Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "v_proj",
-    "q_proj",
-    "gate_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
-    "down_proj",
-    "k_proj"
+    "gate_proj",
+    "q_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:dc0ab9ba34cc4e7412821fa8f3d4e3780e187942d03bf0cf17441bdd2285cb41
+oid sha256:3b2c055b3868f78d2fc5134cdb3b1f749974784e02ad48dce37c75ef231cdc7a
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ab5d6149c23c7a0574e94756be555cd973a8957a447b593408d27a65b8de65
+oid sha256:43efa1a55fde744f4e4aa986ebd3fec23717f74003ca2f2dc88403fae1561be7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
+oid sha256:0fa1bb1091058b70e986852c5817815bf8a4d14bf29aaa636318d9694ad55b4a
 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": 6.13299397433342e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007972892166633447,
+  "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": 6.13299397433342e-05,
       "eval_loss": 2.1146581172943115,
-      "eval_runtime": 265.2648,
-      "eval_samples_per_second": 25.884,
-      "eval_steps_per_second": 12.942,
+      "eval_runtime": 271.7079,
+      "eval_samples_per_second": 25.27,
+      "eval_steps_per_second": 12.635,
       "step": 1
+    },
+    {
+      "epoch": 0.000306649698716671,
+      "grad_norm": 0.4814217686653137,
+      "learning_rate": 5e-05,
+      "loss": 2.122,
+      "step": 5
+    },
+    {
+      "epoch": 0.000613299397433342,
+      "grad_norm": 0.4163660407066345,
+      "learning_rate": 0.0001,
+      "loss": 2.1498,
+      "step": 10
+    },
+    {
+      "epoch": 0.000613299397433342,
+      "eval_loss": 2.0929524898529053,
+      "eval_runtime": 270.9012,
+      "eval_samples_per_second": 25.345,
+      "eval_steps_per_second": 12.673,
+      "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": 32429825851392.0,
+  "total_flos": 486447387770880.0,
   "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:ad7fd458d16718965917338f529ca04e6bf0c83c8a2e2f7cec2dcd917fe70c17
+oid sha256:bedb7859ffc35c26ff5927bf40fd0a4ee75a1e228968566602cca463e288e16a
 size 6776