Upload folder using huggingface_hub

checkpoint-10/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-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3e0cdae368d14a843151822c64d75b9e64eabba537d101b909316145d64f25
+oid sha256:966422cb45a8382bac17cf41216e3afe2053cf607f2da94a632139fc2d0b8ba1
 size 436242776

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fdb544e9a22a371a5d8df82da422560206b79b40d84a212a74ea56b50f59fa
+oid sha256:5c39dfe27d7776c478e77eeae50c2b4248bca4d11a6ea01c21c5e11a9171540f
 size 872568314

checkpoint-10/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5bc6d58edfb094654e0fd7d8830f6528f86d2a2c0b08173da1fe23f3fac2ef
-size 14512
+oid sha256:aacc211f04d2987b22d9e98352791900880485b00e7ba542532f0ecec3bcdfef
+size 15024

checkpoint-10/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1386ecdf853bc6f64d03fe0f70a1791d948a0933fed4c2a20ca0f9ecc9b5ac63
-size 14512
+oid sha256:b8bd5fb280d3a476b13d48a02b0eab8ef08f847c3cfef1b578e294c9487bfbef
+size 15024

checkpoint-10/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5cafbb94312025b0d3e9a10373eb77e4d2cfa96c533075b98d8adca5f98bda2
+oid sha256:90bdd80721c9b7e7e4d190530444466ac19797a0256ba7d2392a13f02d9dfac0
 size 15024

checkpoint-10/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5531210de2190ee016328d2c16999d7dcfc5a2aede25bfe7c7b62f0ac32df14
+oid sha256:180162a870c99e232cbac92cffd2c1be442b364558d2437654326dbfd6a2c018
 size 15024

checkpoint-10/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.6367942690849304,
+  "best_metric": 0.6292536854743958,
   "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-10",
-  "epoch": 0.04956629491945477,
+  "epoch": 0.09900990099009901,
   "eval_steps": 10,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -9,11 +9,11 @@
   "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
     }
   ],
@@ -22,7 +22,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 4.493525352080998e+16,
+  "total_flos": 9.033558328030003e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-10/training_args.bin

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

checkpoint-70/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-70/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb912af6b1796046b92cd31a140d407273ff753ac7f3269fc3c5f3185cb84e1
+oid sha256:3729ade0578702d582ba4201d2056d525c6b98445fc9f287499aa8cc4a04ad0f
 size 436242776

checkpoint-70/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631ee3323927506f442194f35db41e1ecdfb11bea1ce0e91876dfd94f7df30c1
+oid sha256:f41106fec66c8da66955717a5c0e57087dbb2ce1e9c2786539e9d14f13dba082
 size 872568314

checkpoint-70/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a0a43eb1da4e2bdacd5b9613bc246aef81888090db42765afb6f369c67c4c1
-size 14512
+oid sha256:3f23d434a5adf472af32d0d067bd6c7196c5fada3cf7bbec69afdf226737ae9c
+size 15024

checkpoint-70/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90cb909835d393126c788ffdccbb0e802fe522bcd647fc16615a348d6c39cfd4
-size 14512
+oid sha256:f8cd675fa29ceb7104e041bb8b6f813a24babb71dc2874373344d885230ca229
+size 15024

checkpoint-70/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74915e0aef978c84c56eee8bed06ba18d446da4dd1125eda8fbb469b255811be
+oid sha256:a45b3b845e6140514d22eb89d3d82950a7efd6b6e0c772b6f3e23d8289d822fd
 size 1000

checkpoint-70/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.39848339557647705,
+  "best_metric": 0.3856147527694702,
   "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-70",
-  "epoch": 0.3469640644361834,
+  "epoch": 0.693069306930693,
   "eval_steps": 10,
   "global_step": 70,
   "is_hyper_param_search": false,
@@ -9,80 +9,80 @@
   "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": 0.6981944441795349,
+      "eval_runtime": 94.6462,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 0.951,
       "step": 10
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.34346863627433777,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 0.9774,
+      "epoch": 0.2,
+      "grad_norm": 0.2654201090335846,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0016,
       "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": 0.467332661151886,
+      "eval_runtime": 94.5373,
+      "eval_samples_per_second": 30.327,
+      "eval_steps_per_second": 0.952,
       "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": 0.434685617685318,
+      "eval_runtime": 94.5899,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
       "step": 30
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.22729116678237915,
-      "learning_rate": 0.0001529919264233205,
-      "loss": 0.4459,
+      "epoch": 0.4,
+      "grad_norm": 1.3763986825942993,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.4357,
       "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": 0.4082697033882141,
+      "eval_runtime": 94.551,
+      "eval_samples_per_second": 30.322,
+      "eval_steps_per_second": 0.952,
       "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": 0.40642818808555603,
+      "eval_runtime": 94.5831,
+      "eval_samples_per_second": 30.312,
+      "eval_steps_per_second": 0.952,
       "step": 50
     },
     {
-      "epoch": 0.3,
-      "grad_norm": 0.27356910705566406,
-      "learning_rate": 8.608268990399349e-05,
-      "loss": 0.4132,
+      "epoch": 0.59,
+      "grad_norm": 0.16300354897975922,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4012,
       "step": 60
     },
     {
-      "epoch": 0.3,
-      "eval_loss": 0.4156472384929657,
-      "eval_runtime": 180.7116,
-      "eval_samples_per_second": 15.865,
-      "eval_steps_per_second": 0.996,
+      "epoch": 0.59,
+      "eval_loss": 0.39164847135543823,
+      "eval_runtime": 94.6074,
+      "eval_samples_per_second": 30.304,
+      "eval_steps_per_second": 0.951,
       "step": 60
     },
     {
-      "epoch": 0.35,
-      "eval_loss": 0.39848339557647705,
-      "eval_runtime": 180.7856,
-      "eval_samples_per_second": 15.859,
-      "eval_steps_per_second": 0.996,
+      "epoch": 0.69,
+      "eval_loss": 0.3856147527694702,
+      "eval_runtime": 94.5883,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
       "step": 70
     }
   ],
@@ -91,7 +91,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 3.162393138828411e+17,
+  "total_flos": 6.30628785351295e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-70/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
+oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
 size 5176

