Upload 8 files
Browse files- config.json +30 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +733 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "OuteAI/OuteTTS-0.2-500M",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4864,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 24,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 14,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_mrope": false,
|
28 |
+
"use_sliding_window": false,
|
29 |
+
"vocab_size": 157696
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151645,
|
4 |
+
"transformers_version": "4.46.1"
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7546606575ab5b8349efd3b89ea018856001b11d0a0979327663e6e4ad6f2d8
|
3 |
+
size 998419744
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dabbcbb747fa69e6bceadd000802df2eb7bd75ce28f66c4858b11b7649d64e00
|
3 |
+
size 1997018042
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3b258f49991c4a096c23935db8319a3e4bc3ad9a6f57bee8261f4c99db6ae27
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54475ea46f64b49351bcc7f75d4862b8b62320ab3a252e0779e0faba37054ad9
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5076142131979695,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005076142131979695,
|
13 |
+
"grad_norm": 3.015625,
|
14 |
+
"learning_rate": 3.384094754653131e-07,
|
15 |
+
"loss": 3.4275,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01015228426395939,
|
20 |
+
"grad_norm": 3.1875,
|
21 |
+
"learning_rate": 6.768189509306262e-07,
|
22 |
+
"loss": 3.5207,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.015228426395939087,
|
27 |
+
"grad_norm": 3.3125,
|
28 |
+
"learning_rate": 1.0152284263959392e-06,
|
29 |
+
"loss": 3.4307,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02030456852791878,
|
34 |
+
"grad_norm": 3.078125,
|
35 |
+
"learning_rate": 1.3536379018612523e-06,
|
36 |
+
"loss": 3.5356,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.025380710659898477,
|
41 |
+
"grad_norm": 2.84375,
|
42 |
+
"learning_rate": 1.6920473773265652e-06,
|
43 |
+
"loss": 3.4517,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.030456852791878174,
|
48 |
+
"grad_norm": 2.6875,
|
49 |
+
"learning_rate": 2.0304568527918785e-06,
|
50 |
+
"loss": 3.4387,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03553299492385787,
|
55 |
+
"grad_norm": 3.484375,
|
56 |
+
"learning_rate": 2.3688663282571915e-06,
|
57 |
+
"loss": 3.5372,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04060913705583756,
|
62 |
+
"grad_norm": 3.625,
|
63 |
+
"learning_rate": 2.7072758037225046e-06,
|
64 |
+
"loss": 3.4386,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04568527918781726,
|
69 |
+
"grad_norm": 3.25,
|
70 |
+
"learning_rate": 3.0456852791878177e-06,
|
71 |
+
"loss": 3.447,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.050761421319796954,
|
76 |
+
"grad_norm": 3.21875,
|
77 |
+
"learning_rate": 3.3840947546531303e-06,
|
78 |
+
"loss": 3.4071,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.05583756345177665,
|
83 |
+
"grad_norm": 2.625,
|
84 |
+
"learning_rate": 3.722504230118444e-06,
|
85 |
+
"loss": 3.4005,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.06091370558375635,
|
90 |
+
"grad_norm": 3.5,
|
91 |
+
"learning_rate": 4.060913705583757e-06,
|
92 |
+
"loss": 3.446,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.06598984771573604,
|
97 |
+
"grad_norm": 2.609375,
|
98 |
+
"learning_rate": 4.39932318104907e-06,
|
99 |
+
"loss": 3.5267,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07106598984771574,
|
104 |
+
"grad_norm": 2.59375,
|
105 |
+
"learning_rate": 4.737732656514383e-06,
|
106 |
+
"loss": 3.4858,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.07614213197969544,
|
111 |
+
"grad_norm": 2.265625,
|
112 |
+
"learning_rate": 5.076142131979695e-06,
|
113 |
+
"loss": 3.51,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.08121827411167512,
|
118 |
+
"grad_norm": 1.8515625,
|
119 |
+
"learning_rate": 5.414551607445009e-06,
|
120 |
+
"loss": 3.4237,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.08629441624365482,
|
125 |
+
"grad_norm": 1.71875,
|
126 |
+
"learning_rate": 5.752961082910322e-06,
