Training in progress, step 40
Browse files- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367186.d9b5ba24fe65.998.0 +3 -0
- runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367798.d9b5ba24fe65.998.1 +3 -0
- runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367871.d9b5ba24fe65.998.2 +3 -0
- runs/Sep20_11-36-44_d9b5ba24fe65/events.out.tfevents.1758368209.d9b5ba24fe65.8072.0 +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bigcode/starcoderbase-1b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 8,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"c_proj",
|
| 29 |
+
"c_attn",
|
| 30 |
+
"c_fc",
|
| 31 |
+
"q_attn"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65024b3ee6299e15d22d3faeedb6caccaff999968ec7f9d4bbe6829c0ec96976
|
| 3 |
+
size 22241240
|
runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367186.d9b5ba24fe65.998.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6858812c2047569088ef8e770a607281c0df904b3218415807a4eaa4a10fa677
|
| 3 |
+
size 5877
|
runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367798.d9b5ba24fe65.998.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab9a949e8234135857fcbc5005d10a81ccab4be3ab2bb7f9297edd0f86877c58
|
| 3 |
+
size 5877
|
runs/Sep20_11-19-19_d9b5ba24fe65/events.out.tfevents.1758367871.d9b5ba24fe65.998.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0b1036e45f2c3326ada301bf128c83bdcf2b5e104ebf52ba01aba09a2e62d67
|
| 3 |
+
size 5877
|
runs/Sep20_11-36-44_d9b5ba24fe65/events.out.tfevents.1758368209.d9b5ba24fe65.8072.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7381762f446297fcc243c256d2e3775bc0dbf6176155abf7d53b8e66cd4b6e7e
|
| 3 |
+
size 14573
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b8d6f8e98617e748ede367b2154ed123e1daa5cdea0b1a0590cc916de84d85
|
| 3 |
+
size 5841
|