Upload folder using huggingface_hub

checkpoint-20/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "k_proj"
+    "o_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 sha256:5c61db184fd0e4599fe81eede9a7c4e4e66d61c75411ed4fa24c9bceefad2598
+oid sha256:f1bd4deecc25a59d9e7081510dc1c85de2a777a40951eafab3f05cd2fc47facf
 size 27297032

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a73d79a4c6e24675e57eccc221d88d3e22b63e88ee6f26200e3e752db4221a
+oid sha256:5f4fd3845fd9c07fcaecf67c95d17ec832b97260bb4e2aa6bcb99b915f8e1b86
 size 54678010

checkpoint-20/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2933f07bf463658cedf3c1dfe599ce4fe850fc4b964e637a8a22550bd717d69
+oid sha256:5781d61d6318b5684168e138e4e58e323109bc948f2bd2dad6075abad86657c7
 size 14512

checkpoint-20/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde39b4ddb5e4e2b9cf26588b19c8eb140ec75c0c91165b0fa820216fde06c21
+oid sha256:7b4df38a04a262f2c9ae17e5091c42f0a79dfa2e5e2fa1b69b141d8f3f918527
 size 14512

checkpoint-20/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6620982885360718,
+  "best_metric": 0.6632674932479858,
   "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": 1.2618540525436401,
-      "eval_runtime": 210.4635,
-      "eval_samples_per_second": 13.622,
-      "eval_steps_per_second": 3.407,
+      "eval_loss": 1.2639678716659546,
+      "eval_runtime": 212.9338,
+      "eval_samples_per_second": 13.464,
+      "eval_steps_per_second": 3.367,
       "step": 10
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.919330894947052,
+      "grad_norm": 0.9167371988296509,
       "learning_rate": 0.0001686241637868734,
-      "loss": 1.3402,
+      "loss": 1.2841,
       "step": 20
     },
     {
       "epoch": 0.01,
-      "eval_loss": 0.6620982885360718,
-      "eval_runtime": 211.5175,
-      "eval_samples_per_second": 13.554,
-      "eval_steps_per_second": 3.39,
+      "eval_loss": 0.6632674932479858,
+      "eval_runtime": 213.8138,
+      "eval_samples_per_second": 13.409,
+      "eval_steps_per_second": 3.353,
       "step": 20
     }
   ],
@@ -37,7 +37,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 9980294962610176.0,
+  "total_flos": 1.0200994004598784e+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:b299bd5cc2268988933042a1007b13e809128e91e8b83f90595fa635ae59af06
+oid sha256:f759d9115ca82f09dba4a4485ea9736298ef842bc83818bf3fb831f68f5920ed
 size 5112