Hugging Face's logo

sihoon00
/
Bitamin_mutimodal

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
 Metrics Community
sihoon00 commited on
Commit
374aee1
·
verified ·
1 Parent(s): 0e52733

Training in progress, step 10000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +99 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee0f19e5fe682b7a50b0c2b7f11bbfece9784a5a9284724a232e056c8596b07f
3
  size 959732416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1186415f984ec0105131e41ac869ad088c95d3e63a646dcf10ed6f668b70a527
3
  size 959732416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2405d005d01cdadd84ed2ef975229fbc5303ff176cf63f57c86cf8980cec08a
3
  size 1919732806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d59c3829f01b928e7f8ee296635bae1681d515be006c892df8ef86926d91d4
3
  size 1919732806
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c881ad54e2aae8feeb160e05a97e39cf1c147f9aae0937a1b7e41a0710f93d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bd719bf1326b1281aa016ff1c8f48d41524f5feaf22af9267d2acf3daac222
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c589f3acbeec5c6e36834591171153e8af682ebbd66860ce42dbcde5e025a9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddcca23b21d6bdd8ad51b065d4aa1989126b3480f39bbd5a003d90f3b5366d5d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.676727028839705,
5
  "eval_steps": 500,
6
- "global_step": 5000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -90,6 +90,102 @@
90
  "learning_rate": 3.323272971160295e-05,
91
  "loss": 0.1256,
92
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
  }
94
  ],
95
  "logging_steps": 500,
@@ -109,7 +205,7 @@
109
  "attributes": {}
110
  }
111
  },
112
- "total_flos": 3.6087364307291996e+18,
113
  "train_batch_size": 4,
114
  "trial_name": null,
115
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.35345405767941,
5
  "eval_steps": 500,
6
+ "global_step": 10000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
90
  "learning_rate": 3.323272971160295e-05,
91
  "loss": 0.1256,
92
  "step": 5000
93
+ },
94
+ {
95
+ "epoch": 1.8443997317236756,
96
+ "grad_norm": 0.3312112092971802,
97
+ "learning_rate": 3.1556002682763246e-05,
98
+ "loss": 0.1178,
99
+ "step": 5500
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "eval_gen_len": 100.0,
104
+ "eval_loss": 0.1095445454120636,
105
+ "eval_rouge1": 0.8554,
106
+ "eval_rouge2": 0.7275,
107
+ "eval_rougeL": 0.8315,
108
+ "eval_rougeLsum": 0.8554,
109
+ "eval_runtime": 1526.5885,
110
+ "eval_samples_per_second": 0.869,
111
+ "eval_steps_per_second": 0.217,
112
+ "step": 5964
113
+ },
114
+ {
115
+ "epoch": 2.0120724346076457,
116
+ "grad_norm": 0.4150833487510681,
117
+ "learning_rate": 2.9879275653923545e-05,
118
+ "loss": 0.1106,
119
+ "step": 6000
120
+ },
121
+ {
122
+ "epoch": 2.1797451374916164,
123
+ "grad_norm": 0.419521301984787,
124
+ "learning_rate": 2.8202548625083835e-05,
125
+ "loss": 0.0869,
126
+ "step": 6500
127
+ },
128
+ {
129
+ "epoch": 2.347417840375587,
130
+ "grad_norm": 0.30508849024772644,
131
+ "learning_rate": 2.6525821596244134e-05,
132
+ "loss": 0.0857,
133
+ "step": 7000
134
+ },
135
+ {
136
+ "epoch": 2.515090543259557,
137
+ "grad_norm": 0.30741697549819946,
138
+ "learning_rate": 2.4849094567404426e-05,
139
+ "loss": 0.0805,
140
+ "step": 7500
141
+ },
142
+ {
143
+ "epoch": 2.682763246143528,
144
+ "grad_norm": 0.2202298641204834,
145
+ "learning_rate": 2.3172367538564725e-05,
146
+ "loss": 0.0773,
147
+ "step": 8000
148
+ },
149
+ {
150
+ "epoch": 2.8504359490274984,
151
+ "grad_norm": 0.3683091998100281,
152
+ "learning_rate": 2.1495640509725018e-05,
153
+ "loss": 0.0778,
154
+ "step": 8500
155
+ },
156
+ {
157
+ "epoch": 3.0,
158
+ "eval_gen_len": 100.0,
159
+ "eval_loss": 0.08292990177869797,
160
+ "eval_rouge1": 2.7168,
161
+ "eval_rouge2": 1.6458,
162
+ "eval_rougeL": 2.7157,
163
+ "eval_rougeLsum": 2.6864,
164
+ "eval_runtime": 1545.7501,
165
+ "eval_samples_per_second": 0.858,
166
+ "eval_steps_per_second": 0.215,
167
+ "step": 8946
168
+ },
169
+ {
170
+ "epoch": 3.0181086519114686,
171
+ "grad_norm": 0.2871362864971161,
172
+ "learning_rate": 1.9818913480885314e-05,
173
+ "loss": 0.0728,
174
+ "step": 9000
175
+ },
176
+ {
177
+ "epoch": 3.1857813547954392,
178
+ "grad_norm": 0.3297957479953766,
179
+ "learning_rate": 1.814218645204561e-05,
180
+ "loss": 0.0553,
181
+ "step": 9500
182
+ },
183
+ {
184
+ "epoch": 3.35345405767941,
185
+ "grad_norm": 0.5415169596672058,
186
+ "learning_rate": 1.6465459423205902e-05,
187
+ "loss": 0.0545,
188
+ "step": 10000
189
  }
190
  ],
191
  "logging_steps": 500,
 
205
  "attributes": {}
206
  }
207
  },
208
+ "total_flos": 7.216931469785039e+18,
209
  "train_batch_size": 4,
210
  "trial_name": null,
211
  "trial_params": null