Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d87d7b00b2cd87fc029fa649fcad601b3ab7944457ec983484f19f24a594882
+oid sha256:ab0d2cef0a520f95d1b3a5e19c4faf1f2fdd4b669b292c657819c3293f9777df
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665a4d9783c05d43fa2505e60c3df4f8fdb4f033e3075cab2b640d9f0f0ef616
+oid sha256:6e19bb13e6ddd38b55d269b81836df099f52d521292cc3147c8069c577d0d7f7
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6334547612743196cb899c468f052098297738886954360e857941f54e2a3c
+oid sha256:473e97fa4a79ae2cdbec269f5dd726507565e4476964fba62228ef7aefe54818
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a72ce24312e683508adae33679f3e646acad48e43aa6427ea385038cc671f18
+oid sha256:0a564ad02175d1fc4a411742de225c89f8307036c81f34a693a28057e5f5ff71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013385935100524654,
+  "epoch": 0.001487326122280517,
   "eval_steps": 2000,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -70,6 +70,13 @@
       "learning_rate": 1.9999996494428805e-05,
       "loss": 1.5682,
       "step": 1800
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.574249267578125,
+      "learning_rate": 1.9999995668269356e-05,
+      "loss": 1.5658,
+      "step": 2000
     }
   ],
   "logging_steps": 200,
@@ -77,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 2.3336484713988096e+16,
+  "total_flos": 2.6047198846255104e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null