Training in progress, step 7800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68c43c7f004c1eadd91b9fe7a30fc2b0fd69b4f58b1bc37e1b8caf12c6810ef
+oid sha256:8230b48ad5d2d47bded13d0b4a225a6fe458e88f0dfffee4ef6138e3578b7cb7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e2d7e319df6b910d8660f90fe9f5f432aa3e2fcf0fc9f644ada3faf7f04901
+oid sha256:a3ebd683f88765c7f3684d4f1b999d5a7d937536c2acc21fbea1dd5a504ff4c8
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10e311d00a264a46fa5f0eed688f7217fcace7c41779a2ffd66f55f87f67920
+oid sha256:5815229928c679da2154333af4c0852e138211519132990800c387aec8269b78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fe99cd7e53dc1def962f8fb0d7ad9ae866de71ef7bffa4b49eb8c6cbd19c21
+oid sha256:3961966af58db2c2b54115da864b0f30cc2f3fd3fe289e5c948d2dbcbffbe9d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005651839264665965,
+  "epoch": 0.005800571876894017,
   "eval_steps": 2000,
-  "global_step": 7600,
+  "global_step": 7800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,13 @@
       "learning_rate": 1.9999937128842296e-05,
       "loss": 1.6411,
       "step": 7600
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.499472141265869,
+      "learning_rate": 1.9999933771375512e-05,
+      "loss": 1.5566,
+      "step": 7800
     }
   ],
   "logging_steps": 200,
@@ -280,7 +287,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 9.98269473472512e+16,
+  "total_flos": 1.0229934649090867e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null