Upload folder using huggingface_hub
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +6 -6
- checkpoint-45/adapter_config.json +3 -3
- checkpoint-45/adapter_model.safetensors +1 -1
- checkpoint-45/optimizer.pt +1 -1
- checkpoint-45/rng_state.pth +1 -1
- checkpoint-45/trainer_state.json +31 -31
- checkpoint-45/training_args.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +37 -37
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -23,10 +23,10 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"qkv_proj",
|
| 27 |
-
"down_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"o_proj",
|
| 27 |
+
"qkv_proj",
|
| 28 |
+
"gate_up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100697728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fa574614bd2c4f4b60446fc1e1704a6309cd03a1bee5f601b80009c317b85b
|
| 3 |
size 100697728
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 1.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.48,
|
| 3 |
+
"total_flos": 1.2752346185220096e+16,
|
| 4 |
+
"train_loss": 0.643518532647027,
|
| 5 |
+
"train_runtime": 231.7259,
|
| 6 |
+
"train_samples_per_second": 1.554,
|
| 7 |
+
"train_steps_per_second": 0.194
|
| 8 |
}
|
checkpoint-45/adapter_config.json
CHANGED
|
@@ -23,10 +23,10 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"qkv_proj",
|
| 27 |
-
"down_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"o_proj",
|
| 27 |
+
"qkv_proj",
|
| 28 |
+
"gate_up_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
checkpoint-45/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100697728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fa574614bd2c4f4b60446fc1e1704a6309cd03a1bee5f601b80009c317b85b
|
| 3 |
size 100697728
|
checkpoint-45/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 201541754
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97fdf0ab912d2be2e65c97549eee40b206332fd7cfd950d3671d97877d75a0f5
|
| 3 |
size 201541754
|
checkpoint-45/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:f77392d6a4313495d69e48b960a2ff23dda053345de283eaed32a84e6e1f6e2d
|
| 3 |
size 14244
|
checkpoint-45/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": 45,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,73 +10,73 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 4.347826086956522e-05,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
"learning_rate": 8.695652173913044e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.00013043478260869567,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.00017391304347826088,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 0.00019594929736144976,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"grad_norm": 0.
|
| 50 |
"learning_rate": 0.00015406408174555976,
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch":
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 8.57685161726715e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 2.4425042564574184e-05,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 0.0,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 45
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 5,
|
| 77 |
"max_steps": 45,
|
| 78 |
"num_input_tokens_seen": 0,
|
| 79 |
-
"num_train_epochs":
|
| 80 |
"save_steps": 500,
|
| 81 |
"stateful_callbacks": {
|
| 82 |
"TrainerControl": {
|
|
@@ -90,8 +90,8 @@
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
-
"total_flos":
|
| 94 |
-
"train_batch_size":
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
| 97 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.48,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 45,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.26666666666666666,
|
| 14 |
+
"grad_norm": 0.44340959191322327,
|
| 15 |
"learning_rate": 4.347826086956522e-05,
|
| 16 |
+
"loss": 0.7885,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.5333333333333333,
|
| 21 |
+
"grad_norm": 0.25733163952827454,
|
| 22 |
"learning_rate": 8.695652173913044e-05,
|
| 23 |
+
"loss": 0.7907,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.8,
|
| 28 |
+
"grad_norm": 0.22555556893348694,
|
| 29 |
"learning_rate": 0.00013043478260869567,
|
| 30 |
+
"loss": 0.6445,
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 1.1066666666666667,
|
| 35 |
+
"grad_norm": 0.22658060491085052,
|
| 36 |
"learning_rate": 0.00017391304347826088,
|
| 37 |
+
"loss": 0.7548,
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 1.3733333333333333,
|
| 42 |
+
"grad_norm": 0.30281075835227966,
|
| 43 |
"learning_rate": 0.00019594929736144976,
|
| 44 |
+
"loss": 0.5684,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 1.6400000000000001,
|
| 49 |
+
"grad_norm": 0.22937139868736267,
|
| 50 |
"learning_rate": 0.00015406408174555976,
|
| 51 |
+
"loss": 0.609,
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 1.9066666666666667,
|
| 56 |
+
"grad_norm": 0.24968542158603668,
|
| 57 |
"learning_rate": 8.57685161726715e-05,
|
| 58 |
+
"loss": 0.5708,
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 2.2133333333333334,
|
| 63 |
+
"grad_norm": 0.2418316900730133,
|
| 64 |
"learning_rate": 2.4425042564574184e-05,
|
| 65 |
+
"loss": 0.5956,
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 2.48,
|
| 70 |
+
"grad_norm": 0.21928495168685913,
|
| 71 |
"learning_rate": 0.0,
|
| 72 |
+
"loss": 0.4693,
|
| 73 |
"step": 45
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 5,
|
| 77 |
"max_steps": 45,
|
| 78 |
"num_input_tokens_seen": 0,
|
| 79 |
+
"num_train_epochs": 3,
|
| 80 |
"save_steps": 500,
|
| 81 |
"stateful_callbacks": {
|
| 82 |
"TrainerControl": {
|
|
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
+
"total_flos": 1.2752346185220096e+16,
|
| 94 |
+
"train_batch_size": 2,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
| 97 |
}
|
checkpoint-45/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4ebfb1e9e4e099c0a01f2b27c892b7a8026c4e89d97a919ba06de02ef08b08c
|
| 3 |
size 5624
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 1.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.48,
|
| 3 |
+
"total_flos": 1.2752346185220096e+16,
|
| 4 |
+
"train_loss": 0.643518532647027,
|
| 5 |
+
"train_runtime": 231.7259,
|
| 6 |
+
"train_samples_per_second": 1.554,
|
| 7 |
+
"train_steps_per_second": 0.194
|
| 8 |
}
|
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": 45,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,82 +10,82 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm": 0.
