Hugging Face's logo

MAdAiLab
/
SLM_vs_LLM_experiments

Safetensors
Model card Files Community
akkky02 commited on
Commit
94eb8cd
•
1 Parent(s): 7e15240

Upload folder using huggingface_hub

Browse files
Files changed (38) hide show
  1. microsoft/phi_2_ledgar/README.md +93 -0
  2. microsoft/phi_2_ledgar/added_tokens.json +40 -0
  3. microsoft/phi_2_ledgar/all_results.json +23 -0
  4. microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json +40 -0
  5. microsoft/phi_2_ledgar/checkpoint-2800/config.json +241 -0
  6. microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  7. microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  8. microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt +3 -0
  9. microsoft/phi_2_ledgar/checkpoint-2800/latest +1 -0
  10. microsoft/phi_2_ledgar/checkpoint-2800/merges.txt +0 -0
  11. microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors +3 -0
  12. microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors +3 -0
  13. microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json +459 -0
  14. microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth +3 -0
  15. microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth +3 -0
  16. microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt +3 -0
  17. microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json +24 -0
  18. microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json +0 -0
  19. microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json +324 -0
  20. microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json +1113 -0
  21. microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin +3 -0
  22. microsoft/phi_2_ledgar/checkpoint-2800/vocab.json +0 -0
  23. microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py +604 -0
  24. microsoft/phi_2_ledgar/config.json +241 -0
  25. microsoft/phi_2_ledgar/eval_results.json +11 -0
  26. microsoft/phi_2_ledgar/merges.txt +0 -0
  27. microsoft/phi_2_ledgar/model-00001-of-00002.safetensors +3 -0
  28. microsoft/phi_2_ledgar/model-00002-of-00002.safetensors +3 -0
  29. microsoft/phi_2_ledgar/model.safetensors.index.json +459 -0
  30. microsoft/phi_2_ledgar/run.log +4 -0
  31. microsoft/phi_2_ledgar/special_tokens_map.json +24 -0
  32. microsoft/phi_2_ledgar/test_results.json +10 -0
  33. microsoft/phi_2_ledgar/tokenizer.json +0 -0
  34. microsoft/phi_2_ledgar/tokenizer_config.json +324 -0
  35. microsoft/phi_2_ledgar/train_results.json +8 -0
  36. microsoft/phi_2_ledgar/trainer_state.json +1122 -0
  37. microsoft/phi_2_ledgar/training_args.bin +3 -0
  38. microsoft/phi_2_ledgar/vocab.json +0 -0
microsoft/phi_2_ledgar/README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/phi-2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: phi_2_ledgar
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # phi_2_ledgar
17
+
18
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6120
21
+ - Accuracy: 0.826
22
+ - F1 Macro: 0.7355
23
+ - F1 Micro: 0.826
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-06
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 32
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 2
48
+ - total_train_batch_size: 64
49
+ - total_eval_batch_size: 64
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 3.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
58
+ | 3.6034 | 0.11 | 100 | 3.2114 | 0.337 | 0.1236 | 0.337 |
59
+ | 2.2678 | 0.21 | 200 | 1.9837 | 0.5623 | 0.3331 | 0.5623 |
60
+ | 1.4927 | 0.32 | 300 | 1.3369 | 0.6712 | 0.4884 | 0.6712 |
61
+ | 1.1518 | 0.43 | 400 | 1.0526 | 0.7243 | 0.5613 | 0.7243 |
62
+ | 1.1041 | 0.53 | 500 | 0.9305 | 0.7521 | 0.6206 | 0.7521 |
63
+ | 1.0144 | 0.64 | 600 | 0.9068 | 0.7574 | 0.6294 | 0.7574 |
64
+ | 0.9892 | 0.75 | 700 | 0.8712 | 0.7669 | 0.6430 | 0.7669 |
65
+ | 0.9972 | 0.85 | 800 | 0.8591 | 0.7675 | 0.6369 | 0.7675 |
66
+ | 0.8439 | 0.96 | 900 | 0.7895 | 0.7848 | 0.6835 | 0.7848 |
67
+ | 0.7409 | 1.07 | 1000 | 0.7614 | 0.7944 | 0.6809 | 0.7944 |
68
+ | 0.7627 | 1.17 | 1100 | 0.7539 | 0.7946 | 0.6810 | 0.7946 |
69
+ | 0.8065 | 1.28 | 1200 | 0.7289 | 0.8008 | 0.6945 | 0.8008 |
70
+ | 0.7359 | 1.39 | 1300 | 0.7254 | 0.8034 | 0.6976 | 0.8034 |
71
+ | 0.6525 | 1.49 | 1400 | 0.7073 | 0.8065 | 0.7050 | 0.8065 |
72
+ | 0.7359 | 1.6 | 1500 | 0.7206 | 0.8033 | 0.6949 | 0.8033 |
73
+ | 0.7291 | 1.71 | 1600 | 0.6924 | 0.8089 | 0.7066 | 0.8089 |
74
+ | 0.7072 | 1.81 | 1700 | 0.6764 | 0.8102 | 0.7070 | 0.8102 |
75
+ | 0.6688 | 1.92 | 1800 | 0.6546 | 0.814 | 0.7128 | 0.814 |
76
+ | 0.6253 | 2.03 | 1900 | 0.6506 | 0.8158 | 0.7059 | 0.8158 |
77
+ | 0.6044 | 2.13 | 2000 | 0.6603 | 0.8155 | 0.7165 | 0.8155 |
78
+ | 0.6414 | 2.24 | 2100 | 0.6435 | 0.8138 | 0.7185 | 0.8138 |
79
+ | 0.6115 | 2.35 | 2200 | 0.6368 | 0.8216 | 0.7280 | 0.8216 |
80
+ | 0.6331 | 2.45 | 2300 | 0.6273 | 0.8208 | 0.7251 | 0.8208 |
81
+ | 0.608 | 2.56 | 2400 | 0.6252 | 0.8232 | 0.7286 | 0.8232 |
82
+ | 0.5879 | 2.67 | 2500 | 0.6172 | 0.8241 | 0.7308 | 0.8241 |
83
+ | 0.6056 | 2.77 | 2600 | 0.6157 | 0.8257 | 0.7346 | 0.8257 |
84
+ | 0.5711 | 2.88 | 2700 | 0.6129 | 0.8253 | 0.7341 | 0.8253 |
85
+ | 0.5802 | 2.99 | 2800 | 0.6120 | 0.826 | 0.7355 | 0.826 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.39.0.dev0
91
+ - Pytorch 2.2.1+cu121
92
+ - Datasets 2.18.0
93
+ - Tokenizers 0.15.2
microsoft/phi_2_ledgar/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
microsoft/phi_2_ledgar/all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.826,
4
+ "eval_f1_macro": 0.7355084015446216,
5
+ "eval_f1_micro": 0.826,
6
+ "eval_loss": 0.6120218634605408,
7
+ "eval_runtime": 46.3584,
8
+ "eval_samples": 10000,
9
+ "eval_samples_per_second": 215.711,
10
+ "eval_steps_per_second": 3.387,
11
+ "test_accuracy": 0.8311,
12
+ "test_f1_macro": 0.7306467958794756,
13
+ "test_f1_micro": 0.8311,
14
+ "test_loss": 0.6224531531333923,
15
+ "test_runtime": 47.3558,
16
+ "test_samples_per_second": 211.168,
17
+ "test_steps_per_second": 3.315,
18
+ "train_loss": 0.9835220694796108,
19
+ "train_runtime": 6489.4436,
20
+ "train_samples": 60000,
21
+ "train_samples_per_second": 27.737,
22
+ "train_steps_per_second": 0.434
23
+ }
microsoft/phi_2_ledgar/checkpoint-2800/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
microsoft/phi_2_ledgar/checkpoint-2800/config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "architectures": [
4
+ "PhiForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "finetuning_task": "text-classification",
15
+ "hidden_act": "gelu_new",
16
+ "hidden_size": 2560,
17
+ "id2label": {
18
+ "0": "0",
19
+ "1": "1",
20
+ "2": "10",
21
+ "3": "11",
22
+ "4": "12",
23
+ "5": "13",
24
+ "6": "14",
25
+ "7": "15",
26
+ "8": "16",
27
+ "9": "17",
28
+ "10": "18",
29
+ "11": "19",
30
+ "12": "2",
31
+ "13": "20",
32
+ "14": "21",
33
+ "15": "22",
34
+ "16": "23",
35
+ "17": "24",
36
+ "18": "25",
37
+ "19": "26",
38
+ "20": "27",
39
+ "21": "28",
40
+ "22": "29",
41
+ "23": "3",
42
+ "24": "30",
43
+ "25": "31",
44
+ "26": "32",
45
+ "27": "33",
46
+ "28": "34",
47
+ "29": "35",
48
+ "30": "36",
49
+ "31": "37",
50
+ "32": "38",
51
+ "33": "39",
52
+ "34": "4",
53
+ "35": "40",
54
+ "36": "41",
55
+ "37": "42",
56
+ "38": "43",
57
+ "39": "44",
58
+ "40": "45",
59
+ "41": "46",
60
+ "42": "47",
61
+ "43": "48",
62
+ "44": "49",
63
+ "45": "5",
64
+ "46": "50",
65
+ "47": "51",
66
+ "48": "52",
67
+ "49": "53",
68
+ "50": "54",
69
+ "51": "55",
70
+ "52": "56",
71
+ "53": "57",
72
+ "54": "58",
73
+ "55": "59",
74
+ "56": "6",
75
+ "57": "60",
76
+ "58": "61",
77
+ "59": "62",
78
+ "60": "63",
79
+ "61": "64",
80
+ "62": "65",
81
+ "63": "66",
82
+ "64": "67",
83
+ "65": "68",
84
+ "66": "69",
85
+ "67": "7",
86
+ "68": "70",
87
+ "69": "71",
88
+ "70": "72",
89
+ "71": "73",
90
+ "72": "74",
91
+ "73": "75",
92
+ "74": "76",
93
+ "75": "77",
94
+ "76": "78",
95
+ "77": "79",
96
+ "78": "8",
97
+ "79": "80",
98
+ "80": "81",
99
+ "81": "82",
100
+ "82": "83",
101
+ "83": "84",
102
+ "84": "85",
103
+ "85": "86",
104
+ "86": "87",
105
+ "87": "88",
106
+ "88": "89",
107
+ "89": "9",
108
+ "90": "90",
109
+ "91": "91",
110
+ "92": "92",
111
+ "93": "93",
112
+ "94": "94",
113
+ "95": "95",
114
+ "96": "96",
115
+ "97": "97",
116
+ "98": "98",
117
+ "99": "99"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 10240,
121
+ "label2id": {
122
+ "0": 0,
123
+ "1": 1,
124
+ "10": 2,
125
+ "11": 3,
126
+ "12": 4,
127
+ "13": 5,
128
+ "14": 6,
129
+ "15": 7,
130
+ "16": 8,
131
+ "17": 9,
132
+ "18": 10,
133
+ "19": 11,
134
+ "2": 12,
135
+ "20": 13,
136
+ "21": 14,
137
+ "22": 15,
138
+ "23": 16,
139
+ "24": 17,
140
+ "25": 18,
141
+ "26": 19,
142
+ "27": 20,
143
+ "28": 21,
144
+ "29": 22,
145
+ "3": 23,
146
+ "30": 24,
147
+ "31": 25,
148
+ "32": 26,
149
+ "33": 27,
150
+ "34": 28,
151
+ "35": 29,
152
+ "36": 30,
153
+ "37": 31,
154
+ "38": 32,
155
+ "39": 33,
156
+ "4": 34,
157
+ "40": 35,
158
+ "41": 36,
159
+ "42": 37,
160
+ "43": 38,
161
+ "44": 39,
162
+ "45": 40,
163
+ "46": 41,
164
+ "47": 42,
165
+ "48": 43,
166
+ "49": 44,
167
+ "5": 45,
168
+ "50": 46,
169
+ "51": 47,
170
+ "52": 48,
171
+ "53": 49,
172
+ "54": 50,
173
+ "55": 51,
174
+ "56": 52,
175
+ "57": 53,
176
+ "58": 54,
177
+ "59": 55,
178
+ "6": 56,
179
+ "60": 57,
180
+ "61": 58,
181
+ "62": 59,
182
+ "63": 60,
183
+ "64": 61,
184
+ "65": 62,
185
+ "66": 63,
186
+ "67": 64,
187
+ "68": 65,
188
+ "69": 66,
189
+ "7": 67,
190
+ "70": 68,
191
+ "71": 69,
192
+ "72": 70,
193
+ "73": 71,
194
+ "74": 72,
195
+ "75": 73,
196
+ "76": 74,
197
+ "77": 75,
198
+ "78": 76,
199
+ "79": 77,
200
+ "8": 78,
201
+ "80": 79,
202
+ "81": 80,
203
+ "82": 81,
204
+ "83": 82,
205
+ "84": 83,
206
+ "85": 84,
207
+ "86": 85,
208
+ "87": 86,
209
+ "88": 87,
210
+ "89": 88,
211
+ "9": 89,
212
+ "90": 90,
213
+ "91": 91,
214
+ "92": 92,
215
+ "93": 93,
216
+ "94": 94,
217
+ "95": 95,
218
+ "96": 96,
219
+ "97": 97,
220
+ "98": 98,
221
+ "99": 99
222
+ },
223
+ "layer_norm_eps": 1e-05,
224
+ "max_position_embeddings": 2048,
225
+ "model_type": "phi",
226
+ "num_attention_heads": 32,
227
