DeepDream2045
commited on
Commit
•
d1fa04f
1
Parent(s):
abcce1f
Training in progress, step 50, checkpoint
Browse files- last-checkpoint/adapter_config.json +2 -2
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +244 -61
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
@@ -21,10 +21,10 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
-
"
|
25 |
"gate_proj",
|
|
|
26 |
"v_proj",
|
27 |
-
"down_proj",
|
28 |
"up_proj",
|
29 |
"o_proj"
|
30 |
],
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
+
"down_proj",
|
25 |
"gate_proj",
|
26 |
+
"q_proj",
|
27 |
"v_proj",
|
|
|
28 |
"up_proj",
|
29 |
"o_proj"
|
30 |
],
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:020b5754070bfaf7eaf5513f8adb989bb64a52299a64a292eef6230e71963075
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671466706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fa92f2210e69aa0a9c191f16d0e25a72774bf4e987c7510780097c2f3415770
|
3 |
size 671466706
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b60806d9eb74645038e95d587478bbb819f8874e5bfc07240dac2b31b5be74ab
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c3b503957ab4202d6b69d3be7c840126f1715d893c04b2a9db32e2f934c88d9
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73063f6a316d680eb29d574e26024c11cd3de61aaeb6e78155209ebcfe81c8d9
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8466bb20895b5e3f9921f222956751b32211f06e127da813c3b9a266991ca0f
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.052805280528052806,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 5e-05,
|
15 |
"loss": 61.3338,
|
16 |
"step": 1
|
@@ -18,186 +18,369 @@
|
|
18 |
{
|
19 |
"epoch": 0.052805280528052806,
|
20 |
"eval_loss": 3.5627546310424805,
|
21 |
-
"eval_runtime": 4.
|
22 |
-
"eval_samples_per_second": 29.
|
23 |
-
"eval_steps_per_second": 3.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.10561056105610561,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 0.0001,
|
30 |
"loss": 55.4131,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.15841584158415842,
|
35 |
-
"grad_norm":
|
36 |
"learning_rate": 9.989294616193017e-05,
|
37 |
-
"loss": 35.
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.21122112211221122,
|
42 |
-
"grad_norm":
|
43 |
"learning_rate": 9.957224306869053e-05,
|
44 |
-
"loss": 20.
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.264026402640264,
|
49 |
-
"grad_norm":
|
50 |
"learning_rate": 9.903926402016153e-05,
|
51 |
-
"loss": 24.
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
"epoch": 0.31683168316831684,
|
56 |
-
"grad_norm":
|
57 |
"learning_rate": 9.829629131445342e-05,
|
58 |
-
"loss": 18.
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.3696369636963696,
|
63 |
-
"grad_norm":
|
64 |
"learning_rate": 9.73465064747553e-05,
|
65 |
-
"loss": 14.
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.42244224422442245,
|
70 |
-
"grad_norm": 63.
|
71 |
"learning_rate": 9.619397662556435e-05,
|
72 |
-
"loss": 10.
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
"epoch": 0.4752475247524752,
|
77 |
-
"grad_norm":
|
78 |
"learning_rate": 9.484363707663442e-05,
|
79 |
-
"loss": 9.
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.528052805280528,
|
84 |
-
"grad_norm": 97.
|
85 |
"learning_rate": 9.330127018922194e-05,
|
86 |
-
"loss": 19.
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.5808580858085809,
|
91 |
-
"grad_norm": 69.
|
92 |
"learning_rate": 9.157348061512727e-05,
|
93 |
-
"loss":
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.6336633663366337,
|
98 |
-
"grad_norm":
|
99 |
"learning_rate": 8.966766701456177e-05,
|
100 |
-
"loss": 10.
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
"epoch": 0.6864686468646864,
|
105 |
-
"grad_norm":
|
106 |
"learning_rate": 8.759199037394887e-05,
|
107 |
-
"loss": 7.
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
"epoch": 0.7392739273927392,
|
112 |
-
"grad_norm":
|
113 |
"learning_rate": 8.535533905932738e-05,
|
114 |
-
"loss": 9.
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
"epoch": 0.7920792079207921,
|
119 |
-
"grad_norm":
|
120 |
"learning_rate": 8.296729075500344e-05,
|
121 |
-
"loss": 8.
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.8448844884488449,
|
126 |
-
"grad_norm":
|
127 |
"learning_rate": 8.043807145043604e-05,
|
128 |
-
"loss": 5.
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.8976897689768977,
|
133 |
-
"grad_norm":
|
134 |
"learning_rate": 7.777851165098012e-05,
|
135 |
-
"loss": 3.
