Training in progress, step 4620

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7d7f4631cfc2a6222bdae3c87ef97ce8155d48e20fb99575c228c5d98743a1
+oid sha256:3da7c58a11ea73be2ba7b042269eb8f7078a6fc619e1eafee9f57e381707fde8
 size 44871152

last-checkpoint/adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
+    "k_proj",
     "down_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "v_proj"
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7d7f4631cfc2a6222bdae3c87ef97ce8155d48e20fb99575c228c5d98743a1
+oid sha256:d4f6f4f36533eb757dab6bfd23dce19c85a7a77745b55cb08c0795c59685aa91
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f420c74f89712d220950f418ed361c87cad76a338d871e9eb74f9ffa82c70b
-size 24034627
+oid sha256:73d2a41ccd550203cd334513ad32aa162d29f62e672dbcf4aa2e8de62156d9a0
+size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0116abf0b2d5a5f409067760e62505d28928b7cfb9f02e432714071aae879789
+oid sha256:6cb366ee0fd05f23b8fc61bb2f37c12f485044dd90941f61b2bce04d0188321f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179fcbed838a91b1eaf1b06b6f812f5dae6acceeaa4e5e404a0677f4a4114df4
+oid sha256:616f099159baa341618742c3e449495c00a58f04705dd0de97e028eb230e624f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8575816525033275,
+  "epoch": 1.7887785399815705,
   "eval_steps": 500,
-  "global_step": 4536,
+  "global_step": 4368,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3060,125 +3060,6 @@
       "learning_rate": 6.00053082583324e-06,
       "loss": 0.4025435924530029,
       "step": 4360
-    },
-    {
-      "epoch": 1.7895976246544487,
-      "grad_norm": 0.21897482872009277,
-      "learning_rate": 5.776322089099384e-06,
-      "loss": 0.4200548529624939,
-      "step": 4370
-    },
-    {
-      "epoch": 1.7936930480188389,
-      "grad_norm": 0.1700364649295807,
-      "learning_rate": 5.556257654757624e-06,
-      "loss": 0.34192743301391604,
-      "step": 4380
-    },
-    {
-      "epoch": 1.7977884713832293,
-      "grad_norm": 0.2201203852891922,
-      "learning_rate": 5.340347202047669e-06,
-      "loss": 0.3917534828186035,
-      "step": 4390
-    },
-    {
-      "epoch": 1.8018838947476197,
-      "grad_norm": 0.2158016562461853,
-      "learning_rate": 5.128600227501834e-06,
-      "loss": 0.3703617572784424,
-      "step": 4400
-    },
-    {
-      "epoch": 1.8059793181120098,
-      "grad_norm": 0.2428576648235321,
-      "learning_rate": 4.921026044527466e-06,
-      "loss": 0.4067427635192871,
-      "step": 4410
-    },
-    {
-      "epoch": 1.8100747414764,
-      "grad_norm": 0.186968132853508,
-      "learning_rate": 4.7176337829972884e-06,
-      "loss": 0.377484655380249,
-      "step": 4420
-    },
-    {
-      "epoch": 1.8141701648407904,
-      "grad_norm": 0.21294040977954865,
-      "learning_rate": 4.518432388847705e-06,
-      "loss": 0.4246979713439941,
-      "step": 4430
-    },
-    {
-      "epoch": 1.8182655882051808,
-      "grad_norm": 0.20785194635391235,
-      "learning_rate": 4.3234306236855315e-06,
-      "loss": 0.39151136875152587,
-      "step": 4440
-    },
-    {
-      "epoch": 1.822361011569571,
-      "grad_norm": 0.2211901694536209,
-      "learning_rate": 4.132637064402445e-06,
-      "loss": 0.40515637397766113,
-      "step": 4450
-    },
-    {
-      "epoch": 1.8264564349339611,
-      "grad_norm": 0.1828216165304184,
-      "learning_rate": 3.946060102797877e-06,
-      "loss": 0.37872354984283446,
-      "step": 4460
-    },
-    {
-      "epoch": 1.8305518582983515,
-      "grad_norm": 0.19599486887454987,
-      "learning_rate": 3.7637079452098045e-06,
-      "loss": 0.3668804407119751,
-      "step": 4470
-    },
-    {
-      "epoch": 1.834647281662742,
-      "grad_norm": 0.24288585782051086,
-      "learning_rate": 3.585588612153867e-06,
-      "loss": 0.4075489521026611,
-      "step": 4480
-    },
-    {
-      "epoch": 1.838742705027132,
-      "grad_norm": 0.16427487134933472,
-      "learning_rate": 3.4117099379706195e-06,
-      "loss": 0.3669139385223389,
-      "step": 4490
-    },
-    {
-      "epoch": 1.8428381283915225,
-      "grad_norm": 0.20215265452861786,
-      "learning_rate": 3.2420795704808492e-06,
-      "loss": 0.40285863876342776,
-      "step": 4500
-    },
-    {
-      "epoch": 1.846933551755913,
-      "grad_norm": 0.1883266270160675,
-      "learning_rate": 3.0767049706493136e-06,
-      "loss": 0.39141478538513186,
-      "step": 4510
-    },
-    {
-      "epoch": 1.851028975120303,
-      "grad_norm": 0.2351822555065155,
-      "learning_rate": 2.915593412256479e-06,
-      "loss": 0.3928338289260864,
-      "step": 4520
-    },
-    {
-      "epoch": 1.8551243984846932,
-      "grad_norm": 0.21443790197372437,
-      "learning_rate": 2.7587519815786336e-06,
-      "loss": 0.37882561683654786,
-      "step": 4530
     }
   ],
   "logging_steps": 10,
@@ -3198,7 +3079,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.872158025495429e+17,
+  "total_flos": 7.580712771272172e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null