Training in progress, step 2900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0db821ca7e48c8297211f633ec47baf18741683a7d800e6b15331cbd6daa5f9
+oid sha256:5d499eca7618b490a11a8b9a1fb0379501d1817282bda0550652eb4a12779d1f
 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:d0db821ca7e48c8297211f633ec47baf18741683a7d800e6b15331cbd6daa5f9
+oid sha256:027c28cbacad0920c7a8ec1a4dbaf396f0658e37d9c57aa24903513cf568bf29
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fd16711beaccee7895e0dbe700f2bcc95fcbecf7ea7664302ca929452b4c1e
+oid sha256:a811f08d635f9fd429d0ac8672eee899607dd871ece10f326b8ec3e7266d9db2
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b61d58dd50348a218f77056b2aac4b4be92dcec888dddedac62db12976506b2
+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": 0.46357615894039733,
+  "epoch": 0.16556291390728478,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,258 +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
-    },
-    {
-      "epoch": 0.20695364238410596,
-      "grad_norm": 1.634765863418579,
-      "learning_rate": 6.892935982339957e-05,
-      "loss": 0.7051,
-      "step": 1250
-    },
-    {
-      "epoch": 0.2152317880794702,
-      "grad_norm": 1.4463587999343872,
-      "learning_rate": 7.168874172185431e-05,
-      "loss": 0.6955,
-      "step": 1300
-    },
-    {
-      "epoch": 0.22350993377483444,
-      "grad_norm": 1.632133960723877,
-      "learning_rate": 7.444812362030905e-05,
-      "loss": 0.6901,
-      "step": 1350
-    },
-    {
-      "epoch": 0.23178807947019867,
-      "grad_norm": 1.4062328338623047,
-      "learning_rate": 7.72075055187638e-05,
-      "loss": 0.6833,
-      "step": 1400
-    },
-    {
-      "epoch": 0.24006622516556292,
-      "grad_norm": 1.2914466857910156,
-      "learning_rate": 7.996688741721855e-05,
-      "loss": 0.6663,
-      "step": 1450
-    },
-    {
-      "epoch": 0.24834437086092714,
-      "grad_norm": 1.4995919466018677,
-      "learning_rate": 8.272626931567329e-05,
-      "loss": 0.6959,
-      "step": 1500
-    },
-    {
-      "epoch": 0.25662251655629137,
-      "grad_norm": 1.1299749612808228,
-      "learning_rate": 8.548565121412803e-05,
-      "loss": 0.6685,
-      "step": 1550
-    },
-    {
-      "epoch": 0.26490066225165565,
-      "grad_norm": 1.329004168510437,
-      "learning_rate": 8.824503311258279e-05,
-      "loss": 0.6678,
-      "step": 1600
-    },
-    {
-      "epoch": 0.2731788079470199,
-      "grad_norm": 1.5191948413848877,
-      "learning_rate": 9.100441501103754e-05,
-      "loss": 0.6731,
-      "step": 1650
-    },
-    {
-      "epoch": 0.2814569536423841,
-      "grad_norm": 1.739169716835022,
-      "learning_rate": 9.376379690949227e-05,
-      "loss": 0.6691,
-      "step": 1700
-    },
-    {
-      "epoch": 0.2897350993377483,
-      "grad_norm": 1.2906118631362915,
-      "learning_rate": 9.652317880794703e-05,
-      "loss": 0.6718,
-      "step": 1750
-    },
-    {
-      "epoch": 0.2980132450331126,
-      "grad_norm": 1.289502501487732,
-      "learning_rate": 9.928256070640178e-05,
-      "loss": 0.6581,
-      "step": 1800
-    },
-    {
-      "epoch": 0.30629139072847683,
-      "grad_norm": 1.3923128843307495,
-      "learning_rate": 9.999872989402833e-05,
-      "loss": 0.6589,
-      "step": 1850
-    },
-    {
-      "epoch": 0.31456953642384106,
-      "grad_norm": 1.1048816442489624,
-      "learning_rate": 9.999297790520483e-05,
-      "loss": 0.6341,
-      "step": 1900
-    },
-    {
-      "epoch": 0.3228476821192053,
-      "grad_norm": 1.3568603992462158,
-      "learning_rate": 9.998258777484084e-05,
-      "loss": 0.6318,
-      "step": 1950
-    },
-    {
-      "epoch": 0.33112582781456956,
-      "grad_norm": 0.923786997795105,
-      "learning_rate": 9.996756046688961e-05,
-      "loss": 0.6318,
-      "step": 2000
-    },
-    {
-      "epoch": 0.3394039735099338,
-      "grad_norm": 1.102367877960205,
-      "learning_rate": 9.994789737552259e-05,
