Theoreticallyhugo
commited on
Commit
•
8903350
1
Parent(s):
1fa4596
Training in progress, epoch 5, checkpoint
Browse files- checkpoint-405/model.safetensors +1 -1
- checkpoint-405/optimizer.pt +1 -1
- checkpoint-405/rng_state.pth +1 -1
- checkpoint-405/trainer_state.json +151 -151
- checkpoint-405/training_args.bin +1 -1
checkpoint-405/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 sha256:2e3751afa732b41a58ebfc330d9bb9ded3aa989b4d32484d6ae7378f19ed7d12
|
3 |
size 592324828
|
checkpoint-405/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 sha256:2f16a1397d48130563108ecbf8917f5a82d12afa6c9cebe5a97408e2358d6f88
|
3 |
size 1014657786
|
checkpoint-405/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:bf337692f531efc3a23b910237391cc3da6dc28e56ab2fbd5db20c81d4fb98bd
|
3 |
size 14244
|
checkpoint-405/trainer_state.json
CHANGED
@@ -11,225 +11,225 @@
|
|
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 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
-
"f1-score": 0.
|
111 |
-
"precision": 0.
|
112 |
-
"recall": 0.
|
113 |
-
"support":
|
114 |
},
|
115 |
"eval_O": {
|
116 |
-
"f1-score": 0.
|
117 |
-
"precision": 0.
|
118 |
-
"recall": 0.
|
119 |
-
"support":
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
-
"f1-score": 0.
|
123 |
-
"precision": 0.
|
124 |
-
"recall": 0.
|
125 |
-
"support":
|
126 |
},
|
127 |
-
"eval_accuracy": 0.
|
128 |
-
"eval_loss": 0.
|
129 |
"eval_macro avg": {
|
130 |
-
"f1-score": 0.
|
131 |
-
"precision": 0.
|
132 |
-
"recall": 0.
|
133 |
-
"support":
|
134 |
-
},
|
135 |
-
"eval_runtime": 4.
|
136 |
-
"eval_samples_per_second": 16.
|
137 |
-
"eval_steps_per_second": 2.
|
138 |
"eval_weighted avg": {
|
139 |
-
"f1-score": 0.
|
140 |
-
"precision": 0.
|
141 |
-
"recall": 0.
|
142 |
-
"support":
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
-
"f1-score": 0.
|
150 |
-
"precision": 0.
|
151 |
-
"recall": 0.
|
152 |
-
"support":
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
-
"f1-score": 0.
|
156 |
-
"precision": 0.
|
157 |
-
"recall": 0.
|
158 |
-
"support":
|
159 |
},
|
160 |
"eval_O": {
|
161 |
-
"f1-score": 0.
|
162 |
-
"precision": 0.
|
163 |
-
"recall": 0.
|
164 |
-
"support":
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
-
"f1-score": 0.
|
168 |
-
"precision": 0.
|
169 |
-
"recall": 0.
|
170 |
-
"support":
|
171 |
},
|
172 |
-
"eval_accuracy": 0.
|
173 |
-
"eval_loss": 0.
|
174 |
"eval_macro avg": {
|
175 |
-
"f1-score": 0.
|
176 |
-
"precision": 0.
|
177 |
-
"recall": 0.
|
178 |
-
"support":
|
179 |
-
},
|
180 |
-
"eval_runtime": 4.
|
181 |
-
"eval_samples_per_second": 16.
|
182 |
-
"eval_steps_per_second": 2.
|
183 |
"eval_weighted avg": {
|
184 |
-
"f1-score": 0.
|
185 |
-
"precision": 0.
|
186 |
-
"recall": 0.
|
187 |
-
"support":
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
-
"f1-score": 0.
|
195 |
-
"precision": 0.
|
196 |
-
"recall": 0.
|
197 |
-
"support":
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
-
"f1-score": 0.
|
201 |
-
"precision": 0.
|
202 |
-
"recall": 0.
|
203 |
-
"support":
|
204 |
},
|
205 |
"eval_O": {
|
206 |
-
"f1-score": 0.
|
207 |
-
"precision": 0.
|
208 |
-
"recall": 0.
|
209 |
-
"support":
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
-
"f1-score": 0.
|
213 |
-
"precision": 0.
|
214 |
-
"recall": 0.
|
215 |
-
"support":
|
216 |
},
|
217 |
-
"eval_accuracy": 0.
|
218 |
-
"eval_loss": 0.
|
219 |
"eval_macro avg": {
|
220 |
-
"f1-score": 0.
|
221 |
-
"precision": 0.
|
222 |
-
"recall": 0.
|
223 |
-
"support":
|
224 |
-
},
|
225 |
-
"eval_runtime": 4.
|
226 |
-
"eval_samples_per_second": 16.
|
227 |
-
"eval_steps_per_second": 2.
