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
3a35144
·
verified ·
1 Parent(s): fba157b

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 sha256:8583659211c43c979e3ebb2b2077aaad30595ab37a9bef5343af02d10b4c8bfc
3
  size 1625422896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2e2a7a69875b07ff44bb7705aae92322fd74f2cf5b3c3fc0ce5ff7a536e93d
3
  size 1625422896
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7bec18a84f551b816591479a6205f955cf887eb99a0dfe6f178ee390d2f2d15
3
  size 3250759392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fb90d40c7774ad8b3a73bff13e4207b857c5fe6687515354ea196f62a8ce98
3
  size 3250759392
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c06cd809d24fd6588d7182ae83a04c71980b17187bed1fed3de7b640efbf43a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25f0989e8e91af9e8637f85210bc8171a9ace36462fb90ce2e6d3e8f7ae2fa2
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08a4ed0ac44c7cb5fe211aaac922c6c1f4955961ca56a185712498d587eefce0
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b479a091e6482cdb8085a5931fe45bae60997ab8939a20b371d61d6be6f7199
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": 49.45,
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": 1.601,
92
  "eval_steps_per_second": 0.4,
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": 50.2,
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": 1.601,
92
  "eval_steps_per_second": 0.4,
93
  "step": 500
94
+ },
95
+ {
96
+ "epoch": 0.1898679554673341,
97
+ "grad_norm": 3.390817642211914,
98
+ "learning_rate": 4.688058634250984e-06,
99
+ "loss": 0.3289,
100
+ "step": 550
101
+ },
102
+ {
103
+ "epoch": 0.20712867869163717,
104
+ "grad_norm": 2.9106905460357666,
105
+ "learning_rate": 4.643367894172328e-06,
106
+ "loss": 0.3245,
107
+ "step": 600
108
+ },
109
+ {
110
+ "epoch": 0.22438940191594028,
111
+ "grad_norm": 11.3765287399292,
112
+ "learning_rate": 4.598677154093672e-06,
113
+ "loss": 0.3335,
114
+ "step": 650
115
+ },
116
+ {
117
+ "epoch": 0.24165012514024337,
118
+ "grad_norm": 2.70393967628479,
119
+ "learning_rate": 4.553986414015016e-06,
120
+ "loss": 0.3212,
121
+ "step": 700
122
+ },
123
+ {
124
+ "epoch": 0.2589108483645465,
125
+ "grad_norm": 2.325925827026367,
126
+ "learning_rate": 4.509295673936361e-06,
127
+ "loss": 0.3188,
128
+ "step": 750
129
+ },
130
+ {
131
+ "epoch": 0.2761715715888496,
132
+ "grad_norm": 2.699869155883789,
133
+ "learning_rate": 4.464604933857705e-06,
134
+ "loss": 0.3198,
135
+ "step": 800
136
+ },
137
+ {
138
+ "epoch": 0.2934322948131527,
139
+ "grad_norm": 3.212961435317993,
140
+ "learning_rate": 4.419914193779049e-06,
141
+ "loss": 0.3158,
142
+ "step": 850
143
+ },
144
+ {
145
+ "epoch": 0.31069301803745575,
146
+ "grad_norm": 2.4674649238586426,
147
+ "learning_rate": 4.375223453700393e-06,
148
+ "loss": 0.3145,
149
+ "step": 900
150
+ },
151
+ {
152
+ "epoch": 0.32795374126175886,
153
+ "grad_norm": 2.870105504989624,
154
+ "learning_rate": 4.330532713621738e-06,
155
+ "loss": 0.2977,
156
+ "step": 950
157
+ },
158
+ {
159
+ "epoch": 0.34521446448606197,
160
+ "grad_norm": 5.365257263183594,
161
+ "learning_rate": 4.285841973543082e-06,
162
+ "loss": 0.3293,
163
+ "step": 1000
164
+ },
165
+ {
166
+ "epoch": 0.34521446448606197,
167
+ "eval_gen_len": 52.97696335078534,
168
+ "eval_loss": 0.6229833960533142,
169
+ "eval_rouge1": 50.2,
170
+ "eval_rouge2": 35.42,
171
+ "eval_rougeL": 43.42,
172
+ "eval_rougeLsum": 43.84,
173
+ "eval_runtime": 3432.2153,
174
+ "eval_samples_per_second": 1.669,
175
+ "eval_steps_per_second": 0.418,
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