Hugging Face's logo

mrsandip
/
Alfa-Code

Text Generation
Transformers
Safetensors
GGUF
English
code
code-generation
multimodal
llama
conversational
Model card Files
xet
 Community
mrsandip commited on
Commit
f792f10
·
verified ·
1 Parent(s): 87f48ad

Add trained tiny-50M 3 epochs loss 3.8

Browse files
Files changed (8) hide show
  1. outputs/tiny-50M/checkpoint-189/config.json +32 -0
  2. outputs/tiny-50M/checkpoint-189/generation_config.json +9 -0
  3. outputs/tiny-50M/checkpoint-189/model.safetensors +3 -0
  4. outputs/tiny-50M/checkpoint-189/optimizer.pt +3 -0
  5. outputs/tiny-50M/checkpoint-189/rng_state.pth +3 -0
  6. outputs/tiny-50M/checkpoint-189/scheduler.pt +3 -0
  7. outputs/tiny-50M/checkpoint-189/trainer_state.json +293 -0
  8. outputs/tiny-50M/model.safetensors +1 -1
outputs/tiny-50M/checkpoint-189/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1376,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.18.0",
30
+ "use_cache": false,
31
+ "vocab_size": 32000
32
+ }
outputs/tiny-50M/checkpoint-189/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.18.0",
8
+ "use_cache": true
9
+ }
outputs/tiny-50M/checkpoint-189/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5deb780bae879f426b6a3efb1796f622277eb706b0cc3cbedee5935da3bae4
3
+ size 223914096
outputs/tiny-50M/checkpoint-189/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46396bdccfe7b3a4ef5031fd4bd83756d23b44dcc5e7cff57d7146892112924
3
+ size 647627
outputs/tiny-50M/checkpoint-189/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9313c6023b495e709ecd28d837cd3f81498eaee4f34b731e45aa6b342cb585d
3
+ size 14645
outputs/tiny-50M/checkpoint-189/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482e55bb28795bd6acf119cb1f2213ebdd37ad3867c78f1646b0a97c2666919d
3
+ size 1465
outputs/tiny-50M/checkpoint-189/trainer_state.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 189,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0798004987531172,
14
+ "grad_norm": 8.034191131591797,
15
+ "learning_rate": 4.894179894179895e-05,
16
+ "loss": 9.426024627685546,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.1596009975062344,
21
+ "grad_norm": 5.838495254516602,
22
+ "learning_rate": 4.761904761904762e-05,
23
+ "loss": 8.173797607421875,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.23940149625935161,
28
+ "grad_norm": 5.718430042266846,
29
+ "learning_rate": 4.62962962962963e-05,
30
+ "loss": 7.780223846435547,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.3192019950124688,
35
+ "grad_norm": 6.245800971984863,
36
+ "learning_rate": 4.4973544973544974e-05,
37
+ "loss": 7.48138198852539,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.39900249376558605,
42
+ "grad_norm": 5.159392833709717,
43
+ "learning_rate": 4.3650793650793655e-05,
44
+ "loss": 7.260502624511719,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.47880299251870323,
49
+ "grad_norm": 6.719444274902344,
50
+ "learning_rate": 4.232804232804233e-05,
51
+ "loss": 6.943022918701172,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.5586034912718204,
56
+ "grad_norm": 5.4864959716796875,
57
+ "learning_rate": 4.100529100529101e-05,
58
+ "loss": 6.771894073486328,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.6384039900249376,
63
+ "grad_norm": 5.397635459899902,
64
+ "learning_rate": 3.968253968253968e-05,
65
+ "loss": 6.491435241699219,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.7182044887780549,
70
+ "grad_norm": 5.092394828796387,
71
+ "learning_rate": 3.835978835978836e-05,
72
+ "loss": 6.328219604492188,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.7980049875311721,
77
+ "grad_norm": 5.655710220336914,
78
+ "learning_rate": 3.7037037037037037e-05,
79
+ "loss": 6.187330627441407,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.8778054862842892,
84
+ "grad_norm": 5.796696662902832,
85
+ "learning_rate": 3.571428571428572e-05,
86
+ "loss": 5.885580825805664,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.9576059850374065,
91
+ "grad_norm": 5.131153583526611,
92
+ "learning_rate": 3.439153439153439e-05,
93
+ "loss": 5.7022655487060545,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 1.0319201995012468,
98
+ "grad_norm": 4.835399150848389,
99
+ "learning_rate": 3.306878306878307e-05,
100
+ "loss": 5.543949890136719,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 1.1117206982543641,
105
+ "grad_norm": 5.02362060546875,
106
+ "learning_rate": 3.1746031746031745e-05,
107
+ "loss": 5.328775405883789,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 1.1915211970074813,
112
+ "grad_norm": 4.315943241119385,
113
+ "learning_rate": 3.0423280423280425e-05,
114
+ "loss": 5.155892181396484,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 1.2713216957605984,
119
+ "grad_norm": 4.324975967407227,
120
+ "learning_rate": 2.91005291005291e-05,
121
