Hugging Face's logo

rschirem
/
tinyllama-AbstractGenius

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
rschirem commited on
Commit
7e3b646
·
verified ·
1 Parent(s): c6e464c

checkpoint 1400

Browse files
Files changed (8) hide show
  1. config.json +28 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +217 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.37.2",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf8f1d07ed11aae617b3cab8166eceba0d1a5856b7b97c2191843874df8c298
3
+ size 4400216536
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051b3ec5e9dbfb0f727c8a36a96e7ca7f3986cfbe53ff75dd20008e3f7376b06
3
+ size 8800513518
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84c4b4c1481d1143e59c8a8b087fe5b406091ae3b357cd125375068961147a6
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e7c37a0dea83ddf0d0aa7e5cae9e4c47a4a7c37d30b8941f422a78a74612db6
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.12,
5
+ "eval_steps": 100,
6
+ "global_step": 1400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 2.460393662986078e-05,
14
+ "loss": 1.8265,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "eval_loss": 1.7948205471038818,
20
+ "eval_runtime": 2217.6297,
21
+ "eval_samples_per_second": 9.019,
22
+ "eval_steps_per_second": 1.127,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "learning_rate": 2.420387261961914e-05,
28
+ "loss": 1.791,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.16,
33
+ "eval_loss": 1.7855218648910522,
34
+ "eval_runtime": 2218.3372,
35
+ "eval_samples_per_second": 9.016,
36
+ "eval_steps_per_second": 1.127,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.24,
41
+ "learning_rate": 2.38038086093775e-05,
42
+ "loss": 1.7848,
43
+ "step": 300
44
+ },
45
+ {
46
+ "epoch": 0.24,
47
+ "eval_loss": 1.7765330076217651,
48
+ "eval_runtime": 2217.7749,
49
+ "eval_samples_per_second": 9.018,
50
+ "eval_steps_per_second": 1.127,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.32,
55
+ "learning_rate": 2.340374459913586e-05,
56
+ "loss": 1.7843,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.32,
61
+ "eval_loss": 1.7692365646362305,
62
+ "eval_runtime": 2218.7844,
63
+ "eval_samples_per_second": 9.014,
64
+ "eval_steps_per_second": 1.127,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.4,
69
+ "learning_rate": 2.3003680588894225e-05,
70
+ "loss": 1.7736,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 0.4,
75
+ "eval_loss": 1.7632160186767578,
76
+ "eval_runtime": 2217.4605,
77
+ "eval_samples_per_second": 9.019,
78
+ "eval_steps_per_second": 1.127,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.48,
83
+ "learning_rate": 2.2603616578652586e-05,
84
+ "loss": 1.7612,
85
+ "step": 600
86
+ },
87
+ {
88
+ "epoch": 0.48,
89
+ "eval_loss": 1.757413625717163,
90
+ "eval_runtime": 2218.4914,
91
+ "eval_samples_per_second": 9.015,
92
+ "eval_steps_per_second": 1.127,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.56,
97
+ "learning_rate": 2.2203552568410947e-05,
98
+ "loss": 1.7632,
99
+ "step": 700
100
+ },
101
+ {
102
+ "epoch": 0.56,
103
+ "eval_loss": 1.7510673999786377,
104
+ "eval_runtime": 2217.7554,
105
+ "eval_samples_per_second": 9.018,
106
+ "eval_steps_per_second": 1.127,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.64,
111
+ "learning_rate": 2.1803488558169307e-05,
112
+ "loss": 1.7579,
113
+ "step": 800
114
+ },
115
+ {
116
+ "epoch": 0.64,
117
+ "eval_loss": 1.7483996152877808,
118
+ "eval_runtime": 2217.6281,
119
+ "eval_samples_per_second": 9.019,
120
+ "eval_steps_per_second": 1.127,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.72,
125
+ "learning_rate": 2.1403424547927668e-05,
126
+ "loss": 1.7482,
127
+ "step": 900
128
+ },
129
+ {
130
+ "epoch": 0.72,
131
+ "eval_loss": 1.7426660060882568,
132
+ "eval_runtime": 2217.5916,
133
+ "eval_samples_per_second": 9.019,
134
+ "eval_steps_per_second": 1.127,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.8,
139
+ "learning_rate": 2.1003360537686032e-05,
140
+ "loss": 1.7484,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.8,
145
+ "eval_loss": 1.738135576248169,
146
+ "eval_runtime": 2217.1723,
147
+ "eval_samples_per_second": 9.02,
148
+ "eval_steps_per_second": 1.128,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.88,
153
+ "learning_rate": 2.0603296527444393e-05,
154
+ "loss": 1.7448,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.88,
159
+ "eval_loss": 1.7337851524353027,
160
+ "eval_runtime": 2217.4606,
161
+ "eval_samples_per_second": 9.019,
162
+ "eval_steps_per_second": 1.127,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.96,
167
+ "learning_rate": 2.0203232517202754e-05,
168
+ "loss": 1.7351,
169
+ "step": 1200
170
+ },
171
+ {
172
+ "epoch": 0.96,
173
+ "eval_loss": 1.7301291227340698,
174
+ "eval_runtime": 2216.9509,
175
+ "eval_samples_per_second": 9.021,
176
+ "eval_steps_per_second": 1.128,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 1.04,
181
+ "learning_rate": 1.9803168506961114e-05,
182
+ "loss": 1.6193,
183
+ "step": 1300
184
+ },
185
+ {
186
+ "epoch": 1.04,
187
+ "eval_loss": 1.747913122177124,
188
+ "eval_runtime": 2217.695,
189
+ "eval_samples_per_second": 9.018,
190
+ "eval_steps_per_second": 1.127,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 1.12,
195
+ "learning_rate": 1.9403104496719475e-05,
196
+ "loss": 1.4984,
197
+ "step": 1400
198
+ },
199
+ {
200
+ "epoch": 1.12,
201
+ "eval_loss": 1.7492424249649048,
202
+ "eval_runtime": 2223.4607,
203
+ "eval_samples_per_second": 8.995,
204
+ "eval_steps_per_second": 1.124,
205
+ "step": 1400
206
+ }
207
+ ],
208
+ "logging_steps": 100,
209
+ "max_steps": 6250,
210
+ "num_input_tokens_seen": 0,
211
+ "num_train_epochs": 5,
212
+ "save_steps": 100,
213
+ "total_flos": 3.381415454441472e+17,
214
+ "train_batch_size": 64,
215
+ "trial_name": null,
216
+ "trial_params": null
217
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567cc29e5672827c7e999f348e3ee9a3e781d1aee0b8b303a09ac12342bde732
3
+ size 4664