+ "num_hidden_layers": 32,
228
+ "num_key_value_heads": 32,
229
+ "pad_token_id": 50256,
230
+ "partial_rotary_factor": 0.4,
231
+ "problem_type": "single_label_classification",
232
+ "qk_layernorm": false,
233
+ "resid_pdrop": 0.1,
234
+ "rope_scaling": null,
235
+ "rope_theta": 10000.0,
236
+ "tie_word_embeddings": false,
237
+ "torch_dtype": "bfloat16",
238
+ "transformers_version": "4.39.0.dev0",
239
+ "use_cache": true,
240
+ "vocab_size": 50295
241
+ }
microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09041f5d10231956df543f7b49d4426f62b6e4f4e443867206fa003f398404a5
3
+ size 15879020748
microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904baf68664932779da8ff3ff90ac0e29fd6299dca4b22ef421b8c1d2a60c3ef
3
+ size 15879021324
microsoft/phi_2_ledgar/checkpoint-2800/global_step2800/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d10f029e96c6ed4a858f8826674205a2454765a8922b6909b8f58db0e2203a
3
+ size 5293114680
microsoft/phi_2_ledgar/checkpoint-2800/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step2800
microsoft/phi_2_ledgar/checkpoint-2800/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
microsoft/phi_2_ledgar/checkpoint-2800/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae73b51441793d522ad559358cf9079e99146b65973000a15160116545e8f7b4
3
+ size 4990951248
microsoft/phi_2_ledgar/checkpoint-2800/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a147716a17a72dea3519e435ba913dfbe27494f393627a3ba1562fd349409a81
3
+ size 302098480
microsoft/phi_2_ledgar/checkpoint-2800/model.safetensors.index.json ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5292999680
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
8
+ "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
280
+ "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
298
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
304
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
310
+ "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
312
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
322
+ "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
324
+ "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
326
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
346
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
356
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
358
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
457
+ "score.weight": "model-00002-of-00002.safetensors"
458
+ }
459
+ }
microsoft/phi_2_ledgar/checkpoint-2800/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1849dec8c5d9b97301988e37b73406a43a2c26c6e58dd6744998c9b5fd349995
3
+ size 14512
microsoft/phi_2_ledgar/checkpoint-2800/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15657df1db23ea9022753849d573d625454a71daf2e7671466f27d94ecbffa5
3
+ size 14512
microsoft/phi_2_ledgar/checkpoint-2800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a12edfee260015fb8a9dfdd91c719ef6c8fac469ab557f6eb6345dc6d21f36c
3
+ size 1064
microsoft/phi_2_ledgar/checkpoint-2800/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
microsoft/phi_2_ledgar/checkpoint-2800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
microsoft/phi_2_ledgar/checkpoint-2800/tokenizer_config.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
324
+ }
microsoft/phi_2_ledgar/checkpoint-2800/trainer_state.json ADDED
@@ -0,0 +1,1113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6120218634605408,
3
+ "best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/microsoft/phi_2_ledgar/checkpoint-2800",
4
+ "epoch": 2.9850746268656714,
5
+ "eval_steps": 100,
6
+ "global_step": 2800,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "grad_norm": 278.5504455566406,
14
+ "learning_rate": 4.9555792466240235e-06,
15
+ "loss": 4.8556,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 332.1685485839844,
21
+ "learning_rate": 4.911158493248046e-06,
22
+ "loss": 4.2381,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.08,
27
+ "grad_norm": 238.07369995117188,
28
+ "learning_rate": 4.866737739872069e-06,
29
+ "loss": 4.0038,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.11,
34
+ "grad_norm": 152.84237670898438,
35
+ "learning_rate": 4.822316986496091e-06,
36
+ "loss": 3.6034,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.11,
41
+ "eval_accuracy": 0.337,
42
+ "eval_f1_macro": 0.12358690595802334,
43
+ "eval_f1_micro": 0.337,
44
+ "eval_loss": 3.211400032043457,
45
+ "eval_runtime": 47.3513,
46
+ "eval_samples_per_second": 211.188,
47
+ "eval_steps_per_second": 3.316,
48
+ "step": 100
49
+ },
50
+ {
51
+ "epoch": 0.13,
52
+ "grad_norm": 143.5316619873047,
53
+ "learning_rate": 4.777896233120114e-06,
54
+ "loss": 3.1831,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.16,
59
+ "grad_norm": 152.6884765625,
60
+ "learning_rate": 4.733475479744136e-06,
61
+ "loss": 2.9609,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "grad_norm": 116.26598358154297,
67
+ "learning_rate": 4.6890547263681595e-06,
68
+ "loss": 2.4773,
69
+ "step": 175
70
+ },
71
+ {
72
+ "epoch": 0.21,
73
+ "grad_norm": 102.64595031738281,
74
+ "learning_rate": 4.644633972992183e-06,
75
+ "loss": 2.2678,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 0.21,
80
+ "eval_accuracy": 0.5623,
81
+ "eval_f1_macro": 0.3331251034728065,
82
+ "eval_f1_micro": 0.5623,
83
+ "eval_loss": 1.9837249517440796,
84
+ "eval_runtime": 47.4491,
85
+ "eval_samples_per_second": 210.752,
86
+ "eval_steps_per_second": 3.309,
87
+ "step": 200
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "grad_norm": 107.59564208984375,
92
+ "learning_rate": 4.600213219616206e-06,
93
+ "loss": 2.0387,
94
+ "step": 225
95
+ },
96
+ {
97
+ "epoch": 0.27,
98
+ "grad_norm": 129.82203674316406,
99
+ "learning_rate": 4.555792466240228e-06,
100
+ "loss": 1.7772,
101
+ "step": 250
102
+ },
103
+ {
104
+ "epoch": 0.29,
105
+ "grad_norm": 106.58737182617188,
106
+ "learning_rate": 4.51137171286425e-06,
107
+ "loss": 1.5959,
108
+ "step": 275
109
+ },
110
+ {
111
+ "epoch": 0.32,
112
+ "grad_norm": 219.3987274169922,
113
+ "learning_rate": 4.466950959488273e-06,
114
+ "loss": 1.4927,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.32,
119
+ "eval_accuracy": 0.6712,
120
+ "eval_f1_macro": 0.48839865479998884,
121
+ "eval_f1_micro": 0.6712,
122
+ "eval_loss": 1.3369125127792358,
123
+ "eval_runtime": 47.4603,
124
+ "eval_samples_per_second": 210.702,
125
+ "eval_steps_per_second": 3.308,
126
+ "step": 300
127
+ },
128
+ {
129
+ "epoch": 0.35,
130
+ "grad_norm": 62.788822174072266,
131
+ "learning_rate": 4.422530206112296e-06,
132
+ "loss": 1.4203,
133
+ "step": 325
134
+ },
135
+ {
136
+ "epoch": 0.37,
137
+ "grad_norm": 63.6900634765625,
138
+ "learning_rate": 4.378109452736319e-06,
139
+ "loss": 1.2841,
140
+ "step": 350
141
+ },
142
+ {
143
+ "epoch": 0.4,
144
+ "grad_norm": 75.33383178710938,
145
+ "learning_rate": 4.333688699360342e-06,
146
+ "loss": 1.1642,
147
+ "step": 375
148
+ },
149
+ {
150
+ "epoch": 0.43,
151
+ "grad_norm": 89.42117309570312,
152
+ "learning_rate": 4.289267945984365e-06,
153
+ "loss": 1.1518,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 0.43,
158
+ "eval_accuracy": 0.7243,
159
+ "eval_f1_macro": 0.5613056174383468,
160
+ "eval_f1_micro": 0.7243,
161
+ "eval_loss": 1.052606225013733,
162
+ "eval_runtime": 47.3838,
163
+ "eval_samples_per_second": 211.043,
164
+ "eval_steps_per_second": 3.313,
165
+ "step": 400
166
+ },
167
+ {
168
+ "epoch": 0.45,
169
+ "grad_norm": 74.13993072509766,
170
+ "learning_rate": 4.244847192608387e-06,
171
+ "loss": 1.135,
172
+ "step": 425
173
+ },
174
+ {
175
+ "epoch": 0.48,
176
+ "grad_norm": 80.19258117675781,
177
+ "learning_rate": 4.200426439232409e-06,
178
+ "loss": 1.176,
179
+ "step": 450
180
+ },
181
+ {
182
+ "epoch": 0.51,
183
+ "grad_norm": 70.83063507080078,
184
+ "learning_rate": 4.156005685856432e-06,
185
+ "loss": 1.1386,
186
+ "step": 475
187
+ },
188
+ {
189
+ "epoch": 0.53,
190
+ "grad_norm": 109.83588409423828,
191
+ "learning_rate": 4.1115849324804554e-06,
192
+ "loss": 1.1041,
193
+ "step": 500
194
+ },
195
+ {
196
+ "epoch": 0.53,
197
+ "eval_accuracy": 0.7521,
198
+ "eval_f1_macro": 0.6206030644902993,
199
+ "eval_f1_micro": 0.7521,
200
+ "eval_loss": 0.9304812550544739,
201
+ "eval_runtime": 47.4284,
202
+ "eval_samples_per_second": 210.844,
203
+ "eval_steps_per_second": 3.31,
204
+ "step": 500
205
+ },
206
+ {
207
+ "epoch": 0.56,
208
+ "grad_norm": 51.40995788574219,
209
+ "learning_rate": 4.067164179104478e-06,
210
+ "loss": 0.9872,
211
+ "step": 525
212
+ },
213
+ {
214
+ "epoch": 0.59,
215
+ "grad_norm": 75.6723861694336,
216
+ "learning_rate": 4.022743425728501e-06,
217
+ "loss": 0.9832,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 0.61,
222
+ "grad_norm": 86.0229721069336,
223
+ "learning_rate": 3.978322672352524e-06,
224
+ "loss": 0.9485,
225
+ "step": 575
226
+ },
227
+ {
228
+ "epoch": 0.64,
229
+ "grad_norm": 113.96233367919922,
230
+ "learning_rate": 3.933901918976546e-06,
231
+ "loss": 1.0144,
232
+ "step": 600
233
+ },
234
+ {
235
+ "epoch": 0.64,
236
+ "eval_accuracy": 0.7574,
237
+ "eval_f1_macro": 0.6294250374822845,
238
+ "eval_f1_micro": 0.7574,
239
+ "eval_loss": 0.9067593812942505,
240
+ "eval_runtime": 47.4873,
241
+ "eval_samples_per_second": 210.583,
242
+ "eval_steps_per_second": 3.306,
243
+ "step": 600
244
+ },
245
+ {
246
+ "epoch": 0.67,
247
+ "grad_norm": 77.80159759521484,
248
+ "learning_rate": 3.889481165600569e-06,
249
+ "loss": 1.0435,
250
+ "step": 625
251
+ },
252
+ {
253
+ "epoch": 0.69,
254
+ "grad_norm": 77.97108459472656,
255
+ "learning_rate": 3.8450604122245914e-06,
256
+ "loss": 0.9593,
257
+ "step": 650
258
+ },
259
+ {
260
+ "epoch": 0.72,
261
+ "grad_norm": 68.20707702636719,
262
+ "learning_rate": 3.8006396588486145e-06,
263
+ "loss": 0.9818,
264
+ "step": 675
265
+ },
266
+ {
267
+ "epoch": 0.75,
268
+ "grad_norm": 103.11054229736328,
269
+ "learning_rate": 3.756218905472637e-06,
270
+ "loss": 0.9892,
271
+ "step": 700
272
+ },
273
+ {
274
+ "epoch": 0.75,
275
+ "eval_accuracy": 0.7669,
