Commit
•
851dcb6
1
Parent(s):
71c35f5
End of training
Browse files- README.md +3 -1
- trainer_state.json +282 -72
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: cc-by-nc-4.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
base_model: facebook/musicgen-melody
|
7 |
model-index:
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-melody-lora-kk-colab
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- text-to-audio
|
6 |
+
- tiny-kk
|
7 |
- generated_from_trainer
|
8 |
base_model: facebook/musicgen-melody
|
9 |
model-index:
|
|
|
16 |
|
17 |
# musicgen-melody-lora-kk-colab
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the kk/tiny-kk dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,167 +1,377 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
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": 0.19047619047619047,
|
13 |
-
"grad_norm": 1.
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 9.
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.38095238095238093,
|
20 |
-
"grad_norm": 1.
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss": 9.
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5714285714285714,
|
27 |
-
"grad_norm": 1.
|
28 |
-
"learning_rate": 0.
|
29 |
-
"loss": 8.
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7619047619047619,
|
34 |
-
"grad_norm": 2.
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss": 8.
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9523809523809523,
|
41 |
-
"grad_norm": 1.
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 7.
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.1428571428571428,
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss": 7.
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.3333333333333333,
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate": 0.
|
57 |
-
"loss": 7.
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.5238095238095237,
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate": 0.
|
64 |
-
"loss": 7.
|
65 |
"step": 16
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.7142857142857144,
|
69 |
-
"grad_norm":
|
70 |
-
"learning_rate": 0.
|
71 |
-
"loss": 7.
|
72 |
"step": 18
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.9047619047619047,
|
76 |
-
"grad_norm": 0.
|
77 |
-
"learning_rate": 0.
|
78 |
-
"loss": 7.
|
79 |
"step": 20
|
80 |
},
|
81 |
{
|
82 |
"epoch": 2.0952380952380953,
|
83 |
-
"grad_norm": 0.
|
84 |
-
"learning_rate":
|
85 |
-
"loss": 7.
|
86 |
"step": 22
|
87 |
},
|
88 |
{
|
89 |
"epoch": 2.2857142857142856,
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate":
|
92 |
-
"loss": 7.
|
93 |
"step": 24
|
94 |
},
|
95 |
{
|
96 |
"epoch": 2.4761904761904763,
|
97 |
-
"grad_norm": 1.
|
98 |
-
"learning_rate":
|
99 |
-
"loss": 7.
|
100 |
"step": 26
|
101 |
},
|
102 |
{
|
103 |
"epoch": 2.6666666666666665,
|
104 |
-
"grad_norm": 0.
|
105 |
-
"learning_rate":
|
106 |
-
"loss": 7.
|
107 |
"step": 28
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.857142857142857,
|
111 |
-
"grad_norm":
|
112 |
-
"learning_rate":
|
113 |
-
"loss": 7.
|
114 |
"step": 30
|
115 |
},
|
116 |
{
|
117 |
"epoch": 3.0476190476190474,
|
118 |
-
"grad_norm": 0.
|
119 |
-
"learning_rate":
|
120 |
-
"loss": 7.
|
121 |
"step": 32
|
122 |
},
|
123 |
{
|
124 |
"epoch": 3.238095238095238,
|
125 |
-
"grad_norm": 0.
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 7.
|
128 |
"step": 34
|
129 |
},
|
130 |
{
|
131 |
"epoch": 3.4285714285714284,
|
132 |
-
"grad_norm": 0.
|
133 |
-
"learning_rate":
|
134 |
-
"loss": 7.
|
135 |
"step": 36
|
136 |
},
|
137 |
{
|
138 |
"epoch": 3.619047619047619,
|
139 |
-
"grad_norm":
|
140 |
-
"learning_rate":
|
141 |
-
"loss": 7.
|
142 |
"step": 38
|
143 |
},
|
144 |
{
|
145 |
"epoch": 3.8095238095238093,
|
146 |
-
"grad_norm": 0.
|
147 |
-
"learning_rate": 0.
|
148 |
-
"loss": 7.