|
127 |
+
"loss": 3.4005,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.09137055837563451,
|
132 |
+
"grad_norm": 1.8828125,
|
133 |
+
"learning_rate": 6.091370558375635e-06,
|
134 |
+
"loss": 3.3946,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.09644670050761421,
|
139 |
+
"grad_norm": 1.90625,
|
140 |
+
"learning_rate": 6.429780033840948e-06,
|
141 |
+
"loss": 3.3383,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.10152284263959391,
|
146 |
+
"grad_norm": 1.703125,
|
147 |
+
"learning_rate": 6.768189509306261e-06,
|
148 |
+
"loss": 3.28,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.1065989847715736,
|
153 |
+
"grad_norm": 1.6171875,
|
154 |
+
"learning_rate": 7.106598984771575e-06,
|
155 |
+
"loss": 3.3579,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.1116751269035533,
|
160 |
+
"grad_norm": 1.4921875,
|
161 |
+
"learning_rate": 7.445008460236888e-06,
|
162 |
+
"loss": 3.3075,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.116751269035533,
|
167 |
+
"grad_norm": 1.3984375,
|
168 |
+
"learning_rate": 7.7834179357022e-06,
|
169 |
+
"loss": 3.315,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.1218274111675127,
|
174 |
+
"grad_norm": 1.125,
|
175 |
+
"learning_rate": 8.121827411167514e-06,
|
176 |
+
"loss": 3.2354,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.12690355329949238,
|
181 |
+
"grad_norm": 1.140625,
|
182 |
+
"learning_rate": 8.460236886632826e-06,
|
183 |
+
"loss": 3.2279,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.1319796954314721,
|
188 |
+
"grad_norm": 1.453125,
|
189 |
+
"learning_rate": 8.79864636209814e-06,
|
190 |
+
"loss": 3.2781,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.13705583756345177,
|
195 |
+
"grad_norm": 1.3828125,
|
196 |
+
"learning_rate": 9.137055837563452e-06,
|
197 |
+
"loss": 3.3718,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.14213197969543148,
|
202 |
+
"grad_norm": 1.0703125,
|
203 |
+
"learning_rate": 9.475465313028766e-06,
|
204 |
+
"loss": 3.2864,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.14720812182741116,
|
209 |
+
"grad_norm": 1.3984375,
|
210 |
+
"learning_rate": 9.813874788494078e-06,
|
211 |
+
"loss": 3.2203,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.15228426395939088,
|
216 |
+
"grad_norm": 1.0078125,
|
217 |
+
"learning_rate": 1.015228426395939e-05,
|
218 |
+
"loss": 3.3262,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.15736040609137056,
|
223 |
+
"grad_norm": 1.390625,
|
224 |
+
"learning_rate": 1.0490693739424704e-05,
|
225 |
+
"loss": 3.2488,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.16243654822335024,
|
230 |
+
"grad_norm": 1.4140625,
|
231 |
+
"learning_rate": 1.0829103214890018e-05,
|
232 |
+
"loss": 3.2138,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.16751269035532995,
|
237 |
+
"grad_norm": 1.3359375,
|
238 |
+
"learning_rate": 1.116751269035533e-05,
|
239 |
+
"loss": 3.1632,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.17258883248730963,
|
244 |
+
"grad_norm": 1.28125,
|
245 |
+
"learning_rate": 1.1505922165820645e-05,
|
246 |
+
"loss": 3.255,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.17766497461928935,
|
251 |
+
"grad_norm": 1.265625,
|
252 |
+
"learning_rate": 1.1844331641285958e-05,
|
253 |
+
"loss": 3.1887,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.18274111675126903,
|
258 |
+
"grad_norm": 1.3125,
|
259 |
+
"learning_rate": 1.218274111675127e-05,
|
260 |
+
"loss": 3.2509,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.18781725888324874,
|
265 |
+
"grad_norm": 1.1953125,
|
266 |
+
"learning_rate": 1.2521150592216583e-05,
|
267 |
+
"loss": 3.1895,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.19289340101522842,
|
272 |
+
"grad_norm": 2.078125,
|
273 |
+
"learning_rate": 1.2859560067681895e-05,
|
274 |
+
"loss": 3.1627,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.19796954314720813,
|
279 |
+
"grad_norm": 1.078125,
|
280 |
+
"learning_rate": 1.3197969543147209e-05,
|
281 |
+
"loss": 3.2273,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.20304568527918782,
|
286 |
+
"grad_norm": 1.234375,
|
287 |
+
"learning_rate": 1.3536379018612521e-05,
