Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "down_proj",
     "up_proj",
     "q_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
     "k_proj",
-    "v_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:a66d35b9c13bebe1ce3267652b3ccb01b568c58872da7a703957527e530d0fa7
+oid sha256:7f479ad8a8085c93cd0c7dcf1baa21017f2dd511a6f3e591ebd6446782b6487c
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe77fc58ffac31ae384facb416e1f9f3c9dc377028dea397988329a771b0b65
+oid sha256:1aed911d9b32a5591a67e2df93476ac4cc4b1c27d8a9c7f22ee4317c10579b75
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a6594826c91ec3c20d4dbc19b8b0087af2f8ef77a08476690d011d4370459d
+oid sha256:b91eba2ecb8c11f2ba05eeffb946ce79b2d6c10e39a409918596295758d1e604
 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": 0.00014536468365010721,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0018897408874513936,
+  "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": 0.00014536468365010721,
       "eval_loss": NaN,
-      "eval_runtime": 67.1672,
-      "eval_samples_per_second": 43.131,
-      "eval_steps_per_second": 21.573,
+      "eval_runtime": 66.5275,
+      "eval_samples_per_second": 43.546,
+      "eval_steps_per_second": 21.78,
       "step": 1
+    },
+    {
+      "epoch": 0.000726823418250536,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.001453646836501072,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.001453646836501072,
+      "eval_loss": NaN,
+      "eval_runtime": 64.2774,
+      "eval_samples_per_second": 45.07,
+      "eval_steps_per_second": 22.543,
+      "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": 1074876383232.0,
+  "total_flos": 14510831173632.0,
   "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 sha256:7047d959172cee301ce2370f9ede8739e4ec5cf09317303fd4be9b66d35bdd7c
+oid sha256:0f282d9a725cfdb98bace8424b7762669816587c4dd37a38487abdd084902683
 size 6776