Upload folder using huggingface_hub

checkpoint-150/README.md

@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.18.0
+- PEFT 0.16.0

checkpoint-150/adapter_config.json

@@ -1,7 +1,5 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "LlamaForCausalLM",
     "parent_library": "transformers.models.llama.modeling_llama",
@@ -10,7 +8,6 @@
   "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
-  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -27,21 +24,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
     "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
     "q_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

checkpoint-150/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65374b7a5d997154440e34ac4bbd51a566f8d7a4d4ba19c0ffb48634caef35e6
+oid sha256:a7cee91ee920a50a5870d0d736d3af53b0f3e76d10b4f9ee7d8894b9e3a1765f
 size 97307544

checkpoint-150/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2437f673977fef74e8260e1e6d7b3a56d3ba1c164abe4f35ca525e4524b766dc
+oid sha256:0a02a7712989a7bbdcd872d31d8a6e212e74ecd866e06a4cc1bc522874d6a270
 size 194846331

checkpoint-150/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+oid sha256:716d83e48b4ef0ecc739db256420344d8764b568cd2fec53ea128d8653e43804
 size 14645

checkpoint-150/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c272906c5c00ea266d4d7b2f058e95352849407edf35e7999971a0f3aead2e82
+oid sha256:ae8ec43895301a2abc48f62a246f249bdb98524006b5b13cfd6c9b55f6c69c2c
 size 1465

checkpoint-150/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012,
+  "epoch": 0.024,
   "eval_steps": 500,
   "global_step": 150,
   "is_hyper_param_search": false,
@@ -10,7 +10,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 9999999,
-  "max_steps": 12500,
+  "max_steps": 6250,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 150,
@@ -26,8 +26,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3741129112813568e+16,
-  "train_batch_size": 2,
+  "total_flos": 3.38062726877184e+16,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-150/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1e61689e67f92937b424f1859bcd30776e97cdda7fe9a43a40ccef44783eb7
-size 6225
+oid sha256:aa7d60f39157d6af42ddf961454a0f16be99637b24b2dc9dcfdb9f7339f17b36
+size 6161