Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58046564a6a589cf046b1d0ed096919f55ce08a5adccffe843ca27704d205f04
+oid sha256:5209badae317ea0191985e9d2b0657c60495f0e245103e8da2f48bc30b76de0a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b486af472acc17cc180f369840ef98398fc54f8652e4989457cd2fb7dee143
+oid sha256:2c0e1196eb242854610785eb717ce5d397736e1d72a99ab40f99e81408a87da4
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9460a84ba57fb2b123198c54834de44fe0225b3afabca45a0f72ec4b268c32
+oid sha256:d628c8ae931950a378a9db4ecb26be5d61a7980fd613e5a54938458cbc7fb5be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4858d4115c512f42db83d85957355d46797903bfa9e8ae0671a225f442708fed
+oid sha256:6d4e79f8eacfb7ad204b76c28b6041891ae49ddf9bc16a1dfb9c80df15148b7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.27906976744186046,
+  "epoch": 0.28622540250447226,
   "eval_steps": 500,
-  "global_step": 780,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,14 +631,30 @@
       "loss": 0.4076,
       "num_input_tokens_seen": 521248,
       "step": 780
+    },
+    {
+      "epoch": 0.2826475849731664,
+      "grad_norm": 0.3435330092906952,
+      "learning_rate": 0.00014347048300536675,
+      "loss": 0.4109,
+      "num_input_tokens_seen": 527954,
+      "step": 790
+    },
+    {
+      "epoch": 0.28622540250447226,
+      "grad_norm": 0.2566317021846771,
+      "learning_rate": 0.00014275491949910555,
+      "loss": 0.4144,
+      "num_input_tokens_seen": 535308,
+      "step": 800
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 521248,
+  "num_input_tokens_seen": 535308,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.1721026788982784e+16,
+  "total_flos": 1.2037186537611264e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null