Training in progress, step 10, checkpoint

checkpoint-10/adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
+    "q_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "k_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:fa0ee449ad8092b56197f45cf74e7a4cbb581a88aba444656cb8d25a76e6a179
+oid sha256:213e4149e5333fef153ec75df7cfeada3affc4cf1274cbd86e8be5940e882d62
 size 27297032

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a2ebce289b35140db6643201029bb30d4fe0eeeb94a898211cf0041b8a602a
+oid sha256:02334521114a0317774a2cd0a9e77f83d2746dc43e5f11f138281e26e55fbfae
 size 54678010

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d6b8b05b28b11fb19df29ec4da5f7976490fbc4941f1f3e465548c31b90d25
+oid sha256:48704b03cfa5f48d380a2c0f70433ae9a9fb0c6fb3cbb0dfa07bd65e22953db4
 size 14512

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5489dea245ed762ab68ef20e8c1a7c9cf77ceb1b2c43bbb6ab6fae216adfcf46
+oid sha256:7c12f4d0596e72b5705a2a240e5d3c50ef73006c8546aac031b8955275186fcc
 size 14512

checkpoint-10/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec27b56d229809317bd71fa4690986df09485352bf2a99530baf5be2ed6ac3c1
+oid sha256:235af9e0142e33373d5a0c3eca9b645008891b3f929de0bb9dec14be1e0a5498
 size 1000

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.339296579360962,
+  "best_metric": 1.268858551979065,
   "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": 1.339296579360962,
-      "eval_runtime": 213.3411,
-      "eval_samples_per_second": 13.439,
-      "eval_steps_per_second": 3.361,
+      "eval_loss": 1.268858551979065,
+      "eval_runtime": 210.5046,
+      "eval_samples_per_second": 13.62,
+      "eval_steps_per_second": 3.406,
       "step": 10
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 4866987146608640.0,
+  "total_flos": 5578962264653824.0,
   "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 sha256:7e3b7278b89475c5766f12d80ad1bb5584ebb5eac8d0c1422c650e8199bc1159
+oid sha256:fe0fbff02770a0f92e2a7ea855958234a42b39724e3eefaa45f6d3ef5d38af30
 size 5112