Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +2 -2
- trainer_state.json +424 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18cd7996ecd1dc1dbf420a0ab81cde0036b12228cd22ea965a010840f2764c2b
|
3 |
size 966995080
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d03bf4c067b9597eac26dc4a2f0fc8834aad5468187f83f4a7dd2c2331eefe33
|
3 |
+
size 1925064044
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a52f081f4924293d8474c5485e0b13c875749c1e09e4a911fccb555cb30e0d5
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e90b02d24fe55c96080d5eba73dc857321a59f84e8aeacc796ac8510ea27424c
|
3 |
+
size 1064
|
special_tokens_map.json
CHANGED
@@ -125,14 +125,14 @@
|
|
125 |
"pad_token": {
|
126 |
"content": "<|endoftext|>",
|
127 |
"lstrip": false,
|
128 |
-
"normalized":
|
129 |
"rstrip": false,
|
130 |
"single_word": false
|
131 |
},
|
132 |
"unk_token": {
|
133 |
"content": "",
|
134 |
"lstrip": false,
|
135 |
-
"normalized":
|
136 |
"rstrip": false,
|
137 |
"single_word": false
|
138 |
}
|
|
|
125 |
"pad_token": {
|
126 |
"content": "<|endoftext|>",
|
127 |
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
"rstrip": false,
|
130 |
"single_word": false
|
131 |
},
|
132 |
"unk_token": {
|
133 |
"content": "",
|
134 |
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
"rstrip": false,
|
137 |
"single_word": false
|
138 |
}
|
trainer_state.json
ADDED
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 37.0919881305638,
|
3 |
+
"best_model_checkpoint": "abuelnasr/whisper-small-eg/checkpoint-1020",
|
4 |
+
"epoch": 4.2677824267782425,
|
5 |
+
"eval_steps": 60,
|
6 |
+
"global_step": 1020,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.12552301255230125,
|
13 |
+
"grad_norm": 22.29438018798828,
|
14 |
+
"learning_rate": 8.666666666666668e-07,
|
15 |
+
"loss": 2.7449,
|
16 |
+
"step": 30
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2510460251046025,
|
20 |
+
"grad_norm": 13.858986854553223,
|
21 |
+
"learning_rate": 1.8666666666666669e-06,
|
22 |
+
"loss": 2.0487,
|
23 |
+
"step": 60
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.2510460251046025,
|
27 |
+
"eval_loss": 1.6403740644454956,
|
28 |
+
"eval_runtime": 248.9943,
|
29 |
+
"eval_samples_per_second": 1.627,
|
30 |
+
"eval_steps_per_second": 0.052,
|
31 |
+
"eval_wer": 72.87833827893175,
|
32 |
+
"step": 60
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.37656903765690375,
|
36 |
+
"grad_norm": 10.086219787597656,
|
37 |
+
"learning_rate": 2.866666666666667e-06,
|
38 |
+
"loss": 1.3133,
|
39 |
+
"step": 90
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.502092050209205,
|
43 |
+
"grad_norm": 10.840757369995117,
|
44 |
+
"learning_rate": 3.866666666666667e-06,
|
45 |
+
"loss": 1.1414,
|
46 |
+
"step": 120
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.502092050209205,
|
50 |
+
"eval_loss": 1.0603028535842896,
|
51 |
+
"eval_runtime": 279.3129,
|
52 |
+
"eval_samples_per_second": 1.45,
|
53 |
+
"eval_steps_per_second": 0.047,
|
54 |
+
"eval_wer": 73.33333333333333,
|
55 |
+
"step": 120
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.6276150627615062,
|
59 |
+
"grad_norm": 9.947965621948242,
|
60 |
+
"learning_rate": 4.866666666666667e-06,
|
61 |
+
"loss": 0.9772,
|
62 |
+
"step": 150
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.7531380753138075,
|
66 |
+
"grad_norm": 7.831133842468262,
|
67 |
+
"learning_rate": 4.926553672316385e-06,
|
68 |
+
"loss": 0.8749,
|
69 |
+
"step": 180
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.7531380753138075,
|
73 |
+
"eval_loss": 0.865332841873169,
|
74 |
+
"eval_runtime": 239.6319,
|
75 |
+
"eval_samples_per_second": 1.69,
|
76 |
+
