Upload folder using huggingface_hub

checkpoint-20/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "o_proj",
     "k_proj",
-    "v_proj",
-    "o_proj"
+    "v_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:f1bd4deecc25a59d9e7081510dc1c85de2a777a40951eafab3f05cd2fc47facf
+oid sha256:5dcf5a551c349c7e0b733562aa4ae628da73cca6a51b41dbe9aa6df61c725776
 size 27297032

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4fd3845fd9c07fcaecf67c95d17ec832b97260bb4e2aa6bcb99b915f8e1b86
+oid sha256:a377b03d709c4d53ca6e7ad8224d147cf444f80d2cb8b9238a4e4b0c02f61fb9
 size 54678010

checkpoint-20/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5781d61d6318b5684168e138e4e58e323109bc948f2bd2dad6075abad86657c7
+oid sha256:ece29a201498bea2402c25ea6a05c3a44d81e4175ff48953b1031f16a14fe73c
 size 14512

checkpoint-20/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4df38a04a262f2c9ae17e5091c42f0a79dfa2e5e2fa1b69b141d8f3f918527
+oid sha256:99ae85c442798078bca52fa33ec295dc643f25acfc61d967bb4f7e6b529e746c
 size 14512

checkpoint-20/scheduler.pt

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

checkpoint-20/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6632674932479858,
+  "best_metric": 0.6782544255256653,
   "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": 1.2639678716659546,
-      "eval_runtime": 212.9338,
-      "eval_samples_per_second": 13.464,
-      "eval_steps_per_second": 3.367,
+      "eval_loss": 1.3349500894546509,
+      "eval_runtime": 212.0568,
+      "eval_samples_per_second": 13.52,
+      "eval_steps_per_second": 3.381,
       "step": 10
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.9167371988296509,
-      "learning_rate": 0.0001686241637868734,
-      "loss": 1.2841,
+      "grad_norm": 0.9119272828102112,
+      "learning_rate": 0.00017273736415730488,
+      "loss": 1.3576,
       "step": 20
     },
     {
       "epoch": 0.01,
-      "eval_loss": 0.6632674932479858,
-      "eval_runtime": 213.8138,
-      "eval_samples_per_second": 13.409,
-      "eval_steps_per_second": 3.353,
+      "eval_loss": 0.6782544255256653,
+      "eval_runtime": 212.5203,
+      "eval_samples_per_second": 13.49,
+      "eval_steps_per_second": 3.374,
       "step": 20
     }
   ],
@@ -37,7 +37,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.0200994004598784e+16,
+  "total_flos": 1.0232424575270912e+16,
   "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:f759d9115ca82f09dba4a4485ea9736298ef842bc83818bf3fb831f68f5920ed
+oid sha256:09451dd342dbcd48b4952803853b975a8bd13b7e94555d226899f1b4fa2438b7
 size 5112