matCercola18 commited on
Commit
ef7fbd4
·
verified ·
1 Parent(s): ff106f8

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. acq/max_var/reward/checkpoint-1125/chat_template.jinja +3 -0
  2. acq/max_var/reward/checkpoint-1125/config.json +38 -0
  3. acq/max_var/reward/checkpoint-1125/model.safetensors +3 -0
  4. acq/max_var/reward/checkpoint-1125/optimizer.pt +3 -0
  5. acq/max_var/reward/checkpoint-1125/rng_state.pth +3 -0
  6. acq/max_var/reward/checkpoint-1125/scheduler.pt +3 -0
  7. acq/max_var/reward/checkpoint-1125/special_tokens_map.json +30 -0
  8. acq/max_var/reward/checkpoint-1125/tokenizer.json +0 -0
  9. acq/max_var/reward/checkpoint-1125/tokenizer_config.json +224 -0
  10. acq/max_var/reward/checkpoint-1125/trainer_state.json +174 -0
  11. acq/max_var/reward/checkpoint-1125/training_args.bin +3 -0
  12. acq/max_var/reward/checkpoint-1128/chat_template.jinja +3 -0
  13. acq/max_var/reward/checkpoint-1128/config.json +38 -0
  14. acq/max_var/reward/checkpoint-1128/model.safetensors +3 -0
  15. acq/max_var/reward/checkpoint-1128/optimizer.pt +3 -0
  16. acq/max_var/reward/checkpoint-1128/rng_state.pth +3 -0
  17. acq/max_var/reward/checkpoint-1128/scheduler.pt +3 -0
  18. acq/max_var/reward/checkpoint-1128/special_tokens_map.json +30 -0
  19. acq/max_var/reward/checkpoint-1128/tokenizer.json +0 -0
  20. acq/max_var/reward/checkpoint-1128/tokenizer_config.json +224 -0
  21. acq/max_var/reward/checkpoint-1128/trainer_state.json +183 -0
  22. acq/max_var/reward/checkpoint-1128/training_args.bin +3 -0
  23. acq/max_var/reward/checkpoint-1410/chat_template.jinja +3 -0
  24. acq/max_var/reward/checkpoint-1410/config.json +38 -0
  25. acq/max_var/reward/checkpoint-1410/model.safetensors +3 -0
  26. acq/max_var/reward/checkpoint-1410/optimizer.pt +3 -0
  27. acq/max_var/reward/checkpoint-1410/rng_state.pth +3 -0
  28. acq/max_var/reward/checkpoint-1410/scheduler.pt +3 -0
  29. acq/max_var/reward/checkpoint-1410/special_tokens_map.json +30 -0
  30. acq/max_var/reward/checkpoint-1410/tokenizer.json +0 -0
  31. acq/max_var/reward/checkpoint-1410/tokenizer_config.json +224 -0
  32. acq/max_var/reward/checkpoint-1410/trainer_state.json +192 -0
  33. acq/max_var/reward/checkpoint-1410/training_args.bin +3 -0
  34. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759048592.move-hpc-02-gpu.60374.0 +3 -0
  35. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759051979.move-hpc-02-gpu.60374.1 +3 -0
  36. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759051989.move-hpc-02-gpu.60374.2 +3 -0
  37. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759055596.move-hpc-02-gpu.60374.5 +3 -0
  38. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759055616.move-hpc-02-gpu.60374.6 +3 -0
  39. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759059227.move-hpc-02-gpu.60374.9 +3 -0
  40. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759059245.move-hpc-02-gpu.60374.10 +3 -0
  41. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759062859.move-hpc-02-gpu.60374.13 +3 -0
  42. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759062877.move-hpc-02-gpu.60374.14 +3 -0
  43. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759066406.move-hpc-02-gpu.60374.17 +3 -0
  44. acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759066424.move-hpc-02-gpu.60374.18 +3 -0
  45. acq/mixed/reward/checkpoint-1128/chat_template.jinja +3 -0
  46. acq/mixed/reward/checkpoint-1128/config.json +38 -0
  47. acq/mixed/reward/checkpoint-1128/model.safetensors +3 -0
  48. acq/mixed/reward/checkpoint-1128/optimizer.pt +3 -0
  49. acq/mixed/reward/checkpoint-1128/rng_state.pth +3 -0
  50. acq/mixed/reward/checkpoint-1128/scheduler.pt +3 -0
acq/max_var/reward/checkpoint-1125/chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '
2
+