|
288 |
+
"loss": 3.111,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.20812182741116753,
|
293 |
+
"grad_norm": 1.5859375,
|
294 |
+
"learning_rate": 1.3874788494077835e-05,
|
295 |
+
"loss": 3.1964,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.2131979695431472,
|
300 |
+
"grad_norm": 1.359375,
|
301 |
+
"learning_rate": 1.421319796954315e-05,
|
302 |
+
"loss": 3.1705,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.2182741116751269,
|
307 |
+
"grad_norm": 1.3515625,
|
308 |
+
"learning_rate": 1.4551607445008461e-05,
|
309 |
+
"loss": 3.0863,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.2233502538071066,
|
314 |
+
"grad_norm": 1.2890625,
|
315 |
+
"learning_rate": 1.4890016920473775e-05,
|
316 |
+
"loss": 3.2557,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.22842639593908629,
|
321 |
+
"grad_norm": 1.4296875,
|
322 |
+
"learning_rate": 1.5228426395939086e-05,
|
323 |
+
"loss": 3.1892,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.233502538071066,
|
328 |
+
"grad_norm": 1.15625,
|
329 |
+
"learning_rate": 1.55668358714044e-05,
|
330 |
+
"loss": 3.1675,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.23857868020304568,
|
335 |
+
"grad_norm": 1.203125,
|
336 |
+
"learning_rate": 1.5905245346869714e-05,
|
337 |
+
"loss": 3.1534,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.2436548223350254,
|
342 |
+
"grad_norm": 1.09375,
|
343 |
+
"learning_rate": 1.6243654822335028e-05,
|
344 |
+
"loss": 3.252,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.24873096446700507,
|
349 |
+
"grad_norm": 1.1484375,
|
350 |
+
"learning_rate": 1.658206429780034e-05,
|
351 |
+
"loss": 3.2352,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.25380710659898476,
|
356 |
+
"grad_norm": 1.109375,
|
357 |
+
"learning_rate": 1.6920473773265652e-05,
|
358 |
+
"loss": 3.3122,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.25888324873096447,
|
363 |
+
"grad_norm": 1.4765625,
|
364 |
+
"learning_rate": 1.7258883248730966e-05,
|
365 |
+
"loss": 3.1933,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.2639593908629442,
|
370 |
+
"grad_norm": 1.265625,
|
371 |
+
"learning_rate": 1.759729272419628e-05,
|
372 |
+
"loss": 3.2737,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.26903553299492383,
|
377 |
+
"grad_norm": 0.97265625,
|
378 |
+
"learning_rate": 1.793570219966159e-05,
|
379 |
+
"loss": 3.1775,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.27411167512690354,
|
384 |
+
"grad_norm": 1.203125,
|
385 |
+
"learning_rate": 1.8274111675126904e-05,
|
386 |
+
"loss": 3.1394,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.27918781725888325,
|
391 |
+
"grad_norm": 1.6171875,
|
392 |
+
"learning_rate": 1.8612521150592218e-05,
|
393 |
+
"loss": 3.1789,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.28426395939086296,
|
398 |
+
"grad_norm": 1.21875,
|
399 |
+
"learning_rate": 1.8950930626057532e-05,
|
400 |
+
"loss": 3.1097,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.2893401015228426,
|
405 |
+
"grad_norm": 1.21875,
|
406 |
+
"learning_rate": 1.9289340101522843e-05,
|
407 |
+
"loss": 3.2086,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.29441624365482233,
|
412 |
+
"grad_norm": 1.25,
|
413 |
+
"learning_rate": 1.9627749576988157e-05,
|
414 |
+
"loss": 3.1974,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.29949238578680204,
|
419 |
+
"grad_norm": 1.046875,
|
420 |
+
"learning_rate": 1.996615905245347e-05,
|
421 |
+
"loss": 3.0517,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.30456852791878175,
|
426 |
+
"grad_norm": 1.1640625,
|
427 |
+
"learning_rate": 1.996615905245347e-05,
|
428 |
+
"loss": 3.1709,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.3096446700507614,
|
433 |
+
"grad_norm": 1.1484375,
|
434 |
+
"learning_rate": 1.992855799962399e-05,
|
435 |
+
"loss": 3.1709,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.3147208121827411,
|
440 |
+
"grad_norm": 1.5,
|
441 |
+
"learning_rate": 1.9890956946794512e-05,
|
442 |
+
"loss": 3.159,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.3197969543147208,
|
447 |
+
"grad_norm": 1.234375,
|
448 |
+
"learning_rate": 1.9853355893965033e-05,
