Training in progress, step 100, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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:af13b68fa43378eeb1d9477887e1f4b280a05be96737b5750839609cdd90a6d8
+oid sha256:729c7c5cdb24f76ae678bfe1c60e517eccc2b69129a55c74a43e39cb8bfed1c7
 size 157308096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab7c0f5a4a81699b122c49904d07e780819ce82f6ed8f06b2193f1320c4453f
-size 314671226
+oid sha256:896517567377b971af273a96223c85318eae61b3c701965a2ba8e4c121063fb1
+size 314671098

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afbf9b2cc7ffb82e39603ea3e9793624776e974898f71cddb75c50b95a8ff20
+oid sha256:51dee332d2275cc0831c1ea0d0b5b2263457ff95fff00680e5043e944b844a04
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4fa167ac420fbc12a0b1225ad375db648a55f16b7e4866651104ea0cc00a49
+oid sha256:9dd41ef4ed5f7287caff4fbd63c7a8fe2bdaf897c1e0d8462e29234862b1d008
 size 15920

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e799329eb62e1eb372f5e1a106e0710d002dddfe0cb96b7478769d095e752b5f
+oid sha256:38f9352bf4c207908a2139b5f9b00e28565f619c4bf592f8d44d4fd7bab9e233
 size 15920

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148ecc351dae84aea8cdc86447e26d57a1165551634773232252cd35029fec44
+oid sha256:9f65483c1d522a1cffd17408a379086fe58926f97fc8b98bbf33ca6096fedbaa
 size 15920

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c737fa9218e50ea3ce9320b640c05dff0f18b8b0409fe5e3f6340fa144ae6f
+oid sha256:7cde8693d11e7616878cf88486a40f4b06a4e1c5183cede7db3bc7feed749431
 size 15920

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fdcad7ba51bcc458150b1d4b2c87d4dee4fcbb7619ccd347b91ff0f61763b2
+oid sha256:72d0344dcf2d5f0e04a15864a370633a27e082c0bc3a6fc6cb92b047029e94ee
 size 15920

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d21b509f3e70f8a0fe13164c8b6d889c6ab04755a1218812e3a6427ea94537
+oid sha256:b4a6ce273116b22c7e48d400c7fad4266b453a25f35bdb6ff40b8fd387c52039
 size 15920

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1304350d7f8258aaa5c749bd82f5c7ddf08eafecb5eb5f18652eb3f7d1198b19
+oid sha256:721c7edddc274b916092408fb1b3bd5030be85a6bdb989ce16a729345640c7ab
 size 15920

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0bcc3306c506981564a07ff3b261b32731741ed53940e879827feb4c6814eb
+oid sha256:dbaba77b7ae8890f2b70278aac610a39d4e81d78f312f9f6ab0d92ef1151e3b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,36 +1,20 @@
 {
-  "best_metric": 0.05055840685963631,
-  "best_model_checkpoint": "evgmaslov/Mistral-Nemo-Instruct-2407-cars/checkpoint-300",
-  "epoch": 0.37546933667083854,
+  "best_metric": 0.01457285601645708,
+  "best_model_checkpoint": "evgmaslov/Mistral-Nemo-Instruct-2407-cars/checkpoint-100",
+  "epoch": 0.1251564455569462,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1251564455569462,
-      "eval_loss": 0.05901213735342026,
-      "eval_runtime": 5.3266,
-      "eval_samples_per_second": 6.008,
+      "eval_loss": 0.01457285601645708,
+      "eval_runtime": 5.3356,
+      "eval_samples_per_second": 5.997,
       "eval_steps_per_second": 0.375,
       "step": 100
-    },
-    {
-      "epoch": 0.2503128911138924,
-      "eval_loss": 0.05197252705693245,
-      "eval_runtime": 5.3201,
-      "eval_samples_per_second": 6.015,
-      "eval_steps_per_second": 0.376,
-      "step": 200
-    },
-    {
-      "epoch": 0.37546933667083854,
-      "eval_loss": 0.05055840685963631,
-      "eval_runtime": 5.3195,
-      "eval_samples_per_second": 6.016,
-      "eval_steps_per_second": 0.376,
-      "step": 300
     }
   ],
   "logging_steps": 500,
@@ -50,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.425702422511616e+17,
+  "total_flos": 1.141900807503872e+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:b605b358c373440c9ebdf745f0e1f7e58b46da2c8aab9f903bc99604afecb2c9
+oid sha256:8bb37296cb1494e65ca4d99afd2ebccbcedc47e87fcae7b3517de210a3e7a5f4
 size 5560