Upload folder using huggingface_hub

checkpoint-100/adapter_config.json

@@ -21,8 +21,8 @@
   "target_modules": [
     "o_proj",
     "q_proj",
-    "k_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-100/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54fc4264d53b7817584e2bece3faa84e29259146c91e0d9dabff36297282b16a
+oid sha256:4b3be29181cd0bc6297f4a2807e05a7b0465de3300470bff9c3702a18ad742a8
 size 54560368

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd976350789b28f06eccbcaaea9c89d73939a81fa429dd93a04b342df73878df
+oid sha256:c8415338139558c07ee0d2124c173c2b83f22304609bfc8e8f609bdd84eda6e4
 size 109204730

checkpoint-100/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a5cfc0d180ca9515a82326e20e2dca1a0034b75f34ac0f024d267881ee3cf9
+oid sha256:59d8a37ef428d5411dd48b6d9ebacb82b8bc47ecb2fe0a62c0798494709644e5
 size 14512

checkpoint-100/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff09f2de824a65539d4401b01781ac984c601cef0eefa6ee4f0a583e701bdd9
+oid sha256:5d55e6ac2913c509fb7eb01dfd22e053c47bbb7a22a053f2d4c3ced416fed21f
 size 14512

checkpoint-100/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4931565821170807,
+  "best_metric": 0.49974650144577026,
   "best_model_checkpoint": "./mistral/07-03-24-Weni-pipeline_test3_Zeroshot-2_max_steps-3224_batch_64_2024-03-07_ppid_7/checkpoint-100",
   "epoch": 0.24798512089274644,
   "eval_steps": 100,
@@ -10,44 +10,44 @@
   "log_history": [
     {
       "epoch": 0.05,
-      "grad_norm": 1.9672261476516724,
-      "learning_rate": 1.1801242236024846e-05,
-      "loss": 1.8876,
+      "grad_norm": 1.8224879503250122,
+      "learning_rate": 1.1180124223602485e-05,
+      "loss": 1.913,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "grad_norm": 3.650391101837158,
+      "grad_norm": 2.1416420936584473,
       "learning_rate": 2.3602484472049692e-05,
-      "loss": 1.6653,
+      "loss": 1.6555,
       "step": 40
     },
     {
       "epoch": 0.15,
-      "grad_norm": 1.0555133819580078,
+      "grad_norm": 1.7435169219970703,
       "learning_rate": 3.60248447204969e-05,
-      "loss": 1.3654,
+      "loss": 1.3503,
       "step": 60
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.6545969247817993,
+      "grad_norm": 0.6260000467300415,
       "learning_rate": 4.8447204968944106e-05,
-      "loss": 0.9152,
+      "loss": 0.9403,
       "step": 80
     },
     {
       "epoch": 0.25,
-      "grad_norm": 0.24923652410507202,
+      "grad_norm": 0.6695926189422607,
       "learning_rate": 6.086956521739131e-05,
-      "loss": 0.5565,
+      "loss": 0.5642,
       "step": 100
     },
     {
       "epoch": 0.25,
-      "eval_loss": 0.4931565821170807,
-      "eval_runtime": 180.4575,
-      "eval_samples_per_second": 15.887,
+      "eval_loss": 0.49974650144577026,
+      "eval_runtime": 180.5121,
+      "eval_samples_per_second": 15.883,
       "eval_steps_per_second": 0.997,
       "step": 100
     }
@@ -57,7 +57,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 2.060663117494354e+17,
+  "total_flos": 2.0437256133148672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062109216a0084aea3dc340c0b85f9dfab30a0afc265e7ea132f1e1b1a292fe1
+oid sha256:31dd07d3bcf35f257ee096471f2d6906b6529d45189b00701808fc5b82a560cf
 size 5112