Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "gate_proj",
-    "v_proj",
+    "up_proj",
     "q_proj",
+    "k_proj",
     "down_proj",
-    "up_proj"
+    "gate_proj",
+    "v_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 sha256:5e58cb15059156e13f5212c48850758ffd180e60946308e4d1c3a3222c7dd2c8
+oid sha256:9e6884b8e6669a469f0174841b3e7bb3e74a3be6e2d6920d023beb17a7fc6b56
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0dcd226efbb8c35e8fd4c6b8305f90a62c9ef7bb25c97570130902424e1385
+oid sha256:767ea677e0931f68b8674afe522e9ec71e712c16248f123a0b68a331569464ed
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da80317735abd5d7a29a7220f00b3b233d1e998e1437bb05f3ba2da5a84eb5d2
+oid sha256:a0d1131a45cb1eda72293de04b36c5c41c5b67986b9468e2590629138bfa23bb
 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": 0.006802721088435374,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.08843537414965986,
+  "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": 0.006802721088435374,
       "eval_loss": 7.88132381439209,
-      "eval_runtime": 37.6697,
-      "eval_samples_per_second": 26.281,
-      "eval_steps_per_second": 3.292,
+      "eval_runtime": 37.6145,
+      "eval_samples_per_second": 26.32,
+      "eval_steps_per_second": 3.297,
       "step": 1
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 5.561442852020264,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 6.6527,
+      "step": 10
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "eval_loss": 3.9917244911193848,
+      "eval_runtime": 36.513,
+      "eval_samples_per_second": 27.114,
+      "eval_steps_per_second": 3.396,
+      "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": 1037754427244544.0,
+  "total_flos": 1.3101649643962368e+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:bb7f16b06905e9dce17fca0fdfb23324315dafeea3f3264c5620831c32e77204
+oid sha256:5560f479e92c20353ad9e34241752cd54705eb52890788c92b39d7b73bcd0cb3
 size 6776