|
449 |
+
"loss": 3.2162,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.3248730964467005,
|
454 |
+
"grad_norm": 1.21875,
|
455 |
+
"learning_rate": 1.9815754841135553e-05,
|
456 |
+
"loss": 3.1009,
|
457 |
+
"step": 640
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.3299492385786802,
|
461 |
+
"grad_norm": 1.5703125,
|
462 |
+
"learning_rate": 1.9778153788306074e-05,
|
463 |
+
"loss": 3.1409,
|
464 |
+
"step": 650
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.3350253807106599,
|
468 |
+
"grad_norm": 1.1484375,
|
469 |
+
"learning_rate": 1.9740552735476595e-05,
|
470 |
+
"loss": 3.1621,
|
471 |
+
"step": 660
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.3401015228426396,
|
475 |
+
"grad_norm": 1.3359375,
|
476 |
+
"learning_rate": 1.9702951682647115e-05,
|
477 |
+
"loss": 3.0988,
|
478 |
+
"step": 670
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.34517766497461927,
|
482 |
+
"grad_norm": 1.1875,
|
483 |
+
"learning_rate": 1.9665350629817636e-05,
|
484 |
+
"loss": 3.2079,
|
485 |
+
"step": 680
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.350253807106599,
|
489 |
+
"grad_norm": 1.25,
|
490 |
+
"learning_rate": 1.9627749576988157e-05,
|
491 |
+
"loss": 3.1075,
|
492 |
+
"step": 690
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.3553299492385787,
|
496 |
+
"grad_norm": 1.3515625,
|
497 |
+
"learning_rate": 1.9590148524158677e-05,
|
498 |
+
"loss": 3.1286,
|
499 |
+
"step": 700
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.3604060913705584,
|
503 |
+
"grad_norm": 1.2578125,
|
504 |
+
"learning_rate": 1.9552547471329198e-05,
|
505 |
+
"loss": 3.1015,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.36548223350253806,
|
510 |
+
"grad_norm": 1.09375,
|
511 |
+
"learning_rate": 1.9514946418499722e-05,
|
512 |
+
"loss": 3.1522,
|
513 |
+
"step": 720
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.37055837563451777,
|
517 |
+
"grad_norm": 1.0078125,
|
518 |
+
"learning_rate": 1.947734536567024e-05,
|
519 |
+
"loss": 3.1892,
|
520 |
+
"step": 730
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.3756345177664975,
|
524 |
+
"grad_norm": 1.046875,
|
525 |
+
"learning_rate": 1.943974431284076e-05,
|
526 |
+
"loss": 3.0202,
|
527 |
+
"step": 740
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.38071065989847713,
|
531 |
+
"grad_norm": 1.0625,
|
532 |
+
"learning_rate": 1.940214326001128e-05,
|
533 |
+
"loss": 3.0803,
|
534 |
+
"step": 750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.38578680203045684,
|
538 |
+
"grad_norm": 1.671875,
|
539 |
+
"learning_rate": 1.93645422071818e-05,
|
540 |
+
"loss": 3.1514,
|
541 |
+
"step": 760
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.39086294416243655,
|
545 |
+
"grad_norm": 1.4140625,
|
546 |
+
"learning_rate": 1.9326941154352322e-05,
|
547 |
+
"loss": 3.1203,
|
548 |
+
"step": 770
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.39593908629441626,
|
552 |
+
"grad_norm": 1.1796875,
|
553 |
+
"learning_rate": 1.9289340101522843e-05,
|
554 |
+
"loss": 3.1549,
|
555 |
+
"step": 780
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.4010152284263959,
|
559 |
+
"grad_norm": 1.1796875,
|
560 |
+
"learning_rate": 1.9251739048693367e-05,
|
561 |
+
"loss": 3.0981,
|
562 |
+
"step": 790
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.40609137055837563,
|
566 |
+
"grad_norm": 1.5078125,
|
567 |
+
"learning_rate": 1.9214137995863887e-05,
|
568 |
+
"loss": 3.1134,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.41116751269035534,
|
573 |
+
"grad_norm": 1.1640625,
|
574 |
+
"learning_rate": 1.9176536943034408e-05,
|
575 |
+
"loss": 3.177,
|
576 |
+
"step": 810
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.41624365482233505,
|
580 |
+
"grad_norm": 1.0703125,
|
581 |
+
"learning_rate": 1.913893589020493e-05,
|
582 |
+
"loss": 3.0828,
|
583 |
+
"step": 820
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.4213197969543147,
|
587 |
+
"grad_norm": 1.734375,
|
588 |
+
"learning_rate": 1.9101334837375446e-05,
|
589 |
+
"loss": 3.22,
|
590 |
+
"step": 830
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.4263959390862944,
|
594 |
+
