Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
     "gate_proj",
-    "down_proj"
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_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 sha256:4516049e17f41a15b4829536d25def8f22fc78575118c3cefacd520a4fc781fd
+oid sha256:dbc2fe9bfd1c3d414f94ce7e851dd47c348358905c4a54d63d3e0ee7e677805e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e0d0d9547202b50e9a8d096491eefcc9ee2a554cf3725b431068efffe37c47
+oid sha256:a852edc467957eca7c4f682da4a46eac458d5336f8f7e99b91f0fd882d3d516e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6beb92e82d89b74efdd456fb9bf2b41610797ca90b007f020dc4fb8145708801
+oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
 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": 0.003770810158562567,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 7.541620317125135e-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": 7.541620317125135e-05,
       "eval_loss": 2.0435900688171387,
-      "eval_runtime": 665.4247,
-      "eval_samples_per_second": 8.392,
-      "eval_steps_per_second": 4.196,
+      "eval_runtime": 656.559,
+      "eval_samples_per_second": 8.505,
+      "eval_steps_per_second": 4.252,
       "step": 1
-    },
-    {
-      "epoch": 0.0003770810158562567,
-      "grad_norm": 2.116191864013672,
-      "learning_rate": 5e-05,
-      "loss": 2.0936,
-      "step": 5
-    },
-    {
-      "epoch": 0.0007541620317125134,
-      "grad_norm": 1.9126191139221191,
-      "learning_rate": 0.0001,
-      "loss": 1.8052,
-      "step": 10
-    },
-    {
-      "epoch": 0.0007541620317125134,
-      "eval_loss": 1.2857778072357178,
-      "eval_runtime": 669.1514,
-      "eval_samples_per_second": 8.345,
-      "eval_steps_per_second": 4.172,
-      "step": 10
-    },
-    {
-      "epoch": 0.0011312430475687702,
-      "grad_norm": 1.9551734924316406,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.9694,
-      "step": 15
-    },
-    {
-      "epoch": 0.0015083240634250269,
-      "grad_norm": 1.7354230880737305,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.7,
-      "step": 20
-    },
-    {
-      "epoch": 0.0015083240634250269,
-      "eval_loss": 0.6742600798606873,
-      "eval_runtime": 670.7305,
-      "eval_samples_per_second": 8.325,
-      "eval_steps_per_second": 4.163,
-      "step": 20
-    },
-    {
-      "epoch": 0.0018854050792812835,
-      "grad_norm": 1.9610943794250488,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.6783,
-      "step": 25
-    },
-    {
-      "epoch": 0.0022624860951375404,
-      "grad_norm": 1.485725998878479,
-      "learning_rate": 5e-05,
-      "loss": 0.5881,
-      "step": 30
-    },
-    {
-      "epoch": 0.0022624860951375404,
-      "eval_loss": 0.5489432215690613,
-      "eval_runtime": 667.7804,
-      "eval_samples_per_second": 8.362,
-      "eval_steps_per_second": 4.181,
-      "step": 30
-    },
-    {
-      "epoch": 0.002639567110993797,
-      "grad_norm": 1.5018064975738525,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.569,
-      "step": 35
-    },
-    {
-      "epoch": 0.0030166481268500537,
-      "grad_norm": 1.476067066192627,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.5314,
-      "step": 40
-    },
-    {
-      "epoch": 0.0030166481268500537,
-      "eval_loss": 0.5157779455184937,
-      "eval_runtime": 664.516,
-      "eval_samples_per_second": 8.403,
-      "eval_steps_per_second": 4.202,
-      "step": 40
-    },
-    {
-      "epoch": 0.0033937291427063106,
-      "grad_norm": 1.6906317472457886,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.4455,
-      "step": 45
-    },
-    {
-      "epoch": 0.003770810158562567,
-      "grad_norm": 1.3468632698059082,
-      "learning_rate": 0.0,
-      "loss": 0.4905,
-      "step": 50
-    },
-    {
-      "epoch": 0.003770810158562567,
-      "eval_loss": 0.5104564428329468,
-      "eval_runtime": 667.6626,
-      "eval_samples_per_second": 8.364,
-      "eval_steps_per_second": 4.182,
-      "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": 1.780205588840448e+16,
+  "total_flos": 369912849629184.0,
   "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 sha256:41f95d7d211663de3a6cbb869c3e4b1b34984af1e4125b5a95c029829bf37fd4
+oid sha256:e1bb008edf60cc70269feaeab16b31dd1b4dde9796b645dec954455665868925
 size 6776