Abeersherif commited on
Commit
1142cda
·
verified ·
1 Parent(s): f47bdb2

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. chat_template.jinja +4 -0
  2. checkpoint-2000/chat_template.jinja +4 -0
  3. checkpoint-2000/config.json +30 -0
  4. checkpoint-2000/generation_config.json +10 -0
  5. checkpoint-2000/merges.txt +0 -0
  6. checkpoint-2000/model.safetensors +3 -0
  7. checkpoint-2000/optimizer.pt +3 -0
  8. checkpoint-2000/rng_state.pth +3 -0
  9. checkpoint-2000/scaler.pt +3 -0
  10. checkpoint-2000/scheduler.pt +3 -0
  11. checkpoint-2000/special_tokens_map.json +34 -0
  12. checkpoint-2000/tokenizer.json +0 -0
  13. checkpoint-2000/tokenizer_config.json +154 -0
  14. checkpoint-2000/trainer_state.json +314 -0
  15. checkpoint-2000/training_args.bin +3 -0
  16. checkpoint-2000/vocab.json +0 -0
  17. checkpoint-4000/chat_template.jinja +4 -0
  18. checkpoint-4000/config.json +30 -0
  19. checkpoint-4000/generation_config.json +10 -0
  20. checkpoint-4000/merges.txt +0 -0
  21. checkpoint-4000/model.safetensors +3 -0
  22. checkpoint-4000/optimizer.pt +3 -0
  23. checkpoint-4000/rng_state.pth +3 -0
  24. checkpoint-4000/scaler.pt +3 -0
  25. checkpoint-4000/scheduler.pt +3 -0
  26. checkpoint-4000/special_tokens_map.json +34 -0
  27. checkpoint-4000/tokenizer.json +0 -0
  28. checkpoint-4000/tokenizer_config.json +154 -0
  29. checkpoint-4000/trainer_state.json +594 -0
  30. checkpoint-4000/training_args.bin +3 -0
  31. checkpoint-4000/vocab.json +0 -0
  32. checkpoint-4245/chat_template.jinja +4 -0
  33. checkpoint-4245/config.json +30 -0
  34. checkpoint-4245/generation_config.json +10 -0
  35. checkpoint-4245/merges.txt +0 -0
  36. checkpoint-4245/model.safetensors +3 -0
  37. checkpoint-4245/optimizer.pt +3 -0
  38. checkpoint-4245/rng_state.pth +3 -0
  39. checkpoint-4245/scaler.pt +3 -0
  40. checkpoint-4245/scheduler.pt +3 -0
  41. checkpoint-4245/special_tokens_map.json +34 -0
  42. checkpoint-4245/tokenizer.json +0 -0
  43. checkpoint-4245/tokenizer_config.json +154 -0
  44. checkpoint-4245/trainer_state.json +622 -0
  45. checkpoint-4245/training_args.bin +3 -0
  46. checkpoint-4245/vocab.json +0 -0
  47. config.json +30 -0
  48. generation_config.json +10 -0
  49. merges.txt +0 -0
  50. model.safetensors +3 -0
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-2000/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-2000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "4.57.1",
28
+ "use_cache": true,
29
+ "vocab_size": 49152
30
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "max_new_tokens": 40,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.57.1"
10
+ }
checkpoint-2000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e007c6bce0e34753699359c165313cebcb0d7caec991d6d76793ae10976723
3
+ size 538090408
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbe7401f5a3079f5079ecd5a4fb224d2c3cdffdf273b251a3d4ac7bf4e69b39
3
+ size 1076353291
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
3
+ size 1383
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7336ee0ebbd43f587938c211204d98c8a6df3c838104ed7f3f972e00611af785
3
+ size 1465
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "clean_up_tokenization_spaces": false,
147
+ "eos_token": "<|im_end|>",
148
+ "extra_special_tokens": {},
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4711980209683119,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011779950524207798,
14
+ "grad_norm": 2.4857845306396484,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 1.8343,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.023559901048415596,
21
+ "grad_norm": 1.9041292667388916,
22
+ "learning_rate": 1.98e-05,
23
+ "loss": 1.2675,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03533985157262339,
28
+ "grad_norm": 1.7534877061843872,
29
+ "learning_rate": 1.976357056694813e-05,
30
+ "loss": 1.2149,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04711980209683119,
35
+ "grad_norm": 1.2397135496139526,
36
+ "learning_rate": 1.9522316043425815e-05,
37
+ "loss": 1.1763,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05889975262103899,
42
+ "grad_norm": 1.390807032585144,
43
+ "learning_rate": 1.9281061519903498e-05,
44
+ "loss": 1.1537,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.07067970314524678,
49
+ "grad_norm": 1.6474590301513672,
50
+ "learning_rate": 1.9039806996381183e-05,
51
+ "loss": 1.1585,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.08245965366945458,
