Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
     "k_proj",
     "up_proj",
-    "o_proj",
+    "q_proj",
+    "v_proj",
     "gate_proj",
-    "v_proj"
+    "o_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 sha256:7ad04d352bd28bcea2966a73dbdb833a2b17210fee0892d3d1af3dfaa8fa11a8
+oid sha256:9f45e46806d39471055a2f143c06d6a277b06145a23f2f6ba7a886680d16c08a
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b69a7e5d85e9f4098e4037be9bb29595bf461e68ab2b1e7ed5652258faf84f
+oid sha256:954f057c4a72c14fd2bf4aef0be43644027de816975ca56a0f4e7abcaf9763a4
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
+oid sha256:fd5570560c2d5878b2576c09a6170f9a8f99ca083bdaa5f34d36575a3cd13599
 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": 0.007667535654040792,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00015335071308081582,
+  "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": 0.00015335071308081582,
       "eval_loss": 10.366971015930176,
-      "eval_runtime": 12.3422,
-      "eval_samples_per_second": 222.488,
-      "eval_steps_per_second": 111.244,
+      "eval_runtime": 12.0434,
+      "eval_samples_per_second": 228.008,
+      "eval_steps_per_second": 114.004,
       "step": 1
-    },
-    {
-      "epoch": 0.0007667535654040791,
-      "grad_norm": 0.08022961020469666,
-      "learning_rate": 5e-05,
-      "loss": 10.3697,
-      "step": 5
-    },
-    {
-      "epoch": 0.0015335071308081583,
-      "grad_norm": 0.06305605173110962,
-      "learning_rate": 0.0001,
-      "loss": 10.3674,
-      "step": 10
-    },
-    {
-      "epoch": 0.0015335071308081583,
-      "eval_loss": 10.366765975952148,
-      "eval_runtime": 12.0611,
-      "eval_samples_per_second": 227.673,
-      "eval_steps_per_second": 113.837,
-      "step": 10
-    },
-    {
-      "epoch": 0.0023002606962122373,
-      "grad_norm": 0.10325485467910767,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 10.3689,
-      "step": 15
-    },
-    {
-      "epoch": 0.0030670142616163166,
-      "grad_norm": 0.07847774773836136,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 10.3697,
-      "step": 20
-    },
-    {
-      "epoch": 0.0030670142616163166,
-      "eval_loss": 10.366317749023438,
-      "eval_runtime": 12.3041,
-      "eval_samples_per_second": 223.177,
-      "eval_steps_per_second": 111.589,
-      "step": 20
-    },
-    {
-      "epoch": 0.003833767827020396,
-      "grad_norm": 0.06754478067159653,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 10.3658,
-      "step": 25
-    },
-    {
-      "epoch": 0.004600521392424475,
-      "grad_norm": 0.057355694472789764,
-      "learning_rate": 5e-05,
-      "loss": 10.3674,
-      "step": 30
-    },
-    {
-      "epoch": 0.004600521392424475,
-      "eval_loss": 10.365992546081543,
-      "eval_runtime": 12.3307,
-      "eval_samples_per_second": 222.696,
-      "eval_steps_per_second": 111.348,
-      "step": 30
-    },
-    {
-      "epoch": 0.005367274957828554,
-      "grad_norm": 0.07092428207397461,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 10.3656,
-      "step": 35
-    },
-    {
-      "epoch": 0.006134028523232633,
-      "grad_norm": 0.08720716089010239,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 10.3738,
-      "step": 40
-    },
-    {
-      "epoch": 0.006134028523232633,
-      "eval_loss": 10.36583423614502,
-      "eval_runtime": 12.1694,
-      "eval_samples_per_second": 225.649,
-      "eval_steps_per_second": 112.824,
-      "step": 40
-    },
-    {
-      "epoch": 0.006900782088636712,
-      "grad_norm": 0.056701041758060455,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 10.365,
-      "step": 45
-    },
-    {
-      "epoch": 0.007667535654040792,
-      "grad_norm": 0.06472200900316238,
-      "learning_rate": 0.0,
-      "loss": 10.3685,
-      "step": 50
-    },
-    {
-      "epoch": 0.007667535654040792,
-      "eval_loss": 10.365803718566895,
-      "eval_runtime": 12.0641,
-      "eval_samples_per_second": 227.617,
-      "eval_steps_per_second": 113.808,
-      "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": 646545408000.0,
+  "total_flos": 12930908160.0,
   "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 sha256:4163f3ebb95d2f51719a41232c9f33e0890f526268dc5666ae0400f8e955e398
+oid sha256:731472ace594f67d530eb785e2513404e4b5c221b0e656cee73c222617469847
 size 6776