Upload folder using huggingface_hub

checkpoint-20/adapter_config.json

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

checkpoint-20/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcf5a551c349c7e0b733562aa4ae628da73cca6a51b41dbe9aa6df61c725776
+oid sha256:fc3a917ea011616f2e138820f5ec80678f902f460d8c833c1a09a1ffbfeacff5
 size 27297032

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a377b03d709c4d53ca6e7ad8224d147cf444f80d2cb8b9238a4e4b0c02f61fb9
+oid sha256:f3534a549726a2bd1a5f1784c17c5ed93bf055038c239bfa9d8551a10c509531
 size 54678010

checkpoint-20/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece29a201498bea2402c25ea6a05c3a44d81e4175ff48953b1031f16a14fe73c
+oid sha256:b2933f07bf463658cedf3c1dfe599ce4fe850fc4b964e637a8a22550bd717d69
 size 14512

checkpoint-20/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ae85c442798078bca52fa33ec295dc643f25acfc61d967bb4f7e6b529e746c
+oid sha256:393b54f5f5716592c70ccb9953812e7f2d2420e88129d9a6302b103771f5655d
 size 14512

checkpoint-20/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9273428cca691ad47ec11da78b09b76f05725b681e3b9061aeabe6c9d6df431d
+oid sha256:50456e7261e136d297aa7f12fc0e2dc3c2382226b412fd99a25a3022e310d003
 size 1000

checkpoint-20/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6782544255256653,
+  "best_metric": 0.6531360149383545,
   "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-20",
   "epoch": 0.012399256044637322,
   "eval_steps": 10,
@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 0.01,
-      "eval_loss": 1.3349500894546509,
-      "eval_runtime": 212.0568,
-      "eval_samples_per_second": 13.52,
-      "eval_steps_per_second": 3.381,
+      "eval_loss": 1.2581307888031006,
+      "eval_runtime": 215.3103,
+      "eval_samples_per_second": 13.316,
+      "eval_steps_per_second": 3.33,
       "step": 10
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.9119272828102112,
-      "learning_rate": 0.00017273736415730488,
-      "loss": 1.3576,
+      "grad_norm": 1.0680043697357178,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 1.3185,
       "step": 20
     },
     {
       "epoch": 0.01,
-      "eval_loss": 0.6782544255256653,
-      "eval_runtime": 212.5203,
-      "eval_samples_per_second": 13.49,
-      "eval_steps_per_second": 3.374,
+      "eval_loss": 0.6531360149383545,
+      "eval_runtime": 215.822,
+      "eval_samples_per_second": 13.284,
+      "eval_steps_per_second": 3.322,
       "step": 20
     }
   ],
@@ -37,7 +37,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.0232424575270912e+16,
+  "total_flos": 9946814618796032.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-20/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09451dd342dbcd48b4952803853b975a8bd13b7e94555d226899f1b4fa2438b7
+oid sha256:add53164c8641f40e75a374f927c9457bbf2b0878715f67c1711793300a2b818
 size 5112