Instructions to use Team-PIXEL/pixel-small-words with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Team-PIXEL/pixel-small-words with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForPreTraining model = AutoModelForPreTraining.from_pretrained("Team-PIXEL/pixel-small-words", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 260000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 202194449
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a6cf8e52153476c0d24566862211ae73b151847958bccb312e482641f34fe2f
|
| 3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102501541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20d31269cc8100e5fc218adcef1522ff7b0dd07e50b44819d9df2a65286c8129
|
| 3 |
size 102501541
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27a5987a387bd5d5448f919b8fbc047d2f79f2d23737fd4d602720c8f9c95204
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b7fe86b6bf62db9f7989d6e264b9b70447a29a8d4bbea419af77ab1989ca356
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 6.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -5006,11 +5006,211 @@
|
|
| 5006 |
"eval_samples_per_second": 788.807,
|
| 5007 |
"eval_steps_per_second": 12.621,
|
| 5008 |
"step": 250000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5009 |
}
|
| 5010 |
],
|
| 5011 |
"max_steps": 500000,
|
| 5012 |
"num_train_epochs": 13,
|
| 5013 |
-
"total_flos":
|
| 5014 |
"trial_name": null,
|
| 5015 |
"trial_params": null
|
| 5016 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.626229675314746,
|
| 5 |
+
"global_step": 260000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 5006 |
"eval_samples_per_second": 788.807,
|
| 5007 |
"eval_steps_per_second": 12.621,
|
| 5008 |
"step": 250000
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 6.38,
|
| 5012 |
+
"learning_rate": 0.00016649607200138356,
|
| 5013 |
+
"loss": 0.2877,
|
| 5014 |
+
"step": 250500
|
| 5015 |
+
},
|
| 5016 |
+
{
|
| 5017 |
+
"epoch": 6.4,
|
| 5018 |
+
"learning_rate": 0.00016601801319007743,
|
| 5019 |
+
"loss": 0.2877,
|
| 5020 |
+
"step": 251000
|
| 5021 |
+
},
|
| 5022 |
+
{
|
| 5023 |
+
"epoch": 6.4,
|
| 5024 |
+
"eval_loss": 0.810385525226593,
|
| 5025 |
+
"eval_runtime": 1.2931,
|
| 5026 |
+
"eval_samples_per_second": 773.361,
|
| 5027 |
+
"eval_steps_per_second": 12.374,
|
| 5028 |
+
"step": 251000
|
| 5029 |
+
},
|
| 5030 |
+
{
|
| 5031 |
+
"epoch": 6.41,
|
| 5032 |
+
"learning_rate": 0.00016553983388754428,
|
| 5033 |
+
"loss": 0.2872,
|
| 5034 |
+
"step": 251500
|
| 5035 |
+
},
|
| 5036 |
+
{
|
| 5037 |
+
"epoch": 6.42,
|
| 5038 |
+
"learning_rate": 0.00016506153932307636,
|
| 5039 |
+
"loss": 0.2872,
|
| 5040 |
+
"step": 252000
|
| 5041 |
+
},
|
| 5042 |
+
{
|
| 5043 |
+
"epoch": 6.42,
