Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "k_proj",
     "up_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
     "o_proj",
-    "gate_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:e267fbb042d3d59301d0ef7b397bd6003613a16e163d64e2fae9bbc5af2dfb95
+oid sha256:1c67b2d622363724fa52c3c0b194a11bf8ee8727aba4d524360f7caa4924eaf3
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24a10a944a221d168e2e179f477d4be2583e0a3606b3c552cf305c36db60032
+oid sha256:03ac757efc8757e97e6b66e9eda027d877ed8c19194f90ba46eb0c3d8a0bf92e
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae74ed5d8d7aa05e9979453feeae1039a93fc9dab62d2c41cef08e8a6ffd3dd
+oid sha256:81b0fa30ce7d6caf58ef5c2227062e5ee5947fe33564486703caa8d601663ea6
 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": 0.05807200929152149,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0011614401858304297,
+  "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": 0.0011614401858304297,
       "eval_loss": 10.543993949890137,
-      "eval_runtime": 15.6135,
-      "eval_samples_per_second": 23.249,
-      "eval_steps_per_second": 11.657,
+      "eval_runtime": 15.6722,
+      "eval_samples_per_second": 23.162,
+      "eval_steps_per_second": 11.613,
       "step": 1
-    },
-    {
-      "epoch": 0.005807200929152149,
-      "grad_norm": 18.068403244018555,
-      "learning_rate": 5e-05,
-      "loss": 11.0168,
-      "step": 5
-    },
-    {
-      "epoch": 0.011614401858304297,
-      "grad_norm": 14.69466495513916,
-      "learning_rate": 0.0001,
-      "loss": 9.1681,
-      "step": 10
-    },
-    {
-      "epoch": 0.011614401858304297,
-      "eval_loss": 8.221834182739258,
-      "eval_runtime": 13.6255,
-      "eval_samples_per_second": 26.641,
-      "eval_steps_per_second": 13.357,
-      "step": 10
-    },
-    {
-      "epoch": 0.017421602787456445,
-      "grad_norm": 16.43670082092285,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 7.1597,
-      "step": 15
-    },
-    {
-      "epoch": 0.023228803716608595,
-      "grad_norm": 10.922114372253418,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 4.1271,
-      "step": 20
-    },
-    {
-      "epoch": 0.023228803716608595,
-      "eval_loss": 2.9729020595550537,
-      "eval_runtime": 13.619,
-      "eval_samples_per_second": 26.654,
-      "eval_steps_per_second": 13.364,
-      "step": 20
-    },
-    {
-      "epoch": 0.029036004645760744,
-      "grad_norm": 11.228082656860352,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.7945,
-      "step": 25
-    },
-    {
-      "epoch": 0.03484320557491289,
-      "grad_norm": 5.589913845062256,
-      "learning_rate": 5e-05,
-      "loss": 1.0625,
-      "step": 30
-    },
-    {
-      "epoch": 0.03484320557491289,
-      "eval_loss": 0.8721647262573242,
-      "eval_runtime": 13.7754,
-      "eval_samples_per_second": 26.351,
-      "eval_steps_per_second": 13.212,
-      "step": 30
-    },
-    {
-      "epoch": 0.04065040650406504,
-      "grad_norm": 7.702680587768555,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.7803,
-      "step": 35
-    },
-    {
-      "epoch": 0.04645760743321719,
-      "grad_norm": 5.1860737800598145,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.5171,
-      "step": 40
-    },
-    {
-      "epoch": 0.04645760743321719,
-      "eval_loss": 0.40528592467308044,
-      "eval_runtime": 14.0812,
-      "eval_samples_per_second": 25.779,
-      "eval_steps_per_second": 12.925,
-      "step": 40
-    },
-    {
-      "epoch": 0.05226480836236934,
-      "grad_norm": 5.927870273590088,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.3046,
-      "step": 45
-    },
-    {
-      "epoch": 0.05807200929152149,
-      "grad_norm": 3.9271230697631836,
-      "learning_rate": 0.0,
-      "loss": 0.4715,
-      "step": 50
-    },
-    {
-      "epoch": 0.05807200929152149,
-      "eval_loss": 0.34220945835113525,
-      "eval_runtime": 13.9897,
-      "eval_samples_per_second": 25.948,
-      "eval_steps_per_second": 13.01,
-      "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": 713531364212736.0,
+  "total_flos": 15344760520704.0,
   "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 sha256:53d6f6c2c123de55f6a3a7a3fc94cebd87e4235d9022a8608fa26c83c3a43793
+oid sha256:b6da68b9dccc9797752e82795ecd556d16bfa0452de13085898654dfe8661752
 size 6776