56
+ "grad_norm": 1.7290133237838745,
57
+ "learning_rate": 1.879855247285887e-05,
58
+ "loss": 1.1395,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.09423960419366238,
63
+ "grad_norm": 1.5090484619140625,
64
+ "learning_rate": 1.855729794933655e-05,
65
+ "loss": 1.1484,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.10601955471787018,
70
+ "grad_norm": 1.5769039392471313,
71
+ "learning_rate": 1.8316043425814237e-05,
72
+ "loss": 1.1172,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.11779950524207798,
77
+ "grad_norm": 1.869503378868103,
78
+ "learning_rate": 1.807478890229192e-05,
79
+ "loss": 1.1302,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.1295794557662858,
84
+ "grad_norm": 1.4532737731933594,
85
+ "learning_rate": 1.7833534378769604e-05,
86
+ "loss": 1.1165,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.14135940629049357,
91
+ "grad_norm": 1.5250763893127441,
92
+ "learning_rate": 1.7592279855247287e-05,
93
+ "loss": 1.1043,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.15313935681470137,
98
+ "grad_norm": 1.5375722646713257,
99
+ "learning_rate": 1.7351025331724972e-05,
100
+ "loss": 1.1322,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.16491930733890917,
105
+ "grad_norm": 1.4326726198196411,
106
+ "learning_rate": 1.7109770808202654e-05,
107
+ "loss": 1.0999,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.17669925786311697,
112
+ "grad_norm": 1.5550315380096436,
113
+ "learning_rate": 1.686851628468034e-05,
114
+ "loss": 1.0914,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.18847920838732476,
119
+ "grad_norm": 1.5411320924758911,
120
+ "learning_rate": 1.6627261761158022e-05,
121
+ "loss": 1.1068,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.20025915891153256,
126
+ "grad_norm": 1.581898808479309,
127
+ "learning_rate": 1.6386007237635704e-05,
128
+ "loss": 1.1076,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.21203910943574036,
133
+ "grad_norm": 1.3629993200302124,
134
+ "learning_rate": 1.6144752714113393e-05,
135
+ "loss": 1.0853,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.22381905995994816,
140
+ "grad_norm": 1.5700671672821045,
141
+ "learning_rate": 1.5903498190591076e-05,
142
+ "loss": 1.0833,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.23559901048415596,
147
+ "grad_norm": 1.6526682376861572,
148
+ "learning_rate": 1.5662243667068758e-05,
149
+ "loss": 1.1049,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.24737896100836376,
154
+ "grad_norm": 1.663944125175476,
155
+ "learning_rate": 1.5420989143546443e-05,
156
+ "loss": 1.0847,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.2591589115325716,
161
+ "grad_norm": 1.4961705207824707,
162
+ "learning_rate": 1.5179734620024127e-05,
163
+ "loss": 1.0914,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.27093886205677936,
168
+ "grad_norm": 1.76039457321167,
169
+ "learning_rate": 1.4938480096501811e-05,
170
+ "loss": 1.1108,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.28271881258098713,
175
+ "grad_norm": 1.7683743238449097,
176
+ "learning_rate": 1.4697225572979495e-05,
177
+ "loss": 1.0982,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.29449876310519496,
182
+ "grad_norm": 1.540376901626587,
183
+ "learning_rate": 1.4455971049457179e-05,
184
+ "loss": 1.0766,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.30627871362940273,
189
+ "grad_norm": 1.3952268362045288,
190
+ "learning_rate": 1.4214716525934861e-05,
191
+ "loss": 1.0792,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.31805866415361056,
196
+ "grad_norm": 1.5013277530670166,
197
+ "learning_rate": 1.3973462002412545e-05,
198
+ "loss": 1.0843,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.32983861467781833,
203
+ "grad_norm": 1.506777048110962,
204
+ "learning_rate": 1.3732207478890229e-05,
205
+ "loss": 1.0981,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.34161856520202616,
210
+ "grad_norm": 1.3855302333831787,
211
+ "learning_rate": 1.3490952955367914e-05,
212
+ "loss": 1.1056,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.35339851572623393,
217
+ "grad_norm": 1.5296212434768677,
218
+ "learning_rate": 1.3249698431845598e-05,
219
+ "loss": 1.0776,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.36517846625044176,
224
+ "grad_norm": 1.3882752656936646,
225
+ "learning_rate": 1.3008443908323282e-05,
226
