Hugging Face's logo

circlemachinelearning
/
bart-email-multitask

Transformers
Safetensors
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
rosypossyyyy commited on
Commit
a031448
·
verified ·
1 Parent(s): 30d44bf

Training in progress, step 1000, checkpoint

Browse files
Files changed (6) 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/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +89 -6
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:024e31774972ff3820090308d6a53b1687a81cbc1c1e120faa23fe6f2736a792
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6582285e6ceefad293dc43c7b1e46f720b002966ac196d7c0ed75850fa58072f
3
  size 1625422896
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e0e2871711a7f1cbd51c0e9c8d6a1661a58c09dd8132528c56df9afa8fc214b
3
  size 3250759392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1289f0f9e4695a91c66438eb371e115fd2cf13c51b9b60f4d079bcea0df3f1
3
  size 3250759392
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c880a200501ba0b67082f3081094988ba079c54e1ac9a1deb1603230cd2f05
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f64d1914206b27bc308756481002e046d709339f305bb5f119a7f2db9832e2a
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7556a6d66035d11bc10a3374d5ff7bbff46c4fa1cc48d9d21c51bdde6df224e5
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9fe95f5f8339fd092746c4e1f9ecbd1df3cf41b30fe774157fac457b1083509
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6901005092102ab95f1173ef27f9dc91cdbf890535e1b1d5bd4fdb92b6125b7d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5955ff7ae3c292679cb2d15dfab21a83841dbd226cd7e259de6ef2a4c905fc
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 500,
3
- "best_metric": 49.82,
4
- "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-500",
5
- "epoch": 0.17260723224303098,
6
  "eval_steps": 500,
7
- "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -91,6 +91,89 @@
91
  "eval_samples_per_second": 1.064,
92
  "eval_steps_per_second": 0.266,
93
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  }
95
  ],
96
  "logging_steps": 50,
@@ -119,7 +202,7 @@
119
  "attributes": {}
120
  }
121
  },
122
- "total_flos": 1.7167531769856e+16,
123
  "train_batch_size": 4,
124
  "trial_name": null,
125
  "trial_params": null
 
1
  {
2
+ "best_global_step": 1000,
3
+ "best_metric": 50.66,
4
+ "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1000",
5
+ "epoch": 0.34521446448606197,
6
  "eval_steps": 500,
7
+ "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
91
  "eval_samples_per_second": 1.064,
92
  "eval_steps_per_second": 0.266,
93
  "step": 500
94
+ },
95
+ {
96
+ "epoch": 0.1898679554673341,
97
+ "grad_norm": 3.0305216312408447,
98
+ "learning_rate": 4.688058634250984e-06,
99
+ "loss": 0.3849,
100
+ "step": 550
101
+ },
102
+ {
103
+ "epoch": 0.20712867869163717,
104
+ "grad_norm": 3.079951524734497,
105
+ "learning_rate": 4.643367894172328e-06,
106
+ "loss": 0.3802,
107
+ "step": 600
108
+ },
109
+ {
110
+ "epoch": 0.22438940191594028,
111
+ "grad_norm": 2.7168169021606445,
112
+ "learning_rate": 4.598677154093672e-06,
113
+ "loss": 0.3887,
114
+ "step": 650
115
+ },
116
+ {
117
+ "epoch": 0.24165012514024337,
118
+ "grad_norm": 2.76423716545105,
119
+ "learning_rate": 4.553986414015016e-06,
120
+ "loss": 0.3825,
121
+ "step": 700
122
+ },
123
+ {
124
+ "epoch": 0.2589108483645465,
125
+ "grad_norm": 4.16721248626709,
126
+ "learning_rate": 4.509295673936361e-06,
127
+ "loss": 0.3819,
128
+ "step": 750
129
+ },
130
+ {
131
+ "epoch": 0.2761715715888496,
132
+ "grad_norm": 2.646681785583496,
133
+ "learning_rate": 4.464604933857705e-06,
134
+ "loss": 0.3813,
135
+ "step": 800
136
+ },
137
+ {
138
+ "epoch": 0.2934322948131527,
139
+ "grad_norm": 3.4927141666412354,
140
+ "learning_rate": 4.419914193779049e-06,
141
+ "loss": 0.3793,
142
+ "step": 850
143
+ },
144
+ {
145
+ "epoch": 0.31069301803745575,
146
+ "grad_norm": 2.364363193511963,
147
+ "learning_rate": 4.375223453700393e-06,
148
+ "loss": 0.3815,
149
+ "step": 900
150
+ },
151
+ {
152
+ "epoch": 0.32795374126175886,
153
+ "grad_norm": 2.7475292682647705,
154
+ "learning_rate": 4.330532713621738e-06,
155
+ "loss": 0.3652,
156
+ "step": 950
157
+ },
158
+ {
159
+ "epoch": 0.34521446448606197,
160
+ "grad_norm": 3.994381904602051,
161
+ "learning_rate": 4.285841973543082e-06,
162
+ "loss": 0.39,
163
+ "step": 1000
164
+ },
165
+ {
166
+ "epoch": 0.34521446448606197,
167
+ "eval_gen_len": 53.06160558464224,
168
+ "eval_loss": 0.5498749613761902,
169
+ "eval_rouge1": 50.66,
170
+ "eval_rouge2": 36.17,
171
+ "eval_rougeL": 44.07,
172
+ "eval_rougeLsum": 44.56,
173
+ "eval_runtime": 5246.3152,
174
+ "eval_samples_per_second": 1.092,
175
+ "eval_steps_per_second": 0.273,
176
+ "step": 1000
177
  }
178
  ],
179
  "logging_steps": 50,
 
202
  "attributes": {}
203
  }
204
  },
205
+ "total_flos": 3.4335063539712e+16,
206
  "train_batch_size": 4,
207
  "trial_name": null,
208
  "trial_params": null