|
149 |
"step": 40
|
150 |
},
|
151 |
{
|
152 |
-
"epoch":
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
156 |
-
"
|
157 |
-
|
158 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
159 |
}
|
160 |
],
|
161 |
"logging_steps": 2,
|
162 |
-
"max_steps":
|
163 |
"num_input_tokens_seen": 0,
|
164 |
-
"num_train_epochs":
|
165 |
"save_steps": 500,
|
166 |
"stateful_callbacks": {
|
167 |
"TrainerControl": {
|
@@ -175,7 +385,7 @@
|
|
175 |
"attributes": {}
|
176 |
}
|
177 |
},
|
178 |
-
"total_flos":
|
179 |
"train_batch_size": 2,
|
180 |
"trial_name": null,
|
181 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.523809523809524,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.19047619047619047,
|
13 |
+
"grad_norm": 1.0693126916885376,
|
14 |
+
"learning_rate": 0.000196,
|
15 |
+
"loss": 9.5582,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.38095238095238093,
|
20 |
+
"grad_norm": 1.2914847135543823,
|
21 |
+
"learning_rate": 0.000192,
|
22 |
+
"loss": 9.2227,
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5714285714285714,
|
27 |
+
"grad_norm": 1.9945707321166992,
|
28 |
+
"learning_rate": 0.000188,
|
29 |
+
"loss": 8.7759,
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7619047619047619,
|
34 |
+
"grad_norm": 2.011664628982544,
|
35 |
+
"learning_rate": 0.00018400000000000003,
|
36 |
+
"loss": 8.2142,
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9523809523809523,
|
41 |
+
"grad_norm": 1.3491569757461548,
|
42 |
+
"learning_rate": 0.00018,
|
43 |
+
"loss": 7.9009,
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.1428571428571428,
|
48 |
+
"grad_norm": 0.9671052098274231,
|
49 |
+
"learning_rate": 0.00017600000000000002,
|
50 |
+
"loss": 7.6909,
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.3333333333333333,
|
55 |
+
"grad_norm": 1.116225004196167,
|
56 |
+
"learning_rate": 0.000172,
|
57 |
+
"loss": 7.5216,
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.5238095238095237,
|
62 |
+
"grad_norm": 1.0181453227996826,
|
63 |
+
"learning_rate": 0.000168,
|
64 |
+
"loss": 7.4308,
|
65 |
"step": 16
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.7142857142857144,
|
69 |
+
"grad_norm": 0.9790288209915161,
|
70 |
+
"learning_rate": 0.000164,
|
71 |
+
"loss": 7.4444,
|
72 |
"step": 18
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.9047619047619047,
|
76 |
+
"grad_norm": 0.9529135823249817,
|
77 |
+
"learning_rate": 0.00016,
|
78 |
+
"loss": 7.3866,
|
79 |
"step": 20
|
80 |
},
|
81 |
{
|
82 |
"epoch": 2.0952380952380953,
|
83 |
+
"grad_norm": 0.7934174537658691,
|
84 |
+
"learning_rate": 0.00015600000000000002,
|
85 |
+
"loss": 7.3822,
|
86 |
"step": 22
|
87 |
},
|
88 |
{
|
89 |
"epoch": 2.2857142857142856,
|
90 |
+
"grad_norm": 0.7163369059562683,
|
91 |
+
"learning_rate": 0.000152,
|
92 |
+
"loss": 7.3191,
|
93 |
"step": 24
|
94 |
},
|
95 |
{
|
96 |
"epoch": 2.4761904761904763,
|
97 |
+
"grad_norm": 1.347898244857788,
|
98 |
+
"learning_rate": 0.000148,
|
99 |
+
"loss": 7.2142,
|
100 |
"step": 26
|
101 |
},
|
102 |
{
|
103 |
"epoch": 2.6666666666666665,
|
104 |
+
"grad_norm": 0.7439594864845276,
|
105 |
+
"learning_rate": 0.000144,
|
106 |
+
"loss": 7.2718,
|
107 |
"step": 28
|
108 |
},
|
109 |
{
|
110 |
"epoch": 2.857142857142857,
|
111 |
+
"grad_norm": 1.4523087739944458,
|
112 |
+
"learning_rate": 0.00014,
|
113 |
+
"loss": 7.2901,
|
114 |
"step": 30
|
115 |
},
|
116 |
{
|
117 |
"epoch": 3.0476190476190474,
|
118 |
+
"grad_norm": 0.7053799033164978,
|
119 |
+
"learning_rate": 0.00013600000000000003,
|
120 |
+
"loss": 7.2125,
|
121 |
"step": 32
|
122 |
},
|
123 |
{
|
124 |
"epoch": 3.238095238095238,
|
125 |
+
"grad_norm": 0.6156577467918396,
|
126 |