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
acq/max_var/reward/checkpoint-1125/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 512,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 50277,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.53.0",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50278
38
+ }
acq/max_var/reward/checkpoint-1125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fffbf0ebb27311527282e7350349cd9fbf4aa25174a082c17cbcc9aaf53bbc6e
3
+ size 178643424
acq/max_var/reward/checkpoint-1125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669aa582f96d17512b87645d18a3f0d61f1efe3b3309298ef071c2d073866b71
3
+ size 50468196
acq/max_var/reward/checkpoint-1125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1068ff328cb487ff8aa9fa5feef860ceaa4739b14f21e07b898f513df05ffbb1
3
+ size 14645
acq/max_var/reward/checkpoint-1125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43bd5a813f5874ceb54031b83ed56a2b7988ac6215254846b84fcbc6dafd427
3
+ size 1465
acq/max_var/reward/checkpoint-1125/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
acq/max_var/reward/checkpoint-1125/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
acq/max_var/reward/checkpoint-1125/tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "clean_up_tokenization_spaces": false,
217
+ "eos_token": "<|endoftext|>",
218
+ "extra_special_tokens": {},
219
+ "model_max_length": 1000000000000000019884624838656,
220
+ "pad_token": "[PAD]",
221
+ "padding_side": "left",
222
+ "tokenizer_class": "GPTNeoXTokenizer",
223
+ "unk_token": "<|endoftext|>"
224
+ }
acq/max_var/reward/checkpoint-1125/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1125,
3
+ "best_metric": 0.5299662947654724,
4
+ "best_model_checkpoint": "ckpts/acq/max_var/reward/checkpoint-1125",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1125,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.61,
15
+ "eval_loss": 0.7797494530677795,
16
+ "eval_runtime": 0.6929,
17
+ "eval_samples_per_second": 288.656,
18
+ "eval_steps_per_second": 36.082,
19
+ "step": 45
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.635,
24
+ "eval_loss": 0.8450192213058472,
25
+ "eval_runtime": 0.6881,
26
+ "eval_samples_per_second": 290.642,
27
+ "eval_steps_per_second": 36.33,
28
+ "step": 90
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.585,
33
+ "eval_loss": 1.0062354803085327,
34
+ "eval_runtime": 0.6848,
35
+ "eval_samples_per_second": 292.067,
36
+ "eval_steps_per_second": 36.508,
37
+ "step": 135
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.61,
42
+ "eval_loss": 1.2404606342315674,
43
+ "eval_runtime": 0.6804,
44
+ "eval_samples_per_second": 293.958,
45
+ "eval_steps_per_second": 36.745,
46
+ "step": 180
47
+ },
48
+ {
49
+ "epoch": 4.0,
50
+ "eval_accuracy": 0.48,
51
+ "eval_loss": 0.9865803718566895,
52
+ "eval_runtime": 0.1322,
53
+ "eval_samples_per_second": 189.073,
54
+ "eval_steps_per_second": 30.252,
55
+ "step": 228
56
+ },
57
+ {
58
+ "epoch": 5.0,
59
+ "eval_accuracy": 0.52,
60
+ "eval_loss": 0.9823645949363708,
61
+ "eval_runtime": 0.1356,
62
+ "eval_samples_per_second": 184.391,
63
+ "eval_steps_per_second": 29.502,
64
+ "step": 285
65
+ },
66
+ {
67
+ "epoch": 3.0,
68
+ "eval_accuracy": 0.68,
69
+ "eval_loss": 0.6368125677108765,
70
+ "eval_runtime": 0.2587,
71
+ "eval_samples_per_second": 193.286,
72
+ "eval_steps_per_second": 27.06,
73
+ "step": 339
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.62,
78
+ "eval_loss": 0.7137138247489929,
79
+ "eval_runtime": 0.2437,
80
+ "eval_samples_per_second": 205.198,
81
+ "eval_steps_per_second": 28.728,
82
+ "step": 452
83
+ },
84
+ {
85
+ "epoch": 4.424778761061947,
86
+ "grad_norm": 65.47836303710938,
87
+ "learning_rate": 3.9828274442409566e-06,
88
+ "loss": 0.6097,
89
+ "step": 500
