Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- checkpoint-50/adapter_config.json +2 -2
- checkpoint-50/adapter_model.safetensors +1 -1
- checkpoint-50/optimizer.pt +1 -1
- checkpoint-50/rng_state.pth +1 -1
- checkpoint-50/scaler.pt +1 -1
- checkpoint-50/trainer_state.json +18 -18
- checkpoint-50/training_args.bin +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -25,9 +25,9 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"q_proj",
|
| 29 |
-
"o_proj",
|
| 30 |
"v_proj",
|
|
|
|
|
|
|
| 31 |
"k_proj"
|
| 32 |
],
|
| 33 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
"k_proj"
|
| 32 |
],
|
| 33 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 33588528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7527027d86c2f99fb4a21349c730585d104c214f60e49f314d66f5a733bc9a50
|
| 3 |
size 33588528
|
checkpoint-50/adapter_config.json
CHANGED
|
@@ -25,9 +25,9 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
-
"q_proj",
|
| 29 |
-
"o_proj",
|
| 30 |
"v_proj",
|
|
|
|
|
|
|
| 31 |
"k_proj"
|
| 32 |
],
|
| 33 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
"k_proj"
|
| 32 |
],
|
| 33 |
"task_type": "CAUSAL_LM",
|
checkpoint-50/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 33588528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7527027d86c2f99fb4a21349c730585d104c214f60e49f314d66f5a733bc9a50
|
| 3 |
size 33588528
|
checkpoint-50/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17338708
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c074625f59c355cb1db0e83337b49e4b45d7202294c8e85514c2b801bff024e7
|
| 3 |
size 17338708
|
checkpoint-50/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:354615fc8387693f24d82e680c5229ada92ecc73c65770aa0d2ec2f22d519ce2
|
| 3 |
size 14244
|
checkpoint-50/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ae5b6e1493c7b53e741deaed6ac33c1459c9d8e052b89f8241e547b1872d8a8
|
| 3 |
size 988
|
checkpoint-50/trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,45 +10,45 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch":
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 0.00014,
|
| 16 |
-
"loss":
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch":
|
| 21 |
-
"grad_norm":
|
| 22 |
"learning_rate": 0.000165,
|
| 23 |
-
"loss":
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch":
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.00011499999999999999,
|
| 30 |
-
"loss": 1.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 6.500000000000001e-05,
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 1.5e-05,
|
| 44 |
-
"loss":
|
| 45 |
"step": 50
|
| 46 |
}
|
| 47 |
],
|
| 48 |
"logging_steps": 10,
|
| 49 |
"max_steps": 50,
|
| 50 |
"num_input_tokens_seen": 0,
|
| 51 |
-
"num_train_epochs":
|
| 52 |
"save_steps": 50,
|
| 53 |
"stateful_callbacks": {
|
| 54 |
"TrainerControl": {
|
|
@@ -62,7 +62,7 @@
|
|
| 62 |
"attributes": {}
|
| 63 |
}
|
| 64 |
},
|
| 65 |
-
"total_flos":
|
| 66 |
"train_batch_size": 1,
|
| 67 |
"trial_name": null,
|
| 68 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.533333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 2.533333333333333,
|
| 14 |
+
"grad_norm": 5.1353068351745605,
|
| 15 |
"learning_rate": 0.00014,
|
| 16 |
+
"loss": 7.9209,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 5.0,
|
| 21 |
+
"grad_norm": 1.2159311771392822,
|
| 22 |
"learning_rate": 0.000165,
|
| 23 |
+
"loss": 3.5184,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 7.533333333333333,
|
| 28 |
+
"grad_norm": 0.17727278172969818,
|
| 29 |
"learning_rate": 0.00011499999999999999,
|
| 30 |
+
"loss": 1.3178,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 10.0,
|
| 35 |
+
"grad_norm": 0.20721666514873505,
|
| 36 |
"learning_rate": 6.500000000000001e-05,
|
| 37 |
+
"loss": 1.3595,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 12.533333333333333,
|
| 42 |
+
"grad_norm": 0.1987001746892929,
|
| 43 |
"learning_rate": 1.5e-05,
|
| 44 |
+
"loss": 1.2959,
|
| 45 |
"step": 50
|
| 46 |
}
|
| 47 |
],
|
| 48 |
"logging_steps": 10,
|
| 49 |
"max_steps": 50,
|
| 50 |
"num_input_tokens_seen": 0,
|
| 51 |
+
"num_train_epochs": 13,
|
| 52 |
"save_steps": 50,
|
| 53 |
"stateful_callbacks": {
|
| 54 |
"TrainerControl": {
|
|
|
|
| 62 |
"attributes": {}
|
| 63 |
}
|
| 64 |
},
|
| 65 |
+
"total_flos": 7641647051440128.0,
|
| 66 |
"train_batch_size": 1,
|
| 67 |
"trial_name": null,
|
| 68 |
"trial_params": null
|
checkpoint-50/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d803a248f86aede78be3460d30806bdea503d572393c5e5c9706e3cd81f51c6e
|
| 3 |
size 5304
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d803a248f86aede78be3460d30806bdea503d572393c5e5c9706e3cd81f51c6e
|
| 3 |
size 5304
|