Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "o_proj",
     "k_proj",
-    "q_proj",
-    "up_proj",
+    "v_proj",
     "gate_proj",
-    "o_proj",
-    "down_proj"
+    "up_proj",
+    "down_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 sha256:2e2fc75321acff3710fee434ac42e921fe0d65f3085601af06d2ee28af587f32
+oid sha256:120ee317fb59b358ddcfa8ecbb5f143a6ae66d61a077ce2980beece1a4022cc9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60428b516cb99b73e237fc0c2b409af7c5a543c84e221e537462a057b3107580
+oid sha256:03b6d6506a0a47a04901ab48eecab91b6b516f69a3c70134b99074b9a6fa5bbe
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61688a14e872cff2944da3740ce09e8bc17c564c13b093b03d1ee2fcf730f0b
+oid sha256:a483b98e8a0ab343175b49a2aed3c2a9b8c820acab215bf23213740228ef7422
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01582591493570722,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.20573689416419386,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.01582591493570722,
       "eval_loss": 2.9574100971221924,
-      "eval_runtime": 22.4085,
-      "eval_samples_per_second": 19.011,
-      "eval_steps_per_second": 2.41,
+      "eval_runtime": 22.3481,
+      "eval_samples_per_second": 19.062,
+      "eval_steps_per_second": 2.416,
       "step": 1
+    },
+    {
+      "epoch": 0.1582591493570722,
+      "grad_norm": 18.0383358001709,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 25.6469,
+      "step": 10
+    },
+    {
+      "epoch": 0.1582591493570722,
+      "eval_loss": 0.5446298718452454,
+      "eval_runtime": 22.2504,
+      "eval_samples_per_second": 19.146,
+      "eval_steps_per_second": 2.427,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2804274878742528.0,
+  "total_flos": 3.645557342365286e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d7764a278dc1ddccab6323f7efe32e55d7e6b2f3fb651613fd5f2aac367459
+oid sha256:349c3e68c86b06b062692dd603c0208513feda48f017e961a6ce796e1c0129f0
 size 6776