Training in progress, step 20000, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "q_proj",
-    "o_proj",
-    "k_proj",
     "gate_proj",
     "down_proj",
     "up_proj",
-    "v_proj"
+    "k_proj",
+    "o_proj"
   ],
   "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 sha256:30377e3553033d932e69daa7064c259e8a7335e5cc0b78f6a1f4f648bae4b97e
+oid sha256:fb5d4a8e80692092cbb6ea69a8cd6902d7306436bd2ef4db3d268beb6d254345
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727033a6eb5dc35337334fe86877b4a8995db5404205b07aeda22261d1e1f288
+oid sha256:5ed3c0ef76d1963f5e466fac078e7bdfa634f48c1b91aaad0c42e6ae39ac1315
 size 85736914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7de94d4e3bf0d0cab47bcde24f41cd7eb97ed0885fd609023fab02c6a16228
+oid sha256:adc80d060b3614ce93cf171cfa62b9a17755ba93a67b6a802cd87b68b0a907bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf318569a9b4769e81e4790eccd85435a6e6935dc6ee58b1ecc55958c1b71bd0
+oid sha256:55ba296f12eae4fc0511f08bee2c4fc9bf546a7ddf44e3e343ade2d2cae2ed71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028259196323329825,
+  "epoch": 0.02974652244561034,
   "eval_steps": 2000,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -672,6 +672,41 @@
       "learning_rate": 1.9998426349986698e-05,
       "loss": 1.5367,
       "step": 19000
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.7834692001342773,
+      "learning_rate": 1.9998393186348416e-05,
+      "loss": 1.5619,
+      "step": 19200
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.51110577583313,
+      "learning_rate": 1.9998359507659452e-05,
+      "loss": 1.5688,
+      "step": 19400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.6746368408203125,
+      "learning_rate": 1.999832547969925e-05,
+      "loss": 1.5216,
+      "step": 19600
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.6558778285980225,
+      "learning_rate": 1.9998291102469e-05,
+      "loss": 1.5335,
+      "step": 19800
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.4056808948516846,
+      "learning_rate": 1.99982565504712e-05,
+      "loss": 1.5135,
+      "step": 20000
     }
   ],
   "logging_steps": 200,
@@ -679,7 +714,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 3.4393054952298086e+17,
+  "total_flos": 3.6983529369430426e+17,
   "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:fc9e75826f834526adf57daa4ee7a58f88bf2ec9679f7599af2037d01589eb4f
+oid sha256:7da6c64555cac2ee9fc43605b134636b4610ed6cd244e07ab7cb4ce3c058548c
 size 4920