Training in progress, step 1300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685aa3c0a14aed36795208036f85cc60b43d5ade53885df1548a7aeaa315c7b1
+oid sha256:bc1efa741b507f21867acb771d6a2bcb87457c35864022766a1a5ffcb020a0bb
 size 161533160

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "q_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
-    "up_proj"
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_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 sha256:685aa3c0a14aed36795208036f85cc60b43d5ade53885df1548a7aeaa315c7b1
+oid sha256:027c28cbacad0920c7a8ec1a4dbaf396f0658e37d9c57aa24903513cf568bf29
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e13be6d89d13a2f164596a38b8cd272ff53442d96ccec33e5cb5d78683accab
+oid sha256:a811f08d635f9fd429d0ac8672eee899607dd871ece10f326b8ec3e7266d9db2
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54175020cd8ce8004b6fccaf220cae531a1a1e1d035a8a578684e3a3b242741
+oid sha256:824d4a418ca52dbceab02ca3bdda11d00d54b246084fd87a75671a28233a0cb2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1986754966887417,
+  "epoch": 0.16556291390728478,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,34 +164,6 @@
       "learning_rate": 5.513245033112583e-05,
       "loss": 0.7213,
       "step": 1000
-    },
-    {
-      "epoch": 0.173841059602649,
-      "grad_norm": 1.8289754390716553,
-      "learning_rate": 5.789183222958058e-05,
-      "loss": 0.7335,
-      "step": 1050
-    },
-    {
-      "epoch": 0.18211920529801323,
-      "grad_norm": 1.4989681243896484,
-      "learning_rate": 6.065121412803533e-05,
-      "loss": 0.7326,
-      "step": 1100
-    },
-    {
-      "epoch": 0.19039735099337748,
-      "grad_norm": 1.5326098203659058,
-      "learning_rate": 6.341059602649006e-05,
-      "loss": 0.7311,
-      "step": 1150
-    },
-    {
-      "epoch": 0.1986754966887417,
-      "grad_norm": 1.4897147417068481,
-      "learning_rate": 6.616997792494481e-05,
-      "loss": 0.6918,
-      "step": 1200
     }
   ],
   "logging_steps": 50,
@@ -211,7 +183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9367447944560640.0,
+  "total_flos": 7833052747137024.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2543e07a37d2c3de3cd8e1d682eb10ddfc7a8cf84209a331e0b0e44870af81c3
+oid sha256:5dd2ef96eff028fc6db83c8627ce2e789cafe652a25ea367c040819bc392f916
 size 5752

trainer_log.jsonl

@@ -27,3 +27,5 @@
 {"current_steps": 1100, "total_steps": 18120, "loss": 0.7326, "lr": 6.065121412803533e-05, "epoch": 0.18211920529801323, "percentage": 6.07, "elapsed_time": "0:06:27", "remaining_time": "1:39:52"}
 {"current_steps": 1150, "total_steps": 18120, "loss": 0.7311, "lr": 6.341059602649006e-05, "epoch": 0.19039735099337748, "percentage": 6.35, "elapsed_time": "0:09:28", "remaining_time": "2:19:41"}
 {"current_steps": 1200, "total_steps": 18120, "loss": 0.6918, "lr": 6.616997792494481e-05, "epoch": 0.1986754966887417, "percentage": 6.62, "elapsed_time": "0:12:38", "remaining_time": "2:58:14"}
+{"current_steps": 1250, "total_steps": 18120, "loss": 0.7051, "lr": 6.892935982339957e-05, "epoch": 0.20695364238410596, "percentage": 6.9, "elapsed_time": "0:16:00", "remaining_time": "3:36:01"}
+{"current_steps": 1300, "total_steps": 18120, "loss": 0.6955, "lr": 7.168874172185431e-05, "epoch": 0.2152317880794702, "percentage": 7.17, "elapsed_time": "0:19:19", "remaining_time": "4:10:02"}