Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "k_proj",
+    "q_proj",
     "v_proj",
-    "up_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "gate_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 sha256:1d3ec7ddf754bd16bc4828555a29820d1863fdd62e1609b8363408e07b515c77
+oid sha256:1582391b852992bf63e810d66df7fd2e81f3a14a51713195f91282402fcec4c1
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
+oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab066be148ac980abed5131b29bb682b817198fd0dd2fca489ca8ae39871bb3
+oid sha256:88763a7f633ad3a173d3b84a7884c564dae0279efc343366c53c57222a2ec647
 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": 0.0003450060376056581,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004485078488873555,
+  "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": 0.0003450060376056581,
       "eval_loss": NaN,
-      "eval_runtime": 549.5741,
-      "eval_samples_per_second": 2.222,
-      "eval_steps_per_second": 1.112,
+      "eval_runtime": 545.5783,
+      "eval_samples_per_second": 2.238,
+      "eval_steps_per_second": 1.12,
       "step": 1
+    },
+    {
+      "epoch": 0.0017250301880282904,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.003450060376056581,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.003450060376056581,
+      "eval_loss": NaN,
+      "eval_runtime": 548.0832,
+      "eval_samples_per_second": 2.228,
+      "eval_steps_per_second": 1.115,
+      "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": 348527209218048.0,
+  "total_flos": 4530853719834624.0,
   "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 sha256:6517ac8d686e81996732c968dee1e08b73b4657e25a10917ad5343b4ad723f09
+oid sha256:5ef44152c46a21561c60a90f18e6a0b6ed37dd0ab85750912f6d69210f25922b
 size 6776