"grad_norm": 1.4296875,
|
595 |
+
"learning_rate": 1.9063733784545967e-05,
|
596 |
+
"loss": 3.1142,
|
597 |
+
"step": 840
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.43147208121827413,
|
601 |
+
"grad_norm": 1.0546875,
|
602 |
+
"learning_rate": 1.9026132731716487e-05,
|
603 |
+
"loss": 3.1719,
|
604 |
+
"step": 850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.4365482233502538,
|
608 |
+
"grad_norm": 1.546875,
|
609 |
+
"learning_rate": 1.898853167888701e-05,
|
610 |
+
"loss": 3.0995,
|
611 |
+
"step": 860
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.4416243654822335,
|
615 |
+
"grad_norm": 1.390625,
|
616 |
+
"learning_rate": 1.8950930626057532e-05,
|
617 |
+
"loss": 3.1097,
|
618 |
+
"step": 870
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.4467005076142132,
|
622 |
+
"grad_norm": 1.125,
|
623 |
+
"learning_rate": 1.8913329573228053e-05,
|
624 |
+
"loss": 3.0527,
|
625 |
+
"step": 880
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.4517766497461929,
|
629 |
+
"grad_norm": 1.125,
|
630 |
+
"learning_rate": 1.8875728520398574e-05,
|
631 |
+
"loss": 3.1668,
|
632 |
+
"step": 890
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.45685279187817257,
|
636 |
+
"grad_norm": 0.921875,
|
637 |
+
"learning_rate": 1.8838127467569094e-05,
|
638 |
+
"loss": 3.1204,
|
639 |
+
"step": 900
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.4619289340101523,
|
643 |
+
"grad_norm": 0.94921875,
|
644 |
+
"learning_rate": 1.8800526414739615e-05,
|
645 |
+
"loss": 3.1525,
|
646 |
+
"step": 910
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.467005076142132,
|
650 |
+
"grad_norm": 1.03125,
|
651 |
+
"learning_rate": 1.8762925361910136e-05,
|
652 |
+
"loss": 3.1031,
|
653 |
+
"step": 920
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.4720812182741117,
|
657 |
+
"grad_norm": 1.1875,
|
658 |
+
"learning_rate": 1.8725324309080656e-05,
|
659 |
+
"loss": 3.1314,
|
660 |
+
"step": 930
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.47715736040609136,
|
664 |
+
"grad_norm": 1.3984375,
|
665 |
+
"learning_rate": 1.8687723256251177e-05,
|
666 |
+
"loss": 3.1854,
|
667 |
+
"step": 940
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.48223350253807107,
|
671 |
+
"grad_norm": 1.265625,
|
672 |
+
"learning_rate": 1.8650122203421698e-05,
|
673 |
+
"loss": 3.1285,
|
674 |
+
"step": 950
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.4873096446700508,
|
678 |
+
"grad_norm": 1.7109375,
|
679 |
+
"learning_rate": 1.8612521150592218e-05,
|
680 |
+
"loss": 3.0433,
|
681 |
+
"step": 960
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.49238578680203043,
|
685 |
+
"grad_norm": 1.234375,
|
686 |
+
"learning_rate": 1.857492009776274e-05,
|
687 |
+
"loss": 3.1891,
|
688 |
+
"step": 970
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.49746192893401014,
|
692 |
+
"grad_norm": 1.25,
|
693 |
+
"learning_rate": 1.853731904493326e-05,
|
694 |
+
"loss": 3.1181,
|
695 |
+
"step": 980
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.5025380710659898,
|
699 |
+
"grad_norm": 1.0234375,
|
700 |
+
"learning_rate": 1.849971799210378e-05,
|
701 |
+
"loss": 3.0071,
|
702 |
+
"step": 990
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.5076142131979695,
|
706 |
+
"grad_norm": 1.140625,
|
707 |
+
"learning_rate": 1.84621169392743e-05,
|
708 |
+
"loss": 3.0957,
|
709 |
+
"step": 1000
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 10,
|
713 |
+
"max_steps": 5910,
|
714 |
+
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 3,
|
716 |
+
"save_steps": 100,
|
717 |
+
"stateful_callbacks": {
|
718 |
+
"TrainerControl": {
|
719 |
+
"args": {
|
720 |
+
"should_epoch_stop": false,
|
721 |
+
"should_evaluate": false,
|
722 |
+
"should_log": false,
|
723 |
+
"should_save": true,
|
724 |
+
"should_training_stop": false
|
725 |
+
},
|
726 |
+
"attributes": {}
|
727 |
+
}
|
728 |
+
},
|
729 |
+
"total_flos": 1.40731264008192e+17,
|
730 |
+
"train_batch_size": 2,
|
731 |
+
"trial_name": null,
|
732 |
+
"trial_params": null
|
733 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a698b70ac5ae7a6aa00d78b3286821445fa02f83b1ed23637b85ab5520b89e
|
3 |
+
size 5240
|