Training in progress, step 103100, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "k_proj",
-    "gate_proj",
-    "down_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff50e9a0eef14c00f32c5e550257295427f2d666e009aac32472aef43b0c78f
+oid sha256:d8d7cc20b396cca3e8d34e141799f9fb7d26e17cc8eff473c1afd251d8d9b6cc
 size 5544997664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1f3c8b9d1c8514057a760685418307853b2172387d395e371d81516debcc99
+oid sha256:f0932653c53bd9f5af69d8d728513a659e32e307161fd0359d520ee70c7aa3c5
 size 674093138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d52e9778ae961a843d4efe5adba669832146332ec663eac9df46d71427724e3
+oid sha256:6474451a1e2f3e46bed2d21701e092cafc22a415c811eebe38a7a07c535fa7ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1dd725a3e5295711459643d6e1204a1d04a7f905cc6416544fa87ecdfb18228
+oid sha256:212c085ef0256e6cd45cc46be3fe004a003548c018452df3f4f4b8de50ed9745
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07503755596210195,
+  "epoch": 0.07667365728139455,
   "eval_steps": 200,
-  "global_step": 100900,
+  "global_step": 103100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7070,6 +7070,160 @@
       "learning_rate": 1.9988888715649357e-05,
       "loss": 1.5441,
       "step": 100900
+    },
+    {
+      "epoch": 0.07511192420388797,
+      "grad_norm": 1.068562388420105,
+      "learning_rate": 1.998886668338319e-05,
+      "loss": 1.4998,
+      "step": 101000
+    },
+    {
+      "epoch": 0.075186292445674,
+      "grad_norm": 0.6331286430358887,
+      "learning_rate": 1.998884462930723e-05,
+      "loss": 1.5633,
+      "step": 101100
+    },
+    {
+      "epoch": 0.07526066068746003,
+      "grad_norm": 1.3566038608551025,
+      "learning_rate": 1.998882255342152e-05,
+      "loss": 1.4621,
+      "step": 101200
+    },
+    {
+      "epoch": 0.07533502892924605,
+      "grad_norm": 0.9672004580497742,
+      "learning_rate": 1.998880045572611e-05,
+      "loss": 1.5249,
+      "step": 101300
+    },
+    {
+      "epoch": 0.07540939717103208,
+      "grad_norm": 0.36732280254364014,
+      "learning_rate": 1.9988778336221045e-05,
+      "loss": 1.574,
+      "step": 101400
+    },
+    {
+      "epoch": 0.07548376541281811,
+      "grad_norm": 0.4788234829902649,
+      "learning_rate": 1.998875619490638e-05,
+      "loss": 1.5418,
+      "step": 101500
+    },
+    {
+      "epoch": 0.07555813365460413,
+      "grad_norm": 0.8955681324005127,
+      "learning_rate": 1.9988734031782157e-05,
+      "loss": 1.5568,
+      "step": 101600
+    },
+    {
+      "epoch": 0.07563250189639016,
+      "grad_norm": 0.8049163222312927,
+      "learning_rate": 1.9988711846848427e-05,
+      "loss": 1.4838,
+      "step": 101700
+    },
+    {
+      "epoch": 0.07570687013817619,
+      "grad_norm": 0.7558008432388306,
+      "learning_rate": 1.9988689640105235e-05,
+      "loss": 1.4955,
+      "step": 101800
+    },
+    {
+      "epoch": 0.07578123837996222,
+      "grad_norm": 0.4749026596546173,
+      "learning_rate": 1.9988667411552635e-05,
+      "loss": 1.5929,
+      "step": 101900
+    },
+    {
+      "epoch": 0.07585560662174824,
+      "grad_norm": 0.6597522497177124,
+      "learning_rate": 1.998864516119067e-05,
+      "loss": 1.5584,
+      "step": 102000
+    },
+    {
+      "epoch": 0.07592997486353428,
+      "grad_norm": 0.7412188053131104,
+      "learning_rate": 1.9988622889019395e-05,
+      "loss": 1.5842,
+      "step": 102100
+    },
+    {
+      "epoch": 0.07600434310532031,
+      "grad_norm": 0.5564984679222107,
+      "learning_rate": 1.9988600595038853e-05,
+      "loss": 1.5764,
+      "step": 102200
+    },
+    {
+      "epoch": 0.07607871134710634,
+      "grad_norm": 1.0488529205322266,
+      "learning_rate": 1.9988578279249097e-05,
+      "loss": 1.458,
+      "step": 102300
+    },
+    {
+      "epoch": 0.07615307958889236,
+      "grad_norm": 1.40269136428833,
+      "learning_rate": 1.998855594165017e-05,
+      "loss": 1.4588,
+      "step": 102400
+    },
+    {
+      "epoch": 0.07622744783067839,
+      "grad_norm": 0.8488138318061829,
+      "learning_rate": 1.9988533582242127e-05,
+      "loss": 1.522,
+      "step": 102500
+    },
+    {
+      "epoch": 0.07630181607246442,
+      "grad_norm": 0.5191701054573059,
+      "learning_rate": 1.9988511201025015e-05,
+      "loss": 1.5036,
+      "step": 102600
+    },
+    {
+      "epoch": 0.07637618431425044,
+      "grad_norm": 0.6648279428482056,
+      "learning_rate": 1.9988488797998878e-05,
+      "loss": 1.4929,
+      "step": 102700
+    },
+    {
+      "epoch": 0.07645055255603647,
+      "grad_norm": 1.8600202798843384,
+      "learning_rate": 1.9988466373163774e-05,
+      "loss": 1.5692,
+      "step": 102800
+    },
+    {
+      "epoch": 0.0765249207978225,
+      "grad_norm": 0.7583739757537842,
+      "learning_rate": 1.9988443926519743e-05,
+      "loss": 1.5145,
+      "step": 102900
+    },
+    {
+      "epoch": 0.07659928903960853,
+      "grad_norm": 0.6128048300743103,
+      "learning_rate": 1.998842145806684e-05,
+      "loss": 1.5729,
+      "step": 103000
+    },
+    {
+      "epoch": 0.07667365728139455,
+      "grad_norm": 0.7574602365493774,
+      "learning_rate": 1.998839896780511e-05,
+      "loss": 1.4356,
+      "step": 103100
     }
   ],
   "logging_steps": 100,
@@ -7089,7 +7243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3747108667853128e+18,
+  "total_flos": 1.4045543416669962e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null