Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "o_proj",
     "up_proj",
+    "gate_proj",
     "v_proj",
     "q_proj",
-    "down_proj",
-    "gate_proj",
-    "o_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:d665ce24347200e3f9f0f7860eab24dd497eef1b0242f621221081156c92ee11
+oid sha256:99665eb628c8bd5c0dd93a7e09c267fcc72bd4bb9356e20a1ef0d0d775204dde
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19cb011e6e67803346cf79ce198a1005783b77bc4c591ef75e1e77295da36ac
+oid sha256:7a1080c9d277b85afcbb5a7d4774379c5dcb6b3df9a38625b087fef3c6c876b1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c74673ff0bc06cd0ebb7731d803776a08382f09fba4601b17e24ff25336eaa
+oid sha256:b309c5fb8ceac2de6f0e2a441d11cf72ab86ab68ca40b3a011f862d7c995cabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004701457451810061,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0061118946873530795,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0004701457451810061,
       "eval_loss": NaN,
-      "eval_runtime": 143.4113,
-      "eval_samples_per_second": 6.248,
-      "eval_steps_per_second": 3.124,
+      "eval_runtime": 73.554,
+      "eval_samples_per_second": 12.182,
+      "eval_steps_per_second": 6.091,
       "step": 1
+    },
+    {
+      "epoch": 0.0023507287259050304,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.004701457451810061,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.004701457451810061,
+      "eval_loss": NaN,
+      "eval_runtime": 64.9436,
+      "eval_samples_per_second": 13.797,
+      "eval_steps_per_second": 6.898,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 205395528253440.0,
+  "total_flos": 2505825444691968.0,
   "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:fb7c5dd0dcabe3c7bf0320613e451e16a60bec129b944ebf5237dc826085bc5d
+oid sha256:47aa5d394af400801aeba0892d10ef713615f6e3d342e5b8108f36ab6db3daa6
 size 6776