+
"learning_rate": 0.000132,
|
127 |
+
"loss": 7.229,
|
128 |
"step": 34
|
129 |
},
|
130 |
{
|
131 |
"epoch": 3.4285714285714284,
|
132 |
+
"grad_norm": 0.40743571519851685,
|
133 |
+
"learning_rate": 0.00012800000000000002,
|
134 |
+
"loss": 7.2999,
|
135 |
"step": 36
|
136 |
},
|
137 |
{
|
138 |
"epoch": 3.619047619047619,
|
139 |
+
"grad_norm": 1.0756566524505615,
|
140 |
+
"learning_rate": 0.000124,
|
141 |
+
"loss": 7.212,
|
142 |
"step": 38
|
143 |
},
|
144 |
{
|
145 |
"epoch": 3.8095238095238093,
|
146 |
+
"grad_norm": 0.7201813459396362,
|
147 |
+
"learning_rate": 0.00012,
|
148 |
+
"loss": 7.1826,
|
149 |
"step": 40
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 4.0,
|
153 |
+
"grad_norm": 0.5773327946662903,
|
154 |
+
"learning_rate": 0.000116,
|
155 |
+
"loss": 7.1456,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.190476190476191,
|
160 |
+
"grad_norm": 0.6004664301872253,
|
161 |
+
"learning_rate": 0.00011200000000000001,
|
162 |
+
"loss": 7.0349,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.380952380952381,
|
167 |
+
"grad_norm": 1.4157112836837769,
|
168 |
+
"learning_rate": 0.00010800000000000001,
|
169 |
+
"loss": 7.2767,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.571428571428571,
|
174 |
+
"grad_norm": 0.852541446685791,
|
175 |
+
"learning_rate": 0.00010400000000000001,
|
176 |
+
"loss": 7.1745,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.761904761904762,
|
181 |
+
"grad_norm": 0.7835370898246765,
|
182 |
+
"learning_rate": 0.0001,
|
183 |
+
"loss": 7.2477,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.9523809523809526,
|
188 |
+
"grad_norm": 0.414756178855896,
|
189 |
+
"learning_rate": 9.6e-05,
|
190 |
+
"loss": 7.1781,
|
191 |
+
"step": 52
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.142857142857143,
|
195 |
+
"grad_norm": 0.7038145661354065,
|
196 |
+
"learning_rate": 9.200000000000001e-05,
|
197 |
+
"loss": 7.1103,
|
198 |
+
"step": 54
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.333333333333333,
|
202 |
+
"grad_norm": 0.8368222713470459,
|
203 |
+
"learning_rate": 8.800000000000001e-05,
|
204 |
+
"loss": 7.1595,
|
205 |
+
"step": 56
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.523809523809524,
|
209 |
+
"grad_norm": 0.6943209171295166,
|
210 |
+
"learning_rate": 8.4e-05,
|
211 |
+
"loss": 7.1062,
|
212 |
+
"step": 58
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 5.714285714285714,
|
216 |
+
"grad_norm": 0.4186341464519501,
|
217 |
+
"learning_rate": 8e-05,
|
218 |
+
"loss": 7.2348,
|
219 |
+
"step": 60
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 5.904761904761905,
|
223 |
+
"grad_norm": 1.0224595069885254,
|
224 |
+
"learning_rate": 7.6e-05,
|
225 |
+
"loss": 7.1154,
|
226 |
+
"step": 62
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.095238095238095,
|
230 |
+
"grad_norm": 0.428688645362854,
|
231 |
+
"learning_rate": 7.2e-05,
|
232 |
+
"loss": 7.1194,
|
233 |
+
"step": 64
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.285714285714286,
|
237 |
+
"grad_norm": 0.913233757019043,
|
238 |
+
"learning_rate": 6.800000000000001e-05,
|
239 |
+
"loss": 7.1919,
|
240 |
+
"step": 66
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 6.476190476190476,
|
244 |
+
"grad_norm": 0.5481642484664917,
|
245 |
+
"learning_rate": 6.400000000000001e-05,
|
246 |
+
"loss": 7.126,
|
247 |
+
"step": 68
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 6.666666666666667,
|
251 |
+
"grad_norm": 0.49522772431373596,
|
252 |
+
"learning_rate": 6e-05,
|
253 |
+
"loss": 7.1564,
|
254 |
+
"step": 70
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 6.857142857142857,
|
258 |
+
"grad_norm": 0.40602990984916687,
