Upload 6 files
Browse files- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +40 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e68657dbbc8f13c88c8baa92e8a81962f6b56d9173be2e898976af3a3cbe24b8
|
| 3 |
+
size 13648432
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e069f05aed768570ae2d31c5563963183bf2599cc9649a39ef8105b56dbef61
|
| 3 |
+
size 7073594
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc4ab5f608c113ef9b81b5921bd661a21962184c52075538ed871611015781ce
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03636892638929299,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03636892638929299,
|
| 13 |
+
"grad_norm": 8.559616088867188,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 2.9642,
|
| 16 |
+
"step": 500
|
| 17 |
+
}
|
| 18 |
+
],
|
| 19 |
+
"logging_steps": 500,
|
| 20 |
+
"max_steps": 500,
|
| 21 |
+
"num_input_tokens_seen": 0,
|
| 22 |
+
"num_train_epochs": 1,
|
| 23 |
+
"save_steps": 50,
|
| 24 |
+
"stateful_callbacks": {
|
| 25 |
+
"TrainerControl": {
|
| 26 |
+
"args": {
|
| 27 |
+
"should_epoch_stop": false,
|
| 28 |
+
"should_evaluate": false,
|
| 29 |
+
"should_log": false,
|
| 30 |
+
"should_save": true,
|
| 31 |
+
"should_training_stop": true
|
| 32 |
+
},
|
| 33 |
+
"attributes": {}
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"total_flos": 5766399393792000.0,
|
| 37 |
+
"train_batch_size": 1,
|
| 38 |
+
"trial_name": null,
|
| 39 |
+
"trial_params": null
|
| 40 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d707b4f6572ccaab0011dbd149b818ddf84a399dbed7529db2dbce6fa2d46ed0
|
| 3 |
+
size 5304
|