Theoreticallyhugo
commited on
Commit
•
039b3fc
1
Parent(s):
49e1529
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:
|
3 |
size 592324828
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4aa5e2d90a186e1508ce5b9a87bc4db8b7e017ab03c2ea6d748fc021a7c40e7
|
3 |
size 592324828
|
checkpoint-162/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014657786
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a553a9bb92cb1bd27c211d83b7959d8bc81af3cf4ad05c31c8b2dd38b48bef0
|
3 |
size 1014657786
|
checkpoint-162/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e210ec99a19f026e2def82a9c5587c47c7771d7dd08d2e2ba3261c169c79d9
|
3 |
size 14244
|
checkpoint-162/trainer_state.json
CHANGED
@@ -11,90 +11,90 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
-
"f1-score": 0.
|
33 |
-
"precision": 0.
|
34 |
-
"recall": 0.
|
35 |
-
"support":
|
36 |
},
|
37 |
-
"eval_accuracy": 0.
|
38 |
-
"eval_loss": 0.
|
39 |
"eval_macro avg": {
|
40 |
-
"f1-score": 0.
|
41 |
-
"precision": 0.
|
42 |
-
"recall": 0.
|
43 |
-
"support":
|
44 |
},
|
45 |
-
"eval_runtime": 4.
|
46 |
-
"eval_samples_per_second": 16.
|
47 |
-
"eval_steps_per_second": 2.
|
48 |
"eval_weighted avg": {
|
49 |
-
"f1-score": 0.
|
50 |
-
"precision": 0.
|
51 |
-
"recall": 0.
|
52 |
-
"support":
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
"eval_O": {
|
71 |
-
"f1-score": 0.
|
72 |
-
"precision": 0.
|
73 |
-
"recall": 0.
|
74 |
-
"support":
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
-
"f1-score": 0.
|
78 |
-
"precision": 0.
|
79 |
-
"recall": 0.
|
80 |
-
"support":
|
81 |
},
|
82 |
-
"eval_accuracy": 0.
|
83 |
-
"eval_loss": 0.
|
84 |
"eval_macro avg": {
|
85 |
-
"f1-score": 0.
|
86 |
-
"precision": 0.
|
87 |
-
"recall": 0.
|
88 |
-
"support":
|
89 |
},
|
90 |
-
"eval_runtime": 4.
|
91 |
-
"eval_samples_per_second": 16.
|
92 |
-
"eval_steps_per_second": 2.
|
93 |
"eval_weighted avg": {
|
94 |
-
"f1-score": 0.
|
95 |
-
"precision": 0.
|
96 |
-
"recall": 0.
|
97 |
-
"support":
|
98 |
},
|
99 |
"step": 162
|
100 |
}
|
@@ -104,7 +104,7 @@
|
|
104 |
"num_input_tokens_seen": 0,
|
105 |
"num_train_epochs": 50,
|
106 |
"save_steps": 500,
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 4,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.38183790485045715,
|
15 |
+
"precision": 0.6497890295358649,
|
16 |
+
"recall": 0.27035330261136714,
|
17 |
+
"support": 4557.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.6266258607498087,
|
21 |
+
"precision": 0.5535653937140926,
|
22 |
+
"recall": 0.7219039224327898,
|
23 |
+
"support": 2269.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8545803971812939,
|
27 |
+
"precision": 0.8443037974683544,
|
28 |
+
"recall": 0.8651102464332037,
|
29 |
+
"support": 8481.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.878949075575738,
|
33 |
+
"precision": 0.8314310260186549,
|
34 |
+
"recall": 0.9322278794550709,
|
35 |
+
"support": 14534.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.7960859220535504,
|
38 |
+
"eval_loss": 0.5359914898872375,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.6854983095893245,
|
41 |
+
"precision": 0.7197723116842417,
|
42 |
+
"recall": 0.697398837733108,
|
43 |
+
"support": 29841.0
|
44 |
},
|
45 |
+
"eval_runtime": 4.8191,
|
46 |
+
"eval_samples_per_second": 16.601,
|
47 |
+
"eval_steps_per_second": 2.075,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.7769240850962494,
|
50 |
+
"precision": 0.7862232339538372,
|
51 |
+
"recall": 0.7960859220535504,
|
52 |
+
"support": 29841.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.6161300742974051,
|
60 |
+
"precision": 0.6048625792811839,
|
61 |
+
"recall": 0.6278253236778583,
|
62 |
+
"support": 4557.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.7920215150156881,
|
66 |
+
"precision": 0.8057455540355677,
|
67 |
+
"recall": 0.7787571617452622,
|
68 |
+
"support": 2269.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.8922796352583586,
|
72 |
+
"precision": 0.9209436566695947,
|
73 |
+
"recall": 0.865346067680698,
|
74 |
+
"support": 8481.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.8914289590611538,
|
78 |
+
"precision": 0.8790554552143957,
|
79 |
+
"recall": 0.9041557726709784,
|
80 |
+
"support": 14534.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8413927147213566,
|
83 |
+
"eval_loss": 0.443877637386322,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.7979650459081514,
|
86 |
+
"precision": 0.8026518113001855,
|
87 |
+
"recall": 0.7940210814436992,
|
88 |
+
"support": 29841.0
|
89 |
},
|
90 |
+
"eval_runtime": 4.8087,
|
91 |
+
"eval_samples_per_second": 16.637,
|
92 |
+
"eval_steps_per_second": 2.08,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.842071433389123,
|
95 |
+
"precision": 0.8435143116581857,
|
96 |
+
"recall": 0.8413927147213566,
|
97 |
+
"support": 29841.0
|
98 |
},
|
99 |
"step": 162
|
100 |
}
|
|
|
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,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
checkpoint-162/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19f05e33d3889e7c1ce1bf18bf9e16659f52e74109a304d618b5d09955736add
|
3 |
size 4856
|