Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc0e03b9e41c36bebd5290c036c6ab8219fc845aed5c0fa6e9fcd25304615e4
+oid sha256:15df8bb7b0d650ace01d49121a6ff2801e53098ae1fbd955ed4336f0f8e11ee6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b25ff21c077ced998e166c13b16ca46c3928f2a8dec143c1e29895bcf0ed63e
+oid sha256:44804d51d5f6b390f04a3c04221e0560893966402950edc2362e929c63a832a3
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437c777924390da1dedc2bce8c9e0b6f4eb89d30ea814cea3a93ff7b5d5fae05
+oid sha256:42ae668d05ab3aad6ce208eabfc49a053f98a880118709786e12d55282ae6b22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ee446e7e0c91089e5e6b7b626fa10c97dc177ed58fc09c887e3e9c3cd58b38
+oid sha256:9b474e3bac276f26ded4a53adf20938b4253ff5f990814d1b36777f7eb9de45a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007436630611402585,
+  "epoch": 0.0008923956733683103,
   "eval_steps": 2000,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,6 +42,13 @@
       "learning_rate": 1.999999892574807e-05,
       "loss": 1.5775,
       "step": 1000
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.1446919441223145,
+      "learning_rate": 1.9999998448916044e-05,
+      "loss": 1.6922,
+      "step": 1200
     }
   ],
   "logging_steps": 200,
@@ -49,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.2689424120840192e+16,
+  "total_flos": 1.5519816481284096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null