Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "gate_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "k_proj",
     "down_proj",
     "o_proj",
-    "k_proj"
+    "v_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 sha256:60a8832ec969d2d9537521db5268a0c541e414a8de985bce440051aa86517cdf
+oid sha256:c74aa95c0d6843bb56eb659da6307a783209dfb61ef7e5218cff57095e6becbc
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16dc0a3c584fa87c86e04cb6676c8eaba51e29cc3931d06c3cdefad1937c8512
+oid sha256:406d48535f66fbac919f1619c655e2d522b80b8697f9b1ddd13211efa53533d6
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bdb33dccba10f38bc829e5445427c9b948d0827c9a4f67cd30346e160938dad
+oid sha256:dfc5f880a99221c3c2668670b0468ffc28d7a3abf27d797b7a28920c8da464c4
 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": 0.00024786218862312553,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003222208452100632,
+  "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": 0.00024786218862312553,
       "eval_loss": 3.3040616512298584,
-      "eval_runtime": 30.2968,
-      "eval_samples_per_second": 56.079,
-      "eval_steps_per_second": 28.056,
+      "eval_runtime": 30.0995,
+      "eval_samples_per_second": 56.446,
+      "eval_steps_per_second": 28.24,
       "step": 1
+    },
+    {
+      "epoch": 0.0012393109431156277,
+      "grad_norm": 0.612124502658844,
+      "learning_rate": 5e-05,
+      "loss": 3.1742,
+      "step": 5
+    },
+    {
+      "epoch": 0.0024786218862312553,
+      "grad_norm": 0.8830687999725342,
+      "learning_rate": 0.0001,
+      "loss": 3.2666,
+      "step": 10
+    },
+    {
+      "epoch": 0.0024786218862312553,
+      "eval_loss": 3.2535722255706787,
+      "eval_runtime": 30.1596,
+      "eval_samples_per_second": 56.334,
+      "eval_steps_per_second": 28.183,
+      "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": 4286581309440.0,
+  "total_flos": 47152394403840.0,
   "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 sha256:5cb1e16e62afaced4b91dae23063c3df4eb69e64650f8abe2d7887319c70dbb4
+oid sha256:2a6dc0bb7cd2d7bc1e5cc940db56a9d027396581adc954d1923b659e514650e5
 size 6776