Uploaded checkpoint-500
Browse files- config.json +30 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +379 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
3 |
+
"architectures": [
|
4 |
+
"PhiForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": null,
|
8 |
+
"embd_pdrop": 0.0,
|
9 |
+
"eos_token_id": null,
|
10 |
+
"hidden_act": "gelu_new",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 8192,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 2048,
|
16 |
+
"model_type": "phi",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"partial_rotary_factor": 0.5,
|
21 |
+
"qk_layernorm": false,
|
22 |
+
"resid_pdrop": 0.0,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.38.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 51200
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.38.2"
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5d87510e496872c2830f70da9ca0859546b89cea7a68bc278e31001b39453fd
|
3 |
+
size 2836579040
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbedddc86cf2af069c89c6db6661aa94dd4860caeb98b0cc87f673204abbc12f
|
3 |
+
size 5673376169
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4331db6fde055daaa387d6b31fd8eec31f21908a09d4d37a76fd41feb521f465
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b0285085b333dc56b424c8360d2235baf38a3157b07e1c354ef6002e1611d53
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 114.5,
|
14 |
+
"learning_rate": 2.2000000000000002e-08,
|
15 |
+
"loss": 8.3264,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 118.0,
|
21 |
+
"learning_rate": 4.4000000000000004e-08,
|
22 |
+
"loss": 8.3249,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 118.5,
|
28 |
+
"learning_rate": 6.6e-08,
|
29 |
+
"loss": 8.3005,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0,
|
34 |
+
"grad_norm": 116.5,
|
35 |
+
"learning_rate": 8.800000000000001e-08,
|
36 |
+
"loss": 8.2821,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01,
|
41 |
+
"grad_norm": 116.5,
|
42 |
+
"learning_rate": 1.1e-07,
|
43 |
+
"loss": 8.3168,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.01,
|
48 |
+
"grad_norm": 120.0,
|
49 |
+
"learning_rate": 1.32e-07,
|
50 |
+
"loss": 8.288,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.01,
|
55 |
+
"grad_norm": 117.5,
|
56 |
+
"learning_rate": 1.5400000000000003e-07,
|
57 |
+
"loss": 8.3383,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.01,
|
62 |
+
"grad_norm": 119.0,
|
63 |
+
"learning_rate": 1.7600000000000001e-07,
|
64 |
+
"loss": 8.2777,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.01,
|
69 |
+
"grad_norm": 118.0,
|
70 |
+
"learning_rate": 1.98e-07,
|
71 |
+
"loss": 8.2758,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.01,
|
76 |
+
"grad_norm": 118.0,
|
77 |
+
"learning_rate": 2.2e-07,
|
78 |
+
"loss": 8.2869,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.01,
|
83 |
+
"grad_norm": 117.0,
|
84 |
+
"learning_rate": 2.42e-07,
|
85 |
+
"loss": 8.2819,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"grad_norm": 116.0,
|
91 |
+
"learning_rate": 2.64e-07,
|
92 |
+
"loss": 8.2884,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.01,
|
97 |
+
"grad_norm": 117.0,
|
98 |
+
"learning_rate": 2.8600000000000005e-07,
|
99 |
+
"loss": 8.229,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.01,
|
104 |
+
"grad_norm": 115.5,
|
105 |
+
"learning_rate": 3.0800000000000006e-07,
|
106 |
+
"loss": 8.2103,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.01,
|
111 |
+
"grad_norm": 114.0,
|
112 |
+
"learning_rate": 3.3e-07,
|
113 |
+
"loss": 8.2098,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.02,
|
118 |
+
"grad_norm": 114.5,
|
119 |
+
"learning_rate": 3.5200000000000003e-07,
|
120 |
+
"loss": 8.2018,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02,
|
125 |
+
"grad_norm": 115.0,
|
126 |
+
"learning_rate": 3.7400000000000004e-07,
|
127 |
+
"loss": 8.1996,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.02,
|
132 |
+
"grad_norm": 115.0,
|
133 |
+
"learning_rate": 3.96e-07,
|
134 |
+
"loss": 8.1512,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.02,
|
139 |
+
"grad_norm": 112.5,
|
140 |
+
"learning_rate": 4.18e-07,
|
141 |
+
"loss": 8.1395,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.02,
|
146 |
+
"grad_norm": 113.0,
|
147 |
+
"learning_rate": 4.4e-07,
|
148 |
+
"loss": 8.1209,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.02,
|
153 |
+
"grad_norm": 111.0,
|
154 |
+
"learning_rate": 4.62e-07,
|
155 |
+
"loss": 8.0906,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.02,
|
160 |
+
"grad_norm": 111.5,
|
161 |
+
"learning_rate": 4.84e-07,
|
162 |
+
"loss": 8.0615,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02,
|
167 |
+
"grad_norm": 109.0,
|
168 |
+
"learning_rate": 5.06e-07,
|
169 |
+
"loss": 8.0154,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.02,