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "eval_accuracy": 0.62,
94
+ "eval_loss": 0.7127777338027954,
95
+ "eval_runtime": 0.2465,
96
+ "eval_samples_per_second": 202.826,
97
+ "eval_steps_per_second": 28.396,
98
+ "step": 565
99
+ },
100
+ {
101
+ "epoch": 4.0,
102
+ "eval_accuracy": 0.6933333333333334,
103
+ "eval_loss": 0.5826706290245056,
104
+ "eval_runtime": 0.3316,
105
+ "eval_samples_per_second": 226.159,
106
+ "eval_steps_per_second": 30.154,
107
+ "step": 676
108
+ },
109
+ {
110
+ "epoch": 5.0,
111
+ "eval_accuracy": 0.7333333333333333,
112
+ "eval_loss": 0.5467433333396912,
113
+ "eval_runtime": 0.3772,
114
+ "eval_samples_per_second": 198.811,
115
+ "eval_steps_per_second": 26.508,
116
+ "step": 845
117
+ },
118
+ {
119
+ "epoch": 4.0,
120
+ "eval_accuracy": 0.73,
121
+ "eval_loss": 0.5404043793678284,
122
+ "eval_runtime": 0.4345,
123
+ "eval_samples_per_second": 230.175,
124
+ "eval_steps_per_second": 29.923,
125
+ "step": 900
126
+ },
127
+ {
128
+ "epoch": 4.444444444444445,
129
+ "grad_norm": 155.99192810058594,
130
+ "learning_rate": 3.338904260121854e-06,
131
+ "loss": 0.5426,
132
+ "step": 1000
133
+ },
134
+ {
135
+ "epoch": 5.0,
136
+ "eval_accuracy": 0.74,
137
+ "eval_loss": 0.5299662947654724,
138
+ "eval_runtime": 0.4624,
139
+ "eval_samples_per_second": 216.241,
140
+ "eval_steps_per_second": 28.111,
141
+ "step": 1125
142
+ }
143
+ ],
144
+ "logging_steps": 500,
145
+ "max_steps": 1125,
146
+ "num_input_tokens_seen": 0,
147
+ "num_train_epochs": 5,
148
+ "save_steps": 2000,
149
+ "stateful_callbacks": {
150
+ "EarlyStoppingCallback": {
151
+ "args": {
152
+ "early_stopping_patience": 3,
153
+ "early_stopping_threshold": 0.0001
154
+ },
155
+ "attributes": {
156
+ "early_stopping_patience_counter": 0
157
+ }
158
+ },
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": true
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 0.0,
171
+ "train_batch_size": 4,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
acq/max_var/reward/checkpoint-1125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9325692aa4e8ce941ac9ee18b16ca0be3de43d3d292bdf183b404537723d3b08
3
+ size 5841
acq/max_var/reward/checkpoint-1128/chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '
2
+
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
acq/max_var/reward/checkpoint-1128/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 512,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 50277,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.53.0",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50278
38
+ }
acq/max_var/reward/checkpoint-1128/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89a5c391f04a3aa8b3d50a34c23d4cdcd8feb9533c2b746a2c694d41e861528
3
+ size 178643424
acq/max_var/reward/checkpoint-1128/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f4aff4164cb520cc0b6016a947d45ff9bf21800c636474f2ba9f646f4fd06f
3
+ size 50468196
acq/max_var/reward/checkpoint-1128/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bba62abab919d97e86e665bcc2b30cdef0058dbbf59538563dd656f3b9d42e6
3
+ size 14645
acq/max_var/reward/checkpoint-1128/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00cbbc95ae096b8b94a2cdc095a859c0ca1504f77f5a390cc5c3f88995dd3e4
3
+ size 1465
acq/max_var/reward/checkpoint-1128/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
acq/max_var/reward/checkpoint-1128/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
acq/max_var/reward/checkpoint-1128/tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "clean_up_tokenization_spaces": false,
217
+ "eos_token": "<|endoftext|>",
218
+ "extra_special_tokens": {},
219
+ "model_max_length": 1000000000000000019884624838656,
220
+ "pad_token": "[PAD]",
221
+ "padding_side": "left",
222
+ "tokenizer_class": "GPTNeoXTokenizer",
223
+ "unk_token": "<|endoftext|>"