276
+ "eval_f1_macro": 0.642987522646621,
277
+ "eval_f1_micro": 0.7669,
278
+ "eval_loss": 0.8712124824523926,
279
+ "eval_runtime": 47.4988,
280
+ "eval_samples_per_second": 210.531,
281
+ "eval_steps_per_second": 3.305,
282
+ "step": 700
283
+ },
284
+ {
285
+ "epoch": 0.77,
286
+ "grad_norm": 88.3270263671875,
287
+ "learning_rate": 3.71179815209666e-06,
288
+ "loss": 0.8937,
289
+ "step": 725
290
+ },
291
+ {
292
+ "epoch": 0.8,
293
+ "grad_norm": 67.907958984375,
294
+ "learning_rate": 3.667377398720683e-06,
295
+ "loss": 0.9788,
296
+ "step": 750
297
+ },
298
+ {
299
+ "epoch": 0.83,
300
+ "grad_norm": 68.60499572753906,
301
+ "learning_rate": 3.622956645344705e-06,
302
+ "loss": 0.9459,
303
+ "step": 775
304
+ },
305
+ {
306
+ "epoch": 0.85,
307
+ "grad_norm": 71.7964859008789,
308
+ "learning_rate": 3.578535891968728e-06,
309
+ "loss": 0.9972,
310
+ "step": 800
311
+ },
312
+ {
313
+ "epoch": 0.85,
314
+ "eval_accuracy": 0.7675,
315
+ "eval_f1_macro": 0.6369038817239384,
316
+ "eval_f1_micro": 0.7675,
317
+ "eval_loss": 0.8591374754905701,
318
+ "eval_runtime": 47.4288,
319
+ "eval_samples_per_second": 210.842,
320
+ "eval_steps_per_second": 3.31,
321
+ "step": 800
322
+ },
323
+ {
324
+ "epoch": 0.88,
325
+ "grad_norm": 99.17341613769531,
326
+ "learning_rate": 3.534115138592751e-06,
327
+ "loss": 0.9663,
328
+ "step": 825
329
+ },
330
+ {
331
+ "epoch": 0.91,
332
+ "grad_norm": 198.6553955078125,
333
+ "learning_rate": 3.4896943852167736e-06,
334
+ "loss": 0.8617,
335
+ "step": 850
336
+ },
337
+ {
338
+ "epoch": 0.93,
339
+ "grad_norm": 82.58099365234375,
340
+ "learning_rate": 3.4452736318407963e-06,
341
+ "loss": 0.8735,
342
+ "step": 875
343
+ },
344
+ {
345
+ "epoch": 0.96,
346
+ "grad_norm": 63.692623138427734,
347
+ "learning_rate": 3.4008528784648194e-06,
348
+ "loss": 0.8439,
349
+ "step": 900
350
+ },
351
+ {
352
+ "epoch": 0.96,
353
+ "eval_accuracy": 0.7848,
354
+ "eval_f1_macro": 0.6834829058415216,
355
+ "eval_f1_micro": 0.7848,
356
+ "eval_loss": 0.7894874811172485,
357
+ "eval_runtime": 47.4489,
358
+ "eval_samples_per_second": 210.753,
359
+ "eval_steps_per_second": 3.309,
360
+ "step": 900
361
+ },
362
+ {
363
+ "epoch": 0.99,
364
+ "grad_norm": 78.88030242919922,
365
+ "learning_rate": 3.3564321250888416e-06,
366
+ "loss": 0.8582,
367
+ "step": 925
368
+ },
369
+ {
370
+ "epoch": 1.01,
371
+ "grad_norm": 45.49142837524414,
372
+ "learning_rate": 3.3120113717128643e-06,
373
+ "loss": 0.8621,
374
+ "step": 950
375
+ },
376
+ {
377
+ "epoch": 1.04,
378
+ "grad_norm": 37.98048400878906,
379
+ "learning_rate": 3.2675906183368874e-06,
380
+ "loss": 0.8396,
381
+ "step": 975
382
+ },
383
+ {
384
+ "epoch": 1.07,
385
+ "grad_norm": 37.72966384887695,
386
+ "learning_rate": 3.22316986496091e-06,
387
+ "loss": 0.7409,
388
+ "step": 1000
389
+ },
390
+ {
391
+ "epoch": 1.07,
392
+ "eval_accuracy": 0.7944,
393
+ "eval_f1_macro": 0.6808979493082343,
394
+ "eval_f1_micro": 0.7944,
395
+ "eval_loss": 0.7614499926567078,
396
+ "eval_runtime": 47.4823,
397
+ "eval_samples_per_second": 210.605,
398
+ "eval_steps_per_second": 3.306,
399
+ "step": 1000
400
+ },
401
+ {
402
+ "epoch": 1.09,
403
+ "grad_norm": 57.926578521728516,
404
+ "learning_rate": 3.1787491115849327e-06,
405
+ "loss": 0.7475,
406
+ "step": 1025
407
+ },
408
+ {
409
+ "epoch": 1.12,
410
+ "grad_norm": 86.9485855102539,
411
+ "learning_rate": 3.1343283582089558e-06,
412
+ "loss": 0.7197,
413
+ "step": 1050
414
+ },
415
+ {
416
+ "epoch": 1.15,
417
+ "grad_norm": 54.83045959472656,
418
+ "learning_rate": 3.0899076048329785e-06,
419
+ "loss": 0.8314,
420
+ "step": 1075
421
+ },
422
+ {
423
+ "epoch": 1.17,
424
+ "grad_norm": 68.1777114868164,
425
+ "learning_rate": 3.0454868514570007e-06,
426
+ "loss": 0.7627,
427
+ "step": 1100
428
+ },
429
+ {
430
+ "epoch": 1.17,
431
+ "eval_accuracy": 0.7946,
432
+ "eval_f1_macro": 0.6809735037021439,
433
+ "eval_f1_micro": 0.7946,
434
+ "eval_loss": 0.7538655996322632,
435
+ "eval_runtime": 47.4181,
436
+ "eval_samples_per_second": 210.89,
437
+ "eval_steps_per_second": 3.311,
438
+ "step": 1100
439
+ },
440
+ {
441
+ "epoch": 1.2,
442
+ "grad_norm": 31.217445373535156,
443
+ "learning_rate": 3.0010660980810234e-06,
444
+ "loss": 0.7501,
445
+ "step": 1125
446
+ },
447
+ {
448
+ "epoch": 1.23,
449
+ "grad_norm": 38.76744842529297,
450
+ "learning_rate": 2.9566453447050464e-06,
451
+ "loss": 0.6884,
452
+ "step": 1150
453
+ },
454
+ {
455
+ "epoch": 1.25,
456
+ "grad_norm": 50.481388092041016,
457
+ "learning_rate": 2.912224591329069e-06,
458
+ "loss": 0.6911,
459
+ "step": 1175
460
+ },
461
+ {
462
+ "epoch": 1.28,
463
+ "grad_norm": 54.91836929321289,
464
+ "learning_rate": 2.867803837953092e-06,
465
+ "loss": 0.8065,
466
+ "step": 1200
467
+ },
468
+ {
469
+ "epoch": 1.28,
470
+ "eval_accuracy": 0.8008,
471
+ "eval_f1_macro": 0.6945223141031294,
472
+ "eval_f1_micro": 0.8008,
473
+ "eval_loss": 0.7289281487464905,
474
+ "eval_runtime": 47.4458,
475
+ "eval_samples_per_second": 210.767,
476
+ "eval_steps_per_second": 3.309,
477
+ "step": 1200
478
+ },
479
+ {
480
+ "epoch": 1.31,
481
+ "grad_norm": 72.01395416259766,
482
+ "learning_rate": 2.823383084577115e-06,
483
+ "loss": 0.8075,
484
+ "step": 1225
485
+ },
486
+ {
487
+ "epoch": 1.33,
488
+ "grad_norm": 83.60379791259766,
489
+ "learning_rate": 2.7789623312011375e-06,
490
+ "loss": 0.8068,
491
+ "step": 1250
492
+ },
493
+ {
494
+ "epoch": 1.36,
495
+ "grad_norm": 51.42044448852539,
496
+ "learning_rate": 2.7345415778251598e-06,
497
+ "loss": 0.7549,
498
+ "step": 1275
499
+ },
500
+ {
501
+ "epoch": 1.39,
502
+ "grad_norm": 44.68650436401367,
503
+ "learning_rate": 2.690120824449183e-06,
504
+ "loss": 0.7359,
505
+ "step": 1300
506
+ },
507
+ {
508
+ "epoch": 1.39,
509
+ "eval_accuracy": 0.8034,
510
+ "eval_f1_macro": 0.6975565105528009,
511
+ "eval_f1_micro": 0.8034,
512
+ "eval_loss": 0.7253593802452087,
513
+ "eval_runtime": 47.5217,
514
+ "eval_samples_per_second": 210.43,
515
+ "eval_steps_per_second": 3.304,
516
+ "step": 1300
517
+ },
518
+ {
519
+ "epoch": 1.41,
520
+ "grad_norm": 56.39244842529297,
521
+ "learning_rate": 2.6457000710732055e-06,
522
+ "loss": 0.7201,
523
+ "step": 1325
524
+ },
525
+ {
526
+ "epoch": 1.44,
527
+ "grad_norm": 70.84113311767578,
528
+ "learning_rate": 2.601279317697228e-06,
529
+ "loss": 0.7346,
530
+ "step": 1350
531
+ },
532
+ {
533
+ "epoch": 1.47,
534
+ "grad_norm": 69.2415542602539,
535
+ "learning_rate": 2.5568585643212513e-06,
536
+ "loss": 0.6693,
537
+ "step": 1375
538
+ },
539
+ {
540
+ "epoch": 1.49,
541
+ "grad_norm": 50.06897735595703,
542
+ "learning_rate": 2.512437810945274e-06,
543
+ "loss": 0.6525,
544
+ "step": 1400
545
+ },
546
+ {
547
+ "epoch": 1.49,
548
+ "eval_accuracy": 0.8065,
549
+ "eval_f1_macro": 0.7050317065636842,
550
+ "eval_f1_micro": 0.8065,
551
+ "eval_loss": 0.7072968482971191,
552
+ "eval_runtime": 47.4893,
553
+ "eval_samples_per_second": 210.574,
554
+ "eval_steps_per_second": 3.306,
555
+ "step": 1400
556
+ },
557
+ {
558
+ "epoch": 1.52,
559
+ "grad_norm": 45.797054290771484,
560
+ "learning_rate": 2.4680170575692966e-06,
561
+ "loss": 0.7271,
562
+ "step": 1425
563
+ },
564
+ {
565
+ "epoch": 1.55,
566
+ "grad_norm": 46.304473876953125,
567
+ "learning_rate": 2.4235963041933193e-06,
568
+ "loss": 0.8033,
569
+ "step": 1450
570
+ },
571
+ {
572
+ "epoch": 1.57,
573
+ "grad_norm": 80.502685546875,
574
+ "learning_rate": 2.379175550817342e-06,
575
+ "loss": 0.7464,
576
+ "step": 1475
577
+ },
578
+ {
579
+ "epoch": 1.6,
580
+ "grad_norm": 89.19364166259766,
581
+ "learning_rate": 2.3347547974413646e-06,
582
+ "loss": 0.7359,
583
+ "step": 1500
584
+ },
585
+ {
586
+ "epoch": 1.6,
587
+ "eval_accuracy": 0.8033,
588
+ "eval_f1_macro": 0.6948589139841357,
589
+ "eval_f1_micro": 0.8033,
590
+ "eval_loss": 0.720634400844574,
591
+ "eval_runtime": 47.454,
592
+ "eval_samples_per_second": 210.73,
593
+ "eval_steps_per_second": 3.308,
594
+ "step": 1500
595
+ },
596
+ {
597
+ "epoch": 1.63,
598
+ "grad_norm": 36.966548919677734,
599
+ "learning_rate": 2.2903340440653877e-06,
600
+ "loss": 0.697,
601
+ "step": 1525
602
+ },
603
+ {
604
+ "epoch": 1.65,
605
+ "grad_norm": 37.08382797241211,
606
+ "learning_rate": 2.24591329068941e-06,
607
+ "loss": 0.6736,
608
+ "step": 1550
609
+ },
610
+ {
611
+ "epoch": 1.68,
612
+ "grad_norm": 37.009403228759766,
613
+ "learning_rate": 2.201492537313433e-06,
614
+ "loss": 0.6441,
615
+ "step": 1575
616
+ },
617
+ {
618
+ "epoch": 1.71,
619
+ "grad_norm": 29.34271240234375,
620
+ "learning_rate": 2.1570717839374557e-06,
621
+ "loss": 0.7291,
622
+ "step": 1600
623
+ },
624
+ {
625
+ "epoch": 1.71,
626
+ "eval_accuracy": 0.8089,
627
+ "eval_f1_macro": 0.7065968196696667,
628
+ "eval_f1_micro": 0.8089,
629
+ "eval_loss": 0.6923750042915344,
630
+ "eval_runtime": 47.4715,
631
+ "eval_samples_per_second": 210.653,
632
+ "eval_steps_per_second": 3.307,
633
+ "step": 1600
634
+ },
635
+ {
636
+ "epoch": 1.73,
637
+ "grad_norm": 43.28564453125,
638
+ "learning_rate": 2.112651030561479e-06,
639
+ "loss": 0.7153,
640
+ "step": 1625
641
+ },
642
+ {
643
+ "epoch": 1.76,
644
+ "grad_norm": 27.64020347595215,
645
+ "learning_rate": 2.068230277185501e-06,
646
+ "loss": 0.6721,
647
+ "step": 1650
648
+ },
649
+ {
650
+ "epoch": 1.79,
651
+ "grad_norm": 46.75600051879883,
652
+ "learning_rate": 2.023809523809524e-06,
653
+ "loss": 0.6566,
654
+ "step": 1675
655
+ },
656
+ {
657
+ "epoch": 1.81,
658
+ "grad_norm": 34.07355499267578,
659
+ "learning_rate": 1.979388770433547e-06,
660
+ "loss": 0.7072,
661
+ "step": 1700
662
+ },
663
+ {
664
+ "epoch": 1.81,
665
+ "eval_accuracy": 0.8102,
666
+ "eval_f1_macro": 0.7070176051219198,
667
+ "eval_f1_micro": 0.8102,
668
+ "eval_loss": 0.6763781309127808,
669
+ "eval_runtime": 47.526,
670
+ "eval_samples_per_second": 210.411,
671
+ "eval_steps_per_second": 3.303,
672
+ "step": 1700
673
+ },
674
+ {
675
+ "epoch": 1.84,
676
+ "grad_norm": 43.36367416381836,
677
+ "learning_rate": 1.9349680170575695e-06,
678
+ "loss": 0.7289,
679
