Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "k_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj",
-    "up_proj",
-    "k_proj"
+    "v_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:b5f7a7963885db4dc310ee8f76db3a08d585f533da4547fe69e42368db10d734
+oid sha256:d210a10363940a6e2c63cbe1901eb13c2ed206e3a52742be2cc366196a730717
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2d31b5562d14f92f44dd1e2518783015885d4795ce22031525d66185696a83
+oid sha256:05b62843c3ceae2742cad35edb9c09ec58e4fa7c4f671c6e6a65b78c4ac4aa0c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185c6777879539a9f22be57c224b405abde7e14139e163784ea7475d86392d87
+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

@@ -1,137 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022629554197782304,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00045259108395564606,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00045259108395564606,
-      "eval_loss": 0.4409753978252411,
-      "eval_runtime": 117.141,
-      "eval_samples_per_second": 7.948,
-      "eval_steps_per_second": 3.978,
+      "eval_loss": 0.4409754276275635,
+      "eval_runtime": 118.8995,
+      "eval_samples_per_second": 7.83,
+      "eval_steps_per_second": 3.919,
       "step": 1
-    },
-    {
-      "epoch": 0.0022629554197782305,
-      "grad_norm": 0.2900209426879883,
-      "learning_rate": 5e-05,
-      "loss": 0.4615,
-      "step": 5
-    },
-    {
-      "epoch": 0.004525910839556461,
-      "grad_norm": 0.3633456826210022,
-      "learning_rate": 0.0001,
-      "loss": 0.4525,
-      "step": 10
-    },
-    {
-      "epoch": 0.004525910839556461,
-      "eval_loss": 0.40355947613716125,
-      "eval_runtime": 118.0867,
-      "eval_samples_per_second": 7.884,
-      "eval_steps_per_second": 3.946,
-      "step": 10
-    },
-    {
-      "epoch": 0.006788866259334691,
-      "grad_norm": 0.3920026421546936,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.3771,
-      "step": 15
-    },
-    {
-      "epoch": 0.009051821679112922,
-      "grad_norm": 0.40389373898506165,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.3544,
-      "step": 20
-    },
-    {
-      "epoch": 0.009051821679112922,
-      "eval_loss": 0.3478299677371979,
-      "eval_runtime": 118.3316,
-      "eval_samples_per_second": 7.868,
-      "eval_steps_per_second": 3.938,
-      "step": 20
-    },
-    {
-      "epoch": 0.011314777098891152,
-      "grad_norm": 0.2958144545555115,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.3066,
-      "step": 25
-    },
-    {
-      "epoch": 0.013577732518669382,
-      "grad_norm": 0.38287678360939026,
-      "learning_rate": 5e-05,
-      "loss": 0.3844,
-      "step": 30
-    },
-    {
-      "epoch": 0.013577732518669382,
-      "eval_loss": 0.3295285105705261,
-      "eval_runtime": 118.5238,
-      "eval_samples_per_second": 7.855,
-      "eval_steps_per_second": 3.932,
-      "step": 30
-    },
-    {
-      "epoch": 0.015840687938447614,
-      "grad_norm": 0.3919980525970459,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.3412,
-      "step": 35
-    },
-    {
-      "epoch": 0.018103643358225844,
-      "grad_norm": 0.35930296778678894,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.2881,
-      "step": 40
-    },
-    {
-      "epoch": 0.018103643358225844,
-      "eval_loss": 0.3223743736743927,
-      "eval_runtime": 118.489,
-      "eval_samples_per_second": 7.857,
-      "eval_steps_per_second": 3.933,
-      "step": 40
-    },
-    {
-      "epoch": 0.020366598778004074,
-      "grad_norm": 0.34937289357185364,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.3376,
-      "step": 45
-    },
-    {
-      "epoch": 0.022629554197782304,
-      "grad_norm": 0.35940036177635193,
-      "learning_rate": 0.0,
-      "loss": 0.3535,
-      "step": 50
-    },
-    {
-      "epoch": 0.022629554197782304,
-      "eval_loss": 0.3209822475910187,
-      "eval_runtime": 118.1497,
-      "eval_samples_per_second": 7.88,
-      "eval_steps_per_second": 3.944,
-      "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": 1.8171978628202496e+16,
+  "total_flos": 369913050955776.0,
   "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:dbe43e5cddf114f955db5c1272312ed7102a4da681c48149b0cdd044ed4408b5
+oid sha256:952ce1327b846b4f5d6a24f14e67874f8035e5cba8d5d9262b4d410d0112f287
 size 6776