checkpoint-80/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-80/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b527b969a7485a4a5babdabe6555b5c383c05ebc9f26e37428a33b13c8b5da9d
+oid sha256:24e21a859be9d207f149ffc0b46dfcc320ea1ee34732d41bf90a24c1b253b907
 size 436242776

checkpoint-80/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1eec7cb54f027bab8ca6c3381b6ffff8c752180f8c5c51218b412ed94f8b847
+oid sha256:f70660925ff51a9f94e304f49828ef04a284f17d3a7bc460079ba9ce1a8e117e
 size 872568314

checkpoint-80/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a801669d16f26e581b00baf98c1e7c4a03b79841796ecdf09044e710d489912
-size 14512
+oid sha256:93f8281a861fa369d43b6beb0ae6c67fde2ae747fd1b83daa3e6a92279b33244
+size 15024

checkpoint-80/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832aea46110ff9ec827428f726a2265f68e7159fe5184ac4697ecf55087199d1
-size 14512
+oid sha256:090bdbfa5ddd772617ed624bd84911da0c7bf8de602f4e422d57d8f9b2a59994
+size 15024

checkpoint-80/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b71e69a6ae8462bc71f9d5c4bc5cfca3ea5f220e53bbe18bfaf849b8d7997dd
+oid sha256:0af4379a58cfae44f0dbe3cf08fcd1bc98068c05bfa6733ba98cd23f1ebaae09
 size 1000

checkpoint-80/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.3947867155075073,
+  "best_metric": 0.38140159845352173,
   "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-80",
-  "epoch": 0.3965303593556382,
+  "epoch": 0.7920792079207921,
   "eval_steps": 10,
   "global_step": 80,
   "is_hyper_param_search": false,
@@ -9,95 +9,95 @@
   "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": 0.6981944441795349,
+      "eval_runtime": 94.6462,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 0.951,
       "step": 10
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.34346863627433777,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 0.9774,
+      "epoch": 0.2,
+      "grad_norm": 0.2654201090335846,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0016,
       "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": 0.467332661151886,
+      "eval_runtime": 94.5373,
+      "eval_samples_per_second": 30.327,
+      "eval_steps_per_second": 0.952,
       "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": 0.434685617685318,
+      "eval_runtime": 94.5899,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
       "step": 30
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.22729116678237915,
-      "learning_rate": 0.0001529919264233205,
-      "loss": 0.4459,
+      "epoch": 0.4,
+      "grad_norm": 1.3763986825942993,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.4357,
       "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": 0.4082697033882141,
+      "eval_runtime": 94.551,
+      "eval_samples_per_second": 30.322,
+      "eval_steps_per_second": 0.952,
       "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": 0.40642818808555603,
+      "eval_runtime": 94.5831,
+      "eval_samples_per_second": 30.312,
+      "eval_steps_per_second": 0.952,
       "step": 50
     },
     {
-      "epoch": 0.3,
-      "grad_norm": 0.27356910705566406,
-      "learning_rate": 8.608268990399349e-05,
-      "loss": 0.4132,
+      "epoch": 0.59,
+      "grad_norm": 0.16300354897975922,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4012,
       "step": 60
     },
     {
-      "epoch": 0.3,
-      "eval_loss": 0.4156472384929657,
-      "eval_runtime": 180.7116,
-      "eval_samples_per_second": 15.865,
-      "eval_steps_per_second": 0.996,
+      "epoch": 0.59,
+      "eval_loss": 0.39164847135543823,
+      "eval_runtime": 94.6074,
+      "eval_samples_per_second": 30.304,
+      "eval_steps_per_second": 0.951,
       "step": 60
     },
     {
-      "epoch": 0.35,
-      "eval_loss": 0.39848339557647705,
-      "eval_runtime": 180.7856,
-      "eval_samples_per_second": 15.859,
-      "eval_steps_per_second": 0.996,
+      "epoch": 0.69,
+      "eval_loss": 0.3856147527694702,
+      "eval_runtime": 94.5883,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
       "step": 70
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 0.1912572681903839,
-      "learning_rate": 2.5685517452260567e-05,
-      "loss": 0.4004,
+      "epoch": 0.79,
+      "grad_norm": 0.14875428378582,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 0.3846,
       "step": 80
     },
     {
-      "epoch": 0.4,
-      "eval_loss": 0.3947867155075073,
-      "eval_runtime": 180.6659,
-      "eval_samples_per_second": 15.869,
-      "eval_steps_per_second": 0.996,
+      "epoch": 0.79,
+      "eval_loss": 0.38140159845352173,
+      "eval_runtime": 94.5138,
+      "eval_samples_per_second": 30.334,
+      "eval_steps_per_second": 0.952,
       "step": 80
     }
   ],
@@ -106,7 +106,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 3.617727103190958e+17,
+  "total_flos": 7.216782437357978e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-80/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
+oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
 size 5176