224
+ }
acq/max_var/reward/checkpoint-1128/trainer_state.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1128,
3
+ "best_metric": 0.48202478885650635,
4
+ "best_model_checkpoint": "ckpts/acq/max_var/reward/checkpoint-1128",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1128,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.61,
15
+ "eval_loss": 0.7797494530677795,
16
+ "eval_runtime": 0.6929,
17
+ "eval_samples_per_second": 288.656,
18
+ "eval_steps_per_second": 36.082,
19
+ "step": 45
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.635,
24
+ "eval_loss": 0.8450192213058472,
25
+ "eval_runtime": 0.6881,
26
+ "eval_samples_per_second": 290.642,
27
+ "eval_steps_per_second": 36.33,
28
+ "step": 90
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.585,
33
+ "eval_loss": 1.0062354803085327,
34
+ "eval_runtime": 0.6848,
35
+ "eval_samples_per_second": 292.067,
36
+ "eval_steps_per_second": 36.508,
37
+ "step": 135
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.61,
42
+ "eval_loss": 1.2404606342315674,
43
+ "eval_runtime": 0.6804,
44
+ "eval_samples_per_second": 293.958,
45
+ "eval_steps_per_second": 36.745,
46
+ "step": 180
47
+ },
48
+ {
49
+ "epoch": 4.0,
50
+ "eval_accuracy": 0.48,
51
+ "eval_loss": 0.9865803718566895,
52
+ "eval_runtime": 0.1322,
53
+ "eval_samples_per_second": 189.073,
54
+ "eval_steps_per_second": 30.252,
55
+ "step": 228
56
+ },
57
+ {
58
+ "epoch": 5.0,
59
+ "eval_accuracy": 0.52,
60
+ "eval_loss": 0.9823645949363708,
61
+ "eval_runtime": 0.1356,
62
+ "eval_samples_per_second": 184.391,
63
+ "eval_steps_per_second": 29.502,
64
+ "step": 285
65
+ },
66
+ {
67
+ "epoch": 3.0,
68
+ "eval_accuracy": 0.68,
69
+ "eval_loss": 0.6368125677108765,
70
+ "eval_runtime": 0.2587,
71
+ "eval_samples_per_second": 193.286,
72
+ "eval_steps_per_second": 27.06,
73
+ "step": 339
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.62,
78
+ "eval_loss": 0.7137138247489929,
79
+ "eval_runtime": 0.2437,
80
+ "eval_samples_per_second": 205.198,
81
+ "eval_steps_per_second": 28.728,
82
+ "step": 452
83
+ },
84
+ {
85
+ "epoch": 4.424778761061947,
86
+ "grad_norm": 65.47836303710938,
87
+ "learning_rate": 3.9828274442409566e-06,
88
+ "loss": 0.6097,
89
+ "step": 500
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "eval_accuracy": 0.62,
94
+ "eval_loss": 0.7127777338027954,
95
+ "eval_runtime": 0.2465,
96
+ "eval_samples_per_second": 202.826,
97
+ "eval_steps_per_second": 28.396,
98
+ "step": 565
99
+ },
100
+ {
101
+ "epoch": 4.0,
102
+ "eval_accuracy": 0.6933333333333334,
103
+ "eval_loss": 0.5826706290245056,
104
+ "eval_runtime": 0.3316,
105
+ "eval_samples_per_second": 226.159,
106
+ "eval_steps_per_second": 30.154,
107
+ "step": 676
108
+ },
109
+ {
110
+ "epoch": 5.0,
111
+ "eval_accuracy": 0.7333333333333333,
112
+ "eval_loss": 0.5467433333396912,
113
+ "eval_runtime": 0.3772,
114
+ "eval_samples_per_second": 198.811,
115
+ "eval_steps_per_second": 26.508,
116
+ "step": 845
117
+ },
118
+ {
119
+ "epoch": 4.0,
120
+ "eval_accuracy": 0.73,
121
+ "eval_loss": 0.5404043793678284,
122
+ "eval_runtime": 0.4345,
123
+ "eval_samples_per_second": 230.175,
124
+ "eval_steps_per_second": 29.923,
125
+ "step": 900
126
+ },
127
+ {
128
+ "epoch": 4.444444444444445,
129
+ "grad_norm": 155.99192810058594,
130
+ "learning_rate": 3.338904260121854e-06,
131
+ "loss": 0.5426,
132
+ "step": 1000
133
+ },
134
+ {
135
+ "epoch": 5.0,
136
+ "eval_accuracy": 0.74,
137
+ "eval_loss": 0.5299662947654724,
138
+ "eval_runtime": 0.4624,
139
+ "eval_samples_per_second": 216.241,
140
+ "eval_steps_per_second": 28.111,
141
+ "step": 1125
142
+ },
143
+ {
144
+ "epoch": 4.0,
145
+ "eval_accuracy": 0.784,
146
+ "eval_loss": 0.48202478885650635,
147
+ "eval_runtime": 0.5901,
148
+ "eval_samples_per_second": 211.822,
