Upload task output test1334test1234test1234test12334
Browse files- README.md +7 -7
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- checkpoint-1/adapter_config.json +4 -4
- checkpoint-1/adapter_model.safetensors +1 -1
- checkpoint-1/optimizer.pt +1 -1
- checkpoint-1/trainer_state.json +4 -4
- checkpoint-1/training_args.bin +2 -2
README.md
CHANGED
|
@@ -4,7 +4,7 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
base_model: samoline/b7447218-27e6-491c-b3ab-ea03a5b93541
|
| 6 |
model-index:
|
| 7 |
-
- name: app/checkpoints/
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
|
@@ -23,7 +23,7 @@ chat_template: llama3
|
|
| 23 |
dataset_prepared_path: null
|
| 24 |
datasets:
|
| 25 |
- data_files:
|
| 26 |
-
-
|
| 27 |
ds_type: json
|
| 28 |
format: custom
|
| 29 |
path: /workspace/axolotl/data
|
|
@@ -60,11 +60,11 @@ lora_target_linear: true
|
|
| 60 |
lr_scheduler: cosine
|
| 61 |
max_steps: 1
|
| 62 |
micro_batch_size: 2
|
| 63 |
-
mlflow_experiment_name: /workspace/axolotl/data/
|
| 64 |
model_type: AutoModelForCausalLM
|
| 65 |
num_epochs: 1
|
| 66 |
optimizer: adamw_bnb_8bit
|
| 67 |
-
output_dir: /app/checkpoints/
|
| 68 |
pad_to_sequence_len: true
|
| 69 |
resume_from_checkpoint: null
|
| 70 |
s2_attention: null
|
|
@@ -79,10 +79,10 @@ trust_remote_code: true
|
|
| 79 |
val_set_size: 0.05
|
| 80 |
wandb_entity: null
|
| 81 |
wandb_mode: offline
|
| 82 |
-
wandb_name:
|
| 83 |
wandb_project: Gradients-On-Demand
|
| 84 |
wandb_run: your_name
|
| 85 |
-
wandb_runid:
|
| 86 |
warmup_steps: 1
|
| 87 |
weight_decay: 0.0
|
| 88 |
xformers_attention: null
|
|
@@ -91,7 +91,7 @@ xformers_attention: null
|
|
| 91 |
|
| 92 |
</details><br>
|
| 93 |
|
| 94 |
-
# app/checkpoints/
|
| 95 |
|
| 96 |
This model was trained from scratch on the None dataset.
|
| 97 |
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
base_model: samoline/b7447218-27e6-491c-b3ab-ea03a5b93541
|
| 6 |
model-index:
|
| 7 |
+
- name: app/checkpoints/test1334test1234test1234test12334/texttest
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
|
|
|
| 23 |
dataset_prepared_path: null
|
| 24 |
datasets:
|
| 25 |
- data_files:
|
| 26 |
+
- test1334test1234test1234test12334_train_data.json
|
| 27 |
ds_type: json
|
| 28 |
format: custom
|
| 29 |
path: /workspace/axolotl/data
|
|
|
|
| 60 |
lr_scheduler: cosine
|
| 61 |
max_steps: 1
|
| 62 |
micro_batch_size: 2
|
| 63 |
+
mlflow_experiment_name: /workspace/axolotl/data/test1334test1234test1234test12334_train_data.json
|
| 64 |
model_type: AutoModelForCausalLM
|
| 65 |
num_epochs: 1
|
| 66 |
optimizer: adamw_bnb_8bit
|
| 67 |
+
output_dir: /app/checkpoints/test1334test1234test1234test12334/texttest
|
| 68 |
pad_to_sequence_len: true
|
| 69 |
resume_from_checkpoint: null
|
| 70 |
s2_attention: null
|
|
|
|
| 79 |
val_set_size: 0.05
|
| 80 |
wandb_entity: null
|
| 81 |
wandb_mode: offline
|
| 82 |
+
wandb_name: test1334test1234test1234test12334_texttest
|
| 83 |
wandb_project: Gradients-On-Demand
|
| 84 |
wandb_run: your_name
|
| 85 |
+
wandb_runid: test1334test1234test1234test12334_texttest
|
| 86 |
warmup_steps: 1
|
| 87 |
weight_decay: 0.0
|
| 88 |
xformers_attention: null
|
|
|
|
| 91 |
|
| 92 |
</details><br>
|
| 93 |
|
| 94 |
+
# app/checkpoints/test1334test1234test1234test12334/texttest
|
| 95 |
|
| 96 |
This model was trained from scratch on the None dataset.
|
| 97 |
|
adapter_config.json
CHANGED
|
@@ -24,13 +24,13 @@
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"o_proj",
|
| 28 |
-
"up_proj",
|
| 29 |
"down_proj",
|
|
|
|
| 30 |
"v_proj",
|
| 31 |
-
"k_proj",
|
| 32 |
"gate_proj",
|
| 33 |
-
"q_proj"
|
|
|
|
|
|
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
|
|
|
| 27 |
"down_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
"v_proj",
|
|
|
|
| 30 |
"gate_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 22573704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e5c010c04b0ed997c5bcbbdb8362a9c53e6bc5e50f2212fe5ff9c99d75273a4
|
| 3 |
size 22573704
|
checkpoint-1/adapter_config.json
CHANGED
|
@@ -24,13 +24,13 @@
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"o_proj",
|
| 28 |
-
"up_proj",
|
| 29 |
"down_proj",
|
|
|
|
| 30 |
"v_proj",
|
| 31 |
-
"k_proj",
|
| 32 |
"gate_proj",
|
| 33 |
-
"q_proj"
|
|
|
|
|
|
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
|
|
|
| 27 |
"down_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
"v_proj",
|
|
|
|
| 30 |
"gate_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
checkpoint-1/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 22573704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e5c010c04b0ed997c5bcbbdb8362a9c53e6bc5e50f2212fe5ff9c99d75273a4
|
| 3 |
size 22573704
|
checkpoint-1/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11710970
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab750e2213b220358059c8bb1238af05f822ff8058636d3ec44e2cd653d9a7e1
|
| 3 |
size 11710970
|
checkpoint-1/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,10 +10,10 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
-
"loss": 1.
|
| 17 |
"step": 1
|
| 18 |
}
|
| 19 |
],
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.008733624454148471,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 1,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.008733624454148471,
|
| 14 |
+
"grad_norm": 0.692659318447113,
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.6015,
|
| 17 |
"step": 1
|
| 18 |
}
|
| 19 |
],
|
checkpoint-1/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f31b6c3abbe50418c0ea9a5853aed1f1ea7a05142bddae8aa159103fea461861
|
| 3 |
+
size 7160
|