|
259 |
+
"learning_rate": 5.6000000000000006e-05,
|
260 |
+
"loss": 7.081,
|
261 |
+
"step": 72
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.0476190476190474,
|
265 |
+
"grad_norm": 0.4593268036842346,
|
266 |
+
"learning_rate": 5.2000000000000004e-05,
|
267 |
+
"loss": 7.0596,
|
268 |
+
"step": 74
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.238095238095238,
|
272 |
+
"grad_norm": 0.44626158475875854,
|
273 |
+
"learning_rate": 4.8e-05,
|
274 |
+
"loss": 7.0674,
|
275 |
+
"step": 76
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 7.428571428571429,
|
279 |
+
"grad_norm": 0.6573432087898254,
|
280 |
+
"learning_rate": 4.4000000000000006e-05,
|
281 |
+
"loss": 7.0745,
|
282 |
+
"step": 78
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 7.619047619047619,
|
286 |
+
"grad_norm": 0.3820817172527313,
|
287 |
+
"learning_rate": 4e-05,
|
288 |
+
"loss": 7.0785,
|
289 |
+
"step": 80
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 7.809523809523809,
|
293 |
+
"grad_norm": 0.8610634803771973,
|
294 |
+
"learning_rate": 3.6e-05,
|
295 |
+
"loss": 7.1974,
|
296 |
+
"step": 82
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 8.0,
|
300 |
+
"grad_norm": 0.44188380241394043,
|
301 |
+
"learning_rate": 3.2000000000000005e-05,
|
302 |
+
"loss": 7.0847,
|
303 |
+
"step": 84
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.19047619047619,
|
307 |
+
"grad_norm": 0.6792606711387634,
|
308 |
+
"learning_rate": 2.8000000000000003e-05,
|
309 |
+
"loss": 7.1191,
|
310 |
+
"step": 86
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 8.380952380952381,
|
314 |
+
"grad_norm": 0.4903930723667145,
|
315 |
+
"learning_rate": 2.4e-05,
|
316 |
+
"loss": 7.1288,
|
317 |
+
"step": 88
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 8.571428571428571,
|
321 |
+
"grad_norm": 0.5853165984153748,
|
322 |
+
"learning_rate": 2e-05,
|
323 |
+
"loss": 7.0479,
|
324 |
+
"step": 90
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 8.761904761904763,
|
328 |
+
"grad_norm": 0.6836739182472229,
|
329 |
+
"learning_rate": 1.6000000000000003e-05,
|
330 |
+
"loss": 7.0448,
|
331 |
+
"step": 92
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 8.952380952380953,
|
335 |
+
"grad_norm": 0.5737291574478149,
|
336 |
+
"learning_rate": 1.2e-05,
|
337 |
+
"loss": 7.0717,
|
338 |
+
"step": 94
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.142857142857142,
|
342 |
+
"grad_norm": 1.709892988204956,
|
343 |
+
"learning_rate": 8.000000000000001e-06,
|
344 |
+
"loss": 6.9482,
|
345 |
+
"step": 96
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 9.333333333333334,
|
349 |
+
"grad_norm": 0.61203932762146,
|
350 |
+
"learning_rate": 4.000000000000001e-06,
|
351 |
+
"loss": 7.1598,
|
352 |
+
"step": 98
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 9.523809523809524,
|
356 |
+
"grad_norm": 0.3827505111694336,
|
357 |
+
"learning_rate": 0.0,
|
358 |
+
"loss": 7.1112,
|
359 |
+
"step": 100
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 9.523809523809524,
|
363 |
+
"step": 100,
|
364 |
+
"total_flos": 500328301455504.0,
|
365 |
+
"train_loss": 7.34823148727417,
|
366 |
+
"train_runtime": 426.3789,
|
367 |
+
"train_samples_per_second": 3.94,
|
368 |
+
"train_steps_per_second": 0.235
|
369 |
}
|
370 |
],
|
371 |
"logging_steps": 2,
|
372 |
+
"max_steps": 100,
|
373 |
"num_input_tokens_seen": 0,
|
374 |
+
"num_train_epochs": 10,
|
375 |
"save_steps": 500,
|
376 |
"stateful_callbacks": {
|
377 |
"TrainerControl": {
|
|
|
385 |
"attributes": {}
|
386 |
}
|
387 |
},
|
388 |
+
"total_flos": 500328301455504.0,
|
389 |
"train_batch_size": 2,
|
390 |
"trial_name": null,
|
391 |
"trial_params": null
|