Training in progress, step 10, checkpoint

checkpoint-10/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
+    "v_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:fa53b3eb340a3cddab9910dc84cc4d10f325f5b7548580dd8d98e60db9bec895
+oid sha256:b26689a508eed09930d054a00ee65a007c673012eec2de0fb70464589122f6d7
 size 27297032

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b865af35c752678c7ceb1bb8351b318a080effc69c85aeaf6715088808c8502
+oid sha256:cfc60ee41baf9c55d49e474dc504985c9f7f23e3e5336a76985665d30b96a4f8
 size 54678010

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca2a297e7c44cdfd2b64bdcfd36aae2623a83c5c0d7be5dc2786f6037cfe92e
+oid sha256:490a6592679c3e782894c2da6f1151249970898453b75fa8d7d95ff222548378
 size 14512

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a374c072d59f9b1e72d0cbfc881a7ec98e593fce8d036754d6bd9e4901adc453
+oid sha256:35b301caae620f453c55134c8c142094308ec10e7b23806f6ddc6e8e7f8957b1
 size 14512

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.1490468978881836,
+  "best_metric": 1.1541752815246582,
   "best_model_checkpoint": "./mistral/29-02-24-Weni-test-folder-upload_Zeroshot-2_max_steps-30_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": 1.1490468978881836,
-      "eval_runtime": 210.1155,
-      "eval_samples_per_second": 13.645,
-      "eval_steps_per_second": 3.412,
+      "eval_loss": 1.1541752815246582,
+      "eval_runtime": 207.9314,
+      "eval_samples_per_second": 13.788,
+      "eval_steps_per_second": 3.448,
       "step": 10
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 5248255688441856.0,
+  "total_flos": 5115358662885376.0,
   "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:c185641aa778ebf322b648b5876f97d18fd7a50b2686547151fb1af1b5885465
+oid sha256:f09d0841daf9591804106876bdb192dc55f373b1916ac8444c29f5c1b978fee3
 size 5112