+ "step": 1725
680
+ },
681
+ {
682
+ "epoch": 1.87,
683
+ "grad_norm": 34.61235046386719,
684
+ "learning_rate": 1.8905472636815921e-06,
685
+ "loss": 0.6787,
686
+ "step": 1750
687
+ },
688
+ {
689
+ "epoch": 1.89,
690
+ "grad_norm": 44.31460952758789,
691
+ "learning_rate": 1.846126510305615e-06,
692
+ "loss": 0.7188,
693
+ "step": 1775
694
+ },
695
+ {
696
+ "epoch": 1.92,
697
+ "grad_norm": 53.3677864074707,
698
+ "learning_rate": 1.8017057569296375e-06,
699
+ "loss": 0.6688,
700
+ "step": 1800
701
+ },
702
+ {
703
+ "epoch": 1.92,
704
+ "eval_accuracy": 0.814,
705
+ "eval_f1_macro": 0.7128286594201773,
706
+ "eval_f1_micro": 0.814,
707
+ "eval_loss": 0.6546062231063843,
708
+ "eval_runtime": 47.5163,
709
+ "eval_samples_per_second": 210.454,
710
+ "eval_steps_per_second": 3.304,
711
+ "step": 1800
712
+ },
713
+ {
714
+ "epoch": 1.95,
715
+ "grad_norm": 37.4492073059082,
716
+ "learning_rate": 1.7572850035536603e-06,
717
+ "loss": 0.7817,
718
+ "step": 1825
719
+ },
720
+ {
721
+ "epoch": 1.97,
722
+ "grad_norm": 41.068538665771484,
723
+ "learning_rate": 1.7128642501776832e-06,
724
+ "loss": 0.7044,
725
+ "step": 1850
726
+ },
727
+ {
728
+ "epoch": 2.0,
729
+ "grad_norm": 67.96875762939453,
730
+ "learning_rate": 1.668443496801706e-06,
731
+ "loss": 0.5948,
732
+ "step": 1875
733
+ },
734
+ {
735
+ "epoch": 2.03,
736
+ "grad_norm": 51.58526611328125,
737
+ "learning_rate": 1.6240227434257286e-06,
738
+ "loss": 0.6253,
739
+ "step": 1900
740
+ },
741
+ {
742
+ "epoch": 2.03,
743
+ "eval_accuracy": 0.8158,
744
+ "eval_f1_macro": 0.7058775462036815,
745
+ "eval_f1_micro": 0.8158,
746
+ "eval_loss": 0.6505562663078308,
747
+ "eval_runtime": 47.3282,
748
+ "eval_samples_per_second": 211.29,
749
+ "eval_steps_per_second": 3.317,
750
+ "step": 1900
751
+ },
752
+ {
753
+ "epoch": 2.05,
754
+ "grad_norm": 45.662109375,
755
+ "learning_rate": 1.5796019900497514e-06,
756
+ "loss": 0.645,
757
+ "step": 1925
758
+ },
759
+ {
760
+ "epoch": 2.08,
761
+ "grad_norm": 66.76183319091797,
762
+ "learning_rate": 1.5351812366737743e-06,
763
+ "loss": 0.6412,
764
+ "step": 1950
765
+ },
766
+ {
767
+ "epoch": 2.11,
768
+ "grad_norm": 56.84629440307617,
769
+ "learning_rate": 1.4907604832977968e-06,
770
+ "loss": 0.6511,
771
+ "step": 1975
772
+ },
773
+ {
774
+ "epoch": 2.13,
775
+ "grad_norm": 53.2021484375,
776
+ "learning_rate": 1.4463397299218196e-06,
777
+ "loss": 0.6044,
778
+ "step": 2000
779
+ },
780
+ {
781
+ "epoch": 2.13,
782
+ "eval_accuracy": 0.8155,
783
+ "eval_f1_macro": 0.716530877903978,
784
+ "eval_f1_micro": 0.8155,
785
+ "eval_loss": 0.6602968573570251,
786
+ "eval_runtime": 47.473,
787
+ "eval_samples_per_second": 210.646,
788
+ "eval_steps_per_second": 3.307,
789
+ "step": 2000
790
+ },
791
+ {
792
+ "epoch": 2.16,
793
+ "grad_norm": 71.7922134399414,
794
+ "learning_rate": 1.4019189765458423e-06,
795
+ "loss": 0.6381,
796
+ "step": 2025
797
+ },
798
+ {
799
+ "epoch": 2.19,
800
+ "grad_norm": 32.50026321411133,
801
+ "learning_rate": 1.357498223169865e-06,
802
+ "loss": 0.6622,
803
+ "step": 2050
804
+ },
805
+ {
806
+ "epoch": 2.21,
807
+ "grad_norm": 50.483219146728516,
808
+ "learning_rate": 1.3130774697938879e-06,
809
+ "loss": 0.6165,
810
+ "step": 2075
811
+ },
812
+ {
813
+ "epoch": 2.24,
814
+ "grad_norm": 40.9278450012207,
815
+ "learning_rate": 1.2686567164179105e-06,
816
+ "loss": 0.6414,
817
+ "step": 2100
818
+ },
819
+ {
820
+ "epoch": 2.24,
821
+ "eval_accuracy": 0.8138,
822
+ "eval_f1_macro": 0.7185019905510756,
823
+ "eval_f1_micro": 0.8138,
824
+ "eval_loss": 0.6434906125068665,
825
+ "eval_runtime": 47.5169,
826
+ "eval_samples_per_second": 210.452,
827
+ "eval_steps_per_second": 3.304,
828
+ "step": 2100
829
+ },
830
+ {
831
+ "epoch": 2.27,
832
+ "grad_norm": 40.769439697265625,
833
+ "learning_rate": 1.2242359630419332e-06,
834
+ "loss": 0.619,
835
+ "step": 2125
836
+ },
837
+ {
838
+ "epoch": 2.29,
839
+ "grad_norm": 23.210596084594727,
840
+ "learning_rate": 1.179815209665956e-06,
841
+ "loss": 0.6168,
842
+ "step": 2150
843
+ },
844
+ {
845
+ "epoch": 2.32,
846
+ "grad_norm": 43.848052978515625,
847
+ "learning_rate": 1.1353944562899787e-06,
848
+ "loss": 0.5244,
849
+ "step": 2175
850
+ },
851
+ {
852
+ "epoch": 2.35,
853
+ "grad_norm": 40.81973648071289,
854
+ "learning_rate": 1.0909737029140014e-06,
855
+ "loss": 0.6115,
856
+ "step": 2200
857
+ },
858
+ {
859
+ "epoch": 2.35,
860
+ "eval_accuracy": 0.8216,
861
+ "eval_f1_macro": 0.727953382739938,
862
+ "eval_f1_micro": 0.8216,
863
+ "eval_loss": 0.63681560754776,
864
+ "eval_runtime": 47.4723,
865
+ "eval_samples_per_second": 210.649,
866
+ "eval_steps_per_second": 3.307,
867
+ "step": 2200
868
+ },
869
+ {
870
+ "epoch": 2.37,
871
+ "grad_norm": 28.034944534301758,
872
+ "learning_rate": 1.0465529495380243e-06,
873
+ "loss": 0.5613,
874
+ "step": 2225
875
+ },
876
+ {
877
+ "epoch": 2.4,
878
+ "grad_norm": 68.5925521850586,
879
+ "learning_rate": 1.002132196162047e-06,
880
+ "loss": 0.5987,
881
+ "step": 2250
882
+ },
883
+ {
884
+ "epoch": 2.43,
885
+ "grad_norm": 30.3986759185791,
886
+ "learning_rate": 9.577114427860696e-07,
887
+ "loss": 0.6119,
888
+ "step": 2275
889
+ },
890
+ {
891
+ "epoch": 2.45,
892
+ "grad_norm": 38.481117248535156,
893
+ "learning_rate": 9.132906894100925e-07,
894
+ "loss": 0.6331,
895
+ "step": 2300
896
+ },
897
+ {
898
+ "epoch": 2.45,
899
+ "eval_accuracy": 0.8208,
900
+ "eval_f1_macro": 0.7251441527998863,
901
+ "eval_f1_micro": 0.8208,
902
+ "eval_loss": 0.6273249983787537,
903
+ "eval_runtime": 47.475,
904
+ "eval_samples_per_second": 210.637,
905
+ "eval_steps_per_second": 3.307,
906
+ "step": 2300
907
+ },
908
+ {
909
+ "epoch": 2.48,
910
+ "grad_norm": 52.91291427612305,
911
+ "learning_rate": 8.688699360341152e-07,
912
+ "loss": 0.6261,
913
+ "step": 2325
914
+ },
915
+ {
916
+ "epoch": 2.51,
917
+ "grad_norm": 43.07246398925781,
918
+ "learning_rate": 8.24449182658138e-07,
919
+ "loss": 0.6191,
920
+ "step": 2350
921
+ },
922
+ {
923
+ "epoch": 2.53,
924
+ "grad_norm": 40.49489974975586,
925
+ "learning_rate": 7.800284292821607e-07,
926
+ "loss": 0.5856,
927
+ "step": 2375
928
+ },
929
+ {
930
+ "epoch": 2.56,
931
+ "grad_norm": 30.555904388427734,
932
+ "learning_rate": 7.356076759061834e-07,
933
+ "loss": 0.608,
934
+ "step": 2400
935
+ },
936
+ {
937
+ "epoch": 2.56,
938
+ "eval_accuracy": 0.8232,
939
+ "eval_f1_macro": 0.7285501243647127,
940
+ "eval_f1_micro": 0.8232,
941
+ "eval_loss": 0.6251906156539917,
942
+ "eval_runtime": 47.5564,
943
+ "eval_samples_per_second": 210.277,
944
+ "eval_steps_per_second": 3.301,
945
+ "step": 2400
946
+ },
947
+ {
948
+ "epoch": 2.59,
949
+ "grad_norm": 175.31057739257812,
950
+ "learning_rate": 6.911869225302062e-07,
951
+ "loss": 0.6802,
952
+ "step": 2425
953
+ },
954
+ {
955
+ "epoch": 2.61,
956
+ "grad_norm": 30.15215301513672,
957
+ "learning_rate": 6.467661691542289e-07,
958
+ "loss": 0.6307,
959
+ "step": 2450
960
+ },
961
+ {
962
+ "epoch": 2.64,
963
+ "grad_norm": 34.21811294555664,
964
+ "learning_rate": 6.023454157782517e-07,
965
+ "loss": 0.6029,
966
+ "step": 2475
967
+ },
968
+ {
969
+ "epoch": 2.67,
970
+ "grad_norm": 56.559364318847656,
971
+ "learning_rate": 5.579246624022743e-07,
972
+ "loss": 0.5879,
973
+ "step": 2500
974
+ },
975
+ {
976
+ "epoch": 2.67,
977
+ "eval_accuracy": 0.8241,
978
+ "eval_f1_macro": 0.7307624039691639,
979
+ "eval_f1_micro": 0.8241,
980
+ "eval_loss": 0.6171656250953674,
981
+ "eval_runtime": 47.4737,
982
+ "eval_samples_per_second": 210.643,
983
+ "eval_steps_per_second": 3.307,
984
+ "step": 2500
985
+ },
986
+ {
987
+ "epoch": 2.69,
988
+ "grad_norm": 43.20689392089844,
989
+ "learning_rate": 5.135039090262971e-07,
990
+ "loss": 0.5858,
991
+ "step": 2525
992
+ },
993
+ {
994
+ "epoch": 2.72,
995
+ "grad_norm": 46.331817626953125,
996
+ "learning_rate": 4.690831556503199e-07,
997
+ "loss": 0.5959,
998
+ "step": 2550
999
+ },
1000
+ {
1001
+ "epoch": 2.75,
1002
+ "grad_norm": 36.399810791015625,
1003
+ "learning_rate": 4.2466240227434256e-07,
1004
+ "loss": 0.6069,
1005
+ "step": 2575
1006
+ },
1007
+ {
1008
+ "epoch": 2.77,
1009
+ "grad_norm": 79.88939666748047,
1010
+ "learning_rate": 3.8024164889836533e-07,
1011
+ "loss": 0.6056,
1012
+ "step": 2600
1013
+ },
1014
+ {
1015
+ "epoch": 2.77,
1016
+ "eval_accuracy": 0.8257,
1017
+ "eval_f1_macro": 0.7346364945364393,
1018
+ "eval_f1_micro": 0.8257,
1019
+ "eval_loss": 0.6157156229019165,
1020
+ "eval_runtime": 47.4846,
1021
+ "eval_samples_per_second": 210.595,
1022
+ "eval_steps_per_second": 3.306,
1023
+ "step": 2600
1024
+ },
1025
+ {
1026
+ "epoch": 2.8,
1027
+ "grad_norm": 49.164161682128906,
1028
+ "learning_rate": 3.358208955223881e-07,
1029
+ "loss": 0.5675,
1030
+ "step": 2625
1031
+ },
1032
+ {
1033
+ "epoch": 2.83,
1034
+ "grad_norm": 46.98076248168945,
1035
+ "learning_rate": 2.914001421464108e-07,
1036
+ "loss": 0.6607,
1037
+ "step": 2650
1038
+ },
1039
+ {
1040
+ "epoch": 2.85,
1041
+ "grad_norm": 23.488380432128906,
1042
+ "learning_rate": 2.4697938877043354e-07,
1043
+ "loss": 0.5866,
1044
+ "step": 2675
1045
+ },
1046
+ {
1047
+ "epoch": 2.88,
1048
+ "grad_norm": 31.710861206054688,
1049
+ "learning_rate": 2.0255863539445632e-07,
1050
+ "loss": 0.5711,
1051
+ "step": 2700
1052
+ },
1053
+ {
1054
+ "epoch": 2.88,
1055
+ "eval_accuracy": 0.8253,
1056
+ "eval_f1_macro": 0.7341228101010588,
1057
+ "eval_f1_micro": 0.8253,
1058
+ "eval_loss": 0.6129437685012817,
1059
+ "eval_runtime": 47.5391,
1060
+ "eval_samples_per_second": 210.353,
1061
+ "eval_steps_per_second": 3.303,
1062
+ "step": 2700
1063
+ },
1064
+ {
1065
+ "epoch": 2.91,
1066
+ "grad_norm": 33.91932678222656,
1067
+ "learning_rate": 1.5813788201847903e-07,
1068
+ "loss": 0.5565,
1069
+ "step": 2725
1070
+ },
1071
+ {
1072
+ "epoch": 2.93,
1073
+ "grad_norm": 35.29643630981445,
1074
+ "learning_rate": 1.1371712864250178e-07,
1075
+ "loss": 0.5793,
1076
+ "step": 2750
1077
+ },
1078
+ {
1079
+ "epoch": 2.96,
1080
+ "grad_norm": 33.85700988769531,
1081
+ "learning_rate": 6.929637526652453e-08,
