Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "up_proj",
     "q_proj",
-    "o_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj"
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "o_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:e8db6eee1d5dc744aa1c0acc1ae28aa9c9d3dc9a7f72528e93228d7c368a0c96
+oid sha256:2594d80f7ef1928f2b8eef09f4afe50f5d2fb769e02ee06fb2bf0e345b362a3a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1734d8047fcbfbff248bf56a5a2d1a9f6b129f1f9190503cc836ce46fa8598
+oid sha256:c669435d0e03dda238d2bf01e03d592d3b76e9f77d2b861145def193932fc207
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 0.00014158289678606824,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.001840577658218887,
+  "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": 0.00014158289678606824,
       "eval_loss": 7.729015827178955,
-      "eval_runtime": 591.3631,
-      "eval_samples_per_second": 5.029,
-      "eval_steps_per_second": 2.515,
+      "eval_runtime": 834.0188,
+      "eval_samples_per_second": 3.566,
+      "eval_steps_per_second": 1.783,
       "step": 1
+    },
+    {
+      "epoch": 0.0007079144839303412,
+      "grad_norm": 3.9896390438079834,
+      "learning_rate": 5e-05,
+      "loss": 7.5715,
+      "step": 5
+    },
+    {
+      "epoch": 0.0014158289678606825,
+      "grad_norm": 7.42996883392334,
+      "learning_rate": 0.0001,
+      "loss": 7.7081,
+      "step": 10
+    },
+    {
+      "epoch": 0.0014158289678606825,
+      "eval_loss": 6.551854133605957,
+      "eval_runtime": 1047.0566,
+      "eval_samples_per_second": 2.84,
+      "eval_steps_per_second": 1.42,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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:ede40a669ec4617b1de76d3732650ccc61a0e1a4dac54344e86de0655f46a6b5
+oid sha256:6d089e463ec8036f566cabf0c9082fc5a5872b7b2d5b63e01310a14dc59a1e61
 size 6776