Hugging Face's logo

leinms
/
deberta-v3-large-personality-text-classification

Safetensors
deberta-v2
Model card Files Community
leinms commited on
Commit
c54dba5
•
1 Parent(s): 1fc779e

Initial model upload

Browse files
Files changed (6) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +83 -45
  6. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11b8d192550472b9954c979888b3d8ad7655b862fdadf2d13d048e7bf914334f
3
  size 1740320848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f07a97aaf681bb4254356c10bc49b7ea9d47eed3d833beee87b6a2dcb1a016
3
  size 1740320848
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a0c53efbf89d0c1fd9cb9c932cfd39df5a7180d7f56de5f806d6ae25195c85f
3
  size 1217847418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311494ed602ff2c6bfcdc1588fcb9149edfed10906eb1502f7132b4490533841
3
  size 1217847418
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8dd34883ee5f39c7251787e07a2ee30811b62daa17f0f1f415991237d33cca9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd1c3d92fa221f8d29d00103fbf03c9056b7dafceeabb66d7085fa06b52ae42
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d0768fb1331c47f6395a78f4740948e0452839e2a531fc0d429a3abc602de5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ecf1243607361d54a625c225ec02de0677c344dd6166f4cfe37b311c06a78a
3
  size 1064
trainer_state.json CHANGED
@@ -1,73 +1,111 @@
1
  {
2
- "best_metric": 0.04703037813305855,
3
- "best_model_checkpoint": "./results/checkpoint-600",
4
- "epoch": 1.25,
5
  "eval_steps": 200,
6
- "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.4166666666666667,
13
- "grad_norm": 11.54790210723877,
14
- "learning_rate": 2.666666666666667e-06,
15
- "loss": 1.6906,
16
  "step": 200
17
  },
18
  {
19
- "epoch": 0.4166666666666667,
20
- "eval_accuracy": 0.7757009345794392,
21
- "eval_f1": 0.7765921468995,
22
- "eval_loss": 1.205772876739502,
23
- "eval_precision": 0.8385133666594219,
24
- "eval_recall": 0.7757009345794392,
25
- "eval_runtime": 2.0422,
26
- "eval_samples_per_second": 104.791,
27
- "eval_steps_per_second": 26.443,
28
  "step": 200
29
  },
30
  {
31
- "epoch": 0.8333333333333334,
32
- "grad_norm": 1.215197205543518,
33
- "learning_rate": 5.333333333333334e-06,
34
- "loss": 0.4559,
35
  "step": 400
36
  },
37
  {
38
- "epoch": 0.8333333333333334,
39
- "eval_accuracy": 0.985981308411215,
40
- "eval_f1": 0.9859792246220528,
41
- "eval_loss": 0.06015115976333618,
42
- "eval_precision": 0.9861148197596795,
43
- "eval_recall": 0.985981308411215,
44
- "eval_runtime": 2.052,
45
- "eval_samples_per_second": 104.291,
46
- "eval_steps_per_second": 26.316,
47
  "step": 400
48
  },
49
  {
50
- "epoch": 1.25,
51
- "grad_norm": 0.11880175024271011,
52
- "learning_rate": 8.000000000000001e-06,
53
- "loss": 0.0265,
54
  "step": 600
55
  },
56
  {
57
- "epoch": 1.25,
58
- "eval_accuracy": 0.9906542056074766,
59
- "eval_f1": 0.9906542056074766,
60
- "eval_loss": 0.04703037813305855,
61
- "eval_precision": 0.9906542056074766,
62
- "eval_recall": 0.9906542056074766,
63
- "eval_runtime": 2.0321,
64
- "eval_samples_per_second": 105.311,
65
- "eval_steps_per_second": 26.574,
66
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  }
68
  ],
69
  "logging_steps": 200,
70
- "max_steps": 4800,
71
  "num_input_tokens_seen": 0,
72
  "num_train_epochs": 10,
73
  "save_steps": 200,
@@ -92,7 +130,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 98794007359632.0,
96
