Theoreticallyhugo
commited on
Commit
•
a81b0ae
1
Parent(s):
5ffc11d
Training in progress, epoch 4, checkpoint
Browse files- checkpoint-324/model.safetensors +1 -1
- checkpoint-324/optimizer.pt +1 -1
- checkpoint-324/rng_state.pth +1 -1
- checkpoint-324/trainer_state.json +121 -121
- checkpoint-324/training_args.bin +1 -1
checkpoint-324/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:c46f8f2a93cc4a0bad899019b4f49b165f6913e23fc2087bfa1b980d07e23825
|
3 |
size 592324828
|
checkpoint-324/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 sha256:1203a40330643a8f3abc01aecded1f69fb1d1343c4cf5caceb5bbb4e7dcabf8e
|
3 |
size 1014657786
|
checkpoint-324/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 sha256:5474bfb178f1f5ac14d6be6fd7772f757be3e1728e1b25f0f54ac7eff70dac62
|
3 |
size 14244
|
checkpoint-324/trainer_state.json
CHANGED
@@ -11,180 +11,180 @@
|
|
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 |
}
|
@@ -194,7 +194,7 @@
|
|
194 |
"num_input_tokens_seen": 0,
|
195 |
"num_train_epochs": 50,
|
196 |
"save_steps": 500,
|
197 |
-
"total_flos":
|
198 |
"train_batch_size": 4,
|
199 |
"trial_name": null,
|
200 |
"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 |
},
|
101 |
{
|
102 |
"epoch": 3.0,
|
103 |
"eval_Claim": {
|
104 |
+
"f1-score": 0.6042799305957202,
|
105 |
+
"precision": 0.6389432485322897,
|
106 |
+
"recall": 0.5731841123546193,
|
107 |
+
"support": 4557.0
|
108 |
},
|
109 |
"eval_MajorClaim": {
|
110 |
+
"f1-score": 0.8349557522123894,
|
111 |
+
"precision": 0.8382940915148823,
|
112 |
+
"recall": 0.8316438959894227,
|
113 |
+
"support": 2269.0
|
114 |
},
|
115 |
"eval_O": {
|
116 |
+
"f1-score": 0.8941106484235574,
|
117 |
+
"precision": 0.9022691799735862,
|
118 |
+
"recall": 0.8860983374602052,
|
119 |
+
"support": 8481.0
|
120 |
},
|
121 |
"eval_Premise": {
|
122 |
+
"f1-score": 0.8917763490086511,
|
123 |
+
"precision": 0.8729980887102089,
|
124 |
+
"recall": 0.9113802119168846,
|
125 |
+
"support": 14534.0
|
126 |
},
|
127 |
+
"eval_accuracy": 0.8464863778023525,
|
128 |
+
"eval_loss": 0.4555923044681549,
|
129 |
"eval_macro avg": {
|
130 |
+
"f1-score": 0.8062806700600795,
|
131 |
+
"precision": 0.8131261521827418,
|
132 |
+
"recall": 0.8005766394302829,
|
133 |
+
"support": 29841.0
|
134 |
+
},
|
135 |
+
"eval_runtime": 4.7811,
|
136 |
+
"eval_samples_per_second": 16.733,
|
137 |
+
"eval_steps_per_second": 2.092,
|
138 |
"eval_weighted avg": {
|
139 |
+
"f1-score": 0.8442159482345275,
|
140 |
+
"precision": 0.8429359878649869,
|
141 |
+
"recall": 0.8464863778023525,
|
142 |
+
"support": 29841.0
|
143 |
},
|
144 |
"step": 243
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
"eval_Claim": {
|
149 |
+
"f1-score": 0.6278026905829596,
|
150 |
+
"precision": 0.5981717011128775,
|
151 |
+
"recall": 0.6605222734254992,
|
152 |
+
"support": 4557.0
|
153 |
},
|
154 |
"eval_MajorClaim": {
|
155 |
+
"f1-score": 0.8182207014542344,
|
156 |
+
"precision": 0.7947652679684254,
|
157 |
+
"recall": 0.8431026884089907,
|
158 |
+
"support": 2269.0
|
159 |
},
|
160 |
"eval_O": {
|
161 |
+
"f1-score": 0.9069328626209752,
|
162 |
+
"precision": 0.9373427277302466,
|
163 |
+
"recall": 0.8784341469166372,
|
164 |
+
"support": 8481.0
|
165 |
},
|
166 |
"eval_Premise": {
|
167 |
+
"f1-score": 0.888919552918449,
|
168 |
+
"precision": 0.8913795489137954,
|
169 |
+
"recall": 0.8864730975643319,
|
170 |
+
"support": 14534.0
|
171 |
},
|
172 |
+
"eval_accuracy": 0.8463858449783854,
|
173 |
+
"eval_loss": 0.4377317428588867,
|
174 |
"eval_macro avg": {
|
175 |
+
"f1-score": 0.8104689518941546,
|
176 |
+
"precision": 0.8054148114313363,
|
177 |
+
"recall": 0.8171330515788647,
|
178 |
+
"support": 29841.0
|
179 |
+
},
|
180 |
+
"eval_runtime": 4.8109,
|
181 |
+
"eval_samples_per_second": 16.629,
|
182 |
+
"eval_steps_per_second": 2.079,
|
183 |
"eval_weighted avg": {
|
184 |
+
"f1-score": 0.8487883791626096,
|
185 |
+
"precision": 0.8523207959781866,
|
186 |
+
"recall": 0.8463858449783854,
|
187 |
+
"support": 29841.0
|
188 |
},
|
189 |
"step": 324
|
190 |
}
|
|
|
194 |
"num_input_tokens_seen": 0,
|
195 |
"num_train_epochs": 50,
|
196 |
"save_steps": 500,
|
197 |
+
"total_flos": 575154930907200.0,
|
198 |
"train_batch_size": 4,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
checkpoint-324/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
|