1082
+ "loss": 0.5425,
1083
+ "step": 2775
1084
+ },
1085
+ {
1086
+ "epoch": 2.99,
1087
+ "grad_norm": 40.65436935424805,
1088
+ "learning_rate": 2.4875621890547265e-08,
1089
+ "loss": 0.5802,
1090
+ "step": 2800
1091
+ },
1092
+ {
1093
+ "epoch": 2.99,
1094
+ "eval_accuracy": 0.826,
1095
+ "eval_f1_macro": 0.7355084015446216,
1096
+ "eval_f1_micro": 0.826,
1097
+ "eval_loss": 0.6120218634605408,
1098
+ "eval_runtime": 47.528,
1099
+ "eval_samples_per_second": 210.402,
1100
+ "eval_steps_per_second": 3.303,
1101
+ "step": 2800
1102
+ }
1103
+ ],
1104
+ "logging_steps": 25,
1105
+ "max_steps": 2814,
1106
+ "num_input_tokens_seen": 0,
1107
+ "num_train_epochs": 3,
1108
+ "save_steps": 100,
1109
+ "total_flos": 3.4650610733154304e+17,
1110
+ "train_batch_size": 32,
1111
+ "trial_name": null,
1112
+ "trial_params": null
1113
+ }
microsoft/phi_2_ledgar/checkpoint-2800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9726a6f1cd618b1c6756600627232628ca181750693975f1aa65486662e1136c
3
+ size 5944
microsoft/phi_2_ledgar/checkpoint-2800/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
microsoft/phi_2_ledgar/checkpoint-2800/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
microsoft/phi_2_ledgar/config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "architectures": [
4
+ "PhiForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "finetuning_task": "text-classification",
15
+ "hidden_act": "gelu_new",
16
+ "hidden_size": 2560,
17
+ "id2label": {
18
+ "0": "0",
19
+ "1": "1",
20
+ "2": "10",
21
+ "3": "11",
22
+ "4": "12",
23
+ "5": "13",
24
+ "6": "14",
25
+ "7": "15",
26
+ "8": "16",
27
+ "9": "17",
28
+ "10": "18",
29
+ "11": "19",
30
+ "12": "2",
31
+ "13": "20",
32
+ "14": "21",
33
+ "15": "22",
34
+ "16": "23",
35
+ "17": "24",
36
+ "18": "25",
37
+ "19": "26",
38
+ "20": "27",
39
+ "21": "28",
40
+ "22": "29",
41
+ "23": "3",
42
+ "24": "30",
43
+ "25": "31",
44
+ "26": "32",
45
+ "27": "33",
46
+ "28": "34",
47
+ "29": "35",
48
+ "30": "36",
49
+ "31": "37",
50
+ "32": "38",
51
+ "33": "39",
52
+ "34": "4",
53
+ "35": "40",
54
+ "36": "41",
55
+ "37": "42",
56
+ "38": "43",
57
+ "39": "44",
58
+ "40": "45",
59
+ "41": "46",
60
+ "42": "47",
61
+ "43": "48",
62
+ "44": "49",
63
+ "45": "5",
64
+ "46": "50",
65
+ "47": "51",
66
+ "48": "52",
67
+ "49": "53",
68
+ "50": "54",
69
+ "51": "55",
70
+ "52": "56",
71
+ "53": "57",
72
+ "54": "58",
73
+ "55": "59",
74
+ "56": "6",
75
+ "57": "60",
76
+ "58": "61",
77
+ "59": "62",
78
+ "60": "63",
79
+ "61": "64",
80
+ "62": "65",
81
+ "63": "66",
82
+ "64": "67",
83
+ "65": "68",
84
+ "66": "69",
85
+ "67": "7",
86
+ "68": "70",
87
+ "69": "71",
88
+ "70": "72",
89
+ "71": "73",
90
+ "72": "74",
91
+ "73": "75",
92
+ "74": "76",
93
+ "75": "77",
94
+ "76": "78",
95
+ "77": "79",
96
+ "78": "8",
97
+ "79": "80",
98
+ "80": "81",
99
+ "81": "82",
100
+ "82": "83",
101
+ "83": "84",
102
+ "84": "85",
103
+ "85": "86",
104
+ "86": "87",
105
+ "87": "88",
106
+ "88": "89",
107
+ "89": "9",
108
+ "90": "90",
109
+ "91": "91",
110
+ "92": "92",
111
+ "93": "93",
112
+ "94": "94",
113
+ "95": "95",
114
+ "96": "96",
115
+ "97": "97",
116
+ "98": "98",
117
+ "99": "99"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 10240,
121
+ "label2id": {
122
+ "0": 0,
123
+ "1": 1,
124
+ "10": 2,
125
+ "11": 3,
126
+ "12": 4,
127
+ "13": 5,
128
+ "14": 6,
129
+ "15": 7,
130
+ "16": 8,
131
+ "17": 9,
132
+ "18": 10,
133
+ "19": 11,
134
+ "2": 12,
135
+ "20": 13,
136
+ "21": 14,
137
+ "22": 15,
138
+ "23": 16,
139
+ "24": 17,
140
+ "25": 18,
141
+ "26": 19,
142
+ "27": 20,
143
+ "28": 21,
144
+ "29": 22,
145
+ "3": 23,
146
+ "30": 24,
147
+ "31": 25,
148
+ "32": 26,
149
+ "33": 27,
150
+ "34": 28,
151
+ "35": 29,
152
+ "36": 30,
153
+ "37": 31,
154
+ "38": 32,
155
+ "39": 33,
156
+ "4": 34,
157
+ "40": 35,
158
+ "41": 36,
159
+ "42": 37,
160
+ "43": 38,
161
+ "44": 39,
162
+ "45": 40,
163
+ "46": 41,
164
+ "47": 42,
165
+ "48": 43,
166
+ "49": 44,
167
+ "5": 45,
168
+ "50": 46,
169
+ "51": 47,
170
+ "52": 48,
171
+ "53": 49,
172
+ "54": 50,
173
+ "55": 51,
174
+ "56": 52,
175
+ "57": 53,
176
+ "58": 54,
177
+ "59": 55,
178
+ "6": 56,
179
+ "60": 57,
180
+ "61": 58,
181
+ "62": 59,
182
+ "63": 60,
183
+ "64": 61,
184
+ "65": 62,
185
+ "66": 63,
186
+ "67": 64,
187
+ "68": 65,
188
+ "69": 66,
189
+ "7": 67,
190
+ "70": 68,
191
+ "71": 69,
192
+ "72": 70,
193
+ "73": 71,
194
+ "74": 72,
195
+ "75": 73,
196
+ "76": 74,
197
+ "77": 75,
198
+ "78": 76,
199
+ "79": 77,
200
+ "8": 78,
201
+ "80": 79,
202
+ "81": 80,
203
+ "82": 81,
204
+ "83": 82,
205
+ "84": 83,
206
+ "85": 84,
207
+ "86": 85,
208
+ "87": 86,
209
+ "88": 87,
210
+ "89": 88,
211
+ "9": 89,
212
+ "90": 90,
213
+ "91": 91,
214
+ "92": 92,
215
+ "93": 93,
216
+ "94": 94,
217
+ "95": 95,
218
+ "96": 96,
219
+ "97": 97,
220
+ "98": 98,
221
+ "99": 99
222
+ },
223
+ "layer_norm_eps": 1e-05,
224
+ "max_position_embeddings": 2048,
225
+ "model_type": "phi",
226
+ "num_attention_heads": 32,
227
+ "num_hidden_layers": 32,
228
+ "num_key_value_heads": 32,
229
+ "pad_token_id": 50256,
230
+ "partial_rotary_factor": 0.4,
231
+ "problem_type": "single_label_classification",
232
+ "qk_layernorm": false,
233
+ "resid_pdrop": 0.1,
234
+ "rope_scaling": null,
235
+ "rope_theta": 10000.0,
236
+ "tie_word_embeddings": false,
237
+ "torch_dtype": "bfloat16",
238
+ "transformers_version": "4.39.0.dev0",
239
+ "use_cache": true,
240
+ "vocab_size": 50295
241
+ }
microsoft/phi_2_ledgar/eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.826,
4
+ "eval_f1_macro": 0.7355084015446216,
5
+ "eval_f1_micro": 0.826,
6
+ "eval_loss": 0.6120218634605408,
7
+ "eval_runtime": 46.3584,
8
+ "eval_samples": 10000,
9
+ "eval_samples_per_second": 215.711,
10
+ "eval_steps_per_second": 3.387
11
+ }
microsoft/phi_2_ledgar/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
microsoft/phi_2_ledgar/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae73b51441793d522ad559358cf9079e99146b65973000a15160116545e8f7b4
3
+ size 4990951248
microsoft/phi_2_ledgar/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a147716a17a72dea3519e435ba913dfbe27494f393627a3ba1562fd349409a81
3
+ size 302098480
microsoft/phi_2_ledgar/model.safetensors.index.json ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5292999680
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
8
+ "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
60
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
94
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
106
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
108
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
118
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
130
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
132
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
142
+ "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
144
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
154
+ "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
156
+ "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
166
+ "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
168
+ "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
170
+ "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
178
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
180
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
182
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
184
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
192
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
194
+ "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
196
+ "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
206
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
208
+ "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
214
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
220
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
226
+ "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
228
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
232
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
238
+ "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
240
+ "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
250
+ "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
252
+ "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
254
+ "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
262
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
264
+ "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
266
+ "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
268
+ "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
276
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
278
+ "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
280
+ "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
298
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
300
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
304
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
310
+ "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
312
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
314
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
316
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
322
+ "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
324
+ "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
326
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
328
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
334
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
336
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
338
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
340
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
346
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
348
+ "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
356
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
358
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
360
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
368
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
370