149
+ "eval_steps_per_second": 27.113,
150
+ "step": 1128
151
+ }
152
+ ],
153
+ "logging_steps": 500,
154
+ "max_steps": 1410,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 5,
157
+ "save_steps": 2000,
158
+ "stateful_callbacks": {
159
+ "EarlyStoppingCallback": {
160
+ "args": {
161
+ "early_stopping_patience": 3,
162
+ "early_stopping_threshold": 0.0001
163
+ },
164
+ "attributes": {
165
+ "early_stopping_patience_counter": 0
166
+ }
167
+ },
168
+ "TrainerControl": {
169
+ "args": {
170
+ "should_epoch_stop": false,
171
+ "should_evaluate": false,
172
+ "should_log": false,
173
+ "should_save": true,
174
+ "should_training_stop": false
175
+ },
176
+ "attributes": {}
177
+ }
178
+ },
179
+ "total_flos": 0.0,
180
+ "train_batch_size": 4,
181
+ "trial_name": null,
182
+ "trial_params": null
183
+ }
acq/max_var/reward/checkpoint-1128/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd245ee3e1b2a624212523487347e8211ca904df659f61ce1e69e1979243463d
3
+ size 5841
acq/max_var/reward/checkpoint-1410/chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '
2
+
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
acq/max_var/reward/checkpoint-1410/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 512,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 50277,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.53.0",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50278
38
+ }
acq/max_var/reward/checkpoint-1410/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746a1fb0606f342498fb2a8362116c499401ccb3ecddc82a20f8fbee31c01f7a
3
+ size 178643424
acq/max_var/reward/checkpoint-1410/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36f2f264532a788efc3ef8c2e5e7f731b7301ab209270ec0bd3d5a1a92e3033
3
+ size 50468196
acq/max_var/reward/checkpoint-1410/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362339732edadb06d085cfb97531cf355dbaa1b01e2d50ac0f5423f271541fbb
3
+ size 14645
acq/max_var/reward/checkpoint-1410/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a729d033c5297030575503237f25e87145a4d3ac8c32973a38d2010877f09175
3
+ size 1465
acq/max_var/reward/checkpoint-1410/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
acq/max_var/reward/checkpoint-1410/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
acq/max_var/reward/checkpoint-1410/tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "clean_up_tokenization_spaces": false,
217
+ "eos_token": "<|endoftext|>",
218
+ "extra_special_tokens": {},
219
+ "model_max_length": 1000000000000000019884624838656,
220
+ "pad_token": "[PAD]",
221
+ "padding_side": "left",
222
+ "tokenizer_class": "GPTNeoXTokenizer",
223
+ "unk_token": "<|endoftext|>"
224
+ }
acq/max_var/reward/checkpoint-1410/trainer_state.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1410,
3
+ "best_metric": 0.465172678232193,
4
+ "best_model_checkpoint": "ckpts/acq/max_var/reward/checkpoint-1410",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1410,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.61,
15
+ "eval_loss": 0.7797494530677795,
16
+ "eval_runtime": 0.6929,
17
+ "eval_samples_per_second": 288.656,
18
+ "eval_steps_per_second": 36.082,
19
+ "step": 45
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.635,
24
+ "eval_loss": 0.8450192213058472,
25
+ "eval_runtime": 0.6881,
26
+ "eval_samples_per_second": 290.642,
27
+ "eval_steps_per_second": 36.33,
28
+ "step": 90
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.585,
33
+ "eval_loss": 1.0062354803085327,
34
+ "eval_runtime": 0.6848,
35
+ "eval_samples_per_second": 292.067,
36
+ "eval_steps_per_second": 36.508,
37
+ "step": 135
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.61,
42
+ "eval_loss": 1.2404606342315674,
43
+ "eval_runtime": 0.6804,
44
+ "eval_samples_per_second": 293.958,
45
+ "eval_steps_per_second": 36.745,
