Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
     "v_proj",
     "gate_proj",
-    "q_proj",
-    "down_proj"
+    "down_proj",
+    "o_proj",
+    "up_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 sha256:936b5bbf9210811dc41ace0ab6c1be8c0721237891fb1f90981359d5386f10b5
+oid sha256:01a71fc3698d2e3f462c9a0dd186f3e14caf2697d67ba40f2b4ef7ae3955c05c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235c0122b2f5e6be6653e20340b2a67af194ea3783cdf4048dea792dbd81f1bb
+oid sha256:7281d4fb1e821d803ec266f6e047c939dc1abdc5a6e1f55539edf5ef64bb4a64
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:249af31433a811d65c1ae082c753c9b8dc8a88ab84d6f96baca95f6fc1550bdc
 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": 0.010230179028132993,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.1329923273657289,
+  "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": 0.010230179028132993,
       "eval_loss": 2.483304738998413,
-      "eval_runtime": 5.4401,
+      "eval_runtime": 5.4403,
       "eval_samples_per_second": 7.72,
       "eval_steps_per_second": 3.86,
       "step": 1
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 26.666269302368164,
+      "learning_rate": 5e-05,
+      "loss": 10.9039,
+      "step": 5
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 15.509090423583984,
+      "learning_rate": 0.0001,
+      "loss": 10.4859,
+      "step": 10
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "eval_loss": 2.162769079208374,
+      "eval_runtime": 5.6657,
+      "eval_samples_per_second": 7.413,
+      "eval_steps_per_second": 3.706,
+      "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": 262905299730432.0,
+  "total_flos": 3373951346540544.0,
   "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 sha256:9fea7d8e53ae17235fd43a310f21ffb846dda870104ab9f30e32ed5c079c0551
+oid sha256:2ada7783cd58481595d554ff3f7ea34ef89acd8310b4f1454ce6c5b465b9c4f4
 size 6776