aixk commited on
Commit
18e5f06
·
1 Parent(s): 27c696a

System: Prune old checkpoint folder checkpoint-200 to save space

Browse files
checkpoint-200/config.json DELETED
@@ -1,19 +0,0 @@
1
- {
2
- "architectures": [
3
- "FastPlus125mForCausalLM"
4
- ],
5
- "dtype": "float32",
6
- "hidden_size": 768,
7
- "initializer_range": 0.02,
8
- "intermediate_size": 2048,
9
- "kd_alpha": 0.4,
10
- "kd_temperature": 2.5,
11
- "max_position_embeddings": 512,
12
- "model_type": "fastplus_125m",
13
- "num_attention_heads": 12,
14
- "num_hidden_layers": 16,
15
- "tie_word_embeddings": false,
16
- "transformers_version": "5.12.0",
17
- "use_cache": false,
18
- "vocab_size": 32704
19
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-200/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "output_attentions": false,
4
- "output_hidden_states": false,
5
- "transformers_version": "5.12.0"
6
- }
 
 
 
 
 
 
 
checkpoint-200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "bos_token": "<s>",
4
- "eos_token": "</s>",
5
- "extra_special_tokens": [
6
- "<|user|>",
7
- "<|assistant|>"
8
- ],
9
- "is_local": false,
10
- "local_files_only": false,
11
- "model_max_length": 1000000000000000019884624838656,
12
- "pad_token": "<pad>",
13
- "tokenizer_class": "TokenizersBackend",
14
- "unk_token": "<unk>"
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-200/trainer_state.json DELETED
@@ -1,194 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.0032237915818742317,
6
- "eval_steps": 500,
7
- "global_step": 200,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0001611895790937116,
14
- "grad_norm": Infinity,
15
- "learning_rate": 1.7000000000000001e-07,
16
- "lorentz_dist_loss": 1.1774,
17
- "loss": 14.170442199707031,
18
- "step": 10
19
- },
20
- {
21
- "epoch": 0.0003223791581874232,
22
- "grad_norm": 11644.1904296875,
23
- "learning_rate": 6.800000000000001e-07,
24
- "lorentz_dist_loss": 1.1762,
25
- "loss": 14.155226135253907,
26
- "step": 20
27
- },
28
- {
29
- "epoch": 0.0004835687372811348,
30
- "grad_norm": 11821.7451171875,
31
- "learning_rate": 1.19e-06,
32
- "lorentz_dist_loss": 1.166,
33
- "loss": 14.033517456054687,
34
- "step": 30
35
- },
36
- {
37
- "epoch": 0.0006447583163748464,
38
- "grad_norm": 10725.34375,
39
- "learning_rate": 1.7566666666666669e-06,
40
- "lorentz_dist_loss": 1.1524,
41
- "loss": 13.870587158203126,
42
- "step": 40
43
- },
44
- {
45
- "epoch": 0.0008059478954685579,
46
- "grad_norm": 10575.232421875,
47
- "learning_rate": 2.3233333333333337e-06,
48
- "lorentz_dist_loss": 1.1312,
49
- "loss": 13.616365051269531,
50
- "step": 50
51
- },
52
- {
53
- "epoch": 0.0009671374745622695,
54
- "grad_norm": 10407.58984375,
55
- "learning_rate": 2.8900000000000003e-06,
56
- "lorentz_dist_loss": 1.1051,
57
- "loss": 13.303155517578125,
58
- "step": 60
59
- },
60
- {
61
- "epoch": 0.001128327053655981,
62
- "grad_norm": 9515.619140625,
63
- "learning_rate": 3.4566666666666665e-06,
64
- "lorentz_dist_loss": 1.0727,
65
- "loss": 12.913534545898438,
66
- "step": 70
67
- },
68
- {
69
- "epoch": 0.0012895166327496928,
70
- "grad_norm": 8322.388671875,
71
- "learning_rate": 4.0233333333333335e-06,
72
- "lorentz_dist_loss": 1.0396,
73
- "loss": 12.51680908203125,
