Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "v_proj",
     "gate_proj",
-    "down_proj",
-    "o_proj",
     "k_proj",
+    "up_proj",
+    "o_proj",
     "q_proj",
-    "up_proj"
+    "down_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 sha256:68cbd57e487a814f9aef1ce41ae756b6eae5a835a02672d88faacc231637a85b
+oid sha256:9421514092a0966a825276ba27a121698a0fdf881220266bb51c656da91e0791
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74535ff2713b577e98530b1788e76c76e9ec9466b888a27b963e100fbef427f
+oid sha256:900db480d8ae0511d8d17c38272fa57ea27f9c46b8517b3bbce77cdef9dbc3fb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.003568242640499554,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0463871543264942,
+  "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": 0.003568242640499554,
       "eval_loss": 7.846585750579834,
-      "eval_runtime": 84.2074,
-      "eval_samples_per_second": 1.401,
-      "eval_steps_per_second": 0.701,
+      "eval_runtime": 58.1489,
+      "eval_samples_per_second": 2.029,
+      "eval_steps_per_second": 1.015,
       "step": 1
+    },
+    {
+      "epoch": 0.01784121320249777,
+      "grad_norm": 41.419822692871094,
+      "learning_rate": 5e-05,
+      "loss": 30.7878,
+      "step": 5
+    },
+    {
+      "epoch": 0.03568242640499554,
+      "grad_norm": 59.32698059082031,
+      "learning_rate": 0.0001,
+      "loss": 27.0405,
+      "step": 10
+    },
+    {
+      "epoch": 0.03568242640499554,
+      "eval_loss": 3.822364568710327,
+      "eval_runtime": 56.4726,
+      "eval_samples_per_second": 2.09,
+      "eval_steps_per_second": 1.045,
+      "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": 162873313591296.0,
+  "total_flos": 2117353076686848.0,
   "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 sha256:733831175e42deb20b48388e0cce870160fd187326036e3368efd3a1c07c8f64
+oid sha256:bda2fa5ff426cbe3a121b0b49d1d4745df50ba1a7f481a38b7b039302e4be115
 size 6776