Training in progress, step 760, checkpoint

last-checkpoint/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "qkv_proj",
-    "gate_up_proj",
     "down_proj",
-    "o_proj"
+    "o_proj",
+    "gate_up_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 sha256:745ed45ba46e27d4a276a4bd62a985fbd8934270c510745c037ea7283b997c5a
+oid sha256:a21005b0c25f84187a6d837e3d90bc53f433f50e714145c05d0b17b4d6481985
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3666732966e75b7dddea0f14706f3ce6fbe99dbf7fd649207c5ed62a6184fa42
+oid sha256:4f8e8c28b45c3d4944833b51532fd8aea3a328fbd53d387d4481409ba0bd1c56
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db1fe9840930b9fd7409bb742ad453c84b28c1800a3abc1b4cce223762b144f
+oid sha256:744f87a373b7e8aca2b7ead73d8f8e4c8c1a6ad775f7cdeecb51f2b91e13de93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f129e6dbcdc516e08a9aab8d7cc9efeb682288e6509845b97627189c47790bc6
+oid sha256:4433212656c2840008788d3ef4721ac521814715c0310491af53892cc2f91958
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26475849731663686,
+  "epoch": 0.27191413237924866,
   "eval_steps": 500,
-  "global_step": 740,
+  "global_step": 760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -599,14 +599,30 @@
       "loss": 0.4178,
       "num_input_tokens_seen": 494747,
       "step": 740
+    },
+    {
+      "epoch": 0.26833631484794274,
+      "grad_norm": 0.29682761430740356,
+      "learning_rate": 0.00014633273703041147,
+      "loss": 0.4309,
+      "num_input_tokens_seen": 501076,
+      "step": 750
+    },
+    {
+      "epoch": 0.27191413237924866,
+      "grad_norm": 0.44356122612953186,
+      "learning_rate": 0.00014561717352415027,
+      "loss": 0.4113,
+      "num_input_tokens_seen": 508236,
+      "step": 760
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 494747,
+  "num_input_tokens_seen": 508236,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.1125112884402176e+16,
+  "total_flos": 1.1428432859455488e+16,
   "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:e03bc6a1791d1744856a78e4eb438a0c0f57a4d80f850b6de88464095403a4fa
-size 4984
+oid sha256:8bee6a61298e4ba0636e6bf836a1f169e31db19f42b2bb480b9f85ccd38a9c1e
+size 5048