"eval_steps_per_second": 0.054,
|
77 |
+
"eval_wer": 64.15430267062314,
|
78 |
+
"step": 180
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.8786610878661087,
|
82 |
+
"grad_norm": 7.919336318969727,
|
83 |
+
"learning_rate": 4.84180790960452e-06,
|
84 |
+
"loss": 0.8123,
|
85 |
+
"step": 210
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.00418410041841,
|
89 |
+
"grad_norm": 8.757369995117188,
|
90 |
+
"learning_rate": 4.757062146892656e-06,
|
91 |
+
"loss": 0.7374,
|
92 |
+
"step": 240
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.00418410041841,
|
96 |
+
"eval_loss": 0.6884974837303162,
|
97 |
+
"eval_runtime": 220.1085,
|
98 |
+
"eval_samples_per_second": 1.84,
|
99 |
+
"eval_steps_per_second": 0.059,
|
100 |
+
"eval_wer": 53.03659742828882,
|
101 |
+
"step": 240
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.1297071129707112,
|
105 |
+
"grad_norm": 6.005550861358643,
|
106 |
+
"learning_rate": 4.672316384180791e-06,
|
107 |
+
"loss": 0.5269,
|
108 |
+
"step": 270
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.2552301255230125,
|
112 |
+
"grad_norm": 5.889186382293701,
|
113 |
+
"learning_rate": 4.587570621468927e-06,
|
114 |
+
"loss": 0.5152,
|
115 |
+
"step": 300
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.2552301255230125,
|
119 |
+
"eval_loss": 0.5685195326805115,
|
120 |
+
"eval_runtime": 221.5589,
|
121 |
+
"eval_samples_per_second": 1.828,
|
122 |
+
"eval_steps_per_second": 0.059,
|
123 |
+
"eval_wer": 49.61424332344214,
|
124 |
+
"step": 300
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.3807531380753137,
|
128 |
+
"grad_norm": 5.900785446166992,
|
129 |
+
"learning_rate": 4.5028248587570625e-06,
|
130 |
+
"loss": 0.4884,
|
131 |
+
"step": 330
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.506276150627615,
|
135 |
+
"grad_norm": 5.92984676361084,
|
136 |
+
"learning_rate": 4.418079096045198e-06,
|
137 |
+
"loss": 0.4816,
|
138 |
+
"step": 360
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 1.506276150627615,
|
142 |
+
"eval_loss": 0.5440375804901123,
|
143 |
+
"eval_runtime": 268.521,
|
144 |
+
"eval_samples_per_second": 1.508,
|
145 |
+
"eval_steps_per_second": 0.048,
|
146 |
+
"eval_wer": 58.496538081107815,
|
147 |
+
"step": 360
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.6317991631799162,
|
151 |
+
"grad_norm": 5.4634318351745605,
|
152 |
+
"learning_rate": 4.333333333333334e-06,
|
153 |
+
"loss": 0.488,
|
154 |
+
"step": 390
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 1.7573221757322175,
|
158 |
+
"grad_norm": 6.412497043609619,
|
159 |
+
"learning_rate": 4.248587570621469e-06,
|
160 |
+
"loss": 0.4465,
|
161 |
+
"step": 420
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.7573221757322175,
|
165 |
+
"eval_loss": 0.5248781442642212,
|
166 |
+
"eval_runtime": 258.4515,
|
167 |
+
"eval_samples_per_second": 1.567,
|
168 |
+
"eval_steps_per_second": 0.05,
|
169 |
+
"eval_wer": 62.156280909990116,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.8828451882845187,
|
174 |
+
"grad_norm": 6.152505874633789,
|
175 |
+
"learning_rate": 4.1638418079096045e-06,
|
176 |
+
"loss": 0.4736,
|
177 |
+
"step": 450
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.00836820083682,
|
181 |
+
"grad_norm": 5.672488689422607,
|
182 |
+
"learning_rate": 4.079096045197741e-06,
|
183 |
+
"loss": 0.4399,
|
184 |
+
"step": 480
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.00836820083682,
|
188 |
+
"eval_loss": 0.5114672183990479,
|
189 |
+
"eval_runtime": 279.1622,
|
190 |
+
"eval_samples_per_second": 1.451,
|
191 |
+
"eval_steps_per_second": 0.047,
|
192 |
+
"eval_wer": 67.24035608308606,
|
193 |
+
"step": 480