|
| 5044 |
+
"eval_loss": 0.8114423155784607,
|
| 5045 |
+
"eval_runtime": 1.2618,
|
| 5046 |
+
"eval_samples_per_second": 792.538,
|
| 5047 |
+
"eval_steps_per_second": 12.681,
|
| 5048 |
+
"step": 252000
|
| 5049 |
+
},
|
| 5050 |
+
{
|
| 5051 |
+
"epoch": 6.44,
|
| 5052 |
+
"learning_rate": 0.00016458313472722638,
|
| 5053 |
+
"loss": 0.2874,
|
| 5054 |
+
"step": 252500
|
| 5055 |
+
},
|
| 5056 |
+
{
|
| 5057 |
+
"epoch": 6.45,
|
| 5058 |
+
"learning_rate": 0.00016410462533175045,
|
| 5059 |
+
"loss": 0.2871,
|
| 5060 |
+
"step": 253000
|
| 5061 |
+
},
|
| 5062 |
+
{
|
| 5063 |
+
"epoch": 6.45,
|
| 5064 |
+
"eval_loss": 0.814827024936676,
|
| 5065 |
+
"eval_runtime": 1.3254,
|
| 5066 |
+
"eval_samples_per_second": 754.465,
|
| 5067 |
+
"eval_steps_per_second": 12.071,
|
| 5068 |
+
"step": 253000
|
| 5069 |
+
},
|
| 5070 |
+
{
|
| 5071 |
+
"epoch": 6.46,
|
| 5072 |
+
"learning_rate": 0.00016362601636955049,
|
| 5073 |
+
"loss": 0.288,
|
| 5074 |
+
"step": 253500
|
| 5075 |
+
},
|
| 5076 |
+
{
|
| 5077 |
+
"epoch": 6.47,
|
| 5078 |
+
"learning_rate": 0.00016314731307461754,
|
| 5079 |
+
"loss": 0.2875,
|
| 5080 |
+
"step": 254000
|
| 5081 |
+
},
|
| 5082 |
+
{
|
| 5083 |
+
"epoch": 6.47,
|
| 5084 |
+
"eval_loss": 0.812713623046875,
|
| 5085 |
+
"eval_runtime": 1.2619,
|
| 5086 |
+
"eval_samples_per_second": 792.485,
|
| 5087 |
+
"eval_steps_per_second": 12.68,
|
| 5088 |
+
"step": 254000
|
| 5089 |
+
},
|
| 5090 |
+
{
|
| 5091 |
+
"epoch": 6.49,
|
| 5092 |
+
"learning_rate": 0.0001626685206819742,
|
| 5093 |
+
"loss": 0.2874,
|
| 5094 |
+
"step": 254500
|
| 5095 |
+
},
|
| 5096 |
+
{
|
| 5097 |
+
"epoch": 6.5,
|
| 5098 |
+
"learning_rate": 0.0001621896444276172,
|
| 5099 |
+
"loss": 0.287,
|
| 5100 |
+
"step": 255000
|
| 5101 |
+
},
|
| 5102 |
+
{
|
| 5103 |
+
"epoch": 6.5,
|
| 5104 |
+
"eval_loss": 0.820074200630188,
|
| 5105 |
+
"eval_runtime": 1.2181,
|
| 5106 |
+
"eval_samples_per_second": 820.971,
|
| 5107 |
+
"eval_steps_per_second": 13.136,
|
| 5108 |
+
"step": 255000
|
| 5109 |
+
},
|
| 5110 |
+
{
|
| 5111 |
+
"epoch": 6.51,
|
| 5112 |
+
"learning_rate": 0.00016171068954846067,
|
| 5113 |
+
"loss": 0.2865,
|
| 5114 |
+
"step": 255500
|
| 5115 |
+
},
|
| 5116 |
+
{
|
| 5117 |
+
"epoch": 6.52,
|
| 5118 |
+
"learning_rate": 0.00016123166128227835,
|
| 5119 |
+
"loss": 0.2869,
|
| 5120 |
+
"step": 256000
|
| 5121 |
+
},
|
| 5122 |
+
{
|
| 5123 |
+
"epoch": 6.52,
|
| 5124 |
+
"eval_loss": 0.8100768327713013,
|
| 5125 |
+
"eval_runtime": 1.2652,
|
| 5126 |
+
"eval_samples_per_second": 790.379,
|
| 5127 |
+
"eval_steps_per_second": 12.646,
|
| 5128 |
+
"step": 256000
|
| 5129 |
+
},
|
| 5130 |
+
{
|
| 5131 |
+
"epoch": 6.54,
|
| 5132 |
+
"learning_rate": 0.0001607525648676467,