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
382
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
394
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
396
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
406
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
408
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
418
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
430
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
432
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
444
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
457
+ "score.weight": "model-00002-of-00002.safetensors"
458
+ }
459
+ }
microsoft/phi_2_ledgar/run.log ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ 03/15/2024 22:38:52 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
2
+ 03/15/2024 22:38:52 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
3
+ 03/15/2024 22:39:04 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
4
+ 03/15/2024 22:39:04 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
microsoft/phi_2_ledgar/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
microsoft/phi_2_ledgar/test_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "test_accuracy": 0.8311,
4
+ "test_f1_macro": 0.7306467958794756,
5
+ "test_f1_micro": 0.8311,
6
+ "test_loss": 0.6224531531333923,
7
+ "test_runtime": 47.3558,
8
+ "test_samples_per_second": 211.168,
9
+ "test_steps_per_second": 3.315
10
+ }
microsoft/phi_2_ledgar/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
microsoft/phi_2_ledgar/tokenizer_config.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ }
316
+ },
317
+ "bos_token": "<|endoftext|>",
318
+ "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
324
+ }
microsoft/phi_2_ledgar/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.9835220694796108,
4
+ "train_runtime": 6489.4436,
5
+ "train_samples": 60000,
6
+ "train_samples_per_second": 27.737,
7
+ "train_steps_per_second": 0.434
8
+ }
microsoft/phi_2_ledgar/trainer_state.json ADDED
@@ -0,0 +1,1122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6120218634605408,
3
+ "best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/microsoft/phi_2_ledgar/checkpoint-2800",
4
+ "epoch": 3.0,
5
+ "eval_steps": 100,
6
+ "global_step": 2814,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "grad_norm": 278.5504455566406,
14
+ "learning_rate": 4.9555792466240235e-06,
15
+ "loss": 4.8556,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 332.1685485839844,
21
+ "learning_rate": 4.911158493248046e-06,
22
+ "loss": 4.2381,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.08,
27
+ "grad_norm": 238.07369995117188,
28
+ "learning_rate": 4.866737739872069e-06,
29
+ "loss": 4.0038,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.11,
34
+ "grad_norm": 152.84237670898438,
35
+ "learning_rate": 4.822316986496091e-06,
36
+ "loss": 3.6034,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.11,
41
+ "eval_accuracy": 0.337,
42
+ "eval_f1_macro": 0.12358690595802334,
43
+ "eval_f1_micro": 0.337,
44
+ "eval_loss": 3.211400032043457,
45
+ "eval_runtime": 47.3513,
46
+ "eval_samples_per_second": 211.188,
47
+ "eval_steps_per_second": 3.316,
48
+ "step": 100
49
+ },
50
+ {
51
+ "epoch": 0.13,
52
+ "grad_norm": 143.5316619873047,
53
+ "learning_rate": 4.777896233120114e-06,
54
+ "loss": 3.1831,
55
+ "step": 125
56
+ },
57
+ {
58
+ "epoch": 0.16,
59
+ "grad_norm": 152.6884765625,
60
+ "learning_rate": 4.733475479744136e-06,
61
+ "loss": 2.9609,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "grad_norm": 116.26598358154297,
67
+ "learning_rate": 4.6890547263681595e-06,
68
+ "loss": 2.4773,
69
+ "step": 175
70
+ },
71
+ {
72
+ "epoch": 0.21,
73
+ "grad_norm": 102.64595031738281,
74
+ "learning_rate": 4.644633972992183e-06,
75
+ "loss": 2.2678,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 0.21,
80
+ "eval_accuracy": 0.5623,
81
+ "eval_f1_macro": 0.3331251034728065,
82
+ "eval_f1_micro": 0.5623,
83
+ "eval_loss": 1.9837249517440796,
84
+ "eval_runtime": 47.4491,
85
+ "eval_samples_per_second": 210.752,
86
+ "eval_steps_per_second": 3.309,
87
+ "step": 200
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "grad_norm": 107.59564208984375,
92
+ "learning_rate": 4.600213219616206e-06,
93
+ "loss": 2.0387,
94
+ "step": 225
95
+ },
96
+ {
97
+ "epoch": 0.27,
98
+ "grad_norm": 129.82203674316406,
99
+ "learning_rate": 4.555792466240228e-06,
100
+ "loss": 1.7772,
101
+ "step": 250
102
+ },
103
+ {
104
+ "epoch": 0.29,
105
+ "grad_norm": 106.58737182617188,
106
+ "learning_rate": 4.51137171286425e-06,
107
+ "loss": 1.5959,
108
+ "step": 275
109
+ },
110
+ {
111
+ "epoch": 0.32,
112
+ "grad_norm": 219.3987274169922,
113
+ "learning_rate": 4.466950959488273e-06,
114
+ "loss": 1.4927,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 0.32,
119
+ "eval_accuracy": 0.6712,
120
+ "eval_f1_macro": 0.48839865479998884,
121
+ "eval_f1_micro": 0.6712,
122
+ "eval_loss": 1.3369125127792358,
123
+ "eval_runtime": 47.4603,
124
+ "eval_samples_per_second": 210.702,
125
+ "eval_steps_per_second": 3.308,
126
+ "step": 300
127
+ },
128
+ {
129
+ "epoch": 0.35,
130
+ "grad_norm": 62.788822174072266,
131
+ "learning_rate": 4.422530206112296e-06,
132
+ "loss": 1.4203,
133
+ "step": 325
134
+ },
135
+ {
136
+ "epoch": 0.37,
137
+ "grad_norm": 63.6900634765625,
138
+ "learning_rate": 4.378109452736319e-06,
139
+ "loss": 1.2841,
140
+ "step": 350
141
+ },
142
+ {
143
+ "epoch": 0.4,
144
+ "grad_norm": 75.33383178710938,
145
+ "learning_rate": 4.333688699360342e-06,
146
+ "loss": 1.1642,
147
+ "step": 375
148
+ },
149
+ {
150
+ "epoch": 0.43,
151
+ "grad_norm": 89.42117309570312,
152
+ "learning_rate": 4.289267945984365e-06,
153
+ "loss": 1.1518,
154
+ "step": 400
155
+ },
156
+ {
157
+ "epoch": 0.43,
158
+ "eval_accuracy": 0.7243,
159
+ "eval_f1_macro": 0.5613056174383468,
160
+ "eval_f1_micro": 0.7243,
161
+ "eval_loss": 1.052606225013733,
162
+ "eval_runtime": 47.3838,
163
+ "eval_samples_per_second": 211.043,
164
+ "eval_steps_per_second": 3.313,
165
+ "step": 400
166
+ },
167
+ {
168
+ "epoch": 0.45,
169
+ "grad_norm": 74.13993072509766,
170
+ "learning_rate": 4.244847192608387e-06,
171
+ "loss": 1.135,
172
+ "step": 425
173
+ },
174
+ {
175
+ "epoch": 0.48,
176
+ "grad_norm": 80.19258117675781,
177
+ "learning_rate": 4.200426439232409e-06,
178
+ "loss": 1.176,
179
+ "step": 450
180
+ },
181
+ {
182
+ "epoch": 0.51,
183
+ "grad_norm": 70.83063507080078,
184
+ "learning_rate": 4.156005685856432e-06,
185
+ "loss": 1.1386,
186
+ "step": 475
187
+ },
188
+ {
189
+ "epoch": 0.53,
190
+ "grad_norm": 109.83588409423828,
191
+ "learning_rate": 4.1115849324804554e-06,
192
+ "loss": 1.1041,
193
+ "step": 500
194
+ },
195
+ {
196
+ "epoch": 0.53,
197
+ "eval_accuracy": 0.7521,
198
+ "eval_f1_macro": 0.6206030644902993,
199
+ "eval_f1_micro": 0.7521,
200
+ "eval_loss": 0.9304812550544739,
201
+ "eval_runtime": 47.4284,
202
+ "eval_samples_per_second": 210.844,
203
+ "eval_steps_per_second": 3.31,
204
+ "step": 500
205
+ },
206
+ {
207
+ "epoch": 0.56,
208
+ "grad_norm": 51.40995788574219,
209
+ "learning_rate": 4.067164179104478e-06,
210
+ "loss": 0.9872,
211
+ "step": 525
212
+ },
213
+ {
214
+ "epoch": 0.59,
215
+ "grad_norm": 75.6723861694336,
216
+ "learning_rate": 4.022743425728501e-06,
217
+ "loss": 0.9832,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 0.61,
222
+ "grad_norm": 86.0229721069336,
223
+ "learning_rate": 3.978322672352524e-06,
224
+ "loss": 0.9485,
225
+ "step": 575
226
+ },
227
+ {
228
+ "epoch": 0.64,
229
+ "grad_norm": 113.96233367919922,
230
+ "learning_rate": 3.933901918976546e-06,
231
+ "loss": 1.0144,
232
+ "step": 600
233
+ },
234
+ {
235
+ "epoch": 0.64,
236
+ "eval_accuracy": 0.7574,
237
+ "eval_f1_macro": 0.6294250374822845,
238
+ "eval_f1_micro": 0.7574,
239
+ "eval_loss": 0.9067593812942505,
240
+ "eval_runtime": 47.4873,
241
+ "eval_samples_per_second": 210.583,
242
+ "eval_steps_per_second": 3.306,
243
+ "step": 600
244
+ },
245
+ {
246
+ "epoch": 0.67,
247
+ "grad_norm": 77.80159759521484,
248
+ "learning_rate": 3.889481165600569e-06,
249
+ "loss": 1.0435,
250
+ "step": 625
251
+ },
252
+ {
253
+ "epoch": 0.69,
254
+ "grad_norm": 77.97108459472656,
255
+ "learning_rate": 3.8450604122245914e-06,
256
+ "loss": 0.9593,
257
+ "step": 650
258
+ },
259
+ {
260
+ "epoch": 0.72,
261
+ "grad_norm": 68.20707702636719,
262
+ "learning_rate": 3.8006396588486145e-06,
263
+ "loss": 0.9818,
264
+ "step": 675
265
+ },
266
+ {
267
+ "epoch": 0.75,
268
+ "grad_norm": 103.11054229736328,
269
+ "learning_rate": 3.756218905472637e-06,
270
+ "loss": 0.9892,
271
+ "step": 700
272
+ },
273
+ {
274
+ "epoch": 0.75,
275
+ "eval_accuracy": 0.7669,
276
+ "eval_f1_macro": 0.642987522646621,
277
+ "eval_f1_micro": 0.7669,
278
+ "eval_loss": 0.8712124824523926,
279
+ "eval_runtime": 47.4988,
280
+ "eval_samples_per_second": 210.531,
281
+ "eval_steps_per_second": 3.305,
282
+ "step": 700
283
+ },
284
+ {
285
+ "epoch": 0.77,
286
+ "grad_norm": 88.3270263671875,
287
+ "learning_rate": 3.71179815209666e-06,
288
+ "loss": 0.8937,
289
+ "step": 725
290
+ },
291
+ {
292
+ "epoch": 0.8,
293
+ "grad_norm": 67.907958984375,
294
+ "learning_rate": 3.667377398720683e-06,
295
+ "loss": 0.9788,
296
+ "step": 750
297
+ },
298
+ {
299
+ "epoch": 0.83,
300
+ "grad_norm": 68.60499572753906,
301
+ "learning_rate": 3.622956645344705e-06,
302
+ "loss": 0.9459,
303
+ "step": 775
304
+ },
305
+ {
306
+ "epoch": 0.85,
307
+ "grad_norm": 71.7964859008789,
308
+ "learning_rate": 3.578535891968728e-06,
309
+ "loss": 0.9972,
310
+ "step": 800
311
+ },
312
+ {
313
+ "epoch": 0.85,
314
+ "eval_accuracy": 0.7675,
315
+ "eval_f1_macro": 0.6369038817239384,
316
+ "eval_f1_micro": 0.7675,
317
+ "eval_loss": 0.8591374754905701,
318
+ "eval_runtime": 47.4288,
319
+ "eval_samples_per_second": 210.842,
320
+ "eval_steps_per_second": 3.31,
321
+ "step": 800
322
+ },
323
+ {
324
+ "epoch": 0.88,
325
+ "grad_norm": 99.17341613769531,
326
+ "learning_rate": 3.534115138592751e-06,
327
+ "loss": 0.9663,
328
+ "step": 825
