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 210000
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 sha256:378ba8062a28aa965b8015e80cac5a7e8c210f8eae62a9b35de790172a138b2c
|
| 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 sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:e56b27d50a3b069272092971e132d0f9ff41c52313b7354d6ff1c765fa05ea9a
|
| 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:de6aa60c12b8dbcda06c27a65ac30e45d66753f2960bee09a7c0ea364ae7e103
|
| 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": 5.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -4006,11 +4006,211 @@
|
|
| 4006 |
"eval_samples_per_second": 756.949,
|
| 4007 |
"eval_steps_per_second": 12.111,
|
| 4008 |
"step": 200000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4009 |
}
|
| 4010 |
],
|
| 4011 |
"max_steps": 500000,
|
| 4012 |
"num_train_epochs": 13,
|
| 4013 |
-
"total_flos": 6.
|
| 4014 |
"trial_name": null,
|
| 4015 |
"trial_params": null
|
| 4016 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.351954737754218,
|
| 5 |
+
"global_step": 210000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 4006 |
"eval_samples_per_second": 756.949,
|
| 4007 |
"eval_steps_per_second": 12.111,
|
| 4008 |
"step": 200000
|
| 4009 |
+
},
|
| 4010 |
+
{
|
| 4011 |
+
"epoch": 5.11,
|
| 4012 |
+
"learning_rate": 0.000212806399860385,
|
| 4013 |
+
"loss": 0.2949,
|
| 4014 |
+
"step": 200500
|
| 4015 |
+
},
|
| 4016 |
+
{
|
| 4017 |
+
"epoch": 5.12,
|
| 4018 |
+
"learning_rate": 0.00021236633098456196,
|
| 4019 |
+
"loss": 0.2941,
|
| 4020 |
+
"step": 201000
|
| 4021 |
+
},
|
| 4022 |
+
{
|
| 4023 |
+
"epoch": 5.12,
|
| 4024 |
+
"eval_loss": 0.81947922706604,
|
| 4025 |
+
"eval_runtime": 1.576,
|
| 4026 |
+
"eval_samples_per_second": 634.516,
|
| 4027 |
+
"eval_steps_per_second": 10.152,
|
| 4028 |
+
"step": 201000
|
| 4029 |
+
},
|
| 4030 |
+
{
|
| 4031 |
+
"epoch": 5.14,
|
| 4032 |
+
"learning_rate": 0.0002119256347597342,
|
| 4033 |
+
"loss": 0.295,
|
| 4034 |
+
"step": 201500
|
| 4035 |
+
},
|
| 4036 |
+
{
|
| 4037 |
+
"epoch": 5.15,
|
| 4038 |
+
"learning_rate": 0.000211484316005285,
|
| 4039 |
+
"loss": 0.2938,
|
| 4040 |
+
"step": 202000
|
| 4041 |
+
},
|
| 4042 |
+
{
|
| 4043 |
+
"epoch": 5.15,
|
| 4044 |
+
"eval_loss": 0.8285008668899536,
|
| 4045 |
+
"eval_runtime": 1.3278,
|
| 4046 |
+
"eval_samples_per_second": 753.153,
|
| 4047 |
+
"eval_steps_per_second": 12.05,
|
| 4048 |
+
"step": 202000
|
| 4049 |
+
},
|
| 4050 |
+
{
|
| 4051 |
+
"epoch": 5.16,
|
| 4052 |
+
"learning_rate": 0.00021104237954740554,