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
"epoch": 0.9504950495049505,
|
140 |
-
"grad_norm":
|
141 |
"learning_rate": 7.500000000000001e-05,
|
142 |
-
"loss":
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
"epoch": 1.033003300330033,
|
147 |
-
"grad_norm":
|
148 |
"learning_rate": 7.211443451095007e-05,
|
149 |
-
"loss": 5.
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
"epoch": 1.0858085808580857,
|
154 |
-
"grad_norm":
|
155 |
"learning_rate": 6.91341716182545e-05,
|
156 |
-
"loss": 2.
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
"epoch": 1.1386138613861387,
|
161 |
-
"grad_norm":
|
162 |
"learning_rate": 6.607197326515808e-05,
|
163 |
-
"loss": 2.
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
"epoch": 1.1914191419141915,
|
168 |
-
"grad_norm":
|
169 |
"learning_rate": 6.294095225512603e-05,
|
170 |
-
"loss": 1.
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
"epoch": 1.2442244224422443,
|
175 |
-
"grad_norm":
|
176 |
"learning_rate": 5.9754516100806423e-05,
|
177 |
-
"loss": 1.
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
"epoch": 1.297029702970297,
|
182 |
-
"grad_norm":
|
183 |
"learning_rate": 5.6526309611002594e-05,
|
184 |
-
"loss": 2.
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.3498349834983498,
|
189 |
-
"grad_norm":
|
190 |
"learning_rate": 5.327015646150716e-05,
|
191 |
-
"loss": 0.
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
"epoch": 1.3498349834983498,
|
196 |
-
"eval_loss": 0.
|
197 |
-
"eval_runtime": 4.
|
198 |
-
"eval_samples_per_second":
|
199 |
-
"eval_steps_per_second": 3.
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +404,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos":
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.039766620844602585,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 2.6996699669966997,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.052805280528052806,
|
13 |
+
"grad_norm": 240.08116149902344,
|
14 |
"learning_rate": 5e-05,
|
15 |
"loss": 61.3338,
|
16 |
"step": 1
|
|
|
18 |
{
|
19 |
"epoch": 0.052805280528052806,
|
20 |
"eval_loss": 3.5627546310424805,
|
21 |
+
"eval_runtime": 4.3057,
|
22 |
+
"eval_samples_per_second": 29.728,
|
23 |
+
"eval_steps_per_second": 3.716,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.10561056105610561,
|
28 |
+
"grad_norm": 311.3833923339844,
|
29 |
"learning_rate": 0.0001,
|
30 |
"loss": 55.4131,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.15841584158415842,
|
35 |
+
"grad_norm": 186.2847137451172,
|
36 |
"learning_rate": 9.989294616193017e-05,
|
37 |
+
"loss": 35.886,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.21122112211221122,
|
42 |
+
"grad_norm": 109.15618896484375,
|
43 |
"learning_rate": 9.957224306869053e-05,
|
44 |
+
"loss": 20.0972,
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.264026402640264,
|
49 |
+
"grad_norm": 88.25745391845703,
|
50 |
"learning_rate": 9.903926402016153e-05,
|
51 |
+
"loss": 24.9318,
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
"epoch": 0.31683168316831684,
|
56 |
+
"grad_norm": 140.07655334472656,
|
57 |
"learning_rate": 9.829629131445342e-05,
|
58 |
+
"loss": 18.6597,
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.3696369636963696,
|
63 |
+
"grad_norm": 134.88388061523438,
|
64 |
"learning_rate": 9.73465064747553e-05,
|
65 |
+
"loss": 14.9552,
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.42244224422442245,
|
70 |
+
"grad_norm": 63.23054122924805,
|
71 |
"learning_rate": 9.619397662556435e-05,
|
72 |
+
"loss": 10.7139,
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
"epoch": 0.4752475247524752,
|
77 |
+
"grad_norm": 71.05472564697266,
|
78 |
"learning_rate": 9.484363707663442e-05,
|
79 |
+
"loss": 9.8416,
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.528052805280528,
|
84 |
+
"grad_norm": 97.5541763305664,
|
85 |
"learning_rate": 9.330127018922194e-05,
|
86 |
+
"loss": 19.9574,
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.5808580858085809,
|
91 |
+
"grad_norm": 69.11842346191406,
|
92 |
"learning_rate": 9.157348061512727e-05,
|
93 |
+
"loss": 11.0275,
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.6336633663366337,