|
228 |
"eval_weighted avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
},
|
234 |
"step": 405
|
235 |
}
|
@@ -239,7 +239,7 @@
|
|
239 |
"num_input_tokens_seen": 0,
|
240 |
"num_train_epochs": 50,
|
241 |
"save_steps": 500,
|
242 |
-
"total_flos":
|
243 |
"train_batch_size": 4,
|
244 |
"trial_name": null,
|
245 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_Claim": {
|
14 |
+
"f1-score": 0.4888068880688806,
|
15 |
+
"precision": 0.6228840125391849,
|
16 |
+
"recall": 0.40222672064777326,
|
17 |
+
"support": 4940.0
|
18 |
},
|
19 |
"eval_MajorClaim": {
|
20 |
+
"f1-score": 0.7325278370054489,
|
21 |
+
"precision": 0.7604525332021643,
|
22 |
+
"recall": 0.706581352833638,
|
23 |
+
"support": 2188.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8634848138844484,
|
27 |
+
"precision": 0.827613377692173,
|
28 |
+
"recall": 0.902606702950444,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
"eval_Premise": {
|
32 |
+
"f1-score": 0.8792819197655248,
|
33 |
+
"precision": 0.8543458914268763,
|
34 |
+
"recall": 0.9057173407132524,
|
35 |
+
"support": 15899.0
|
36 |
},
|
37 |
+
"eval_accuracy": 0.8174925373134329,
|
38 |
+
"eval_loss": 0.49806877970695496,
|
39 |
"eval_macro avg": {
|
40 |
+
"f1-score": 0.7410253646810757,
|
41 |
+
"precision": 0.7663239537150996,
|
42 |
+
"recall": 0.7292830292862769,
|
43 |
+
"support": 33500.0
|
44 |
+
},
|
45 |
+
"eval_runtime": 4.9194,
|
46 |
+
"eval_samples_per_second": 16.465,
|
47 |
+
"eval_steps_per_second": 2.236,
|
48 |
"eval_weighted avg": {
|
49 |
+
"f1-score": 0.8071778099281224,
|
50 |
+
"precision": 0.80572410140167,
|
51 |
+
"recall": 0.8174925373134329,
|
52 |
+
"support": 33500.0
|
53 |
},
|
54 |
"step": 81
|
55 |
},
|
56 |
{
|
57 |
"epoch": 2.0,
|
58 |
"eval_Claim": {
|
59 |
+
"f1-score": 0.5993816254416962,
|
60 |
+
"precision": 0.6593780369290574,
|
61 |
+
"recall": 0.5493927125506073,
|
62 |
+
"support": 4940.0
|
63 |
},
|
64 |
"eval_MajorClaim": {
|
65 |
+
"f1-score": 0.8017817371937639,
|
66 |
+
"precision": 0.7197382769901853,
|
67 |
+
"recall": 0.9049360146252285,
|
68 |
+
"support": 2188.0
|
69 |
},
|
70 |
"eval_O": {
|
71 |
+
"f1-score": 0.9058997050147494,
|
72 |
+
"precision": 0.9337184554575859,
|
73 |
+
"recall": 0.8796906330564308,
|
74 |
+
"support": 10473.0
|
75 |
},
|
76 |
"eval_Premise": {
|
77 |
+
"f1-score": 0.8854737486606459,
|
78 |
+
"precision": 0.862579028987236,
|
79 |
+
"recall": 0.9096169570413234,
|
80 |
+
"support": 15899.0
|
81 |
},
|
82 |
+
"eval_accuracy": 0.8468358208955223,
|
83 |
+
"eval_loss": 0.4562840759754181,
|
84 |
"eval_macro avg": {
|
85 |
+
"f1-score": 0.7981342040777137,
|
86 |
+
"precision": 0.7938534495910161,
|
87 |
+
"recall": 0.8109090793183975,
|
88 |
+
"support": 33500.0
|
89 |
+
},
|
90 |
+
"eval_runtime": 4.904,
|
91 |
+
"eval_samples_per_second": 16.517,
|
92 |
+
"eval_steps_per_second": 2.243,
|
93 |
"eval_weighted avg": {
|
94 |
+
"f1-score": 0.8442053257085675,
|
95 |
+
"precision": 0.8455251408465503,
|
96 |
+
"recall": 0.8468358208955223,
|
97 |
+
"support": 33500.0
|
98 |
},
|
99 |
"step": 162
|
100 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.6235462150581514,
|
105 |
+
"precision": 0.6285479226655697,
|
106 |
+
"recall": 0.6186234817813765,
|
107 |
+
"support": 4940.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.8338848444738584,
|
111 |
+
"precision": 0.8059701492537313,
|
112 |
+
"recall": 0.8638025594149908,
|
113 |
+
"support": 2188.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.9066250826953974,
|
117 |
+
"precision": 0.8974646833193002,
|
118 |
+
"recall": 0.9159744103886184,
|
119 |
+
"support": 10473.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.8827730692315017,
|
123 |
+
"precision": 0.8911176621379133,
|
124 |
+
"recall": 0.8745833071262343,
|
125 |
+
