Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
+    "v_proj",
     "o_proj",
+    "gate_proj",
     "q_proj",
-    "gate_proj"
+    "k_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 sha256:0f1d0e7b231ead5bd384d34bd00fd75209c2e21a3a0b84100fbbf2b7d4fdb577
+oid sha256:90684ea075a81e3303fb9ad43369e96abf9d6f04f43f5872b08ac39f3a543120
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49601ac3a425e13296f82cad8360446b016edf99b6116d55181bb58186a5d6d5
+oid sha256:860b05b1c9db5fb993dff2412084de8b073ebc369f9a674e93775bcbd32764ea
 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": 0.00028258565877781704,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.003673613564111621,
+  "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": 0.00028258565877781704,
       "eval_loss": 1.151291847229004,
-      "eval_runtime": 178.5051,
-      "eval_samples_per_second": 8.347,
-      "eval_steps_per_second": 4.174,
+      "eval_runtime": 178.3855,
+      "eval_samples_per_second": 8.353,
+      "eval_steps_per_second": 4.176,
       "step": 1
+    },
+    {
+      "epoch": 0.001412928293889085,
+      "grad_norm": 6.91673469543457,
+      "learning_rate": 5e-05,
+      "loss": 4.7003,
+      "step": 5
+    },
+    {
+      "epoch": 0.00282585658777817,
+      "grad_norm": 6.784793376922607,
+      "learning_rate": 0.0001,
+      "loss": 3.4863,
+      "step": 10
+    },
+    {
+      "epoch": 0.00282585658777817,
+      "eval_loss": 0.638950526714325,
+      "eval_runtime": 179.2534,
+      "eval_samples_per_second": 8.312,
+      "eval_steps_per_second": 4.156,
+      "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": 350534359842816.0,
+  "total_flos": 4556946677956608.0,
   "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:a6472a94ad9062460eb116611565030d18fed62bffeaa5a4bdf48d26612b78c9
+oid sha256:22dc5226a12bb78108d30dd6e6d7b87c71dcc8fcf6ca354c7681e37317c676fe
 size 6776