Hugging Face's logo

ingu627
/
finetuned-flan-t5-dialogsum

Safetensors
English
t5
flan
fine-tuned
instruction
Model card Files
xet
Community
ingu627 commited on
Commit
6801ea1
·
verified ·
1 Parent(s): 398390e

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. checkpoint-1170/trainer_state.json +22 -22
  2. checkpoint-1170/training_args.bin +1 -1
  3. checkpoint-1560/trainer_state.json +29 -29
  4. checkpoint-1560/training_args.bin +1 -1
  5. checkpoint-1950/trainer_state.json +36 -36
  6. checkpoint-1950/training_args.bin +1 -1
  7. checkpoint-390/trainer_state.json +8 -8
  8. checkpoint-390/training_args.bin +1 -1
  9. checkpoint-780/trainer_state.json +15 -15
  10. checkpoint-780/training_args.bin +1 -1
  11. training_args.bin +1 -1
checkpoint-1170/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.37302049291469286,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1170",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
@@ -11,13 +11,13 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
- "eval_rouge1": 0.44390533529516707,
15
- "eval_rouge2": 0.17816004659159018,
16
- "eval_rougeL": 0.3549576722879668,
17
- "eval_rougeLsum": 0.35441826265370524,
18
- "eval_runtime": 80.6959,
19
- "eval_samples_per_second": 6.196,
20
- "eval_steps_per_second": 0.198,
21
  "step": 390
22
  },
23
  {
@@ -30,13 +30,13 @@
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
- "eval_rouge1": 0.4482698780932518,
34
- "eval_rouge2": 0.18739096580891712,
35
- "eval_rougeL": 0.36483112986239974,
36
- "eval_rougeLsum": 0.36534174634073446,
37
- "eval_runtime": 71.8805,
38
- "eval_samples_per_second": 6.956,
39
- "eval_steps_per_second": 0.223,
40
  "step": 780
41
  },
42
  {
@@ -49,13 +49,13 @@
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
- "eval_rouge1": 0.4552365012882353,
53
- "eval_rouge2": 0.19360204012821247,
54
- "eval_rougeL": 0.37302049291469286,
55
- "eval_rougeLsum": 0.37299575058153295,
56
- "eval_runtime": 73.9699,
57
- "eval_samples_per_second": 6.76,
58
- "eval_steps_per_second": 0.216,
59
  "step": 1170
60
  }
61
  ],
 
1
  {
2
+ "best_metric": 0.37278811615341145,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1170",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
+ "eval_rouge1": 0.44388160380951946,
15
+ "eval_rouge2": 0.17811053634418733,
16
+ "eval_rougeL": 0.35470174491389483,
17
+ "eval_rougeLsum": 0.35400351619004,
18
+ "eval_runtime": 73.2026,
19
+ "eval_samples_per_second": 6.83,
20
+ "eval_steps_per_second": 0.219,
21
  "step": 390
22
  },
23
  {
 
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
+ "eval_rouge1": 0.4481724027358116,
34
+ "eval_rouge2": 0.18706683962522586,
35
+ "eval_rougeL": 0.36502676602307105,
36
+ "eval_rougeLsum": 0.3646421437489298,
37
+ "eval_runtime": 65.5308,
38
+ "eval_samples_per_second": 7.63,
39
+ "eval_steps_per_second": 0.244,
40
  "step": 780
41
  },
42
  {
 
