Training in progress, step 600, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
-    "o_proj",
-    "up_proj",
     "q_proj",
+    "k_proj",
     "down_proj",
-    "k_proj"
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "gate_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 sha256:9dc37ac8998164b62cc5c357975ad2514f2d816cf2dfac6d529691b87d2dfaf1
+oid sha256:8a53adb1ece7e14078c5cbcd5925b731e174893ac4f79b83e75a1d118a6a16ca
 size 1556140392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6627bb63d695774d45ecca1879ba82fd0536c0a670ae5661d352c5bfe846d1b4
-size 790676214
+oid sha256:ecc0b6e807c2e801b966aac222c07c5a4d3aa838d101d41d5e11b3af8c1b26c4
+size 791682818

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a3df72428119d67493f2721530756b100fb0686d60bf8e5cc1c46868c50a7c
+oid sha256:133a27a96bf2028fd94eb62846a16114ede5a872ddea6198ae6b8df77a089e67
 size 1064

last-checkpoint/special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
+size 17210019

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00013909647105298114,
+  "epoch": 0.0008345782458834428,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,10 +14,24 @@
       "learning_rate": 1.999999977309048e-05,
       "loss": 2.1904,
       "step": 200
+    },
+    {
+      "epoch": 0.0005563854972556286,
+      "grad_norm": 6.481947422027588,
+      "learning_rate": 1.999999627575226e-05,
+      "loss": 1.9936,
+      "step": 400
+    },
+    {
+      "epoch": 0.0008345782458834428,
+      "grad_norm": 1.2531054019927979,
+      "learning_rate": 1.9999991549580503e-05,
+      "loss": 1.9425,
+      "step": 600
     }
   ],
   "logging_steps": 200,
-  "max_steps": 2875702,
+  "max_steps": 1437852,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 200,
@@ -33,7 +47,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1062124422727680.0,
+  "total_flos": 6846848392034304.0,
   "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 sha256:6a40cf0fe8e62e5b501787d77ca8eb595c430c75a909b2c2022895351fb86f6c
+oid sha256:aa5aa241dd55111be21c66e31c3a9c312c22de9c6ecf5bc3d18a21ae67e9aeea
 size 6776