|
| 15 |
"learning_rate": 4.347826086956522e-05,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm": 0.
|
| 22 |
"learning_rate": 8.695652173913044e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 0.00013043478260869567,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 0.00017391304347826088,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 0.00019594929736144976,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"grad_norm": 0.
|
| 50 |
"learning_rate": 0.00015406408174555976,
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch":
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 8.57685161726715e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 2.4425042564574184e-05,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 0.0,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 45
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch":
|
| 77 |
"step": 45,
|
| 78 |
-
"total_flos":
|
| 79 |
-
"train_loss": 0.
|
| 80 |
-
"train_runtime":
|
| 81 |
-
"train_samples_per_second": 1.
|
| 82 |
-
"train_steps_per_second": 0.
|
| 83 |
}
|
| 84 |
],
|
| 85 |
"logging_steps": 5,
|
| 86 |
"max_steps": 45,
|
| 87 |
"num_input_tokens_seen": 0,
|
| 88 |
-
"num_train_epochs":
|
| 89 |
"save_steps": 500,
|
| 90 |
"stateful_callbacks": {
|
| 91 |
"TrainerControl": {
|
|
@@ -99,8 +99,8 @@
|
|
| 99 |
"attributes": {}
|
| 100 |
}
|
| 101 |
},
|
| 102 |
-
"total_flos":
|
| 103 |
-
"train_batch_size":
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
| 106 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.48,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 45,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.26666666666666666,
|
| 14 |
+
"grad_norm": 0.44340959191322327,
|
| 15 |
"learning_rate": 4.347826086956522e-05,
|
| 16 |
+
"loss": 0.7885,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.5333333333333333,
|
| 21 |
+
"grad_norm": 0.25733163952827454,
|
| 22 |
"learning_rate": 8.695652173913044e-05,
|
| 23 |
+
"loss": 0.7907,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.8,
|
| 28 |
+
"grad_norm": 0.22555556893348694,
|
| 29 |
"learning_rate": 0.00013043478260869567,
|
| 30 |
+
"loss": 0.6445,
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 1.1066666666666667,
|
| 35 |
+
"grad_norm": 0.22658060491085052,
|
| 36 |
"learning_rate": 0.00017391304347826088,
|
| 37 |
+
"loss": 0.7548,
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 1.3733333333333333,
|
| 42 |
+
"grad_norm": 0.30281075835227966,
|
| 43 |
"learning_rate": 0.00019594929736144976,
|
| 44 |
+
"loss": 0.5684,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 1.6400000000000001,
|
| 49 |
+
"grad_norm": 0.22937139868736267,
|
| 50 |
"learning_rate": 0.00015406408174555976,
|
| 51 |
+
"loss": 0.609,
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 1.9066666666666667,
|
| 56 |
+
"grad_norm": 0.24968542158603668,
|
| 57 |
"learning_rate": 8.57685161726715e-05,
|
| 58 |
+
"loss": 0.5708,
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 2.2133333333333334,
|
| 63 |
+
"grad_norm": 0.2418316900730133,
|
| 64 |
"learning_rate": 2.4425042564574184e-05,
|
| 65 |
+
"loss": 0.5956,
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 2.48,
|
| 70 |
+
"grad_norm": 0.21928495168685913,
|
| 71 |
"learning_rate": 0.0,
|
| 72 |
+
"loss": 0.4693,
|
| 73 |
"step": 45
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 2.48,
|
| 77 |
"step": 45,
|
| 78 |
+
"total_flos": 1.2752346185220096e+16,
|
| 79 |
+
"train_loss": 0.643518532647027,
|
| 80 |
+
"train_runtime": 231.7259,
|
| 81 |
+
"train_samples_per_second": 1.554,
|
| 82 |
+
"train_steps_per_second": 0.194
|
| 83 |
}
|
| 84 |
],
|
| 85 |
"logging_steps": 5,
|
| 86 |
"max_steps": 45,
|
| 87 |
"num_input_tokens_seen": 0,
|
| 88 |
+
"num_train_epochs": 3,
|
| 89 |
"save_steps": 500,
|
| 90 |
"stateful_callbacks": {
|
| 91 |
"TrainerControl": {
|
|
|
|
| 99 |
"attributes": {}
|
| 100 |
}
|
| 101 |
},
|
| 102 |
+
"total_flos": 1.2752346185220096e+16,
|
| 103 |
+
"train_batch_size": 2,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
| 106 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4ebfb1e9e4e099c0a01f2b27c892b7a8026c4e89d97a919ba06de02ef08b08c
|
| 3 |
size 5624
|