|
98 |
+
"grad_norm": 56.24506759643555,
|
99 |
"learning_rate": 8.966766701456177e-05,
|
100 |
+
"loss": 10.1437,
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
"epoch": 0.6864686468646864,
|
105 |
+
"grad_norm": 54.2360954284668,
|
106 |
"learning_rate": 8.759199037394887e-05,
|
107 |
+
"loss": 7.8817,
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
"epoch": 0.7392739273927392,
|
112 |
+
"grad_norm": 65.11487579345703,
|
113 |
"learning_rate": 8.535533905932738e-05,
|
114 |
+
"loss": 9.9734,
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
"epoch": 0.7920792079207921,
|
119 |
+
"grad_norm": 63.567726135253906,
|
120 |
"learning_rate": 8.296729075500344e-05,
|
121 |
+
"loss": 8.4856,
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.8448844884488449,
|
126 |
+
"grad_norm": 54.104248046875,
|
127 |
"learning_rate": 8.043807145043604e-05,
|
128 |
+
"loss": 5.8322,
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.8976897689768977,
|
133 |
+
"grad_norm": 41.041969299316406,
|
134 |
"learning_rate": 7.777851165098012e-05,
|
135 |
+
"loss": 3.4734,
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
"epoch": 0.9504950495049505,
|
140 |
+
"grad_norm": 51.88878631591797,
|
141 |
"learning_rate": 7.500000000000001e-05,
|
142 |
+
"loss": 3.058,
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
"epoch": 1.033003300330033,
|
147 |
+
"grad_norm": 63.439964294433594,
|
148 |
"learning_rate": 7.211443451095007e-05,
|
149 |
+
"loss": 5.4253,
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
"epoch": 1.0858085808580857,
|
154 |
+
"grad_norm": 48.61954116821289,
|
155 |
"learning_rate": 6.91341716182545e-05,
|
156 |
+
"loss": 2.854,
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
"epoch": 1.1386138613861387,
|
161 |
+
"grad_norm": 55.616329193115234,
|
162 |
"learning_rate": 6.607197326515808e-05,
|
163 |
+
"loss": 2.0837,
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
"epoch": 1.1914191419141915,
|
168 |
+
"grad_norm": 50.29981231689453,
|
169 |
"learning_rate": 6.294095225512603e-05,
|
170 |
+
"loss": 1.5129,
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
"epoch": 1.2442244224422443,
|
175 |
+
"grad_norm": 48.272666931152344,
|
176 |
"learning_rate": 5.9754516100806423e-05,
|
177 |
+
"loss": 1.6346,
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
"epoch": 1.297029702970297,
|
182 |
+
"grad_norm": 82.75598907470703,
|
183 |
"learning_rate": 5.6526309611002594e-05,
|
184 |
+
"loss": 2.8828,
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.3498349834983498,
|
189 |
+
"grad_norm": 55.31129837036133,
|
190 |
"learning_rate": 5.327015646150716e-05,
|
191 |
+
"loss": 0.9758,
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
"epoch": 1.3498349834983498,
|
196 |
+
"eval_loss": 0.11382482945919037,
|
197 |
+
"eval_runtime": 4.569,
|
198 |
+
"eval_samples_per_second": 28.015,
|
199 |
+
"eval_steps_per_second": 3.502,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.4026402640264026,
|
204 |
+
"grad_norm": 80.16549682617188,
|
205 |
+
"learning_rate": 5e-05,
|
206 |
+
"loss": 0.9275,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.4554455445544554,
|
211 |
+
"grad_norm": 44.94060516357422,
|
212 |
+
"learning_rate": 4.6729843538492847e-05,
|
213 |
+
"loss": 0.6253,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.5082508250825084,
|
218 |
+
"grad_norm": 53.476905822753906,
|
219 |
+
"learning_rate": 4.347369038899744e-05,
|
220 |
+
"loss": 2.6445,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.561056105610561,
|
225 |
+
"grad_norm": 72.94212341308594,
|
226 |
+
"learning_rate": 4.0245483899193595e-05,
|
227 |
+
"loss": 0.9836,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.613861386138614,
|
232 |
+
"grad_norm": 51.1599235534668,
|
233 |
+
"learning_rate": 3.705904774487396e-05,
|
234 |
+
"loss": 0.539,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 1.6666666666666665,
|
239 |
+
"grad_norm": 18.60490608215332,
|
240 |
+
"learning_rate": 3.392802673484193e-05,
|
241 |
+
"loss": 0.2169,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.7194719471947195,
|
246 |
+
"grad_norm": 47.54155349731445,
|
247 |
+
"learning_rate": 3.086582838174551e-05,
