Training in progress, step 10, checkpoint

checkpoint-10/adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347f0eda6580cadbe0640ce86054b0bbe862cfe4704b257ac5f3c331092c0675
+oid sha256:fa0ee449ad8092b56197f45cf74e7a4cbb581a88aba444656cb8d25a76e6a179
 size 27297032

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f3a8ce4f53cfb1cc8d15681aa89341631c54eeda8455d7a2309fb68ccccd8d
+oid sha256:05a2ebce289b35140db6643201029bb30d4fe0eeeb94a898211cf0041b8a602a
 size 54678010

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa88bd01c20ed7f51c4ffc4c0e105d58f84d47fa6510b5f3dea4c3f2a2c6094a
+oid sha256:09d6b8b05b28b11fb19df29ec4da5f7976490fbc4941f1f3e465548c31b90d25
 size 14512

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad63ecc2f0ee3034c7d6b5ec77eea06e1e97bf6c8f8e19114904d563ffde5989
+oid sha256:5489dea245ed762ab68ef20e8c1a7c9cf77ceb1b2c43bbb6ab6fae216adfcf46
 size 14512

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.34207284450531,
+  "best_metric": 1.339296579360962,
   "best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
   "epoch": 0.006199628022318661,
   "eval_steps": 10,
@@ -10,10 +10,10 @@
   "log_history": [
     {
       "epoch": 0.01,
-      "eval_loss": 1.34207284450531,
-      "eval_runtime": 211.9495,
-      "eval_samples_per_second": 13.527,
-      "eval_steps_per_second": 3.383,
+      "eval_loss": 1.339296579360962,
+      "eval_runtime": 213.3411,
+      "eval_samples_per_second": 13.439,
+      "eval_steps_per_second": 3.361,
       "step": 10
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 4989635306455040.0,
+  "total_flos": 4866987146608640.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55fef1baf040c97ea612999dab2e3ea9b4bc4904e42d865dd7556f3582f069d
+oid sha256:7e3b7278b89475c5766f12d80ad1bb5584ebb5eac8d0c1422c650e8199bc1159
 size 5112