Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
+    "o_proj",
     "up_proj",
-    "gate_proj",
-    "q_proj"
+    "down_proj",
+    "v_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:d61796726b88f7661c6506076589dd9848d83cd4ca1daba9d488e948aba68913
+oid sha256:6b35063aaab181a39cce77df9b95472f9057fde8c6c5f2020a38ad309fff1a13
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664b5b97f935ba6636542d7db11b71d88b88d265f76e7cb4f235df38acfc7f6b
+oid sha256:187aac00403677cedac6c4447b4c33d7d5460f45edd1edf618b26427e190d463
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39695fcb9f08db633890768057bbc32c32f41e7751478fd88f18f797b40289d5
+oid sha256:fa7f4725782b2745512bc50fd5941504e7a432f467521ff4e6de734610f94ebb
 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": 0.0002643579406516423,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0034366532284713504,
+  "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": 0.0002643579406516423,
       "eval_loss": 0.4451306462287903,
-      "eval_runtime": 516.2442,
-      "eval_samples_per_second": 3.086,
-      "eval_steps_per_second": 1.544,
+      "eval_runtime": 511.697,
+      "eval_samples_per_second": 3.113,
+      "eval_steps_per_second": 1.558,
       "step": 1
+    },
+    {
+      "epoch": 0.0013217897032582115,
+      "grad_norm": 0.28188425302505493,
+      "learning_rate": 5e-05,
+      "loss": 0.4138,
+      "step": 5
+    },
+    {
+      "epoch": 0.002643579406516423,
+      "grad_norm": 0.25118669867515564,
+      "learning_rate": 0.0001,
+      "loss": 0.2222,
+      "step": 10
+    },
+    {
+      "epoch": 0.002643579406516423,
+      "eval_loss": 0.3350960314273834,
+      "eval_runtime": 251.8051,
+      "eval_samples_per_second": 6.326,
+      "eval_steps_per_second": 3.165,
+      "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": 244309970386944.0,
+  "total_flos": 3053874629836800.0,
   "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 sha256:730a572fe218118fb5162e9b20fdfcbf89d45f42cefb9a7a22ef7b465dd46a96
+oid sha256:0f8a5c9bf7333c6b9455b227833d415e54815886a0f5f25f86bbb3213c2495d1
 size 6776