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
+ "eval_rouge1": 0.45487076866137466,
53
+ "eval_rouge2": 0.19364689560301196,
54
+ "eval_rougeL": 0.37278811615341145,
55
+ "eval_rougeLsum": 0.3724689402967539,
56
+ "eval_runtime": 67.4046,
57
+ "eval_samples_per_second": 7.418,
58
+ "eval_steps_per_second": 0.237,
59
  "step": 1170
60
  }
61
  ],
checkpoint-1170/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496
checkpoint-1560/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.37354020516399644,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1560",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
@@ -11,13 +11,13 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
- "eval_rouge1": 0.44390533529516707,
15
- "eval_rouge2": 0.17816004659159018,
16
- "eval_rougeL": 0.3549576722879668,
17
- "eval_rougeLsum": 0.35441826265370524,
18
- "eval_runtime": 80.6959,
19
- "eval_samples_per_second": 6.196,
20
- "eval_steps_per_second": 0.198,
21
  "step": 390
22
  },
23
  {
@@ -30,13 +30,13 @@
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
- "eval_rouge1": 0.4482698780932518,
34
- "eval_rouge2": 0.18739096580891712,
35
- "eval_rougeL": 0.36483112986239974,
36
- "eval_rougeLsum": 0.36534174634073446,
37
- "eval_runtime": 71.8805,
38
- "eval_samples_per_second": 6.956,
39
- "eval_steps_per_second": 0.223,
40
  "step": 780
41
  },
42
  {
@@ -49,13 +49,13 @@
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
- "eval_rouge1": 0.4552365012882353,
53
- "eval_rouge2": 0.19360204012821247,
54
- "eval_rougeL": 0.37302049291469286,
55
- "eval_rougeLsum": 0.37299575058153295,
56
- "eval_runtime": 73.9699,
57
- "eval_samples_per_second": 6.76,
58
- "eval_steps_per_second": 0.216,
59
  "step": 1170
60
  },
61
  {
@@ -68,13 +68,13 @@
68
  {
69
  "epoch": 4.0,
70
  "eval_loss": 0.29470932483673096,
71
- "eval_rouge1": 0.45601516547866866,
72
- "eval_rouge2": 0.19372580419992047,
73
- "eval_rougeL": 0.37354020516399644,
74
- "eval_rougeLsum": 0.3735440879776317,
75
- "eval_runtime": 70.929,
76
- "eval_samples_per_second": 7.049,
77
- "eval_steps_per_second": 0.226,
78
  "step": 1560
79
  }
80
  ],
 
1
  {
2
+ "best_metric": 0.3732990631191409,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1560",
4
  "epoch": 4.0,
5
  "eval_steps": 500,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
+ "eval_rouge1": 0.44388160380951946,
15
+ "eval_rouge2": 0.17811053634418733,
16
+ "eval_rougeL": 0.35470174491389483,
17
+ "eval_rougeLsum": 0.35400351619004,
18
+ "eval_runtime": 73.2026,
19
+ "eval_samples_per_second": 6.83,
20
+ "eval_steps_per_second": 0.219,
21
  "step": 390
22
  },
23
  {
 
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
+ "eval_rouge1": 0.4481724027358116,
34
+ "eval_rouge2": 0.18706683962522586,
35
+ "eval_rougeL": 0.36502676602307105,
36
+ "eval_rougeLsum": 0.3646421437489298,
37
+ "eval_runtime": 65.5308,
38
+ "eval_samples_per_second": 7.63,
39
+ "eval_steps_per_second": 0.244,
40
  "step": 780
41
  },
42
  {
 
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
+ "eval_rouge1": 0.45487076866137466,
53
+ "eval_rouge2": 0.19364689560301196,
54
+ "eval_rougeL": 0.37278811615341145,
55
+ "eval_rougeLsum": 0.3724689402967539,
56
+ "eval_runtime": 67.4046,
57
+ "eval_samples_per_second": 7.418,
58
+ "eval_steps_per_second": 0.237,
59
  "step": 1170
60
  },
61
  {
 
