Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "up_proj",
     "q_proj",
-    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
-    "gate_proj"
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565b467fbbdbf25cc2bfa3c71f0bd336e8de28ad86df3918e596ca504bd31ced
+oid sha256:96dc805f8ec4bd0e855d7adf77c4e5aeb8fccae1eb9b6a75e0b8cf80a66ca6b9
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf47764c7f0af2d260e514ff53be11a069fc1773d2d9785ce9f40fca8159f6f7
+oid sha256:111022490b414d8de24040a2def6d07ef67150fecce1d375dd858f5ead2d602f
 size 74188650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97fb176f598ac490ccae77ec442df96e8ad14280345b9f1e433afd80f74a6b78
+oid sha256:d2030b6fa4cba3b806c7bd50086686655d43925111f7c1f49e9476afbacf3c36
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b524f48acea96061f9e17824552379d210ce1c60f82e25c1280fb8b2df4b21f0
+oid sha256:3866b207848bde64e003e2009c19ad36b11cfa7e85afea28bcb9e78b9bbbc07c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd240061f71d888d805feed14123a68774f5e130888a3057bdaa388caa9028c
+oid sha256:30c91fcbbb30d4ea264cde8e92f569f82e13868db72bdecd83da3096aa62b6fc
 size 1064

last-checkpoint/trainer_state.json

@@ -2,18 +2,18 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 10,
-  "global_step": 1,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [],
-  "logging_steps": 10,
-  "max_steps": 1,
+  "logging_steps": 100,
+  "max_steps": 3,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 20,
+  "num_train_epochs": 3,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -26,7 +26,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16214912925696.0,
+  "total_flos": 1362052685758464.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a226bdb6c8f1d8a261b365e32993c518d7b102eea55ff51a4f3775eac230c30
-size 5496
+oid sha256:246f4beac515de39119f51ef65f2d1a9e068fb98a957786c00d690b3fe1de63e
+size 5560