|
| 4053 |
+
"loss": 0.2936,
|
| 4054 |
+
"step": 202500
|
| 4055 |
+
},
|
| 4056 |
+
{
|
| 4057 |
+
"epoch": 5.17,
|
| 4058 |
+
"learning_rate": 0.00021059983021904215,
|
| 4059 |
+
"loss": 0.2934,
|
| 4060 |
+
"step": 203000
|
| 4061 |
+
},
|
| 4062 |
+
{
|
| 4063 |
+
"epoch": 5.17,
|
| 4064 |
+
"eval_loss": 0.8159323930740356,
|
| 4065 |
+
"eval_runtime": 1.3067,
|
| 4066 |
+
"eval_samples_per_second": 765.291,
|
| 4067 |
+
"eval_steps_per_second": 12.245,
|
| 4068 |
+
"step": 203000
|
| 4069 |
+
},
|
| 4070 |
+
{
|
| 4071 |
+
"epoch": 5.19,
|
| 4072 |
+
"learning_rate": 0.00021015667285984336,
|
| 4073 |
+
"loss": 0.2934,
|
| 4074 |
+
"step": 203500
|
| 4075 |
+
},
|
| 4076 |
+
{
|
| 4077 |
+
"epoch": 5.2,
|
| 4078 |
+
"learning_rate": 0.00020971291231610707,
|
| 4079 |
+
"loss": 0.2932,
|
| 4080 |
+
"step": 204000
|
| 4081 |
+
},
|
| 4082 |
+
{
|
| 4083 |
+
"epoch": 5.2,
|
| 4084 |
+
"eval_loss": 0.8072566986083984,
|
| 4085 |
+
"eval_runtime": 1.4047,
|
| 4086 |
+
"eval_samples_per_second": 711.906,
|
| 4087 |
+
"eval_steps_per_second": 11.39,
|
| 4088 |
+
"step": 204000
|
| 4089 |
+
},
|
| 4090 |
+
{
|
| 4091 |
+
"epoch": 5.21,
|
| 4092 |
+
"learning_rate": 0.0002092685534407274,
|
| 4093 |
+
"loss": 0.2938,
|
| 4094 |
+
"step": 204500
|
| 4095 |
+
},
|
| 4096 |
+
{
|
| 4097 |
+
"epoch": 5.22,
|
| 4098 |
+
"learning_rate": 0.00020882360109314197,
|
| 4099 |
+
"loss": 0.2946,
|
| 4100 |
+
"step": 205000
|
| 4101 |
+
},
|
| 4102 |
+
{
|
| 4103 |
+
"epoch": 5.22,
|
| 4104 |
+
"eval_loss": 0.8255318403244019,
|
| 4105 |
+
"eval_runtime": 1.3095,
|
| 4106 |
+
"eval_samples_per_second": 763.663,
|
| 4107 |
+
"eval_steps_per_second": 12.219,
|
| 4108 |
+
"step": 205000
|
| 4109 |
+
},
|
| 4110 |
+
{
|
| 4111 |
+
"epoch": 5.24,
|
| 4112 |
+
"learning_rate": 0.0002083780601392783,
|
| 4113 |
+
"loss": 0.293,
|
| 4114 |
+
"step": 205500
|
| 4115 |
+
},
|
| 4116 |
+
{
|
| 4117 |
+
"epoch": 5.25,
|
| 4118 |
+
"learning_rate": 0.0002079319354515008,
|
| 4119 |
+
"loss": 0.2939,
|
| 4120 |
+
"step": 206000
|
| 4121 |
+
},
|
| 4122 |
+
{
|
| 4123 |
+
"epoch": 5.25,
|
| 4124 |
+
"eval_loss": 0.8249548077583313,
|
| 4125 |
+
"eval_runtime": 1.2456,
|
| 4126 |
+
"eval_samples_per_second": 802.804,
|
| 4127 |
+
"eval_steps_per_second": 12.845,
|
| 4128 |
+
"step": 206000
|
| 4129 |
+
},
|
| 4130 |
+
{
|
| 4131 |
+
"epoch": 5.26,
|
| 4132 |
+
"learning_rate": 0.00020748523190855772,
|
| 4133 |
+
"loss": 0.2929,
|
| 4134 |
+
"step": 206500
|
| 4135 |
+
},
|
| 4136 |
+
{
|
| 4137 |
+
"epoch": 5.28,
|
