Upload folder using huggingface_hub
Browse files- checkpoint-10/adapter_config.json +2 -2
- checkpoint-10/adapter_model.safetensors +1 -1
- checkpoint-10/optimizer.pt +1 -1
- checkpoint-10/rng_state_0.pth +1 -1
- checkpoint-10/rng_state_1.pth +1 -1
- checkpoint-10/rng_state_2.pth +1 -1
- checkpoint-10/rng_state_3.pth +1 -1
- checkpoint-10/trainer_state.json +6 -6
- checkpoint-10/training_args.bin +1 -1
checkpoint-10/adapter_config.json
CHANGED
|
@@ -19,10 +19,10 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"o_proj",
|
| 23 |
"v_proj",
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
-
"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"v_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
"q_proj",
|
| 25 |
+
"o_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_rslora": false
|
checkpoint-10/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 436242776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e5e058a1408de0cc48b6752fbd2722421a06899ffddb51164e711bf3b6a0c6
|
| 3 |
size 436242776
|
checkpoint-10/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 872568314
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e51cf62a9d4f1a95a688a95ef89e504d3d99f025703c8d747e633dc7678143
|
| 3 |
size 872568314
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0aa4eba153ab676e644b72c29d09ab9e7352522bf1d44cd8e845ea829abb303
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cddb143576b1a89a58cf96c2958962ae5c9ff0e8e306a41ed0663381ed197811
|
| 3 |
size 15024
|
checkpoint-10/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a78ef0e79808122757dd79a6cd4242485f52739b6ea515759b85ac718465064f
|
| 3 |
size 15024
|
checkpoint-10/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47e9715ea3ecb199e2bd90db10503b0200bff14dfcdcb3543ab1e93a2869e3f
|
| 3 |
size 15024
|
checkpoint-10/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-800_batch_256_2024-03-01_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.09900990099009901,
|
| 5 |
"eval_steps": 10,
|
|
@@ -10,10 +10,10 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.1,
|
| 13 |
-
"eval_loss": 1.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 0.
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 8,
|
| 24 |
"save_steps": 10,
|
| 25 |
-
"total_flos": 9.
|
| 26 |
"train_batch_size": 16,
|
| 27 |
"trial_name": null,
|
| 28 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.413617491722107,
|
| 3 |
"best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-800_batch_256_2024-03-01_ppid_7/checkpoint-10",
|
| 4 |
"epoch": 0.09900990099009901,
|
| 5 |
"eval_steps": 10,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.1,
|
| 13 |
+
"eval_loss": 1.413617491722107,
|
| 14 |
+
"eval_runtime": 95.403,
|
| 15 |
+
"eval_samples_per_second": 30.051,
|
| 16 |
+
"eval_steps_per_second": 0.943,
|
| 17 |
"step": 10
|
| 18 |
}
|
| 19 |
],
|
|
|
|
| 22 |
"num_input_tokens_seen": 0,
|
| 23 |
"num_train_epochs": 8,
|
| 24 |
"save_steps": 10,
|
| 25 |
+
"total_flos": 9.080895739579597e+16,
|
| 26 |
"train_batch_size": 16,
|
| 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 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b11fc6f843a914c564bb12c8e2c2f5979eb9fcba388ba55a442a116f554cfd1
|
| 3 |
size 5176
|