329
+ },
330
+ {
331
+ "epoch": 0.91,
332
+ "grad_norm": 198.6553955078125,
333
+ "learning_rate": 3.4896943852167736e-06,
334
+ "loss": 0.8617,
335
+ "step": 850
336
+ },
337
+ {
338
+ "epoch": 0.93,
339
+ "grad_norm": 82.58099365234375,
340
+ "learning_rate": 3.4452736318407963e-06,
341
+ "loss": 0.8735,
342
+ "step": 875
343
+ },
344
+ {
345
+ "epoch": 0.96,
346
+ "grad_norm": 63.692623138427734,
347
+ "learning_rate": 3.4008528784648194e-06,
348
+ "loss": 0.8439,
349
+ "step": 900
350
+ },
351
+ {
352
+ "epoch": 0.96,
353
+ "eval_accuracy": 0.7848,
354
+ "eval_f1_macro": 0.6834829058415216,
355
+ "eval_f1_micro": 0.7848,
356
+ "eval_loss": 0.7894874811172485,
357
+ "eval_runtime": 47.4489,
358
+ "eval_samples_per_second": 210.753,
359
+ "eval_steps_per_second": 3.309,
360
+ "step": 900
361
+ },
362
+ {
363
+ "epoch": 0.99,
364
+ "grad_norm": 78.88030242919922,
365
+ "learning_rate": 3.3564321250888416e-06,
366
+ "loss": 0.8582,
367
+ "step": 925
368
+ },
369
+ {
370
+ "epoch": 1.01,
371
+ "grad_norm": 45.49142837524414,
372
+ "learning_rate": 3.3120113717128643e-06,
373
+ "loss": 0.8621,
374
+ "step": 950
375
+ },
376
+ {
377
+ "epoch": 1.04,
378
+ "grad_norm": 37.98048400878906,
379
+ "learning_rate": 3.2675906183368874e-06,
380
+ "loss": 0.8396,
381
+ "step": 975
382
+ },
383
+ {
384
+ "epoch": 1.07,
385
+ "grad_norm": 37.72966384887695,
386
+ "learning_rate": 3.22316986496091e-06,
387
+ "loss": 0.7409,
388
+ "step": 1000
389
+ },
390
+ {
391
+ "epoch": 1.07,
392
+ "eval_accuracy": 0.7944,
393
+ "eval_f1_macro": 0.6808979493082343,
394
+ "eval_f1_micro": 0.7944,
395
+ "eval_loss": 0.7614499926567078,
396
+ "eval_runtime": 47.4823,
397
+ "eval_samples_per_second": 210.605,
398
+ "eval_steps_per_second": 3.306,
399
+ "step": 1000
400
+ },
401
+ {
402
+ "epoch": 1.09,
403
+ "grad_norm": 57.926578521728516,
404
+ "learning_rate": 3.1787491115849327e-06,
405
+ "loss": 0.7475,
406
+ "step": 1025
407
+ },
408
+ {
409
+ "epoch": 1.12,
410
+ "grad_norm": 86.9485855102539,
411
+ "learning_rate": 3.1343283582089558e-06,
412
+ "loss": 0.7197,
413
+ "step": 1050
414
+ },
415
+ {
416
+ "epoch": 1.15,
417
+ "grad_norm": 54.83045959472656,
418
+ "learning_rate": 3.0899076048329785e-06,
419
+ "loss": 0.8314,
420
+ "step": 1075
421
+ },
422
+ {
423
+ "epoch": 1.17,
424
+ "grad_norm": 68.1777114868164,
425
+ "learning_rate": 3.0454868514570007e-06,
426
+ "loss": 0.7627,
427
+ "step": 1100
428
+ },
429
+ {
430
+ "epoch": 1.17,
431
+ "eval_accuracy": 0.7946,
432
+ "eval_f1_macro": 0.6809735037021439,
433
+ "eval_f1_micro": 0.7946,
434
+ "eval_loss": 0.7538655996322632,
435
+ "eval_runtime": 47.4181,
436
+ "eval_samples_per_second": 210.89,
437
+ "eval_steps_per_second": 3.311,
438
+ "step": 1100
439
+ },
440
+ {
441
+ "epoch": 1.2,
442
+ "grad_norm": 31.217445373535156,
443
+ "learning_rate": 3.0010660980810234e-06,
444
+ "loss": 0.7501,
445
+ "step": 1125
446
+ },
447
+ {
448
+ "epoch": 1.23,
449
+ "grad_norm": 38.76744842529297,
450
+ "learning_rate": 2.9566453447050464e-06,
451
+ "loss": 0.6884,
452
+ "step": 1150
453
+ },
454
+ {
455
+ "epoch": 1.25,
456
+ "grad_norm": 50.481388092041016,
457
+ "learning_rate": 2.912224591329069e-06,
458
+ "loss": 0.6911,
459
+ "step": 1175
460
+ },
461
+ {
462
+ "epoch": 1.28,
463
+ "grad_norm": 54.91836929321289,
464
+ "learning_rate": 2.867803837953092e-06,
465
+ "loss": 0.8065,
466
+ "step": 1200
467
+ },
468
+ {
469
+ "epoch": 1.28,
470
+ "eval_accuracy": 0.8008,
471
+ "eval_f1_macro": 0.6945223141031294,
472
+ "eval_f1_micro": 0.8008,
473
+ "eval_loss": 0.7289281487464905,
474
+ "eval_runtime": 47.4458,
475
+ "eval_samples_per_second": 210.767,
476
+ "eval_steps_per_second": 3.309,
477
+ "step": 1200
478
+ },
479
+ {
480
+ "epoch": 1.31,
481
+ "grad_norm": 72.01395416259766,
482
+ "learning_rate": 2.823383084577115e-06,
483
+ "loss": 0.8075,
484
+ "step": 1225
485
+ },
486
+ {
487
+ "epoch": 1.33,
488
+ "grad_norm": 83.60379791259766,
489
+ "learning_rate": 2.7789623312011375e-06,
490
+ "loss": 0.8068,
491
+ "step": 1250
492
+ },
493
+ {
494
+ "epoch": 1.36,
495
+ "grad_norm": 51.42044448852539,
496
+ "learning_rate": 2.7345415778251598e-06,
497
+ "loss": 0.7549,
498
+ "step": 1275
499
+ },
500
+ {
501
+ "epoch": 1.39,
502
+ "grad_norm": 44.68650436401367,
503
+ "learning_rate": 2.690120824449183e-06,
504
+ "loss": 0.7359,
505
+ "step": 1300
506
+ },
507
+ {
508
+ "epoch": 1.39,
509
+ "eval_accuracy": 0.8034,
510
+ "eval_f1_macro": 0.6975565105528009,
511
+ "eval_f1_micro": 0.8034,
512
+ "eval_loss": 0.7253593802452087,
513
+ "eval_runtime": 47.5217,
514
+ "eval_samples_per_second": 210.43,
515
+ "eval_steps_per_second": 3.304,
516
+ "step": 1300
517
+ },
518
+ {
519
+ "epoch": 1.41,
520
+ "grad_norm": 56.39244842529297,
521
+ "learning_rate": 2.6457000710732055e-06,
522
+ "loss": 0.7201,
523
+ "step": 1325
524
+ },
525
+ {
526
+ "epoch": 1.44,
527
+ "grad_norm": 70.84113311767578,
528
+ "learning_rate": 2.601279317697228e-06,
529
+ "loss": 0.7346,
530
+ "step": 1350
531
+ },
532
+ {
533
+ "epoch": 1.47,
534
+ "grad_norm": 69.2415542602539,
535
+ "learning_rate": 2.5568585643212513e-06,
536
+ "loss": 0.6693,
537
+ "step": 1375
538
+ },
539
+ {
540
+ "epoch": 1.49,
541
+ "grad_norm": 50.06897735595703,
542
+ "learning_rate": 2.512437810945274e-06,
543
+ "loss": 0.6525,
544
+ "step": 1400
545
+ },
546
+ {
547
+ "epoch": 1.49,
548
+ "eval_accuracy": 0.8065,
549
+ "eval_f1_macro": 0.7050317065636842,
550
+ "eval_f1_micro": 0.8065,
551
+ "eval_loss": 0.7072968482971191,
552
+ "eval_runtime": 47.4893,
553
+ "eval_samples_per_second": 210.574,
554
+ "eval_steps_per_second": 3.306,
555
+ "step": 1400
556
+ },
557
+ {
558
+ "epoch": 1.52,
559
+ "grad_norm": 45.797054290771484,
560
+ "learning_rate": 2.4680170575692966e-06,
561
+ "loss": 0.7271,
562
+ "step": 1425
563
+ },
564
+ {
565
+ "epoch": 1.55,
566
+ "grad_norm": 46.304473876953125,
567
+ "learning_rate": 2.4235963041933193e-06,
568
+ "loss": 0.8033,
569
+ "step": 1450
570
+ },
571
+ {
572
+ "epoch": 1.57,
573
+ "grad_norm": 80.502685546875,
574
+ "learning_rate": 2.379175550817342e-06,
575
+ "loss": 0.7464,
576
+ "step": 1475
577
+ },
578
+ {
579
+ "epoch": 1.6,
580
+ "grad_norm": 89.19364166259766,
581
+ "learning_rate": 2.3347547974413646e-06,
582
+ "loss": 0.7359,
583
+ "step": 1500
584
+ },
585
+ {
586
+ "epoch": 1.6,
587
+ "eval_accuracy": 0.8033,
588
+ "eval_f1_macro": 0.6948589139841357,
589
+ "eval_f1_micro": 0.8033,
590
+ "eval_loss": 0.720634400844574,
591
+ "eval_runtime": 47.454,
592
+ "eval_samples_per_second": 210.73,
593
+ "eval_steps_per_second": 3.308,
594
+ "step": 1500
595
+ },
596
+ {
597
+ "epoch": 1.63,
598
+ "grad_norm": 36.966548919677734,
599
+ "learning_rate": 2.2903340440653877e-06,
600
+ "loss": 0.697,
601
+ "step": 1525
602
+ },
603
+ {
604
+ "epoch": 1.65,
605
+ "grad_norm": 37.08382797241211,
606
+ "learning_rate": 2.24591329068941e-06,
607
+ "loss": 0.6736,
608
+ "step": 1550
609
+ },
610
+ {
611
+ "epoch": 1.68,
612
+ "grad_norm": 37.009403228759766,
613
+ "learning_rate": 2.201492537313433e-06,
614
+ "loss": 0.6441,
615
+ "step": 1575
616
+ },
617
+ {
618
+ "epoch": 1.71,
619
+ "grad_norm": 29.34271240234375,
620
+ "learning_rate": 2.1570717839374557e-06,
621
+ "loss": 0.7291,
622
+ "step": 1600
623
+ },
624
+ {
625
+ "epoch": 1.71,
626
+ "eval_accuracy": 0.8089,
627
+ "eval_f1_macro": 0.7065968196696667,
628
+ "eval_f1_micro": 0.8089,
629
+ "eval_loss": 0.6923750042915344,
630
+ "eval_runtime": 47.4715,
631
+ "eval_samples_per_second": 210.653,
632
+ "eval_steps_per_second": 3.307,
633
+ "step": 1600
634
+ },
635
+ {
636
+ "epoch": 1.73,
637
+ "grad_norm": 43.28564453125,
638
+ "learning_rate": 2.112651030561479e-06,
639
+ "loss": 0.7153,
640
+ "step": 1625
641
+ },
642
+ {
643
+ "epoch": 1.76,
644
+ "grad_norm": 27.64020347595215,
645
+ "learning_rate": 2.068230277185501e-06,
646
+ "loss": 0.6721,
647
+ "step": 1650
648
+ },
649
+ {
650
+ "epoch": 1.79,
651
+ "grad_norm": 46.75600051879883,
652
+ "learning_rate": 2.023809523809524e-06,
653
+ "loss": 0.6566,
654
+ "step": 1675
655
+ },
656
+ {
657
+ "epoch": 1.81,
658
+ "grad_norm": 34.07355499267578,
659
+ "learning_rate": 1.979388770433547e-06,
660
+ "loss": 0.7072,
661
+ "step": 1700
662
+ },
663
+ {
664
+ "epoch": 1.81,
665
+ "eval_accuracy": 0.8102,
666
+ "eval_f1_macro": 0.7070176051219198,
667
+ "eval_f1_micro": 0.8102,
668
+ "eval_loss": 0.6763781309127808,
669
+ "eval_runtime": 47.526,
670
+ "eval_samples_per_second": 210.411,
671
+ "eval_steps_per_second": 3.303,
672
+ "step": 1700
673
+ },
674
+ {
675
+ "epoch": 1.84,
676
+ "grad_norm": 43.36367416381836,
677
+ "learning_rate": 1.9349680170575695e-06,
678
+ "loss": 0.7289,
679
+ "step": 1725
680
+ },
681
+ {
682
+ "epoch": 1.87,
683
+ "grad_norm": 34.61235046386719,
684
+ "learning_rate": 1.8905472636815921e-06,
685
+ "loss": 0.6787,
686
+ "step": 1750
687
+ },
688
+ {
689
+ "epoch": 1.89,
690
+ "grad_norm": 44.31460952758789,
691
+ "learning_rate": 1.846126510305615e-06,
692
+ "loss": 0.7188,
693
+ "step": 1775
694
+ },
695
+ {
696
+ "epoch": 1.92,
697
+ "grad_norm": 53.3677864074707,
698
+ "learning_rate": 1.8017057569296375e-06,
699
+ "loss": 0.6688,
700
+ "step": 1800
701
+ },
702
+ {
703
+ "epoch": 1.92,
704
+ "eval_accuracy": 0.814,
705
+ "eval_f1_macro": 0.7128286594201773,
706
+ "eval_f1_micro": 0.814,
707
+ "eval_loss": 0.6546062231063843,
708
+ "eval_runtime": 47.5163,
709
+ "eval_samples_per_second": 210.454,
710
+ "eval_steps_per_second": 3.304,
711
+ "step": 1800
712
+ },
713
+ {
714
+ "epoch": 1.95,
715
+ "grad_norm": 37.4492073059082,
716
+ "learning_rate": 1.7572850035536603e-06,
717
+ "loss": 0.7817,
718
+ "step": 1825
719
+ },
720
+ {
721
+ "epoch": 1.97,
722
+ "grad_norm": 41.068538665771484,
723
+ "learning_rate": 1.7128642501776832e-06,
724
+ "loss": 0.7044,
725
+ "step": 1850
726
+ },
727
+ {
728
+ "epoch": 2.0,
729
+ "grad_norm": 67.96875762939453,
730
+ "learning_rate": 1.668443496801706e-06,
731
+ "loss": 0.5948,
732
+ "step": 1875
733
+ },
734
+ {
735
+ "epoch": 2.03,
736
