Training in progress, step 23400, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
     "v_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
-    "o_proj"
+    "gate_proj",
+    "down_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 sha256:2e7f627d305f378c78e9f5383b187508dd29135634d00313e9ea84b8956b2c84
+oid sha256:8c7f93eabe6ac3c54d66eaa201fd02227487a26f7778737a9f254ff462e973e4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46e266c798c9afd8e6ff2fa3e7ace3e707953edb004e4467129ee189289adcc
+oid sha256:73914a91d2c85155b01b949bf4bca1b47684ea4ff1764db4a597aed9516fd5ab
 size 85736914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e76919056ec8898be3700e1aa15e2687b14a94dd025c0e9da95ad09620b0a32
+oid sha256:0f8c4f9076fe893e7a53debd026211a9b9066658d86f31864434230c495759f3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4951502290c05c8b85ac5c7ba7e4d82d3ec30601aec1ebc772e1f7b17f05750
+oid sha256:8114cada636c19d5007acc44352f3b0449c4b5ebb7cb27bcb702507137d58166
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.051758949055362,
+  "epoch": 0.0696068625227282,
   "eval_steps": 2000,
-  "global_step": 23200,
+  "global_step": 23400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -819,14 +819,21 @@
       "learning_rate": 1.9994721882148102e-05,
       "loss": 1.5488,
       "step": 23200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.663493275642395,
+      "learning_rate": 1.999045551990737e-05,
+      "loss": 1.536,
+      "step": 23400
     }
   ],
   "logging_steps": 200,
-  "max_steps": 2241155,
+  "max_steps": 1680865,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.6409799585243955e+17,
+  "total_flos": 4.745472228553851e+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:c8b8d5d55034cf9499e0ba365ba364383f0583a4c0942d2f91245e7ceb5c8746
+oid sha256:e88463ac0cd6182d9b1cd0ac83ec16eba34109ec5568773d1ab337bb23a66942
 size 4920