|
| 5133 |
+
"loss": 0.2868,
|
| 5134 |
+
"step": 256500
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 6.55,
|
| 5138 |
+
"learning_rate": 0.0001602734055438873,
|
| 5139 |
+
"loss": 0.2868,
|
| 5140 |
+
"step": 257000
|
| 5141 |
+
},
|
| 5142 |
+
{
|
| 5143 |
+
"epoch": 6.55,
|
| 5144 |
+
"eval_loss": 0.814249575138092,
|
| 5145 |
+
"eval_runtime": 1.2757,
|
| 5146 |
+
"eval_samples_per_second": 783.912,
|
| 5147 |
+
"eval_steps_per_second": 12.543,
|
| 5148 |
+
"step": 257000
|
| 5149 |
+
},
|
| 5150 |
+
{
|
| 5151 |
+
"epoch": 6.56,
|
| 5152 |
+
"learning_rate": 0.00015979418855100963,
|
| 5153 |
+
"loss": 0.2869,
|
| 5154 |
+
"step": 257500
|
| 5155 |
+
},
|
| 5156 |
+
{
|
| 5157 |
+
"epoch": 6.58,
|
| 5158 |
+
"learning_rate": 0.00015931491912965417,
|
| 5159 |
+
"loss": 0.2869,
|
| 5160 |
+
"step": 258000
|
| 5161 |
+
},
|
| 5162 |
+
{
|
| 5163 |
+
"epoch": 6.58,
|
| 5164 |
+
"eval_loss": 0.815778374671936,
|
| 5165 |
+
"eval_runtime": 1.2351,
|
| 5166 |
+
"eval_samples_per_second": 809.649,
|
| 5167 |
+
"eval_steps_per_second": 12.954,
|
| 5168 |
+
"step": 258000
|
| 5169 |
+
},
|
| 5170 |
+
{
|
| 5171 |
+
"epoch": 6.59,
|
| 5172 |
+
"learning_rate": 0.0001588356025210344,
|
| 5173 |
+
"loss": 0.2866,
|
| 5174 |
+
"step": 258500
|
| 5175 |
+
},
|
| 5176 |
+
{
|
| 5177 |
+
"epoch": 6.6,
|
| 5178 |
+
"learning_rate": 0.00015835624396688,
|
| 5179 |
+
"loss": 0.2868,
|
| 5180 |
+
"step": 259000
|
| 5181 |
+
},
|
| 5182 |
+
{
|
| 5183 |
+
"epoch": 6.6,
|
| 5184 |
+
"eval_loss": 0.81247878074646,
|
| 5185 |
+
"eval_runtime": 1.3012,
|
| 5186 |
+
"eval_samples_per_second": 768.517,
|
| 5187 |
+
"eval_steps_per_second": 12.296,
|
| 5188 |
+
"step": 259000
|
| 5189 |
+
},
|
| 5190 |
+
{
|
| 5191 |
+
"epoch": 6.61,
|
| 5192 |
+
"learning_rate": 0.00015787684870937924,
|
| 5193 |
+
"loss": 0.2862,
|
| 5194 |
+
"step": 259500
|
| 5195 |
+
},
|
| 5196 |
+
{
|
| 5197 |
+
"epoch": 6.63,
|
| 5198 |
+
"learning_rate": 0.00015739742199112196,
|
| 5199 |
+
"loss": 0.2865,
|
| 5200 |
+
"step": 260000
|
| 5201 |
+
},
|
| 5202 |
+
{
|
| 5203 |
+
"epoch": 6.63,
|
| 5204 |
+
"eval_loss": 0.816739559173584,
|
| 5205 |
+
"eval_runtime": 1.3361,
|
| 5206 |
+
"eval_samples_per_second": 748.473,
|
| 5207 |
+
"eval_steps_per_second": 11.976,
|
| 5208 |
+
"step": 260000
|
| 5209 |
}
|
| 5210 |
],
|
| 5211 |
"max_steps": 500000,
|
| 5212 |
"num_train_epochs": 13,
|
| 5213 |
+
"total_flos": 8.30658473465873e+21,
|
| 5214 |
"trial_name": null,
|
| 5215 |
"trial_params": null
|
| 5216 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102501541
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20d31269cc8100e5fc218adcef1522ff7b0dd07e50b44819d9df2a65286c8129
|
| 3 |
size 102501541
|