| 4138 |
+
"learning_rate": 0.0002070379543955273,
|
| 4139 |
+
"loss": 0.2933,
|
| 4140 |
+
"step": 207000
|
| 4141 |
+
},
|
| 4142 |
+
{
|
| 4143 |
+
"epoch": 5.28,
|
| 4144 |
+
"eval_loss": 0.8215068578720093,
|
| 4145 |
+
"eval_runtime": 1.3095,
|
| 4146 |
+
"eval_samples_per_second": 763.673,
|
| 4147 |
+
"eval_steps_per_second": 12.219,
|
| 4148 |
+
"step": 207000
|
| 4149 |
+
},
|
| 4150 |
+
{
|
| 4151 |
+
"epoch": 5.29,
|
| 4152 |
+
"learning_rate": 0.00020659010780376487,
|
| 4153 |
+
"loss": 0.2928,
|
| 4154 |
+
"step": 207500
|
| 4155 |
+
},
|
| 4156 |
+
{
|
| 4157 |
+
"epoch": 5.3,
|
| 4158 |
+
"learning_rate": 0.00020614169703084896,
|
| 4159 |
+
"loss": 0.2927,
|
| 4160 |
+
"step": 208000
|
| 4161 |
+
},
|
| 4162 |
+
{
|
| 4163 |
+
"epoch": 5.3,
|
| 4164 |
+
"eval_loss": 0.8152709007263184,
|
| 4165 |
+
"eval_runtime": 1.2719,
|
| 4166 |
+
"eval_samples_per_second": 786.201,
|
| 4167 |
+
"eval_steps_per_second": 12.579,
|
| 4168 |
+
"step": 208000
|
| 4169 |
+
},
|
| 4170 |
+
{
|
| 4171 |
+
"epoch": 5.31,
|
| 4172 |
+
"learning_rate": 0.0002056927269805279,
|
| 4173 |
+
"loss": 0.2928,
|
| 4174 |
+
"step": 208500
|
| 4175 |
+
},
|
| 4176 |
+
{
|
| 4177 |
+
"epoch": 5.33,
|
| 4178 |
+
"learning_rate": 0.00020524320256266635,
|
| 4179 |
+
"loss": 0.2931,
|
| 4180 |
+
"step": 209000
|
| 4181 |
+
},
|
| 4182 |
+
{
|
| 4183 |
+
"epoch": 5.33,
|
| 4184 |
+
"eval_loss": 0.8284364938735962,
|
| 4185 |
+
"eval_runtime": 1.322,
|
| 4186 |
+
"eval_samples_per_second": 756.405,
|
| 4187 |
+
"eval_steps_per_second": 12.102,
|
| 4188 |
+
"step": 209000
|
| 4189 |
+
},
|
| 4190 |
+
{
|
| 4191 |
+
"epoch": 5.34,
|
| 4192 |
+
"learning_rate": 0.0002047931286931912,
|
| 4193 |
+
"loss": 0.2923,
|
| 4194 |
+
"step": 209500
|
| 4195 |
+
},
|
| 4196 |
+
{
|
| 4197 |
+
"epoch": 5.35,
|
| 4198 |
+
"learning_rate": 0.00020434251029403824,
|
| 4199 |
+
"loss": 0.2928,
|
| 4200 |
+
"step": 210000
|
| 4201 |
+
},
|
| 4202 |
+
{
|
| 4203 |
+
"epoch": 5.35,
|
| 4204 |
+
"eval_loss": 0.8203576803207397,
|
| 4205 |
+
"eval_runtime": 1.366,
|
| 4206 |
+
"eval_samples_per_second": 732.046,
|
| 4207 |
+
"eval_steps_per_second": 11.713,
|
| 4208 |
+
"step": 210000
|
| 4209 |
}
|
| 4210 |
],
|
| 4211 |
"max_steps": 500000,
|
| 4212 |
"num_train_epochs": 13,
|
| 4213 |
+
"total_flos": 6.709162519699275e+21,
|
| 4214 |
"trial_name": null,
|
| 4215 |
"trial_params": null
|
| 4216 |
}
|
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 sha256:500bbe867ded0d4e115c70f239c6f305c19492ee5158d2b7bb72cd84b524f5aa
|
| 3 |
size 102501541
|