  "train_batch_size": 4,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.01993558369576931,
3
+ "best_model_checkpoint": "./results2/checkpoint-1000",
4
+ "epoch": 1.6103059581320451,
5
  "eval_steps": 200,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.322061191626409,
13
+ "grad_norm": 7.609610557556152,
14
+ "learning_rate": 6.666666666666667e-07,
15
+ "loss": 1.7968,
16
  "step": 200
17
  },
18
  {
19
+ "epoch": 0.322061191626409,
20
+ "eval_accuracy": 0.3440514469453376,
21
+ "eval_f1": 0.24150421570387215,
22
+ "eval_loss": 1.720999836921692,
23
+ "eval_precision": 0.2639446733696112,
24
+ "eval_recall": 0.3440514469453376,
25
+ "eval_runtime": 5.8122,
26
+ "eval_samples_per_second": 107.017,
27
+ "eval_steps_per_second": 26.84,
28
  "step": 200
29
  },
30
  {
31
+ "epoch": 0.644122383252818,
32
+ "grad_norm": 11.357446670532227,
33
+ "learning_rate": 1.3333333333333334e-06,
34
+ "loss": 1.4943,
35
  "step": 400
36
  },
37
  {
38
+ "epoch": 0.644122383252818,
39
+ "eval_accuracy": 0.8778135048231511,
40
+ "eval_f1": 0.8785472935162124,
41
+ "eval_loss": 1.0978388786315918,
42
+ "eval_precision": 0.8896873197081571,
43
+ "eval_recall": 0.8778135048231511,
44
+ "eval_runtime": 5.7759,
45
+ "eval_samples_per_second": 107.689,
46
+ "eval_steps_per_second": 27.009,
47
  "step": 400
48
  },
49
  {
50
+ "epoch": 0.966183574879227,
51
+ "grad_norm": 16.037065505981445,
52
+ "learning_rate": 2.0000000000000003e-06,
53
+ "loss": 0.6621,
54
  "step": 600
55
  },
56
  {
57
+ "epoch": 0.966183574879227,
58
+ "eval_accuracy": 0.9790996784565916,
59
+ "eval_f1": 0.9792541096699141,
60
+ "eval_loss": 0.2813081741333008,
61
+ "eval_precision": 0.9805446650011903,
62
+ "eval_recall": 0.9790996784565916,
63
+ "eval_runtime": 5.7298,
64
+ "eval_samples_per_second": 108.556,
65
+ "eval_steps_per_second": 27.226,
66
  "step": 600
67
+ },
68
+ {
69
+ "epoch": 1.288244766505636,
70
+ "grad_norm": 0.4586528539657593,
71
+ "learning_rate": 2.666666666666667e-06,
72
+ "loss": 0.1152,
73
+ "step": 800
74
+ },
75
+ {
76
+ "epoch": 1.288244766505636,
77
+ "eval_accuracy": 0.9935691318327974,
78
+ "eval_f1": 0.9935865646567709,
79
+ "eval_loss": 0.0392923541367054,
80
+ "eval_precision": 0.9937258515287424,
81
+ "eval_recall": 0.9935691318327974,
82
+ "eval_runtime": 5.9659,
83
+ "eval_samples_per_second": 104.26,
84
+ "eval_steps_per_second": 26.149,
85
+ "step": 800
86
+ },
87
+ {
88
+ "epoch": 1.6103059581320451,
89
+ "grad_norm": 0.7026401162147522,
90
+ "learning_rate": 3.3333333333333333e-06,
91
+ "loss": 0.0279,
92
+ "step": 1000
93
+ },
94
+ {
95
+ "epoch": 1.6103059581320451,
96
+ "eval_accuracy": 0.9967845659163987,
97
+ "eval_f1": 0.9967848366604815,
98
+ "eval_loss": 0.01993558369576931,
99
+ "eval_precision": 0.9968008054824775,
100
+ "eval_recall": 0.9967845659163987,
101
+ "eval_runtime": 5.9055,
102
+ "eval_samples_per_second": 105.326,
103
+ "eval_steps_per_second": 26.416,
104
+ "step": 1000
105
  }
106
  ],
107
  "logging_steps": 200,
108
+ "max_steps": 6210,
109
  "num_input_tokens_seen": 0,
110
  "num_train_epochs": 10,
111
  "save_steps": 200,
 
130
  "attributes": {}
131
  }
132
  },
133
+ "total_flos": 160310004719904.0,
134
  "train_batch_size": 4,
135
  "trial_name": null,
136
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a352b6acb5d6671ea76d03f0a9239077e1262d5900ce0400b95d907f3dec05
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98ebf8db11f98343117e215684c70a08dfcfcdce0fbf522b530c9ff7272f338
3
  size 5240