Training in progress, step 101500, 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 sha256:2801fc5fd3438e62fb52e2e065d7a41a311c5eb5c8d6526a16ac5ebf45c5eb82
 size 5544997664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1f3c8b9d1c8514057a760685418307853b2172387d395e371d81516debcc99
+oid sha256:6192d7915ba76d3f28f82b949366ec1d2a47e71e6a98bf337436f53b6d95c233
 size 674093138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d52e9778ae961a843d4efe5adba669832146332ec663eac9df46d71427724e3
+oid sha256:66b9ddb8310f52522967ff23739bdad1c9881db846e17007ae3309f43eba2a31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1dd725a3e5295711459643d6e1204a1d04a7f905cc6416544fa87ecdfb18228
+oid sha256:034d1c80c88cb467b42aa72ba1468a4943845dfc48ccd365eaf74dcf4c59a204
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07503755596210195,
+  "epoch": 0.07548376541281811,
   "eval_steps": 200,
-  "global_step": 100900,
+  "global_step": 101500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7070,6 +7070,48 @@
       "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
     }
   ],
   "logging_steps": 100,
@@ -7089,7 +7131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3747108667853128e+18,
+  "total_flos": 1.3828391678867374e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null