68
  {
69
  "epoch": 4.0,
70
  "eval_loss": 0.29470932483673096,
71
+ "eval_rouge1": 0.45634329846140587,
72
+ "eval_rouge2": 0.1935668856761302,
73
+ "eval_rougeL": 0.3732990631191409,
74
+ "eval_rougeLsum": 0.3728926972461234,
75
+ "eval_runtime": 64.629,
76
+ "eval_samples_per_second": 7.736,
77
+ "eval_steps_per_second": 0.248,
78
  "step": 1560
79
  }
80
  ],
checkpoint-1560/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496
checkpoint-1950/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.37354020516399644,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1560",
4
  "epoch": 5.0,
5
  "eval_steps": 500,
@@ -11,13 +11,13 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
- "eval_rouge1": 0.44390533529516707,
15
- "eval_rouge2": 0.17816004659159018,
16
- "eval_rougeL": 0.3549576722879668,
17
- "eval_rougeLsum": 0.35441826265370524,
18
- "eval_runtime": 80.6959,
19
- "eval_samples_per_second": 6.196,
20
- "eval_steps_per_second": 0.198,
21
  "step": 390
22
  },
23
  {
@@ -30,13 +30,13 @@
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
- "eval_rouge1": 0.4482698780932518,
34
- "eval_rouge2": 0.18739096580891712,
35
- "eval_rougeL": 0.36483112986239974,
36
- "eval_rougeLsum": 0.36534174634073446,
37
- "eval_runtime": 71.8805,
38
- "eval_samples_per_second": 6.956,
39
- "eval_steps_per_second": 0.223,
40
  "step": 780
41
  },
42
  {
@@ -49,13 +49,13 @@
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
- "eval_rouge1": 0.4552365012882353,
53
- "eval_rouge2": 0.19360204012821247,
54
- "eval_rougeL": 0.37302049291469286,
55
- "eval_rougeLsum": 0.37299575058153295,
56
- "eval_runtime": 73.9699,
57
- "eval_samples_per_second": 6.76,
58
- "eval_steps_per_second": 0.216,
59
  "step": 1170
60
  },
61
  {
@@ -68,25 +68,25 @@
68
  {
69
  "epoch": 4.0,
70
  "eval_loss": 0.29470932483673096,
71
- "eval_rouge1": 0.45601516547866866,
72
- "eval_rouge2": 0.19372580419992047,
73
- "eval_rougeL": 0.37354020516399644,
74
- "eval_rougeLsum": 0.3735440879776317,
75
- "eval_runtime": 70.929,
76
- "eval_samples_per_second": 7.049,
77
- "eval_steps_per_second": 0.226,
78
  "step": 1560
79
  },
80
  {
81
  "epoch": 5.0,
82
  "eval_loss": 0.29482799768447876,
83
- "eval_rouge1": 0.4548074338758987,
84
- "eval_rouge2": 0.1892886198010884,
85
- "eval_rougeL": 0.3673308042257807,
86
- "eval_rougeLsum": 0.367167688006684,
87
- "eval_runtime": 71.2424,
88
- "eval_samples_per_second": 7.018,
89
- "eval_steps_per_second": 0.225,
90
  "step": 1950
91
  }
92
  ],
 
1
  {
2
+ "best_metric": 0.3732990631191409,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-1560",
4
  "epoch": 5.0,
5
  "eval_steps": 500,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
+ "eval_rouge1": 0.44388160380951946,
15
+ "eval_rouge2": 0.17811053634418733,
16
+ "eval_rougeL": 0.35470174491389483,
17
+ "eval_rougeLsum": 0.35400351619004,
18
+ "eval_runtime": 73.2026,
19
+ "eval_samples_per_second": 6.83,
20
+ "eval_steps_per_second": 0.219,
21
  "step": 390
22
  },
23
  {
 
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
+ "eval_rouge1": 0.4481724027358116,
34
+ "eval_rouge2": 0.18706683962522586,
35
+ "eval_rougeL": 0.36502676602307105,
36
+ "eval_rougeLsum": 0.3646421437489298,
37
+ "eval_runtime": 65.5308,
38
+ "eval_samples_per_second": 7.63,
39
+ "eval_steps_per_second": 0.244,
40
  "step": 780
41
  },
42
  {
 
49
  {
50
  "epoch": 3.0,
51
  "eval_loss": 0.2967517375946045,
52
+ "eval_rouge1": 0.45487076866137466,
53
+ "eval_rouge2": 0.19364689560301196,
54
+ "eval_rougeL": 0.37278811615341145,
55
+ "eval_rougeLsum": 0.3724689402967539,
56
+ "eval_runtime": 67.4046,
57
+ "eval_samples_per_second": 7.418,
58
+ "eval_steps_per_second": 0.237,
59
  "step": 1170
60
  },
61
  {
 
