288d9c661a2de0e7721acd04f65d12b2744dda53823792f55
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b37c1c4fa9a9e825ea05b1ca35dc1c4929d943b7bddd2f6086f57e6c5064ff4
+oid sha256:9e52fae042af788b20ffbe20c3dffe04e516add806bf2e66c036ba1becc61501
 size 51613668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875830942629bcea9e8c73e146b1df9f89fd36cd8b3e95d6764a6f4e78bd912d
+oid sha256:79e5ef6a566f54a2b32cb3e8d5a68a7370551bdcc68ea3fc820d6c009103c0c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f8e14b456d7fc01f5ad21526616d8f86a1c6c40024725332f505f34df4d95a
+oid sha256:d7641dde43bc7a22d17d22ddcaa29ef3541065d43d71357b77f45ce61017cfec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056627092618254,
+  "epoch": 0.06291899179806,
   "eval_steps": 42,
-  "global_step": 378,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -969,6 +969,112 @@
       "eval_samples_per_second": 35.943,
       "eval_steps_per_second": 4.495,
       "step": 378
+    },
+    {
+      "epoch": 0.05707651398824014,
+      "grad_norm": 0.17599642276763916,
+      "learning_rate": 6.930128404315214e-06,
+      "loss": 1.1339,
+      "step": 381
+    },
+    {
+      "epoch": 0.05752593535822628,
+      "grad_norm": 0.16360458731651306,
+      "learning_rate": 6.601189685384126e-06,
+      "loss": 1.1844,
+      "step": 384
+    },
+    {
+      "epoch": 0.05797535672821243,
+      "grad_norm": 0.1602054089307785,
+      "learning_rate": 6.279057507181796e-06,
+      "loss": 1.0835,
+      "step": 387
+    },
+    {
+      "epoch": 0.05842477809819857,
+      "grad_norm": 0.33288466930389404,
+      "learning_rate": 5.9638510407716394e-06,
+      "loss": 1.0366,
+      "step": 390
+    },
+    {
+      "epoch": 0.058874199468184715,
+      "grad_norm": 0.17551077902317047,
+      "learning_rate": 5.655686895087329e-06,
+      "loss": 1.0361,
+      "step": 393
+    },
+    {
+      "epoch": 0.05932362083817085,
+      "grad_norm": 0.19817480444908142,
+      "learning_rate": 5.354679073793942e-06,
+      "loss": 1.1113,
+      "step": 396
+    },
+    {
+      "epoch": 0.059773042208157,
+      "grad_norm": 0.18397966027259827,
+      "learning_rate": 5.060938933112891e-06,
+      "loss": 1.0809,
+      "step": 399
+    },
+    {
+      "epoch": 0.06022246357814314,
+      "grad_norm": 0.18848171830177307,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.0232,
+      "step": 402
+    },
+    {
+      "epoch": 0.060671884948129286,
+      "grad_norm": 0.18873141705989838,
+      "learning_rate": 4.495693635076101e-06,
+      "loss": 1.0633,
+      "step": 405
+    },
+    {
+      "epoch": 0.06112130631811542,
+      "grad_norm": 0.17433975636959076,
+      "learning_rate": 4.224397587172402e-06,
+      "loss": 1.0064,
+      "step": 408
+    },
+    {
+      "epoch": 0.06157072768810157,
+      "grad_norm": 0.2025955468416214,
+      "learning_rate": 3.9607873614261715e-06,
+      "loss": 1.1142,
+      "step": 411
+    },
+    {
+      "epoch": 0.06202014905808771,
+      "grad_norm": 0.1579374223947525,
+      "learning_rate": 3.7049604790198976e-06,
+      "loss": 1.0722,
+      "step": 414
+    },
+    {
+      "epoch": 0.062469570428073856,
+      "grad_norm": 0.15210741758346558,
+      "learning_rate": 3.4570115817301243e-06,
+      "loss": 1.011,
+      "step": 417
+    },
+    {
+      "epoch": 0.06291899179806,
+      "grad_norm": 0.21344028413295746,
+      "learning_rate": 3.217032396915265e-06,
+      "loss": 1.1333,
+      "step": 420
+    },
+    {
+      "epoch": 0.06291899179806,
+      "eval_loss": 1.0891081094741821,
+      "eval_runtime": 312.8277,
+      "eval_samples_per_second": 35.94,
+      "eval_steps_per_second": 4.494,
+      "step": 420
     }
   ],
   "logging_steps": 3,
@@ -988,7 +1094,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2131417357234995e+17,
+  "total_flos": 1.3537807518872371e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null