Upload folder using huggingface_hub
Browse files
checkpoint-10/adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"q_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
"v_proj",
|
|
|
|
| 25 |
"o_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
"q_proj",
|
|
|
|
| 23 |
"v_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
"o_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
checkpoint-10/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27297032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:347f0eda6580cadbe0640ce86054b0bbe862cfe4704b257ac5f3c331092c0675
|
| 3 |
size 27297032
|
checkpoint-10/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 54678010
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4f3a8ce4f53cfb1cc8d15681aa89341631c54eeda8455d7a2309fb68ccccd8d
|
| 3 |
size 54678010
|
checkpoint-10/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa88bd01c20ed7f51c4ffc4c0e105d58f84d47fa6510b5f3dea4c3f2a2c6094a
|
| 3 |
size 14512
|
checkpoint-10/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad63ecc2f0ee3034c7d6b5ec77eea06e1e97bf6c8f8e19114904d563ffde5989
|
| 3 |
size 14512
|
checkpoint-10/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.006199628022318661,
|
| 5 |
"eval_steps": 10,
|
|
@@ -10,10 +10,10 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
-
"eval_loss": 1.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second": 13.
|
| 16 |
-
"eval_steps_per_second": 3.
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 10,
|
| 25 |
-
"total_flos":
|
| 26 |
"train_batch_size": 8,
|
| 27 |
"trial_name": null,
|
| 28 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.34207284450531,
|
| 3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.006199628022318661,
|
| 5 |
"eval_steps": 10,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
+
"eval_loss": 1.34207284450531,
|
| 14 |
+
"eval_runtime": 211.9495,
|
| 15 |
+
"eval_samples_per_second": 13.527,
|
| 16 |
+
"eval_steps_per_second": 3.383,
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 1,
|
| 24 |
"save_steps": 10,
|
| 25 |
+
"total_flos": 4989635306455040.0,
|
| 26 |
"train_batch_size": 8,
|
| 27 |
"trial_name": null,
|
| 28 |
"trial_params": null
|
checkpoint-10/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b55fef1baf040c97ea612999dab2e3ea9b4bc4904e42d865dd7556f3582f069d
|
| 3 |
size 5112
|