68
  {
69
  "epoch": 4.0,
70
  "eval_loss": 0.29470932483673096,
71
+ "eval_rouge1": 0.45634329846140587,
72
+ "eval_rouge2": 0.1935668856761302,
73
+ "eval_rougeL": 0.3732990631191409,
74
+ "eval_rougeLsum": 0.3728926972461234,
75
+ "eval_runtime": 64.629,
76
+ "eval_samples_per_second": 7.736,
77
+ "eval_steps_per_second": 0.248,
78
  "step": 1560
79
  },
80
  {
81
  "epoch": 5.0,
82
  "eval_loss": 0.29482799768447876,
83
+ "eval_rouge1": 0.4547042383346209,
84
+ "eval_rouge2": 0.18917345073480046,
85
+ "eval_rougeL": 0.3670910829591487,
86
+ "eval_rougeLsum": 0.3666732624155983,
87
+ "eval_runtime": 65.3537,
88
+ "eval_samples_per_second": 7.651,
89
+ "eval_steps_per_second": 0.245,
90
  "step": 1950
91
  }
92
  ],
checkpoint-1950/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496
checkpoint-390/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.3549576722879668,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-390",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -11,13 +11,13 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
- "eval_rouge1": 0.44390533529516707,
15
- "eval_rouge2": 0.17816004659159018,
16
- "eval_rougeL": 0.3549576722879668,
17
- "eval_rougeLsum": 0.35441826265370524,
18
- "eval_runtime": 80.6959,
19
- "eval_samples_per_second": 6.196,
20
- "eval_steps_per_second": 0.198,
21
  "step": 390
22
  }
23
  ],
 
1
  {
2
+ "best_metric": 0.35470174491389483,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-390",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
+ "eval_rouge1": 0.44388160380951946,
15
+ "eval_rouge2": 0.17811053634418733,
16
+ "eval_rougeL": 0.35470174491389483,
17
+ "eval_rougeLsum": 0.35400351619004,
18
+ "eval_runtime": 73.2026,
19
+ "eval_samples_per_second": 6.83,
20
+ "eval_steps_per_second": 0.219,
21
  "step": 390
22
  }
23
  ],
checkpoint-390/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496
checkpoint-780/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.36483112986239974,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-780",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -11,13 +11,13 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
- "eval_rouge1": 0.44390533529516707,
15
- "eval_rouge2": 0.17816004659159018,
16
- "eval_rougeL": 0.3549576722879668,
17
- "eval_rougeLsum": 0.35441826265370524,
18
- "eval_runtime": 80.6959,
19
- "eval_samples_per_second": 6.196,
20
- "eval_steps_per_second": 0.198,
21
  "step": 390
22
  },
23
  {
@@ -30,13 +30,13 @@
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
- "eval_rouge1": 0.4482698780932518,
34
- "eval_rouge2": 0.18739096580891712,
35
- "eval_rougeL": 0.36483112986239974,
36
- "eval_rougeLsum": 0.36534174634073446,
37
- "eval_runtime": 71.8805,
38
- "eval_samples_per_second": 6.956,
39
- "eval_steps_per_second": 0.223,
40
  "step": 780
41
  }
42
  ],
 
1
  {
2
+ "best_metric": 0.36502676602307105,
3
  "best_model_checkpoint": "./flan-t5-dialogsum/checkpoint-780",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_loss": 0.31267526745796204,
14
+ "eval_rouge1": 0.44388160380951946,
15
+ "eval_rouge2": 0.17811053634418733,
16
+ "eval_rougeL": 0.35470174491389483,
17
+ "eval_rougeLsum": 0.35400351619004,
18
+ "eval_runtime": 73.2026,
19
+ "eval_samples_per_second": 6.83,
20
+ "eval_steps_per_second": 0.219,
21
  "step": 390
22
  },
23
  {
 
30
  {
31
  "epoch": 2.0,
32
  "eval_loss": 0.3003218472003937,
33
+ "eval_rouge1": 0.4481724027358116,
34
+ "eval_rouge2": 0.18706683962522586,
35
+ "eval_rougeL": 0.36502676602307105,
36
+ "eval_rougeLsum": 0.3646421437489298,
37
+ "eval_runtime": 65.5308,
38
+ "eval_samples_per_second": 7.63,
39
+ "eval_steps_per_second": 0.244,
40
  "step": 780
41
  }
42
  ],
checkpoint-780/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95d01320e9d3e2d7907a228c0efc910d6964b9c2efade9b7b4d1685ffc83243
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773f767b9a9562339691703bbfc85f7986c2526c05a733b43b1a20013d33ad8e
3
  size 5496