Training in progress, step 155, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "k_proj",
-    "q_proj",
+    "up_proj",
     "o_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
-    "up_proj"
+    "gate_proj",
+    "q_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:a773ea0dbcfc7e337969d0b30be78c9554e01bb93f47eda62271a5ddeb1df522
+oid sha256:de76e8113e2afbf41ef93d0e0fd362308b34c1db6eef6ae12919e82437109a4f
 size 60010048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1ae67157a14cc5e9e66d7324330a14133cd61f7f7807ab15e23433c113c39a
+oid sha256:00cef0af92c7c0e26b5fee5c777d6ffda824e64692f84737c0def7ab965cc605
 size 31301554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6f71d78751e60f5217bd5845b6e2fe7b961457bce5ae9144bc7db2633b6d9b
+oid sha256:cb3fad64d81cfddf262a3f1534bfee70711d1dee3a680afc12b5a109910df52a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311facfa3e32e7638c019d54b1aa0a473bba9437f6098704527bbd28eeab77d8
+oid sha256:f12f546de35e8e54bf8bd9058643912399ffe3523a997be9687261fa7f9a83e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6760176960801125,
+  "epoch": 0.680407421379334,
   "eval_steps": 500,
-  "global_step": 154,
+  "global_step": 155,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1085,6 +1085,13 @@
       "learning_rate": 0.00011496062992125984,
       "loss": 1.1814,
       "step": 154
+    },
+    {
+      "epoch": 0.680407421379334,
+      "grad_norm": 0.11099740117788315,
+      "learning_rate": 0.00011338582677165355,
+      "loss": 1.1604,
+      "step": 155
     }
   ],
   "logging_steps": 1,
@@ -1104,7 +1111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.96517710528938e+17,
+  "total_flos": 2.984654806628598e+17,
   "train_batch_size": 2,
   "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:ab3a8e455f4a2780ad35ebac90b2710ee9b20330adf435e22c960d91ed9cfedd
+oid sha256:26c2144d17ba12987ac00ae094a1c2152265f2f07cbffb635cc10556a0a1ef3e
 size 5112