46
+ "step": 180
47
+ },
48
+ {
49
+ "epoch": 4.0,
50
+ "eval_accuracy": 0.48,
51
+ "eval_loss": 0.9865803718566895,
52
+ "eval_runtime": 0.1322,
53
+ "eval_samples_per_second": 189.073,
54
+ "eval_steps_per_second": 30.252,
55
+ "step": 228
56
+ },
57
+ {
58
+ "epoch": 5.0,
59
+ "eval_accuracy": 0.52,
60
+ "eval_loss": 0.9823645949363708,
61
+ "eval_runtime": 0.1356,
62
+ "eval_samples_per_second": 184.391,
63
+ "eval_steps_per_second": 29.502,
64
+ "step": 285
65
+ },
66
+ {
67
+ "epoch": 3.0,
68
+ "eval_accuracy": 0.68,
69
+ "eval_loss": 0.6368125677108765,
70
+ "eval_runtime": 0.2587,
71
+ "eval_samples_per_second": 193.286,
72
+ "eval_steps_per_second": 27.06,
73
+ "step": 339
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.62,
78
+ "eval_loss": 0.7137138247489929,
79
+ "eval_runtime": 0.2437,
80
+ "eval_samples_per_second": 205.198,
81
+ "eval_steps_per_second": 28.728,
82
+ "step": 452
83
+ },
84
+ {
85
+ "epoch": 4.424778761061947,
86
+ "grad_norm": 65.47836303710938,
87
+ "learning_rate": 3.9828274442409566e-06,
88
+ "loss": 0.6097,
89
+ "step": 500
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "eval_accuracy": 0.62,
94
+ "eval_loss": 0.7127777338027954,
95
+ "eval_runtime": 0.2465,
96
+ "eval_samples_per_second": 202.826,
97
+ "eval_steps_per_second": 28.396,
98
+ "step": 565
99
+ },
100
+ {
101
+ "epoch": 4.0,
102
+ "eval_accuracy": 0.6933333333333334,
103
+ "eval_loss": 0.5826706290245056,
104
+ "eval_runtime": 0.3316,
105
+ "eval_samples_per_second": 226.159,
106
+ "eval_steps_per_second": 30.154,
107
+ "step": 676
108
+ },
109
+ {
110
+ "epoch": 5.0,
111
+ "eval_accuracy": 0.7333333333333333,
112
+ "eval_loss": 0.5467433333396912,
113
+ "eval_runtime": 0.3772,
114
+ "eval_samples_per_second": 198.811,
115
+ "eval_steps_per_second": 26.508,
116
+ "step": 845
117
+ },
118
+ {
119
+ "epoch": 4.0,
120
+ "eval_accuracy": 0.73,
121
+ "eval_loss": 0.5404043793678284,
122
+ "eval_runtime": 0.4345,
123
+ "eval_samples_per_second": 230.175,
124
+ "eval_steps_per_second": 29.923,
125
+ "step": 900
126
+ },
127
+ {
128
+ "epoch": 4.444444444444445,
129
+ "grad_norm": 155.99192810058594,
130
+ "learning_rate": 3.338904260121854e-06,
131
+ "loss": 0.5426,
132
+ "step": 1000
133
+ },
134
+ {
135
+ "epoch": 5.0,
136
+ "eval_accuracy": 0.74,
137
+ "eval_loss": 0.5299662947654724,
138
+ "eval_runtime": 0.4624,
139
+ "eval_samples_per_second": 216.241,
140
+ "eval_steps_per_second": 28.111,
141
+ "step": 1125
142
+ },
143
+ {
144
+ "epoch": 4.0,
145
+ "eval_accuracy": 0.784,
146
+ "eval_loss": 0.48202478885650635,
147
+ "eval_runtime": 0.5901,
148
+ "eval_samples_per_second": 211.822,
149
+ "eval_steps_per_second": 27.113,
150
+ "step": 1128
151
+ },
152
+ {
153
+ "epoch": 5.0,
154
+ "eval_accuracy": 0.792,
155
+ "eval_loss": 0.465172678232193,
156
+ "eval_runtime": 0.6074,
157
+ "eval_samples_per_second": 205.805,
158
+ "eval_steps_per_second": 26.343,
159
+ "step": 1410
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 1410,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 5,
166
+ "save_steps": 2000,
167
+ "stateful_callbacks": {
168
+ "EarlyStoppingCallback": {
169
+ "args": {
170
+ "early_stopping_patience": 3,
171
+ "early_stopping_threshold": 0.0001
172
+ },
173
+ "attributes": {
174
+ "early_stopping_patience_counter": 0
175
+ }
176
+ },
177
+ "TrainerControl": {
178
+ "args": {
179
+ "should_epoch_stop": false,
180
+ "should_evaluate": false,
181
+ "should_log": false,
182
+ "should_save": true,
183
+ "should_training_stop": true
184
+ },
185
+ "attributes": {}
186
+ }
187
+ },
188
+ "total_flos": 0.0,
189
+ "train_batch_size": 4,
190
+ "trial_name": null,
191
+ "trial_params": null
192
+ }
acq/max_var/reward/checkpoint-1410/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd245ee3e1b2a624212523487347e8211ca904df659f61ce1e69e1979243463d
