Upload task output test13

README.md

@@ -4,7 +4,7 @@ tags:
 - generated_from_trainer
 base_model: samoline/b7447218-27e6-491c-b3ab-ea03a5b93541
 model-index:
-- name: workspace/axolotl/outputs/test1334test1234test1234test34/texttest
+- name: app/checkpoints/test13/texttest
   results: []
 ---
 
@@ -23,7 +23,7 @@ chat_template: llama3
 dataset_prepared_path: null
 datasets:
 - data_files:
-  - test1334test1234test1234test34_train_data.json
+  - test13_train_data.json
   ds_type: json
   format: custom
   path: /workspace/axolotl/data
@@ -60,11 +60,11 @@ lora_target_linear: true
 lr_scheduler: cosine
 max_steps: 1
 micro_batch_size: 2
-mlflow_experiment_name: /workspace/axolotl/data/test1334test1234test1234test34_train_data.json
+mlflow_experiment_name: /workspace/axolotl/data/test13_train_data.json
 model_type: AutoModelForCausalLM
 num_epochs: 1
 optimizer: adamw_bnb_8bit
-output_dir: /workspace/axolotl/outputs/test1334test1234test1234test34/texttest
+output_dir: /app/checkpoints/test13/texttest
 pad_to_sequence_len: true
 resume_from_checkpoint: null
 s2_attention: null
@@ -79,10 +79,10 @@ trust_remote_code: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: offline
-wandb_name: test1334test1234test1234test34_texttest
+wandb_name: test13_texttest
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: test1334test1234test1234test34_texttest
+wandb_runid: test13_texttest
 warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
@@ -91,7 +91,7 @@ xformers_attention: null
 
 </details><br>
 
-# workspace/axolotl/outputs/test1334test1234test1234test34/texttest
+# app/checkpoints/test13/texttest
 
 This model was trained from scratch on the None dataset.
 

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "v_proj",
     "gate_proj",
     "q_proj",
     "k_proj",
-    "up_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj"
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea6929ca6dde2a3ac9c8a46014547707c434edda5748ced18cd7d5a5201fef2
+oid sha256:df441b8b6e1aeb048f34ab2a069d2a04d352efc664a687eab4e722c96c5253f7
 size 22573704

checkpoint-1/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: /cache/test1334test1234test1234test34/models/samoline--b7447218-27e6-491c-b3ab-ea03a5b93541
+base_model: /cache/models/samoline--b7447218-27e6-491c-b3ab-ea03a5b93541
 library_name: peft
 ---
 

checkpoint-1/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/cache/test1334test1234test1234test34/models/samoline--b7447218-27e6-491c-b3ab-ea03a5b93541",
+  "base_model_name_or_path": "/cache/models/samoline--b7447218-27e6-491c-b3ab-ea03a5b93541",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "v_proj",
     "gate_proj",
     "q_proj",
     "k_proj",
-    "up_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj"
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint-1/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea6929ca6dde2a3ac9c8a46014547707c434edda5748ced18cd7d5a5201fef2
+oid sha256:df441b8b6e1aeb048f34ab2a069d2a04d352efc664a687eab4e722c96c5253f7
 size 22573704

checkpoint-1/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984dce112fc24ae4eaba62d2904d0043a7f32ec1a9ca5e5894925adf96d89a5b
+oid sha256:cbec75f3f8d93faf59f3fc0b466eb5c915a4ef9cc3a34589a1abcb3ff391778b
 size 11710970

checkpoint-1/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009900990099009901,
+  "epoch": 0.010416666666666666,
   "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
@@ -10,10 +10,10 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.009900990099009901,
-      "grad_norm": 0.472037672996521,
+      "epoch": 0.010416666666666666,
+      "grad_norm": 0.7040483951568604,
       "learning_rate": 0.0,
-      "loss": 0.9592,
+      "loss": 1.8913,
       "step": 1
     }
   ],

checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d896a8d25c643391583d2ed5bb4dced3ad66e83c5f45be84dfcb518f2faa37f
-size 7224
+oid sha256:9bdf7e71da960d3efa1aa8d8cbea4d85ac0a45f3974df04b03a4784773714147
+size 7096