Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
-    "v_proj",
     "up_proj",
+    "k_proj",
     "o_proj",
+    "v_proj",
     "q_proj",
-    "k_proj"
+    "down_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 sha256:871bfe0c97cf67f9c8da7c5f1bb15eccfa17f6da34a7e7ef35d80803339f346f
+oid sha256:dd1749af2c53b776fe9b79e858bb8e1f1ee5c3fb2b91753546e649185d87e712
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84dbb8c1445f36cb0de060b3c3002cc75502974974c8c8a8b85ae947ff54cb14
+oid sha256:e53b64058491e3ede053f37a8e69d6ed56eba2c103a167853a127a0849687712
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f70044af2bf806d36eee202f06cd6fe1ee465e8a1d9f7ce321d93c2a261931e
+oid sha256:7bb5dd3632f621f63027a71316dd458a1d0eb2cb6f6bdb9c2be6da1bb386cb19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006385614487682149,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 1.2771228975364299e-05,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 1.2771228975364299e-05,
       "eval_loss": 2.566653251647949,
-      "eval_runtime": 1243.7929,
-      "eval_samples_per_second": 26.507,
-      "eval_steps_per_second": 13.254,
+      "eval_runtime": 1209.8868,
+      "eval_samples_per_second": 27.25,
+      "eval_steps_per_second": 13.625,
       "step": 1
-    },
-    {
-      "epoch": 6.38561448768215e-05,
-      "grad_norm": 0.4447006285190582,
-      "learning_rate": 5e-05,
-      "loss": 2.5535,
-      "step": 5
-    },
-    {
-      "epoch": 0.000127712289753643,
-      "grad_norm": 0.5098279714584351,
-      "learning_rate": 0.0001,
-      "loss": 2.5961,
-      "step": 10
-    },
-    {
-      "epoch": 0.000127712289753643,
-      "eval_loss": 2.474618673324585,
-      "eval_runtime": 1232.6015,
-      "eval_samples_per_second": 26.747,
-      "eval_steps_per_second": 13.374,
-      "step": 10
-    },
-    {
-      "epoch": 0.0001915684346304645,
-      "grad_norm": 0.6390445828437805,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.3093,
-      "step": 15
-    },
-    {
-      "epoch": 0.000255424579507286,
-      "grad_norm": 1.3653255701065063,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 2.1242,
-      "step": 20
-    },
-    {
-      "epoch": 0.000255424579507286,
-      "eval_loss": 2.100123167037964,
-      "eval_runtime": 1242.7158,
-      "eval_samples_per_second": 26.53,
-      "eval_steps_per_second": 13.265,
-      "step": 20
-    },
-    {
-      "epoch": 0.00031928072438410746,
-      "grad_norm": 0.813316285610199,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.0565,
-      "step": 25
-    },
-    {
-      "epoch": 0.000383136869260929,
-      "grad_norm": 0.8100643157958984,
-      "learning_rate": 5e-05,
-      "loss": 2.0235,
-      "step": 30
-    },
-    {
-      "epoch": 0.000383136869260929,
-      "eval_loss": 1.9638915061950684,
-      "eval_runtime": 1238.8703,
-      "eval_samples_per_second": 26.612,
-      "eval_steps_per_second": 13.306,
-      "step": 30
-    },
-    {
-      "epoch": 0.00044699301413775045,
-      "grad_norm": 0.8723477125167847,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 1.9767,
-      "step": 35
-    },
-    {
-      "epoch": 0.000510849159014572,
-      "grad_norm": 0.7385880947113037,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 1.9297,
-      "step": 40
-    },
-    {
-      "epoch": 0.000510849159014572,
-      "eval_loss": 1.923941731452942,
-      "eval_runtime": 1249.2037,
-      "eval_samples_per_second": 26.392,
-      "eval_steps_per_second": 13.196,
-      "step": 40
-    },
-    {
-      "epoch": 0.0005747053038913935,
-      "grad_norm": 0.838437020778656,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.9813,
-      "step": 45
-    },
-    {
-      "epoch": 0.0006385614487682149,
-      "grad_norm": 0.8514693379402161,
-      "learning_rate": 0.0,
-      "loss": 2.0379,
-      "step": 50
-    },
-    {
-      "epoch": 0.0006385614487682149,
-      "eval_loss": 1.9171334505081177,
-      "eval_runtime": 1246.8552,
-      "eval_samples_per_second": 26.442,
-      "eval_steps_per_second": 13.221,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4100243324928000.0,
+  "total_flos": 82004866498560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7efb209d159a83ecc2ac37c64ddc270bd468f61262659a12ba2c89113dfa4c32
+oid sha256:8b665d3dfc9a743ca931ce03a978e9f6e01e0006349e49ca61276e24f0c339f0
 size 6776