Upload folder using huggingface_hub

checkpoint-50/adapter_config.json

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "v_proj",
+    "k_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792bf8f744bca5db30a5b2fe80e0610d871d2e0e9c0a4f386c15921efdc2cada
+oid sha256:8124a081a7ccfa909b9e072bfa0377d8895934427a97f45a78b899294c019006
 size 436242776

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfe60b7f0163e31d4d317b854f7aa8b441fdda4591c40ed389e383d3a3f89cf
+oid sha256:9ea58ef1f259cc64213e083069205c6a7c87f3bda280b0cedd8d82aa9ea9a001
 size 872568314

checkpoint-50/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155af0328dced3a7822123bfbbfc0a98082468058997d134358c43dd61128a48
-size 14512
+oid sha256:37f8cf6ff0104f126e962b837e6aadc34920baa4dba5c947d76a4d280d03d435
+size 15024

checkpoint-50/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b7ab3a551c96c4ceca4cd3993bf33763b09c0ba81bc2a77fec0f7faa8f7890
-size 14512
+oid sha256:522e793c65745183643c72542cf75d1f9178a0262c7be626f122c78da45ba43b
+size 15024

checkpoint-50/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d967f7ca7413da97b4ea337e08080f0a99b7e9e9112a37c490f5456bb88c9f55
+oid sha256:715a6d2d00c49a8f827f26e430939815ec4b310cc1838bb170e0cd29a335df83
 size 15024

checkpoint-50/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce606d0eda198f3c803125cc3e4b89d1b4062b31873f62965301029791846992
+oid sha256:56b9eef68233418cf695ee351c740b2435854b7f56a1de55cda0a2cb934925b9
 size 15024

checkpoint-50/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.40922558307647705,
+  "best_metric": 0.40609535574913025,
   "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-50",
-  "epoch": 0.24783147459727387,
+  "epoch": 0.49504950495049505,
   "eval_steps": 10,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -9,57 +9,57 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.05,
-      "eval_loss": 0.6367942690849304,
-      "eval_runtime": 180.8957,
-      "eval_samples_per_second": 15.849,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.1,
+      "eval_loss": 0.6292536854743958,
+      "eval_runtime": 93.2576,
+      "eval_samples_per_second": 30.743,
+      "eval_steps_per_second": 0.965,
       "step": 10
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.34346863627433777,
+      "epoch": 0.2,
+      "grad_norm": 0.24918170273303986,
       "learning_rate": 0.00019510565162951537,
-      "loss": 0.9774,
+      "loss": 0.9604,
       "step": 20
     },
     {
-      "epoch": 0.1,
-      "eval_loss": 0.48089343309402466,
-      "eval_runtime": 180.8882,
-      "eval_samples_per_second": 15.85,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.2,
+      "eval_loss": 0.46683359146118164,
+      "eval_runtime": 93.2154,
+      "eval_samples_per_second": 30.757,
+      "eval_steps_per_second": 0.966,
       "step": 20
     },
     {
-      "epoch": 0.15,
-      "eval_loss": 0.44581571221351624,
-      "eval_runtime": 180.8305,
-      "eval_samples_per_second": 15.855,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.3,
+      "eval_loss": 0.4341636002063751,
+      "eval_runtime": 93.1765,
+      "eval_samples_per_second": 30.77,
+      "eval_steps_per_second": 0.966,
       "step": 30
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.22729116678237915,
+      "epoch": 0.4,
+      "grad_norm": 0.16474689543247223,
       "learning_rate": 0.0001529919264233205,
-      "loss": 0.4459,
+      "loss": 0.4381,
       "step": 40
     },
     {
-      "epoch": 0.2,
-      "eval_loss": 0.4221758544445038,
-      "eval_runtime": 180.8406,
-      "eval_samples_per_second": 15.854,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.4,
+      "eval_loss": 0.40781059861183167,
+      "eval_runtime": 93.1933,
+      "eval_samples_per_second": 30.764,
+      "eval_steps_per_second": 0.966,
       "step": 40
     },
     {
-      "epoch": 0.25,
-      "eval_loss": 0.40922558307647705,
-      "eval_runtime": 181.1791,
-      "eval_samples_per_second": 15.824,
-      "eval_steps_per_second": 0.993,
+      "epoch": 0.5,
+      "eval_loss": 0.40609535574913025,
+      "eval_runtime": 93.1926,
+      "eval_samples_per_second": 30.764,
+      "eval_steps_per_second": 0.966,
       "step": 50
     }
   ],
@@ -68,7 +68,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2.2680060137832448e+17,
+  "total_flos": 4.5255742262450586e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-50/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
+oid sha256:daf4ca86cd3cb3688a488e999435cb5aec8a4b0702902c7de81df751b2180e05
 size 5176