+ "loss": 5.076448440551758,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 1.3511221945137157,
126
+ "grad_norm": 5.048192024230957,
127
+ "learning_rate": 2.777777777777778e-05,
128
+ "loss": 4.910471725463867,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 1.4309226932668329,
133
+ "grad_norm": 4.231033802032471,
134
+ "learning_rate": 2.6455026455026456e-05,
135
+ "loss": 4.793542098999024,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 1.5107231920199502,
140
+ "grad_norm": 3.9685726165771484,
141
+ "learning_rate": 2.5132275132275137e-05,
142
+ "loss": 4.664012908935547,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 1.5905236907730673,
147
+ "grad_norm": 4.092652797698975,
148
+ "learning_rate": 2.380952380952381e-05,
149
+ "loss": 4.569596862792968,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 1.6703241895261844,
154
+ "grad_norm": 3.9706995487213135,
155
+ "learning_rate": 2.2486772486772487e-05,
156
+ "loss": 4.495666122436523,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 1.7501246882793018,
161
+ "grad_norm": 3.680717945098877,
162
+ "learning_rate": 2.1164021164021164e-05,
163
+ "loss": 4.460382080078125,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 1.829925187032419,
168
+ "grad_norm": 3.9032771587371826,
169
+ "learning_rate": 1.984126984126984e-05,
170
+ "loss": 4.333694839477539,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 1.9097256857855363,
175
+ "grad_norm": 3.469503164291382,
176
+ "learning_rate": 1.8518518518518518e-05,
177
+ "loss": 4.224870300292968,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 1.9895261845386534,
182
+ "grad_norm": 3.262664556503296,
183
+ "learning_rate": 1.7195767195767195e-05,
184
+ "loss": 4.105544662475586,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 2.0638403990024936,
189
+ "grad_norm": 3.065542459487915,
190
+ "learning_rate": 1.5873015873015872e-05,
191
+ "loss": 4.142061233520508,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 2.143640897755611,
196
+ "grad_norm": 3.1756491661071777,
197
+ "learning_rate": 1.455026455026455e-05,
198
+ "loss": 3.995269012451172,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 2.2234413965087283,
203
+ "grad_norm": 3.23256778717041,
204
+ "learning_rate": 1.3227513227513228e-05,
205
+ "loss": 3.9744003295898436,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 2.3032418952618454,
210
+ "grad_norm": 3.386157512664795,
211
+ "learning_rate": 1.1904761904761905e-05,
212
+ "loss": 3.8902103424072267,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 2.3830423940149625,
217
+ "grad_norm": 3.117622137069702,
218
+ "learning_rate": 1.0582010582010582e-05,
219
+ "loss": 3.9169342041015627,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 2.4628428927680797,
224
+ "grad_norm": 3.074450731277466,
225
+ "learning_rate": 9.259259259259259e-06,
226
+ "loss": 3.9450088500976563,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 2.542643391521197,
231
+ "grad_norm": 3.1683943271636963,
232
+ "learning_rate": 7.936507936507936e-06,
233
+ "loss": 3.8834693908691404,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 2.6224438902743143,
238
+ "grad_norm": 3.094578742980957,
239
+ "learning_rate": 6.613756613756614e-06,
240
+ "loss": 3.811432647705078,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 2.7022443890274315,
245
+ "grad_norm": 2.872598171234131,
246
+ "learning_rate": 5.291005291005291e-06,
247
+ "loss": 3.798085403442383,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 2.7820448877805486,
252
+ "grad_norm": 2.967658519744873,
253
+ "learning_rate": 3.968253968253968e-06,
254
+ "loss": 3.770914077758789,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 2.8618453865336657,
259
+ "grad_norm": 2.7463254928588867,
260
+ "learning_rate": 2.6455026455026455e-06,
261
+ "loss": 3.8234378814697267,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 2.941645885286783,
266
+ "grad_norm": 3.0620932579040527,
267
+ "learning_rate": 1.3227513227513228e-06,
268
+ "loss": 3.8097812652587892,
269
+ "step": 185
270
+ }
271
+ ],
272
+ "logging_steps": 5,
273
+ "max_steps": 189,
274
+ "num_input_tokens_seen": 0,
275
+ "num_train_epochs": 3,
276
+ "save_steps": 200,
277
+ "stateful_callbacks": {
278
+ "TrainerControl": {
279
+ "args": {
280
+ "should_epoch_stop": false,
281
+ "should_evaluate": false,
282
+ "should_log": false,
283
+ "should_save": true,
284
+ "should_training_stop": true
285
+ },
286
+ "attributes": {}
287
+ }
288
+ },
289
+ "total_flos": 182898105384960.0,
290
+ "train_batch_size": 1,
291
+ "trial_name": null,
292
+ "trial_params": null
293
+ }
outputs/tiny-50M/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6adbe01bb1b1f3f43d9527d1ecca76f622b7fa0e8f2792a961b2a7ff29c2894e
3
  size 223914096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5deb780bae879f426b6a3efb1796f622277eb706b0cc3cbedee5935da3bae4
3
  size 223914096