Theoreticallyhugo commited on
Commit
dd56c1a
1 Parent(s): 06f43a7

Training in progress, epoch 2, checkpoint

Browse files
checkpoint-162/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:083ce1f37a3462328c6364dfaccbfc65ffa0009ed52257a7d6ccdf6869126fd5
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8ea56ad0dda8537612707e877f8a6964dd8996d47274a00e683ce6423c8c0f
3
  size 592324828
checkpoint-162/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5568bb69ec64d2bc10324738613cedaff08796e1755a10e4f8c8cc7a132726b2
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6131f5f7775205acc1a58ce8b1bf409116b5f7b78814168d0e0267ff86c32587
3
  size 1014657786
checkpoint-162/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bd8264931534616018335b535732049961e4647585455e22b74dcb3e6034c63
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46048b97dd03acf4cb6c82fc924d60322fb8fb6d0b9ecb6d39c987081744ecab
3
  size 1064
checkpoint-162/trainer_state.json CHANGED
@@ -11,98 +11,98 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
- "f1-score": 0.5254768748366867,
15
- "precision": 0.5768789443488239,
16
- "recall": 0.4824856046065259,
17
- "support": 4168.0
18
  },
19
  "eval_MajorClaim": {
20
- "f1-score": 0.7984361424847959,
21
- "precision": 0.7495921696574225,
22
- "recall": 0.854089219330855,
23
- "support": 2152.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.9990277532260916,
27
- "precision": 0.9988511841640155,
28
- "recall": 0.9992043847241867,
29
- "support": 11312.0
30
  },
31
  "eval_Premise": {
32
- "f1-score": 0.8854183656825966,
33
- "precision": 0.8719781543651113,
34
- "recall": 0.8992793837488611,
35
- "support": 12073.0
36
  },
37
- "eval_accuracy": 0.8755765022723447,
38
- "eval_loss": 0.28303390741348267,
39
  "eval_macro avg": {
40
- "f1-score": 0.8020897840575427,
41
- "precision": 0.7993251131338432,
42
- "recall": 0.8087646481026072,
43
- "support": 29705.0
44
  },
45
- "eval_runtime": 4.8106,
46
- "eval_samples_per_second": 16.63,
47
- "eval_steps_per_second": 2.079,
48
  "eval_weighted avg": {
49
- "f1-score": 0.8718761173649596,
50
- "precision": 0.8700202202343714,
51
- "recall": 0.8755765022723447,
52
- "support": 29705.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
- "f1-score": 0.5578782336033447,
60
- "precision": 0.6124497991967871,
61
- "recall": 0.5122360844529751,
62
- "support": 4168.0
63
  },
64
  "eval_MajorClaim": {
65
- "f1-score": 0.784421283598464,
66
- "precision": 0.9571619812583668,
67
- "recall": 0.6644981412639405,
68
- "support": 2152.0
69
  },
70
  "eval_O": {
71
- "f1-score": 0.9998674150351351,
72
- "precision": 0.9997348652231551,
73
- "recall": 1.0,
74
- "support": 11312.0
75
  },
76
  "eval_Premise": {
77
- "f1-score": 0.8977749872463995,
78
- "precision": 0.8530201342281879,
79
- "recall": 0.9474861260664292,
80
- "support": 12073.0
81
  },
82
- "eval_accuracy": 0.8859114627167144,
83
- "eval_loss": 0.27363118529319763,
84
  "eval_macro avg": {
85
- "f1-score": 0.8099854798708358,
86
- "precision": 0.8555916949766242,
87
- "recall": 0.7810550879458362,
88
- "support": 29705.0
89
  },
90
- "eval_runtime": 4.7727,
91
- "eval_samples_per_second": 16.762,
92
- "eval_steps_per_second": 2.095,
93
  "eval_weighted avg": {
94
- "f1-score": 0.8807489883812781,
95
- "precision": 0.8826802296805741,
96
- "recall": 0.8859114627167144,
97
- "support": 29705.0
98
  },
99
  "step": 162
100
  }
101
  ],
102
  "logging_steps": 500,
103
- "max_steps": 4050,
104
  "num_input_tokens_seen": 0,
105
- "num_train_epochs": 50,
106
  "save_steps": 500,
107
  "total_flos": 287577465453600.0,
108
  "train_batch_size": 4,
 
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
+ "f1-score": 0.580553004795429,
15
+ "precision": 0.5136306192453511,
16
+ "recall": 0.6675269826372595,
17
+ "support": 4262.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.6929252383341696,
21
+ "precision": 0.7583745194947831,
22
+ "recall": 0.6378752886836028,
23
+ "support": 2165.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.9968272281511393,
27
+ "precision": 0.9967861557478368,
28
+ "recall": 0.996868303939344,
29
+ "support": 12134.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8769487750556793,
33
+ "precision": 0.9107806691449815,
34
+ "recall": 0.8455403021704119,
35
+ "support": 13039.0
36
  },
37
+ "eval_accuracy": 0.8654113924050633,
38
+ "eval_loss": 0.32089120149612427,
39
  "eval_macro avg": {
40
+ "f1-score": 0.7868135615841043,
41
+ "precision": 0.7948929909082382,
42
+ "recall": 0.7869527193576545,
43
+ "support": 31600.0
44
  },
45
+ "eval_runtime": 5.9789,
46
+ "eval_samples_per_second": 13.38,
47
+ "eval_steps_per_second": 1.673,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.8703967313850799,
50
+ "precision": 0.8797989523023909,
51
+ "recall": 0.8654113924050633,
52
+ "support": 31600.0
53
  },
54
  "step": 81
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.6029902384776968,
60
+ "precision": 0.6369094231271208,
61
+ "recall": 0.5725011731581418,
62
+ "support": 4262.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.8179940325912326,
66
+ "precision": 0.8129562043795621,
67
+ "recall": 0.8230946882217091,
68
+ "support": 2165.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.9984359565360553,
72
+ "precision": 0.9972866304884065,
73
+ "recall": 0.9995879347288611,
74
+ "support": 12134.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.9017917895214335,
78
+ "precision": 0.8891539321654864,
79
+ "recall": 0.9147940793005599,
80
+ "support": 13039.0
81
  },
82
+ "eval_accuracy": 0.8949050632911393,
83
+ "eval_loss": 0.25671303272247314,
84
  "eval_macro avg": {
85
+ "f1-score": 0.8303030042816045,
86
+ "precision": 0.8340765475401439,
87
+ "recall": 0.8274944688523179,
88
+ "support": 31600.0
89
  },
90
+ "eval_runtime": 6.0616,
91
+ "eval_samples_per_second": 13.198,
92
+ "eval_steps_per_second": 1.65,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8928603328205832,
95
+ "precision": 0.8914339316361279,
96
+ "recall": 0.8949050632911393,
97
+ "support": 31600.0
98
  },
99
  "step": 162
100
  }
101
  ],
102
  "logging_steps": 500,
103
+ "max_steps": 1620,
104
  "num_input_tokens_seen": 0,
105
+ "num_train_epochs": 20,
106
  "save_steps": 500,
107
  "total_flos": 287577465453600.0,
108
  "train_batch_size": 4,
checkpoint-162/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c4152f1ae85467509d6d1bf2d3b859abf08e786a1c118f9c84f899edc2df5d1
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa93f134f1d4f6f4c7db9ba5be632f50fd4a52b8d6cce9d00588b8a1094a71e
3
  size 4856