-      "loss": 0.6193,
-      "step": 2050
-    },
-    {
-      "epoch": 0.347682119205298,
-      "grad_norm": 1.0738896131515503,
-      "learning_rate": 9.992360032500001e-05,
-      "loss": 0.6184,
-      "step": 2100
-    },
-    {
-      "epoch": 0.35596026490066224,
-      "grad_norm": 1.279288649559021,
-      "learning_rate": 9.98946715695016e-05,
-      "loss": 0.626,
-      "step": 2150
-    },
-    {
-      "epoch": 0.36423841059602646,
-      "grad_norm": 1.2009036540985107,
-      "learning_rate": 9.986111379291759e-05,
-      "loss": 0.6305,
-      "step": 2200
-    },
-    {
-      "epoch": 0.37251655629139074,
-      "grad_norm": 0.8177038431167603,
-      "learning_rate": 9.982293010859955e-05,
-      "loss": 0.6266,
-      "step": 2250
-    },
-    {
-      "epoch": 0.38079470198675497,
-      "grad_norm": 1.2464983463287354,
-      "learning_rate": 9.978012405907165e-05,
-      "loss": 0.6148,
-      "step": 2300
-    },
-    {
-      "epoch": 0.3890728476821192,
-      "grad_norm": 1.2841860055923462,
-      "learning_rate": 9.973269961570195e-05,
-      "loss": 0.5946,
-      "step": 2350
-    },
-    {
-      "epoch": 0.3973509933774834,
-      "grad_norm": 1.2200431823730469,
-      "learning_rate": 9.968066117833401e-05,
-      "loss": 0.6166,
-      "step": 2400
-    },
-    {
-      "epoch": 0.4056291390728477,
-      "grad_norm": 1.128247857093811,
-      "learning_rate": 9.962401357487863e-05,
-      "loss": 0.5992,
-      "step": 2450
-    },
-    {
-      "epoch": 0.4139072847682119,
-      "grad_norm": 1.0683091878890991,
-      "learning_rate": 9.956276206086597e-05,
-      "loss": 0.6048,
-      "step": 2500
-    },
-    {
-      "epoch": 0.42218543046357615,
-      "grad_norm": 1.1819758415222168,
-      "learning_rate": 9.949691231895791e-05,
-      "loss": 0.5944,
-      "step": 2550
-    },
-    {
-      "epoch": 0.4304635761589404,
-      "grad_norm": 1.0043411254882812,
-      "learning_rate": 9.942647045842095e-05,
-      "loss": 0.5962,
-      "step": 2600
-    },
-    {
-      "epoch": 0.43874172185430466,
-      "grad_norm": 1.0588668584823608,
-      "learning_rate": 9.93514430145593e-05,
-      "loss": 0.6067,
-      "step": 2650
-    },
-    {
-      "epoch": 0.4470198675496689,
-      "grad_norm": 0.9364084601402283,
-      "learning_rate": 9.927183694810862e-05,
-      "loss": 0.5928,
-      "step": 2700
-    },
-    {
-      "epoch": 0.4552980132450331,
-      "grad_norm": 1.155172348022461,
-      "learning_rate": 9.918765964459022e-05,
-      "loss": 0.5987,
-      "step": 2750
-    },
-    {
-      "epoch": 0.46357615894039733,
-      "grad_norm": 1.1639224290847778,
-      "learning_rate": 9.909891891362587e-05,
-      "loss": 0.5745,
-      "step": 2800
     }
   ],
   "logging_steps": 50,
@@ -435,7 +183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.19279270346752e+16,
+  "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

@@ -59,3 +59,5 @@
 {"current_steps": 2700, "total_steps": 18120, "loss": 0.5928, "lr": 9.927183694810862e-05, "epoch": 0.4470198675496689, "percentage": 14.9, "elapsed_time": "1:49:40", "remaining_time": "10:26:24"}
 {"current_steps": 2750, "total_steps": 18120, "loss": 0.5987, "lr": 9.918765964459022e-05, "epoch": 0.4552980132450331, "percentage": 15.18, "elapsed_time": "1:52:56", "remaining_time": "10:31:13"}
 {"current_steps": 2800, "total_steps": 18120, "loss": 0.5745, "lr": 9.909891891362587e-05, "epoch": 0.46357615894039733, "percentage": 15.45, "elapsed_time": "1:56:17", "remaining_time": "10:36:16"}
+{"current_steps": 2850, "total_steps": 18120, "loss": 0.5825, "lr": 9.900562298821323e-05, "epoch": 0.4718543046357616, "percentage": 15.73, "elapsed_time": "1:59:31", "remaining_time": "10:40:26"}
+{"current_steps": 2900, "total_steps": 18120, "loss": 0.5806, "lr": 9.890778052396205e-05, "epoch": 0.48013245033112584, "percentage": 16.0, "elapsed_time": "2:02:52", "remaining_time": "10:44:51"}