Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
-    "v_proj",
+    "down_proj",
     "o_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad41327481ec874aa76d498bfc49a1907ea9fc4626072563efe1c9efde6cba5
+oid sha256:b799260f63996557fcebb14b617ff32e2c46661a83a29c012c91d9b00d721e98
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b57ede50b1fd5acde507208bd54ae1c26818722d3cf99ff38cf3fa2e25069a
+oid sha256:d4edf804f14d70effb770a9524d2c48acb139c801042e65c1f98ea57ae264faa
 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": 0.019138755980861243,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.24880382775119617,
+  "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": 0.019138755980861243,
       "eval_loss": 0.7566470503807068,
-      "eval_runtime": 4.1205,
-      "eval_samples_per_second": 5.582,
-      "eval_steps_per_second": 2.912,
+      "eval_runtime": 4.1261,
+      "eval_samples_per_second": 5.574,
+      "eval_steps_per_second": 2.908,
       "step": 1
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 0.9212210774421692,
+      "learning_rate": 5e-05,
+      "loss": 0.6801,
+      "step": 5
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 0.8981757760047913,
+      "learning_rate": 0.0001,
+      "loss": 0.61,
+      "step": 10
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "eval_loss": 0.4450052082538605,
+      "eval_runtime": 4.3641,
+      "eval_samples_per_second": 5.27,
+      "eval_steps_per_second": 2.75,
+      "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 sha256:273195c1469dec0a5a3c2741698363b7afe036d8b2e74fb72bca3a9460668d3b
+oid sha256:96d795142fa2758f710e1658d0d731a980b8a2fa6af78a8c9ea72dcaa7c1ccec
 size 6776