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 2.1338912133891212,
|
197 |
+
"grad_norm": 6.103506565093994,
|
198 |
+
"learning_rate": 3.994350282485876e-06,
|
199 |
+
"loss": 0.3451,
|
200 |
+
"step": 510
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.2594142259414225,
|
204 |
+
"grad_norm": 5.109236717224121,
|
205 |
+
"learning_rate": 3.909604519774012e-06,
|
206 |
+
"loss": 0.3324,
|
207 |
+
"step": 540
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.2594142259414225,
|
211 |
+
"eval_loss": 0.5136451721191406,
|
212 |
+
"eval_runtime": 268.029,
|
213 |
+
"eval_samples_per_second": 1.511,
|
214 |
+
"eval_steps_per_second": 0.049,
|
215 |
+
"eval_wer": 54.77744807121662,
|
216 |
+
"step": 540
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.3849372384937237,
|
220 |
+
"grad_norm": 4.577359199523926,
|
221 |
+
"learning_rate": 3.8248587570621474e-06,
|
222 |
+
"loss": 0.3343,
|
223 |
+
"step": 570
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 2.510460251046025,
|
227 |
+
"grad_norm": 6.362017631530762,
|
228 |
+
"learning_rate": 3.7401129943502828e-06,
|
229 |
+
"loss": 0.3366,
|
230 |
+
"step": 600
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.510460251046025,
|
234 |
+
"eval_loss": 0.5054488778114319,
|
235 |
+
"eval_runtime": 259.5993,
|
236 |
+
"eval_samples_per_second": 1.56,
|
237 |
+
"eval_steps_per_second": 0.05,
|
238 |
+
"eval_wer": 49.00098911968348,
|
239 |
+
"step": 600
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 2.6359832635983262,
|
243 |
+
"grad_norm": 4.350444316864014,
|
244 |
+
"learning_rate": 3.655367231638418e-06,
|
245 |
+
"loss": 0.3447,
|
246 |
+
"step": 630
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 2.7615062761506275,
|
250 |
+
"grad_norm": 4.399082183837891,
|
251 |
+
"learning_rate": 3.570621468926554e-06,
|
252 |
+
"loss": 0.3232,
|
253 |
+
"step": 660
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 2.7615062761506275,
|
257 |
+
"eval_loss": 0.4949069023132324,
|
258 |
+
"eval_runtime": 249.7373,
|
259 |
+
"eval_samples_per_second": 1.622,
|
260 |
+
"eval_steps_per_second": 0.052,
|
261 |
+
"eval_wer": 42.57171117705242,
|
262 |
+
"step": 660
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 2.8870292887029287,
|
266 |
+
"grad_norm": 4.29299259185791,
|
267 |
+
"learning_rate": 3.48587570621469e-06,
|
268 |
+
"loss": 0.3365,
|
269 |
+
"step": 690
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 3.01255230125523,
|
273 |
+
"grad_norm": 4.033880710601807,
|
274 |
+
"learning_rate": 3.401129943502825e-06,
|
275 |
+
"loss": 0.3374,
|
276 |
+
"step": 720
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 3.01255230125523,
|
280 |
+
"eval_loss": 0.487780898809433,
|
281 |
+
"eval_runtime": 280.4517,
|
282 |
+
"eval_samples_per_second": 1.444,
|
283 |
+
"eval_steps_per_second": 0.046,
|
284 |
+
"eval_wer": 43.48170128585559,
|
285 |
+
"step": 720
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 3.1380753138075312,
|
289 |
+
"grad_norm": 3.836930274963379,
|
290 |
+
"learning_rate": 3.316384180790961e-06,
|
291 |
+
"loss": 0.2821,
|
292 |
+
"step": 750
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 3.2635983263598325,
|
296 |
+
"grad_norm": 4.796186447143555,
|
297 |
+
"learning_rate": 3.231638418079096e-06,
|
298 |
+
"loss": 0.2295,
|
299 |
+
"step": 780
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 3.2635983263598325,
|
303 |
+
"eval_loss": 0.4930148124694824,
|
304 |
+
"eval_runtime": 270.3473,
|
305 |
+
"eval_samples_per_second": 1.498,
|
306 |
+
"eval_steps_per_second": 0.048,
|
307 |
+
"eval_wer": 46.70623145400594,
|
308 |
+
"step": 780