"support": 15899.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.8490746268656716,
|
128 |
+
"eval_loss": 0.43820467591285706,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.8117073028647273,
|
131 |
+
"precision": 0.8057751043441286,
|
132 |
+
"recall": 0.818245939677805,
|
133 |
+
"support": 33500.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 4.9179,
|
136 |
+
"eval_samples_per_second": 16.47,
|
137 |
+
"eval_steps_per_second": 2.237,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.8488105033097496,
|
140 |
+
"precision": 0.8488213959184715,
|
141 |
+
"recall": 0.8490746268656716,
|
142 |
+
"support": 33500.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.6415287144900879,
|
150 |
+
"precision": 0.6477507222451506,
|
151 |
+
"recall": 0.6354251012145749,
|
152 |
+
"support": 4940.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.8005126014523707,
|
156 |
+
"precision": 0.7514033680834001,
|
157 |
+
"recall": 0.856489945155393,
|
158 |
+
"support": 2188.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 0.9065169636319258,
|
162 |
+
"precision": 0.9273871354374751,
|
163 |
+
"recall": 0.8865654540246348,
|
164 |
+
"support": 10473.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.8932505382719131,
|
168 |
+
"precision": 0.8863636363636364,
|
169 |
+
"recall": 0.9002452984464432,
|
170 |
+
"support": 15899.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.8540597014925373,
|
173 |
+
"eval_loss": 0.4749625325202942,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.8104522044615743,
|
176 |
+
"precision": 0.8032262155324155,
|
177 |
+
"recall": 0.8196814497102615,
|
178 |
+
"support": 33500.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 4.8972,
|
181 |
+
"eval_samples_per_second": 16.54,
|
182 |
+
"eval_steps_per_second": 2.246,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.8542213698406307,
|
185 |
+
"precision": 0.8551874645146165,
|
186 |
+
"recall": 0.8540597014925373,
|
187 |
+
"support": 33500.0
|
188 |
},
|
189 |
"step": 324
|
190 |
},
|
191 |
{
|
192 |
"epoch": 5.0,
|
193 |
"eval_Claim": {
|
194 |
+
"f1-score": 0.6099687080911935,
|
195 |
+
"precision": 0.6808882235528942,
|
196 |
+
"recall": 0.5524291497975709,
|
197 |
+
"support": 4940.0
|
198 |
},
|
199 |
"eval_MajorClaim": {
|
200 |
+
"f1-score": 0.8315018315018317,
|
201 |
+
"precision": 0.8330275229357799,
|
202 |
+
"recall": 0.829981718464351,
|
203 |
+
"support": 2188.0
|
204 |
},
|
205 |
"eval_O": {
|
206 |
+
"f1-score": 0.9103454839630722,
|
207 |
+
"precision": 0.9074091642159188,
|
208 |
+
"recall": 0.9133008689009835,
|
209 |
+
"support": 10473.0
|
210 |
},
|
211 |
"eval_Premise": {
|
212 |
+
"f1-score": 0.8913988368533824,
|
213 |
+
"precision": 0.8682249120505635,
|
214 |
+
"recall": 0.915843763758727,
|
215 |
+
"support": 15899.0
|
216 |
},
|
217 |
+
"eval_accuracy": 0.8558507462686568,
|
218 |
+
"eval_loss": 0.5162495374679565,
|
219 |
"eval_macro avg": {
|
220 |
+
"f1-score": 0.8108037151023699,
|
221 |
+
"precision": 0.8223874556887891,
|
222 |
+
"recall": 0.8028888752304081,
|
223 |
+
"support": 33500.0
|
224 |
+
},
|
225 |
+
"eval_runtime": 4.9413,
|
226 |
+
"eval_samples_per_second": 16.392,
|
227 |
+
"eval_steps_per_second": 2.226,
|
228 |
"eval_weighted avg": {
|
229 |
+
"f1-score": 0.8519095458499607,
|
230 |
+
"precision": 0.8505509283002989,
|
231 |
+
"recall": 0.8558507462686568,
|
232 |
+
"support": 33500.0
|
233 |
},
|
234 |
"step": 405
|
235 |
}
|
|
|
239 |
"num_input_tokens_seen": 0,
|
240 |
"num_train_epochs": 50,
|
241 |
"save_steps": 500,
|
242 |
+
"total_flos": 716710919337000.0,
|
243 |
"train_batch_size": 4,
|
244 |
"trial_name": null,
|
245 |
"trial_params": null
|
checkpoint-405/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:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
|
3 |
size 4856
|