Training in progress, step 2300, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj"
+    "k_proj",
+    "up_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 sha256:027c28cbacad0920c7a8ec1a4dbaf396f0658e37d9c57aa24903513cf568bf29
+oid sha256:42b21865b1cff699c1edc0d876038580b55aadc3b6212c9ee3252346ae8790b2
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a811f08d635f9fd429d0ac8672eee899607dd871ece10f326b8ec3e7266d9db2
+oid sha256:7e96946ff3ba755069c41867f1f6718e71185dd788c112a7a8788a245bc15b85
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824d4a418ca52dbceab02ca3bdda11d00d54b246084fd87a75671a28233a0cb2
+oid sha256:451396d101937287833f37c6d75c7dd580aac62697d2e7d9e39f9e5139467845
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16556291390728478,
+  "epoch": 0.38079470198675497,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,188 @@
       "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
     }
   ],
   "logging_steps": 50,
@@ -183,7 +365,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7833052747137024.0,
+  "total_flos": 1.8040897164804096e+16,
   "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 sha256:5dd2ef96eff028fc6db83c8627ce2e789cafe652a25ea367c040819bc392f916
+oid sha256:2543e07a37d2c3de3cd8e1d682eb10ddfc7a8cf84209a331e0b0e44870af81c3
 size 5752