3
+ size 5841
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759048592.move-hpc-02-gpu.60374.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21796ece8c6a144b4573536811ad686d917787873b60c79059162c23e9db493
3
+ size 6901
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759051979.move-hpc-02-gpu.60374.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb37a941bc22886a6e83cb4d02dc1c6af08ca71b8c6e7156f808925440f6267
3
+ size 6281
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759051989.move-hpc-02-gpu.60374.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73184594675e6e836f04a10c61ef6c1bb90d6be38d2bc4f6b7fc871238153ddc
3
+ size 769
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759055596.move-hpc-02-gpu.60374.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f241d63c87fca5186cb03cfbd12f7abee518b05de4763c4df6c59f7bdf3bfe
3
+ size 6893
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759055616.move-hpc-02-gpu.60374.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211ffbc15ec089bc234bba0e1fc0a62ae72139500f84f473df6246c3781bc1d5
3
+ size 769
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759059227.move-hpc-02-gpu.60374.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f030b874ac731ab973776ba143bea64f143a16ae1e9a5bbdb0156fa2c8134eef
3
+ size 6359
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759059245.move-hpc-02-gpu.60374.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7d8bc40dc083ab0cdd04df740b8c8b70e7e024086e65e1155182145517d337
3
+ size 769
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759062859.move-hpc-02-gpu.60374.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a523ef43f12c24720854b9d78464d3dd90edd8dde8b41a401ab81ac4bbafa4e
3
+ size 6570
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759062877.move-hpc-02-gpu.60374.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a73b927da542f858ded43322be6367f52dd5591d2eb07881441f9a3dd64c152
3
+ size 769
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759066406.move-hpc-02-gpu.60374.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b20f71f9ec4e71f2eb0f316aac48c8066f0c66a4069d7f4a9ba8aabcbef7671
3
+ size 6359
acq/max_var/reward/runs/Sep28_08-36-31_move-hpc-02-gpu/events.out.tfevents.1759066424.move-hpc-02-gpu.60374.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5dc6e42f8c9ee1c884be3cee45958b4fc1be0de3d687cb20a66f88c63eeffd
3
+ size 769
acq/mixed/reward/checkpoint-1128/chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '
2
+
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
acq/mixed/reward/checkpoint-1128/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForSequenceClassification"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 512,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 50277,
27
+ "partial_rotary_factor": 0.25,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000,
30
+ "rotary_emb_base": 10000,
31
+ "rotary_pct": 0.25,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.53.0",
35
+ "use_cache": true,
36
+ "use_parallel_residual": true,
37
+ "vocab_size": 50278
38
+ }
acq/mixed/reward/checkpoint-1128/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371b94960bc973ba9e0c370713b53f21e543c6f3355cbec3a45f205a061028f8
3
+ size 178643424
acq/mixed/reward/checkpoint-1128/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2121fe5a579ff57ef33fef55848873e4c4bb8ee79d6a262328aa826033ca11e
3
+ size 50468196
acq/mixed/reward/checkpoint-1128/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362339732edadb06d085cfb97531cf355dbaa1b01e2d50ac0f5423f271541fbb
3
+ size 14645
acq/mixed/reward/checkpoint-1128/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00cbbc95ae096b8b94a2cdc095a859c0ca1504f77f5a390cc5c3f88995dd3e4
3
+ size 1465