74
- "step": 80
75
- },
76
- {
77
- "epoch": 0.0014507062118434043,
78
- "grad_norm": 7218.798828125,
79
- "learning_rate": 4.59e-06,
80
- "lorentz_dist_loss": 1.0072,
81
- "loss": 12.128275299072266,
82
- "step": 90
83
- },
84
- {
85
- "epoch": 0.0016118957909371158,
86
- "grad_norm": 5936.27294921875,
87
- "learning_rate": 5.156666666666667e-06,
88
- "lorentz_dist_loss": 0.9771,
89
- "loss": 11.766087341308594,
90
- "step": 100
91
- },
92
- {
93
- "epoch": 0.0017730853700308276,
94
- "grad_norm": 4860.89990234375,
95
- "learning_rate": 5.723333333333333e-06,
96
- "lorentz_dist_loss": 0.9544,
97
- "loss": 11.49432144165039,
98
- "step": 110
99
- },
100
- {
101
- "epoch": 0.001934274949124539,
102
- "grad_norm": 3848.34814453125,
103
- "learning_rate": 6.29e-06,
104
- "lorentz_dist_loss": 0.9391,
105
- "loss": 11.310404205322266,
106
- "step": 120
107
- },
108
- {
109
- "epoch": 0.002095464528218251,
110
- "grad_norm": 3314.070068359375,
111
- "learning_rate": 6.856666666666667e-06,
112
- "lorentz_dist_loss": 0.9293,
113
- "loss": 11.192581939697266,
114
- "step": 130
115
- },
116
- {
117
- "epoch": 0.002256654107311962,
118
- "grad_norm": 2885.541015625,
119
- "learning_rate": 7.423333333333334e-06,
120
- "lorentz_dist_loss": 0.9242,
121
- "loss": 11.131652069091796,
122
- "step": 140
123
- },
124
- {
125
- "epoch": 0.002417843686405674,
126
- "grad_norm": 2752.97021484375,
127
- "learning_rate": 7.990000000000001e-06,
128
- "lorentz_dist_loss": 0.9203,
129
- "loss": 11.085308837890626,
130
- "step": 150
131
- },
132
- {
133
- "epoch": 0.0025790332654993856,
134
- "grad_norm": 2966.74853515625,
135
- "learning_rate": 8.556666666666667e-06,
136
- "lorentz_dist_loss": 0.9166,
137
- "loss": 11.040792083740234,
138
- "step": 160
139
- },
140
- {
141
- "epoch": 0.002740222844593097,
142
- "grad_norm": 2726.117919921875,
143
- "learning_rate": 9.123333333333335e-06,
144
- "lorentz_dist_loss": 0.9137,
145
- "loss": 11.00632095336914,
146
- "step": 170
147
- },
148
- {
149
- "epoch": 0.0029014124236868086,
150
- "grad_norm": 2733.96728515625,
151
- "learning_rate": 9.69e-06,
152
- "lorentz_dist_loss": 0.9113,
153
- "loss": 10.977420043945312,
154
- "step": 180
155
- },
156
- {
157
- "epoch": 0.0030626020027805204,
158
- "grad_norm": 2651.473876953125,
159
- "learning_rate": 1.0256666666666668e-05,
160
- "lorentz_dist_loss": 0.9076,
161
- "loss": 10.932640838623048,
162
- "step": 190
163
- },
164
- {
165
- "epoch": 0.0032237915818742317,
166
- "grad_norm": 2543.915771484375,
167
- "learning_rate": 1.0823333333333334e-05,
168
- "lorentz_dist_loss": 0.9051,
169
- "loss": 10.90311279296875,
170
- "step": 200
171
- }
172
- ],
173
- "logging_steps": 10,
174
- "max_steps": 62039,
175
- "num_input_tokens_seen": 0,
176
- "num_train_epochs": 1,
177
- "save_steps": 200,
178
- "stateful_callbacks": {
179
- "TrainerControl": {
180
- "args": {
181
- "should_epoch_stop": false,
182
- "should_evaluate": false,
183
- "should_log": false,
184
- "should_save": true,
185
- "should_training_stop": false
186
- },
187
- "attributes": {}
188
- }
189
- },
190
- "total_flos": 3736378041200640.0,
191
- "train_batch_size": 12,
192
- "trial_name": null,
193
- "trial_params": null
194
- }