Instructions to use somaia02/arabart-gec-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use somaia02/arabart-gec-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("moussaKam/AraBART") model = PeftModel.from_pretrained(base_model, "somaia02/arabart-gec-lora") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 2, checkpoint
Browse files- last-checkpoint/adapter_model.bin +1 -1
- last-checkpoint/global_step1226/mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step1226/zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/latest +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/trainer_state.json +85 -5
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2692157
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee5c23e36a220ddfb323d32d463c212f902254630a4ca1f579a0caca6ef359f
|
| 3 |
size 2692157
|
last-checkpoint/global_step1226/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89cd82ea15fe75736613dff47ec935108aac97520c6feafd3ef6a5ea0a5351ce
|
| 3 |
+
size 1116913857
|
last-checkpoint/global_step1226/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8095ed9c2415eed8d4f96ec9276547574c2ed6d8eb4c8997ba3c9f81c07b3dd0
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11e12de0377c60745878d006bd2f73ec378d94085267eab9fa5dd0337029cc22
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc1d9ea8c8e487b2ba85ef9d22488bcde62954d3490969243b167ffc99d54468
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6b7b23671b2745f82bf31c7b80e63063fe9f83368dcfc287a5c270efd8a5f9e
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adcab907dfac0ac296b9d5e115333d0d0f0b2ad6fb5e95ccdeff755ca8898d5c
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9269e73f67102ebe55c2515ca8cd91f405f9260c97d298805d292899da3d02f
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:189a65db859f06ed8939b5f886e49c7c627d4fdccdb8e1d39739abad63c84050
|
| 3 |
+
size 999614
|
last-checkpoint/global_step1226/zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b5f06b855b03792c61b5bb65179dfa13de959c1078c89c29503d1956cd5d9e9
|
| 3 |
+
size 999614
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step1226
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c31e33d70b3fe7f61d71a2b4a5353d94b31f406bedabb2083e35ac5bbc106208
|
| 3 |
size 21687
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38fe384dd20308f07ec5585d9912cb965830bcc11808cbdc846275b932905119
|
| 3 |
size 21687
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39ce95745d8ff40a4f8ee5a97f3689eaa9467213f9b27ce66ca594efc37198cf
|
| 3 |
size 21687
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c349f517e129599281e2e4a383da6c74c212dfb7e6bad5c542f121cde888a562
|
| 3 |
size 21687
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df27a56b73699e712acf3ed2a1bec8b4dc1f7438a81b82196f0c2f34f00b7551
|
| 3 |
size 21687
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34696be6d136ea03ea905aa2941fd96da980291d6b92db0de6b0a3b4d6447267
|
| 3 |
size 21687
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0e2cbda44be671f5b71ae2543f2cec67328a527bccee980bbad52fe0ebf7dd5
|
| 3 |
size 21687
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4070b9e9beda56664b5815d344e6c0f296840034807befc40392beac83c285b1
|
| 3 |
size 21687
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "outputs/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -87,13 +87,93 @@
|
|
| 87 |
"eval_samples_per_second": 568.098,
|
| 88 |
"eval_steps_per_second": 17.95,
|
| 89 |
"step": 613
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
}
|
| 91 |
],
|
| 92 |
"logging_steps": 50,
|
| 93 |
"max_steps": 9195,
|
| 94 |
"num_train_epochs": 15,
|
| 95 |
"save_steps": 500,
|
| 96 |
-
"total_flos":
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
| 99 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6314801573753357,
|
| 3 |
+
"best_model_checkpoint": "outputs/checkpoint-1226",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1226,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 87 |
"eval_samples_per_second": 568.098,
|
| 88 |
"eval_steps_per_second": 17.95,
|
| 89 |
"step": 613
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.06,
|
| 93 |
+
"learning_rate": 4.914318573893042e-05,
|
| 94 |
+
"loss": 0.8284,
|
| 95 |
+
"step": 650
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.14,
|
| 99 |
+
"learning_rate": 4.8855664174813115e-05,
|
| 100 |
+
"loss": 0.8152,
|
| 101 |
+
"step": 700
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.22,
|
| 105 |
+
"learning_rate": 4.856814261069581e-05,
|
| 106 |
+
"loss": 0.8085,
|
| 107 |
+
"step": 750
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.31,
|
| 111 |
+
"learning_rate": 4.8280621046578495e-05,
|
| 112 |
+
"loss": 0.8156,
|
| 113 |
+
"step": 800
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.39,
|
| 117 |
+
"learning_rate": 4.799309948246118e-05,
|
| 118 |
+
"loss": 0.7773,
|
| 119 |
+
"step": 850
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.47,
|
| 123 |
+
"learning_rate": 4.770557791834388e-05,
|
| 124 |
+
"loss": 0.7913,
|
| 125 |
+
"step": 900
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.55,
|
| 129 |
+
"learning_rate": 4.741805635422657e-05,
|
| 130 |
+
"loss": 0.7787,
|
| 131 |
+
"step": 950
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.63,
|
| 135 |
+
"learning_rate": 4.713053479010926e-05,
|
| 136 |
+
"loss": 0.7589,
|
| 137 |
+
"step": 1000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.71,
|
| 141 |
+
"learning_rate": 4.684301322599195e-05,
|
| 142 |
+
"loss": 0.7671,
|
| 143 |
+
"step": 1050
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.79,
|
| 147 |
+
"learning_rate": 4.655549166187464e-05,
|
| 148 |
+
"loss": 0.7461,
|
| 149 |
+
"step": 1100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.88,
|
| 153 |
+
"learning_rate": 4.6267970097757336e-05,
|
| 154 |
+
"loss": 0.7469,
|
| 155 |
+
"step": 1150
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.96,
|
| 159 |
+
"learning_rate": 4.598044853364002e-05,
|
| 160 |
+
"loss": 0.743,
|
| 161 |
+
"step": 1200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.0,
|
| 165 |
+
"eval_loss": 0.6314801573753357,
|
| 166 |
+
"eval_runtime": 2.0735,
|
| 167 |
+
"eval_samples_per_second": 564.759,
|
| 168 |
+
"eval_steps_per_second": 17.845,
|
| 169 |
+
"step": 1226
|
| 170 |
}
|
| 171 |
],
|
| 172 |
"logging_steps": 50,
|
| 173 |
"max_steps": 9195,
|
| 174 |
"num_train_epochs": 15,
|
| 175 |
"save_steps": 500,
|
| 176 |
+
"total_flos": 2038462404362240.0,
|
| 177 |
"trial_name": null,
|
| 178 |
"trial_params": null
|
| 179 |
}
|