Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "k_proj",
-    "gate_proj",
+    "v_proj",
     "o_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
-    "v_proj"
+    "gate_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:b9a82e6c0a637474c68f24ab7674c53c6c442787afe381f4f42db778619b351a
+oid sha256:2a012cb95fcd31e3ddf3d73f530f6892701cb8aa30c8e3573fa465de3c1576dd
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdbf8b4e0d38d84a73a9264e02a1dd3a5ad811d990faf1f8069246718ff02aae
+oid sha256:b3e14587f9abb0ed36fce5a54dff59d8b90fc1a3a1ccb7822adbd2a7d630958d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
+oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
 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": 0.0008680781617576847,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 1.7361563235153692e-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": 1.7361563235153692e-05,
       "eval_loss": 3.2406625747680664,
-      "eval_runtime": 1579.9553,
-      "eval_samples_per_second": 15.35,
-      "eval_steps_per_second": 7.675,
+      "eval_runtime": 1564.8666,
+      "eval_samples_per_second": 15.498,
+      "eval_steps_per_second": 7.749,
       "step": 1
-    },
-    {
-      "epoch": 8.680781617576846e-05,
-      "grad_norm": 56.969181060791016,
-      "learning_rate": 5e-05,
-      "loss": 12.0664,
-      "step": 5
-    },
-    {
-      "epoch": 0.00017361563235153692,
-      "grad_norm": 48.02027130126953,
-      "learning_rate": 0.0001,
-      "loss": 8.5399,
-      "step": 10
-    },
-    {
-      "epoch": 0.00017361563235153692,
-      "eval_loss": 1.7465617656707764,
-      "eval_runtime": 1583.1765,
-      "eval_samples_per_second": 15.319,
-      "eval_steps_per_second": 7.659,
-      "step": 10
-    },
-    {
-      "epoch": 0.0002604234485273054,
-      "grad_norm": 24.002090454101562,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 6.8368,
-      "step": 15
-    },
-    {
-      "epoch": 0.00034723126470307384,
-      "grad_norm": 22.417949676513672,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 6.5063,
-      "step": 20
-    },
-    {
-      "epoch": 0.00034723126470307384,
-      "eval_loss": 1.3497487306594849,
-      "eval_runtime": 1582.5355,
-      "eval_samples_per_second": 15.325,
-      "eval_steps_per_second": 7.662,
-      "step": 20
-    },
-    {
-      "epoch": 0.00043403908087884236,
-      "grad_norm": 26.679052352905273,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 5.296,
-      "step": 25
-    },
-    {
-      "epoch": 0.0005208468970546108,
-      "grad_norm": 23.542726516723633,
-      "learning_rate": 5e-05,
-      "loss": 5.1197,
-      "step": 30
-    },
-    {
-      "epoch": 0.0005208468970546108,
-      "eval_loss": 1.267897367477417,
-      "eval_runtime": 1579.6304,
-      "eval_samples_per_second": 15.353,
-      "eval_steps_per_second": 7.676,
-      "step": 30
-    },
-    {
-      "epoch": 0.0006076547132303793,
-      "grad_norm": 19.179880142211914,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 4.7048,
-      "step": 35
-    },
-    {
-      "epoch": 0.0006944625294061477,
-      "grad_norm": 19.000234603881836,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 5.4107,
-      "step": 40
-    },
-    {
-      "epoch": 0.0006944625294061477,
-      "eval_loss": 1.2511236667633057,
-      "eval_runtime": 1584.0605,
-      "eval_samples_per_second": 15.31,
-      "eval_steps_per_second": 7.655,
-      "step": 40
-    },
-    {
-      "epoch": 0.0007812703455819162,
-      "grad_norm": 22.011131286621094,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 5.3537,
-      "step": 45
-    },
-    {
-      "epoch": 0.0008680781617576847,
-      "grad_norm": 17.464994430541992,
-      "learning_rate": 0.0,
-      "loss": 4.3659,
-      "step": 50
-    },
-    {
-      "epoch": 0.0008680781617576847,
-      "eval_loss": 1.2439897060394287,
-      "eval_runtime": 1587.0763,
-      "eval_samples_per_second": 15.281,
-      "eval_steps_per_second": 7.64,
-      "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": 8763509991014400.0,
+  "total_flos": 175270199820288.0,
   "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 sha256:561cdbc68f943c8e8087aeb44c56cd0b85133b29ad816d9b062466523f34fed2
+oid sha256:32fcfe3114d903bf5a9323fba1c465c56294841a3ea32f765f68aea420a55532
 size 6776