Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e737501f2b45e7567ee47af1ddb09b9cbaa6f653e680bb4a4cad7d8ad854e388
+oid sha256:9d76318004fa1ca94e84d719808602e034a0c9197c7f1c0de68223eacddec379
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b322f65dbb3d497733de58208d7e2ff958939a0bbcd4b0f1665fb36b3e6d1a6f
+oid sha256:cfdfe9efcc3a66f883ebcea8872b83260dcdf530c6cb79b57e97a39975317c42
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1dbd056bdba902bbd15884fe0ae45df7b81d1dab50b96a0c9b32d0eae3e262
+oid sha256:df81fc9d078b3589f3e74ce10344ae2b9ba2f47edb0c855a81de1c3ca1991673
 size 14244

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:12cb93e09fed5cf770f42b645926821cd300de44a57db3ca5e284142571864c2
+size 14500638

last-checkpoint/trainer_state.json

@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 0.39290162920951843,
+      "grad_norm": 2.1512844562530518,
       "learning_rate": 1.5833333333333336e-06,
-      "loss": 4.0074,
+      "loss": 4.4875,
       "step": 20
     }
   ],
@@ -21,7 +21,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 20,
-  "total_flos": 9824796131328.0,
+  "total_flos": 167462914424832.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e76cb4f6a41bce2aadf48ff7cb6d05ab2c9b686a1100b4a6b9867db37ed9160
+oid sha256:2144efe638cdc54910486057ddff9e1420f8f369906d08c03aeb6ed693951c8e
 size 4984