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.3891213389121337,
|
312 |
+
"grad_norm": 4.248520851135254,
|
313 |
+
"learning_rate": 3.146892655367232e-06,
|
314 |
+
"loss": 0.2681,
|
315 |
+
"step": 810
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 3.514644351464435,
|
319 |
+
"grad_norm": 4.470262050628662,
|
320 |
+
"learning_rate": 3.0621468926553677e-06,
|
321 |
+
"loss": 0.2479,
|
322 |
+
"step": 840
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 3.514644351464435,
|
326 |
+
"eval_loss": 0.4894804358482361,
|
327 |
+
"eval_runtime": 250.2043,
|
328 |
+
"eval_samples_per_second": 1.619,
|
329 |
+
"eval_steps_per_second": 0.052,
|
330 |
+
"eval_wer": 41.66172106824926,
|
331 |
+
"step": 840
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 3.6401673640167362,
|
335 |
+
"grad_norm": 4.155009746551514,
|
336 |
+
"learning_rate": 2.977401129943503e-06,
|
337 |
+
"loss": 0.2438,
|
338 |
+
"step": 870
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.7656903765690375,
|
342 |
+
"grad_norm": 4.195906639099121,
|
343 |
+
"learning_rate": 2.8926553672316388e-06,
|
344 |
+
"loss": 0.2419,
|
345 |
+
"step": 900
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.7656903765690375,
|
349 |
+
"eval_loss": 0.4896373152732849,
|
350 |
+
"eval_runtime": 258.2624,
|
351 |
+
"eval_samples_per_second": 1.568,
|
352 |
+
"eval_steps_per_second": 0.05,
|
353 |
+
"eval_wer": 46.36993076162216,
|
354 |
+
"step": 900
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 3.891213389121339,
|
358 |
+
"grad_norm": 4.5145487785339355,
|
359 |
+
"learning_rate": 2.807909604519774e-06,
|
360 |
+
"loss": 0.2525,
|
361 |
+
"step": 930
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 4.01673640167364,
|
365 |
+
"grad_norm": 3.6618359088897705,
|
366 |
+
"learning_rate": 2.72316384180791e-06,
|
367 |
+
"loss": 0.2373,
|
368 |
+
"step": 960
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.01673640167364,
|
372 |
+
"eval_loss": 0.4873057007789612,
|
373 |
+
"eval_runtime": 238.693,
|
374 |
+
"eval_samples_per_second": 1.697,
|
375 |
+
"eval_steps_per_second": 0.054,
|
376 |
+
"eval_wer": 39.58456973293769,
|
377 |
+
"step": 960
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 4.142259414225942,
|
381 |
+
"grad_norm": 3.126338481903076,
|
382 |
+
"learning_rate": 2.6384180790960455e-06,
|
383 |
+
"loss": 0.1846,
|
384 |
+
"step": 990
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 4.2677824267782425,
|
388 |
+
"grad_norm": 3.1524906158447266,
|
389 |
+
"learning_rate": 2.553672316384181e-06,
|
390 |
+
"loss": 0.1887,
|
391 |
+
"step": 1020
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 4.2677824267782425,
|
395 |
+
"eval_loss": 0.49608033895492554,
|
396 |
+
"eval_runtime": 222.7087,
|
397 |
+
"eval_samples_per_second": 1.819,
|
398 |
+
"eval_steps_per_second": 0.058,
|
399 |
+
"eval_wer": 37.0919881305638,
|
400 |
+
"step": 1020
|
401 |
+
}
|
402 |
+
],
|
403 |
+
"logging_steps": 30,
|
404 |
+
"max_steps": 1920,
|
405 |
+
"num_input_tokens_seen": 0,
|
406 |
+
"num_train_epochs": 9,
|
407 |
+
"save_steps": 60,
|
408 |
+
"stateful_callbacks": {
|
409 |
+
"TrainerControl": {
|
410 |
+
"args": {
|
411 |
+
"should_epoch_stop": false,
|
412 |
+
"should_evaluate": false,
|
413 |
+
"should_log": false,
|
414 |
+
"should_save": true,
|
415 |
+
"should_training_stop": false
|
416 |
+
},
|
417 |
+
"attributes": {}
|
418 |
+
}
|
419 |
+
},
|
420 |
+
"total_flos": 9.3963406344192e+18,
|
421 |
+
"train_batch_size": 32,
|
422 |
+
"trial_name": null,
|
423 |
+
"trial_params": null
|
424 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adf550daf7a5c2b9708f6b489eacc1d897e3f311426c9c3af9d27457b030a65e
|
3 |
size 5368
|