Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "word_embeddings",
-    "query_key_value"
+    "query_key_value",
+    "word_embeddings"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386f7859b4de007c7ae7c61ec6cb00a515d4711ba21b1c67d45d80097a8fa61d
+oid sha256:533927acb55df80e6c77c4e44b5e95d6906f3b0015497942bec83230a6f3834f
 size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0685b12efbb09b894e2972c18a08bca793a00db99b574a7e0547cacf1ffdbf
+oid sha256:f27fef141faf64728af757f67c5780cb028a986f2c45c5531ac42189a282292f
 size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4435a7825b6133e5243ce242cb736cca7675210c39cbc95a71b79603a1500997
+oid sha256:fe64354641a5ec2c9a41b64d26d231319df630261ab67db3cc1e8252d594fddf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4b34a50c55a680830f99a77a52585bb05290e33d30ce86746475157ba56d09
+oid sha256:d0351811b292a925d9e90fecda402ef74b5027ecf82c420e29489a6a985de561
 size 1064

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1130100472399276e-05,
+  "epoch": 6.226020094479855e-05,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 55.33664321899414,
-      "learning_rate": 0.0,
-      "loss": 3.9798,
+      "grad_norm": 75.3083267211914,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 3.6651,
       "step": 20
     }
   ],
   "logging_steps": 20,
-  "max_steps": 20,
+  "max_steps": 20000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 17506699161600.0,
+  "total_flos": 39042685440000.0,
   "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:aafe4b5783fda09fa4658a5b32dd84824c708b77a0e76c309db11ad31ee86141
+oid sha256:f81e09372397f7e5aa06ad532b71524705df27d8d386bc119142c8b4c15cf6b1
 size 4984