Training in progress, step 23200, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "gate_proj",
     "up_proj",
     "v_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj",
-    "k_proj"
+    "k_proj",
+    "q_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 sha256:20e56293ea86924617db1d72bddea10585e4be98a582ddca170c081dd3d642c9
+oid sha256:2e7f627d305f378c78e9f5383b187508dd29135634d00313e9ea84b8956b2c84
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7c5ec127b3617a18b3d72d14dceb0ba197088d23e289ef92a6837ce8b5e15f
+oid sha256:b46e266c798c9afd8e6ff2fa3e7ace3e707953edb004e4467129ee189289adcc
 size 85736914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4762419da8cab351088827e4869a7225442c8f1f7484efb21afc6c2799818eb
+oid sha256:5e76919056ec8898be3700e1aa15e2687b14a94dd025c0e9da95ad09620b0a32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e872382e84dc07d00209e557644b4bf1503898fe7aa404af9c426170e40ad4
+oid sha256:f4951502290c05c8b85ac5c7ba7e4d82d3ec30601aec1ebc772e1f7b17f05750
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033316105139083584,
+  "epoch": 0.051758949055362,
   "eval_steps": 2000,
-  "global_step": 22400,
+  "global_step": 23200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -791,14 +791,42 @@
       "learning_rate": 1.9997813001808763e-05,
       "loss": 1.5603,
       "step": 22400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.027528762817383,
+      "learning_rate": 1.9994991132809548e-05,
+      "loss": 1.5228,
+      "step": 22600
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.9839845895767212,
+      "learning_rate": 1.9994902463916502e-05,
+      "loss": 1.5413,
+      "step": 22800
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.558858871459961,
+      "learning_rate": 1.999481256582422e-05,
+      "loss": 1.5713,
+      "step": 23000
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.022099256515503,
+      "learning_rate": 1.9994721882148102e-05,
+      "loss": 1.5488,
+      "step": 23200
     }
   ],
   "logging_steps": 200,
-  "max_steps": 3361735,
+  "max_steps": 2241155,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.327171237194056e+17,
+  "total_flos": 4.6409799585243955e+17,
   "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 sha256:9a7800ffb29813f89bbd542587a923598ba056a5186a554421f6b09a6d22b374
+oid sha256:c8b8d5d55034cf9499e0ba365ba364383f0583a4c0942d2f91245e7ceb5c8746
 size 4920