|
248 |
+
"loss": 0.7477,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.7722772277227723,
|
253 |
+
"grad_norm": 68.19134521484375,
|
254 |
+
"learning_rate": 2.7885565489049946e-05,
|
255 |
+
"loss": 0.846,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.825082508250825,
|
260 |
+
"grad_norm": 39.737762451171875,
|
261 |
+
"learning_rate": 2.500000000000001e-05,
|
262 |
+
"loss": 0.4499,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.8778877887788779,
|
267 |
+
"grad_norm": 22.386844635009766,
|
268 |
+
"learning_rate": 2.2221488349019903e-05,
|
269 |
+
"loss": 0.1428,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 1.9306930693069306,
|
274 |
+
"grad_norm": 8.85619068145752,
|
275 |
+
"learning_rate": 1.9561928549563968e-05,
|
276 |
+
"loss": 0.0899,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 2.0132013201320134,
|
281 |
+
"grad_norm": 13.05267333984375,
|
282 |
+
"learning_rate": 1.703270924499656e-05,
|
283 |
+
"loss": 0.4039,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.066006600660066,
|
288 |
+
"grad_norm": 10.15993881225586,
|
289 |
+
"learning_rate": 1.4644660940672627e-05,
|
290 |
+
"loss": 0.2195,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 2.118811881188119,
|
295 |
+
"grad_norm": 4.588918685913086,
|
296 |
+
"learning_rate": 1.2408009626051137e-05,
|
297 |
+
"loss": 0.0582,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 2.1716171617161715,
|
302 |
+
"grad_norm": 17.074146270751953,
|
303 |
+
"learning_rate": 1.0332332985438248e-05,
|
304 |
+
"loss": 0.0406,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 2.2244224422442245,
|
309 |
+
"grad_norm": 1.4361339807510376,
|
310 |
+
"learning_rate": 8.426519384872733e-06,
|
311 |
+
"loss": 0.0148,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 2.2772277227722775,
|
316 |
+
"grad_norm": 19.55823516845703,
|
317 |
+
"learning_rate": 6.698729810778065e-06,
|
318 |
+
"loss": 0.3258,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 2.33003300330033,
|
323 |
+
"grad_norm": 23.317541122436523,
|
324 |
+
"learning_rate": 5.156362923365588e-06,
|
325 |
+
"loss": 0.1395,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.382838283828383,
|
330 |
+
"grad_norm": 3.5347235202789307,
|
331 |
+
"learning_rate": 3.8060233744356633e-06,
|
332 |
+
"loss": 0.0133,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 2.4356435643564356,
|
337 |
+
"grad_norm": 48.761112213134766,
|
338 |
+
"learning_rate": 2.653493525244721e-06,
|
339 |
+
"loss": 0.1465,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 2.4884488448844886,
|
344 |
+
"grad_norm": 64.77693176269531,
|
345 |
+
"learning_rate": 1.70370868554659e-06,
|
346 |
+
"loss": 0.5884,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 2.541254125412541,
|
351 |
+
"grad_norm": 21.97736167907715,
|
352 |
+
"learning_rate": 9.607359798384785e-07,
|
353 |
+
"loss": 0.0732,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 2.594059405940594,
|
358 |
+
"grad_norm": 19.152101516723633,
|
359 |
+
"learning_rate": 4.277569313094809e-07,
|
360 |
+
"loss": 0.162,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 2.6468646864686467,
|
365 |
+
"grad_norm": 14.94710636138916,
|
366 |
+
"learning_rate": 1.0705383806982606e-07,
|
367 |
+
"loss": 0.1771,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.6996699669966997,
|
372 |
+
"grad_norm": 8.99813461303711,
|
373 |
+
"learning_rate": 0.0,
|
374 |
+
"loss": 0.2619,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 2.6996699669966997,
|
379 |
+
"eval_loss": 0.039766620844602585,
|
380 |
+
"eval_runtime": 4.8436,
|
381 |
+
"eval_samples_per_second": 26.427,
|
382 |
+
"eval_steps_per_second": 3.303,
|
383 |
+
"step": 50
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
|
|
404 |
"should_evaluate": false,
|
405 |
"should_log": false,
|
406 |
"should_save": true,
|
407 |
+
"should_training_stop": true
|
408 |
},
|
409 |
"attributes": {}
|
410 |
}
|
411 |
},
|
412 |
+
"total_flos": 5.932088473514148e+17,
|
413 |
"train_batch_size": 2,
|
414 |
"trial_name": null,
|
415 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce2681dc79991c6f33e2d27573b5f6d6f5cf0f1fcde8d296e5d63aeff6c313b
|
3 |
size 6776
|