|
174 |
+
"grad_norm": 110.5,
|
175 |
+
"learning_rate": 5.28e-07,
|
176 |
+
"loss": 7.986,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.03,
|
181 |
+
"grad_norm": 110.5,
|
182 |
+
"learning_rate": 5.5e-07,
|
183 |
+
"loss": 7.9651,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.03,
|
188 |
+
"grad_norm": 107.0,
|
189 |
+
"learning_rate": 5.720000000000001e-07,
|
190 |
+
"loss": 7.8918,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.03,
|
195 |
+
"grad_norm": 109.0,
|
196 |
+
"learning_rate": 5.94e-07,
|
197 |
+
"loss": 7.8074,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.03,
|
202 |
+
"grad_norm": 102.5,
|
203 |
+
"learning_rate": 6.160000000000001e-07,
|
204 |
+
"loss": 7.7464,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.03,
|
209 |
+
"grad_norm": 103.5,
|
210 |
+
"learning_rate": 6.38e-07,
|
211 |
+
"loss": 7.6693,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.03,
|
216 |
+
"grad_norm": 105.0,
|
217 |
+
"learning_rate": 6.6e-07,
|
218 |
+
"loss": 7.6443,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.03,
|
223 |
+
"grad_norm": 103.0,
|
224 |
+
"learning_rate": 6.82e-07,
|
225 |
+
"loss": 7.5796,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.03,
|
230 |
+
"grad_norm": 100.0,
|
231 |
+
"learning_rate": 7.040000000000001e-07,
|
232 |
+
"loss": 7.4966,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.03,
|
237 |
+
"grad_norm": 103.0,
|
238 |
+
"learning_rate": 7.260000000000001e-07,
|
239 |
+
"loss": 7.4265,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.03,
|
244 |
+
"grad_norm": 98.5,
|
245 |
+
"learning_rate": 7.480000000000001e-07,
|
246 |
+
"loss": 7.3721,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.04,
|
251 |
+
"grad_norm": 100.0,
|
252 |
+
"learning_rate": 7.7e-07,
|
253 |
+
"loss": 7.2681,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.04,
|
258 |
+
"grad_norm": 102.0,
|
259 |
+
"learning_rate": 7.92e-07,
|
260 |
+
"loss": 7.207,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.04,
|
265 |
+
"grad_norm": 106.0,
|
266 |
+
"learning_rate": 8.140000000000001e-07,
|
267 |
+
"loss": 7.1546,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.04,
|
272 |
+
"grad_norm": 104.0,
|
273 |
+
"learning_rate": 8.36e-07,
|
274 |
+
"loss": 7.0713,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.04,
|
279 |
+
"grad_norm": 104.5,
|
280 |
+
"learning_rate": 8.580000000000001e-07,
|
281 |
+
"loss": 6.9667,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.04,
|
286 |
+
"grad_norm": 100.5,
|
287 |
+
"learning_rate": 8.8e-07,
|
288 |
+
"loss": 6.8803,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.04,
|
293 |
+
"grad_norm": 92.5,
|
294 |
+
"learning_rate": 9.02e-07,
|
295 |
+
"loss": 6.7517,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.04,
|
300 |
+
"grad_norm": 96.0,
|
301 |
+
"learning_rate": 9.24e-07,
|
302 |
+
"loss": 6.6599,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.04,
|
307 |
+
"grad_norm": 94.5,
|
308 |
+
"learning_rate": 9.46e-07,
|
309 |
+
"loss": 6.5193,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.04,
|
314 |
+
"grad_norm": 90.0,
|
315 |
+
"learning_rate": 9.68e-07,
|
316 |
+
"loss": 6.4,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.04,
|
321 |
+
"grad_norm": 87.5,
|
322 |
+
"learning_rate": 9.9e-07,
|
323 |
+
"loss": 6.3021,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.05,
|
328 |
+
"grad_norm": 87.0,
|
329 |
+
"learning_rate": 1.012e-06,
|
330 |
+
"loss": 6.1852,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.05,
|
335 |
+
"grad_norm": 82.0,
|
336 |
+
"learning_rate": 1.034e-06,
|
337 |
+
"loss": 6.0423,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.05,
|
342 |
+
"grad_norm": 84.0,
|
343 |
+
"learning_rate": 1.056e-06,
|
344 |
+
"loss": 5.9377,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.05,
|
349 |
+
"grad_norm": 82.5,
|
350 |
+
"learning_rate": 1.078e-06,
|
351 |
+
"loss": 5.7858,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.05,
|
356 |
+
"grad_norm": 81.0,
|
357 |
+
"learning_rate": 1.1e-06,
|
358 |
+
"loss": 5.6391,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.05,
|
363 |
+
"eval_loss": 5.58803129196167,
|
364 |
+
"eval_runtime": 64.9971,
|
365 |
+
"eval_samples_per_second": 15.385,
|
366 |
+
"eval_steps_per_second": 15.385,
|
367 |
+
"step": 500
|
368 |
+
}
|
369 |
+
],
|
370 |
+
"logging_steps": 10,
|
371 |
+
"max_steps": 1500,
|
372 |
+
"num_input_tokens_seen": 0,
|
373 |
+
"num_train_epochs": 1,
|
374 |
+
"save_steps": 500,
|
375 |
+
"total_flos": 8069610209280000.0,
|
376 |
+
"train_batch_size": 1,
|
377 |
+
"trial_name": null,
|
378 |
+
"trial_params": null
|
379 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bb0fc562011b329fc7c8a50d01d1578c61307070ca4d20ef38be1dead807f6
|
3 |
+
size 4856
|