Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "q_proj",
-    "k_proj",
+    "up_proj",
     "down_proj",
+    "o_proj",
+    "k_proj",
     "v_proj",
-    "o_proj"
+    "gate_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:aea35ca66e09d98625e2ed12d2671d6d48d1e53c87e017a98e0fb3db97c86ff4
+oid sha256:37f49fefe628530aca56863a5cfa56b3fafa7925fc1ac1a885f0b1ff46f9cb57
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd325714ad083bc2c17dc83f95bac7a0c25f3a912a8c25f32eb89535d0d716f8
+oid sha256:bb9e848007c2945edb6a1091aa4731b873d8343b268d9e69711a70f12cd2ccd9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 0.004571428571428572,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.05942857142857143,
+  "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": 0.004571428571428572,
       "eval_loss": 2.6391401290893555,
-      "eval_runtime": 16.2987,
-      "eval_samples_per_second": 5.706,
-      "eval_steps_per_second": 2.884,
+      "eval_runtime": 16.3106,
+      "eval_samples_per_second": 5.702,
+      "eval_steps_per_second": 2.882,
       "step": 1
+    },
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 0.6253376007080078,
+      "learning_rate": 5e-05,
+      "loss": 2.6482,
+      "step": 5
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.686288058757782,
+      "learning_rate": 0.0001,
+      "loss": 2.7664,
+      "step": 10
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "eval_loss": 2.545773983001709,
+      "eval_runtime": 17.3817,
+      "eval_samples_per_second": 5.35,
+      "eval_steps_per_second": 2.704,
+      "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": 369912849629184.0,
+  "total_flos": 4808867045179392.0,
   "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 sha256:5466c42b47990f76dbed25cd8bb6e9389e867275d8e292d4867f5865c7fdfac7
+oid sha256:fe879f58435619e0ee1a31e2c8655eef056bca46054d0ab93f748c469eaf9915
 size 6776