Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
     "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
     "gate_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:cfe203efd6e2f43f9f737333241ec880b67a59b939847930f87bcf9276cea614
+oid sha256:c3d4d7deec4ff3f8a752a2e584e256246fe62964cd2d0f443fb6894292f5cc7a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62aa1b20954be3e46b592006f661948ebaa811d02a69015f553cb4c230302544
+oid sha256:b7d58adcba5a2e5f29255a9548a74de04a6933293cdab9ade3b397cfea2b050c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
+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": 0.000885696445257317,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 1.771392890514634e-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": 1.771392890514634e-05,
       "eval_loss": 10.875212669372559,
-      "eval_runtime": 1582.7534,
-      "eval_samples_per_second": 15.018,
-      "eval_steps_per_second": 7.509,
+      "eval_runtime": 1590.6275,
+      "eval_samples_per_second": 14.944,
+      "eval_steps_per_second": 7.472,
       "step": 1
-    },
-    {
-      "epoch": 8.85696445257317e-05,
-      "grad_norm": 10.420663833618164,
-      "learning_rate": 5e-05,
-      "loss": 9.9355,
-      "step": 5
-    },
-    {
-      "epoch": 0.0001771392890514634,
-      "grad_norm": 16.734085083007812,
-      "learning_rate": 0.0001,
-      "loss": 10.519,
-      "step": 10
-    },
-    {
-      "epoch": 0.0001771392890514634,
-      "eval_loss": 8.125746726989746,
-      "eval_runtime": 1584.2923,
-      "eval_samples_per_second": 15.004,
-      "eval_steps_per_second": 7.502,
-      "step": 10
-    },
-    {
-      "epoch": 0.00026570893357719507,
-      "grad_norm": 19.977203369140625,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 5.6098,
-      "step": 15
-    },
-    {
-      "epoch": 0.0003542785781029268,
-      "grad_norm": 12.790882110595703,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 2.4823,
-      "step": 20
-    },
-    {
-      "epoch": 0.0003542785781029268,
-      "eval_loss": 2.3625357151031494,
-      "eval_runtime": 1581.1351,
-      "eval_samples_per_second": 15.034,
-      "eval_steps_per_second": 7.517,
-      "step": 20
-    },
-    {
-      "epoch": 0.0004428482226286585,
-      "grad_norm": 11.51273250579834,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 1.8262,
-      "step": 25
-    },
-    {
-      "epoch": 0.0005314178671543901,
-      "grad_norm": 12.141860961914062,
-      "learning_rate": 5e-05,
-      "loss": 1.6263,
-      "step": 30
-    },
-    {
-      "epoch": 0.0005314178671543901,
-      "eval_loss": 1.721574068069458,
-      "eval_runtime": 1588.3277,
-      "eval_samples_per_second": 14.965,
-      "eval_steps_per_second": 7.483,
-      "step": 30
-    },
-    {
-      "epoch": 0.0006199875116801219,
-      "grad_norm": 16.959461212158203,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 1.6185,
-      "step": 35
-    },
-    {
-      "epoch": 0.0007085571562058535,
-      "grad_norm": 6.89641809463501,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 1.4555,
-      "step": 40
-    },
-    {
-      "epoch": 0.0007085571562058535,
-      "eval_loss": 1.518613576889038,
-      "eval_runtime": 1589.0732,
-      "eval_samples_per_second": 14.958,
-      "eval_steps_per_second": 7.479,
-      "step": 40
-    },
-    {
-      "epoch": 0.0007971268007315853,
-      "grad_norm": 9.788350105285645,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.1805,
-      "step": 45
-    },
-    {
-      "epoch": 0.000885696445257317,
-      "grad_norm": 10.444169998168945,
-      "learning_rate": 0.0,
-      "loss": 1.3808,
-      "step": 50
-    },
-    {
-      "epoch": 0.000885696445257317,
-      "eval_loss": 1.495301604270935,
-      "eval_runtime": 1584.3918,
-      "eval_samples_per_second": 15.003,
-      "eval_steps_per_second": 7.501,
-      "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": 9386538559340544.0,
+  "total_flos": 184956424814592.0,
   "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 sha256:3de38f119b0da98e5a7817400adbe070b14826c99bd779f51ce779d6cae9f906
+oid sha256:41fd5ff0c930881bcc5d0637ecb02ea37370d229c463653e5c95adabd6f4b34c
 size 6776