Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
-    "gate_proj",
-    "down_proj",
     "o_proj",
     "up_proj",
-    "v_proj"
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_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 sha256:2ba173f9c7a20b6448fd647c6fa7ba7c8f139d49778188bba393c0a2eb0df6c5
+oid sha256:b4ed443dd40c8d24de5de670d0e976b65d3ee897ca7ef642491291daaa16fac8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd294de232b93f1303dbdd2bd5ac255b2ba52f6401c49908f63518ff461a9bcf
+oid sha256:1a0bebdc77851de87bd174352881a6e28069d4b1d8f9b7b480b30992c82480bd
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dc269c204efc2e9a4c4cbe20de7c7547b2a048bf7e9385229ea63d598fdfd
+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": 7.107573119158464e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009239845054906002,
+  "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": 7.107573119158464e-05,
       "eval_loss": 2.738691806793213,
-      "eval_runtime": 396.9822,
-      "eval_samples_per_second": 14.923,
-      "eval_steps_per_second": 7.461,
+      "eval_runtime": 395.8619,
+      "eval_samples_per_second": 14.965,
+      "eval_steps_per_second": 7.482,
       "step": 1
+    },
+    {
+      "epoch": 0.0003553786559579232,
+      "grad_norm": 83.14938354492188,
+      "learning_rate": 5e-05,
+      "loss": 11.2519,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007107573119158464,
+      "grad_norm": 47.0615234375,
+      "learning_rate": 0.0001,
+      "loss": 6.3236,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007107573119158464,
+      "eval_loss": 1.474220633506775,
+      "eval_runtime": 396.755,
+      "eval_samples_per_second": 14.931,
+      "eval_steps_per_second": 7.466,
+      "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": 175270199820288.0,
+  "total_flos": 2278512597663744.0,
   "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 sha256:9ac449ced814b9f68d962aa9e75bd7d80a18b4f00883c3aa615312204c5975a2
+oid sha256:ac149de4fe4386862b1c87bd5fb50622fa6a5b09877c61fd129d73647d06ae23
 size 6776