Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "word_embeddings",
-    "query_key_valuelm_head"
+    "query_key_value"
   ],
   "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:b6b239758e5710fe78fd10d067ef696b9ecf7a57962dcbfc99ea16b5f0f15474
-size 13982248
+oid sha256:386f7859b4de007c7ae7c61ec6cb00a515d4711ba21b1c67d45d80097a8fa61d
+size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240c436b277f674752c771cab6fecf23fb9c30d6346d1eae1b590cffdd9c7a4a
-size 1128
+oid sha256:aa0685b12efbb09b894e2972c18a08bca793a00db99b574a7e0547cacf1ffdbf
+size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357fbaa636c40c1254d97d309539cc9555b5fab8ffbe087025279d50feec0849
+oid sha256:4435a7825b6133e5243ce242cb736cca7675210c39cbc95a71b79603a1500997
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f582b354f682a1388049ebe7692fec43d44fc4825862e8f8a7d835e907b849a9
+oid sha256:8f4b34a50c55a680830f99a77a52585bb05290e33d30ce86746475157ba56d09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002830335536277826,
+  "epoch": 3.1130100472399276e-05,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 0.0,
+      "grad_norm": 55.33664321899414,
       "learning_rate": 0.0,
-      "loss": 3.5917,
+      "loss": 3.9798,
       "step": 20
     }
   ],
@@ -21,8 +21,8 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 49799375290368.0,
-  "train_batch_size": 8,
+  "total_flos": 17506699161600.0,
+  "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:b6c34bfd1caa32715f73ad2763e8f79f467c0f7f673199f1db21d933e08b71a2
+oid sha256:aafe4b5783fda09fa4658a5b32dd84824c708b77a0e76c309db11ad31ee86141
 size 4984