+ "grad_norm": 51.58526611328125,
737
+ "learning_rate": 1.6240227434257286e-06,
738
+ "loss": 0.6253,
739
+ "step": 1900
740
+ },
741
+ {
742
+ "epoch": 2.03,
743
+ "eval_accuracy": 0.8158,
744
+ "eval_f1_macro": 0.7058775462036815,
745
+ "eval_f1_micro": 0.8158,
746
+ "eval_loss": 0.6505562663078308,
747
+ "eval_runtime": 47.3282,
748
+ "eval_samples_per_second": 211.29,
749
+ "eval_steps_per_second": 3.317,
750
+ "step": 1900
751
+ },
752
+ {
753
+ "epoch": 2.05,
754
+ "grad_norm": 45.662109375,
755
+ "learning_rate": 1.5796019900497514e-06,
756
+ "loss": 0.645,
757
+ "step": 1925
758
+ },
759
+ {
760
+ "epoch": 2.08,
761
+ "grad_norm": 66.76183319091797,
762
+ "learning_rate": 1.5351812366737743e-06,
763
+ "loss": 0.6412,
764
+ "step": 1950
765
+ },
766
+ {
767
+ "epoch": 2.11,
768
+ "grad_norm": 56.84629440307617,
769
+ "learning_rate": 1.4907604832977968e-06,
770
+ "loss": 0.6511,
771
+ "step": 1975
772
+ },
773
+ {
774
+ "epoch": 2.13,
775
+ "grad_norm": 53.2021484375,
776
+ "learning_rate": 1.4463397299218196e-06,
777
+ "loss": 0.6044,
778
+ "step": 2000
779
+ },
780
+ {
781
+ "epoch": 2.13,
782
+ "eval_accuracy": 0.8155,
783
+ "eval_f1_macro": 0.716530877903978,
784
+ "eval_f1_micro": 0.8155,
785
+ "eval_loss": 0.6602968573570251,
786
+ "eval_runtime": 47.473,
787
+ "eval_samples_per_second": 210.646,
788
+ "eval_steps_per_second": 3.307,
789
+ "step": 2000
790
+ },
791
+ {
792
+ "epoch": 2.16,
793
+ "grad_norm": 71.7922134399414,
794
+ "learning_rate": 1.4019189765458423e-06,
795
+ "loss": 0.6381,
796
+ "step": 2025
797
+ },
798
+ {
799
+ "epoch": 2.19,
800
+ "grad_norm": 32.50026321411133,
801
+ "learning_rate": 1.357498223169865e-06,
802
+ "loss": 0.6622,
803
+ "step": 2050
804
+ },
805
+ {
806
+ "epoch": 2.21,
807
+ "grad_norm": 50.483219146728516,
808
+ "learning_rate": 1.3130774697938879e-06,
809
+ "loss": 0.6165,
810
+ "step": 2075
811
+ },
812
+ {
813
+ "epoch": 2.24,
814
+ "grad_norm": 40.9278450012207,
815
+ "learning_rate": 1.2686567164179105e-06,
816
+ "loss": 0.6414,
817
+ "step": 2100
818
+ },
819
+ {
820
+ "epoch": 2.24,
821
+ "eval_accuracy": 0.8138,
822
+ "eval_f1_macro": 0.7185019905510756,
823
+ "eval_f1_micro": 0.8138,
824
+ "eval_loss": 0.6434906125068665,
825
+ "eval_runtime": 47.5169,
826
+ "eval_samples_per_second": 210.452,
827
+ "eval_steps_per_second": 3.304,
828
+ "step": 2100
829
+ },
830
+ {
831
+ "epoch": 2.27,
832
+ "grad_norm": 40.769439697265625,
833
+ "learning_rate": 1.2242359630419332e-06,
834
+ "loss": 0.619,
835
+ "step": 2125
836
+ },
837
+ {
838
+ "epoch": 2.29,
839
+ "grad_norm": 23.210596084594727,
840
+ "learning_rate": 1.179815209665956e-06,
841
+ "loss": 0.6168,
842
+ "step": 2150
843
+ },
844
+ {
845
+ "epoch": 2.32,
846
+ "grad_norm": 43.848052978515625,
847
+ "learning_rate": 1.1353944562899787e-06,
848
+ "loss": 0.5244,
849
+ "step": 2175
850
+ },
851
+ {
852
+ "epoch": 2.35,
853
+ "grad_norm": 40.81973648071289,
854
+ "learning_rate": 1.0909737029140014e-06,
855
+ "loss": 0.6115,
856
+ "step": 2200
857
+ },
858
+ {
859
+ "epoch": 2.35,
860
+ "eval_accuracy": 0.8216,
861
+ "eval_f1_macro": 0.727953382739938,
862
+ "eval_f1_micro": 0.8216,
863
+ "eval_loss": 0.63681560754776,
864
+ "eval_runtime": 47.4723,
865
+ "eval_samples_per_second": 210.649,
866
+ "eval_steps_per_second": 3.307,
867
+ "step": 2200
868
+ },
869
+ {
870
+ "epoch": 2.37,
871
+ "grad_norm": 28.034944534301758,
872
+ "learning_rate": 1.0465529495380243e-06,
873
+ "loss": 0.5613,
874
+ "step": 2225
875
+ },
876
+ {
877
+ "epoch": 2.4,
878
+ "grad_norm": 68.5925521850586,
879
+ "learning_rate": 1.002132196162047e-06,
880
+ "loss": 0.5987,
881
+ "step": 2250
882
+ },
883
+ {
884
+ "epoch": 2.43,
885
+ "grad_norm": 30.3986759185791,
886
+ "learning_rate": 9.577114427860696e-07,
887
+ "loss": 0.6119,
888
+ "step": 2275
889
+ },
890
+ {
891
+ "epoch": 2.45,
892
+ "grad_norm": 38.481117248535156,
893
+ "learning_rate": 9.132906894100925e-07,
894
+ "loss": 0.6331,
895
+ "step": 2300
896
+ },
897
+ {
898
+ "epoch": 2.45,
899
+ "eval_accuracy": 0.8208,
900
+ "eval_f1_macro": 0.7251441527998863,
901
+ "eval_f1_micro": 0.8208,
902
+ "eval_loss": 0.6273249983787537,
903
+ "eval_runtime": 47.475,
904
+ "eval_samples_per_second": 210.637,
905
+ "eval_steps_per_second": 3.307,
906
+ "step": 2300
907
+ },
908
+ {
909
+ "epoch": 2.48,
910
+ "grad_norm": 52.91291427612305,
911
+ "learning_rate": 8.688699360341152e-07,
912
+ "loss": 0.6261,
913
+ "step": 2325
914
+ },
915
+ {
916
+ "epoch": 2.51,
917
+ "grad_norm": 43.07246398925781,
918
+ "learning_rate": 8.24449182658138e-07,
919
+ "loss": 0.6191,
920
+ "step": 2350
921
+ },
922
+ {
923
+ "epoch": 2.53,
924
+ "grad_norm": 40.49489974975586,
925
+ "learning_rate": 7.800284292821607e-07,
926
+ "loss": 0.5856,
927
+ "step": 2375
928
+ },
929
+ {
930
+ "epoch": 2.56,
931
+ "grad_norm": 30.555904388427734,
932
+ "learning_rate": 7.356076759061834e-07,
933
+ "loss": 0.608,
934
+ "step": 2400
935
+ },
936
+ {
937
+ "epoch": 2.56,
938
+ "eval_accuracy": 0.8232,
939
+ "eval_f1_macro": 0.7285501243647127,
940
+ "eval_f1_micro": 0.8232,
941
+ "eval_loss": 0.6251906156539917,
942
+ "eval_runtime": 47.5564,
943
+ "eval_samples_per_second": 210.277,
944
+ "eval_steps_per_second": 3.301,
945
+ "step": 2400
946
+ },
947
+ {
948
+ "epoch": 2.59,
949
+ "grad_norm": 175.31057739257812,
950
+ "learning_rate": 6.911869225302062e-07,
951
+ "loss": 0.6802,
952
+ "step": 2425
953
+ },
954
+ {
955
+ "epoch": 2.61,
956
+ "grad_norm": 30.15215301513672,
957
+ "learning_rate": 6.467661691542289e-07,
958
+ "loss": 0.6307,
959
+ "step": 2450
960
+ },
961
+ {
962
+ "epoch": 2.64,
963
+ "grad_norm": 34.21811294555664,
964
+ "learning_rate": 6.023454157782517e-07,
965
+ "loss": 0.6029,
966
+ "step": 2475
967
+ },
968
+ {
969
+ "epoch": 2.67,
970
+ "grad_norm": 56.559364318847656,
971
+ "learning_rate": 5.579246624022743e-07,
972
+ "loss": 0.5879,
973
+ "step": 2500
974
+ },
975
+ {
976
+ "epoch": 2.67,
977
+ "eval_accuracy": 0.8241,
978
+ "eval_f1_macro": 0.7307624039691639,
979
+ "eval_f1_micro": 0.8241,
980
+ "eval_loss": 0.6171656250953674,
981
+ "eval_runtime": 47.4737,
982
+ "eval_samples_per_second": 210.643,
983
+ "eval_steps_per_second": 3.307,
984
+ "step": 2500
985
+ },
986
+ {
987
+ "epoch": 2.69,
988
+ "grad_norm": 43.20689392089844,
989
+ "learning_rate": 5.135039090262971e-07,
990
+ "loss": 0.5858,
991
+ "step": 2525
992
+ },
993
+ {
994
+ "epoch": 2.72,
995
+ "grad_norm": 46.331817626953125,
996
+ "learning_rate": 4.690831556503199e-07,
997
+ "loss": 0.5959,
998
+ "step": 2550
999
+ },
1000
+ {
1001
+ "epoch": 2.75,
1002
+ "grad_norm": 36.399810791015625,
1003
+ "learning_rate": 4.2466240227434256e-07,
1004
+ "loss": 0.6069,
1005
+ "step": 2575
1006
+ },
1007
+ {
1008
+ "epoch": 2.77,
1009
+ "grad_norm": 79.88939666748047,
1010
+ "learning_rate": 3.8024164889836533e-07,
1011
+ "loss": 0.6056,
1012
+ "step": 2600
1013
+ },
1014
+ {
1015
+ "epoch": 2.77,
1016
+ "eval_accuracy": 0.8257,
1017
+ "eval_f1_macro": 0.7346364945364393,
1018
+ "eval_f1_micro": 0.8257,
1019
+ "eval_loss": 0.6157156229019165,
1020
+ "eval_runtime": 47.4846,
1021
+ "eval_samples_per_second": 210.595,
1022
+ "eval_steps_per_second": 3.306,
1023
+ "step": 2600
1024
+ },
1025
+ {
1026
+ "epoch": 2.8,
1027
+ "grad_norm": 49.164161682128906,
1028
+ "learning_rate": 3.358208955223881e-07,
1029
+ "loss": 0.5675,
1030
+ "step": 2625
1031
+ },
1032
+ {
1033
+ "epoch": 2.83,
1034
+ "grad_norm": 46.98076248168945,
1035
+ "learning_rate": 2.914001421464108e-07,
1036
+ "loss": 0.6607,
1037
+ "step": 2650
1038
+ },
1039
+ {
1040
+ "epoch": 2.85,
1041
+ "grad_norm": 23.488380432128906,
1042
+ "learning_rate": 2.4697938877043354e-07,
1043
+ "loss": 0.5866,
1044
+ "step": 2675
1045
+ },
1046
+ {
1047
+ "epoch": 2.88,
1048
+ "grad_norm": 31.710861206054688,
1049
+ "learning_rate": 2.0255863539445632e-07,
1050
+ "loss": 0.5711,
1051
+ "step": 2700
1052
+ },
1053
+ {
1054
+ "epoch": 2.88,
1055
+ "eval_accuracy": 0.8253,
1056
+ "eval_f1_macro": 0.7341228101010588,
1057
+ "eval_f1_micro": 0.8253,
1058
+ "eval_loss": 0.6129437685012817,
1059
+ "eval_runtime": 47.5391,
1060
+ "eval_samples_per_second": 210.353,
1061
+ "eval_steps_per_second": 3.303,
1062
+ "step": 2700
1063
+ },
1064
+ {
1065
+ "epoch": 2.91,
1066
+ "grad_norm": 33.91932678222656,
1067
+ "learning_rate": 1.5813788201847903e-07,
1068
+ "loss": 0.5565,
1069
+ "step": 2725
1070
+ },
1071
+ {
1072
+ "epoch": 2.93,
1073
+ "grad_norm": 35.29643630981445,
1074
+ "learning_rate": 1.1371712864250178e-07,
1075
+ "loss": 0.5793,
1076
+ "step": 2750
1077
+ },
1078
+ {
1079
+ "epoch": 2.96,
1080
+ "grad_norm": 33.85700988769531,
1081
+ "learning_rate": 6.929637526652453e-08,
1082
+ "loss": 0.5425,
1083
+ "step": 2775
1084
+ },
1085
+ {
1086
+ "epoch": 2.99,
1087
+ "grad_norm": 40.65436935424805,
1088
+ "learning_rate": 2.4875621890547265e-08,
1089
+ "loss": 0.5802,
1090
+ "step": 2800
1091
+ },
1092
+ {
1093
+ "epoch": 2.99,
1094
+ "eval_accuracy": 0.826,
1095
+ "eval_f1_macro": 0.7355084015446216,
1096
+ "eval_f1_micro": 0.826,
1097
+ "eval_loss": 0.6120218634605408,
1098
+ "eval_runtime": 47.528,
1099
+ "eval_samples_per_second": 210.402,
1100
+ "eval_steps_per_second": 3.303,
1101
+ "step": 2800
1102
+ },
1103
+ {
1104
+ "epoch": 3.0,
1105
+ "step": 2814,
1106
+ "total_flos": 3.482386379487314e+17,
1107
+ "train_loss": 0.9835220694796108,
1108
+ "train_runtime": 6489.4436,
1109
+ "train_samples_per_second": 27.737,
1110
+ "train_steps_per_second": 0.434
1111
+ }
1112
+ ],
1113
+ "logging_steps": 25,
1114
+ "max_steps": 2814,
1115
+ "num_input_tokens_seen": 0,
1116
+ "num_train_epochs": 3,
1117
+ "save_steps": 100,
1118
+ "total_flos": 3.482386379487314e+17,
1119
+ "train_batch_size": 32,
1120
+ "trial_name": null,
1121
+ "trial_params": null
1122
+ }
microsoft/phi_2_ledgar/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9726a6f1cd618b1c6756600627232628ca181750693975f1aa65486662e1136c
3
+ size 5944
microsoft/phi_2_ledgar/vocab.json ADDED
The diff for this file is too large to render. See raw diff