+ "loss": 1.0834,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.37695841677464953,
231
+ "grad_norm": 1.5645182132720947,
232
+ "learning_rate": 1.2767189384800966e-05,
233
+ "loss": 1.0751,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.38873836729885736,
238
+ "grad_norm": 1.42621910572052,
239
+ "learning_rate": 1.252593486127865e-05,
240
+ "loss": 1.0736,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.40051831782306513,
245
+ "grad_norm": 1.6674786806106567,
246
+ "learning_rate": 1.2284680337756334e-05,
247
+ "loss": 1.0872,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.41229826834727296,
252
+ "grad_norm": 1.2423211336135864,
253
+ "learning_rate": 1.2043425814234018e-05,
254
+ "loss": 1.0522,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.4240782188714807,
259
+ "grad_norm": 1.6971081495285034,
260
+ "learning_rate": 1.1802171290711702e-05,
261
+ "loss": 1.0585,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.43585816939568855,
266
+ "grad_norm": 1.5267912149429321,
267
+ "learning_rate": 1.1560916767189386e-05,
268
+ "loss": 1.0765,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.4476381199198963,
273
+ "grad_norm": 1.5102652311325073,
274
+ "learning_rate": 1.131966224366707e-05,
275
+ "loss": 1.0361,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.45941807044410415,
280
+ "grad_norm": 1.1953086853027344,
281
+ "learning_rate": 1.1078407720144753e-05,
282
+ "loss": 1.056,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4711980209683119,
287
+ "grad_norm": 1.5494145154953003,
288
+ "learning_rate": 1.0837153196622439e-05,
289
+ "loss": 1.0614,
290
+ "step": 2000
291
+ }
292
+ ],
293
+ "logging_steps": 50,
294
+ "max_steps": 4245,
295
+ "num_input_tokens_seen": 0,
296
+ "num_train_epochs": 1,
297
+ "save_steps": 2000,
298
+ "stateful_callbacks": {
299
+ "TrainerControl": {
300
+ "args": {
301
+ "should_epoch_stop": false,
302
+ "should_evaluate": false,
303
+ "should_log": false,
304
+ "should_save": true,
305
+ "should_training_stop": false
306
+ },
307
+ "attributes": {}
308
+ }
309
+ },
310
+ "total_flos": 1845006370131456.0,
311
+ "train_batch_size": 4,
312
+ "trial_name": null,
313
+ "trial_params": null
314
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f20a3b02b00239ae2899f66eebf8dcf57fa94f04a1164c46967c63200582c3
3
+ size 5777
checkpoint-2000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-4000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "4.57.1",
28
+ "use_cache": true,
29
+ "vocab_size": 49152
30
+ }
checkpoint-4000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "max_new_tokens": 40,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.57.1"
10
+ }
checkpoint-4000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0592fb12a4feb53b9acfcc3a6513d99b30dcdbacb511221c4f85afe732e082
3
+ size 538090408
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d909bf53b0e9fa9321d49805958601383ed983d1bc026239870b95240d3b36f2
3
+ size 1076353291
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-4000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
3
+ size 1383
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c0a3804aeabc7766d12cfd8bce6f469faec420f8d198351e9174df181b76ac
3
+ size 1465
checkpoint-4000/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-4000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "clean_up_tokenization_spaces": false,
147
+ "eos_token": "<|im_end|>",
148
+ "extra_special_tokens": {},
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9423960419366239,
6
+ "eval_steps": 500,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011779950524207798,
14
+ "grad_norm": 2.4857845306396484,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 1.8343,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.023559901048415596,
21
+ "grad_norm": 1.9041292667388916,
22
+ "learning_rate": 1.98e-05,
23
+ "loss": 1.2675,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03533985157262339,
28
+ "grad_norm": 1.7534877061843872,
29
+ "learning_rate": 1.976357056694813e-05,
30
+ "loss": 1.2149,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04711980209683119,
35
+ "grad_norm": 1.2397135496139526,
36
+ "learning_rate": 1.9522316043425815e-05,
37
+ "loss": 1.1763,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05889975262103899,
42
+ "grad_norm": 1.390807032585144,
43
+ "learning_rate": 1.9281061519903498e-05,
44
+ "loss": 1.1537,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.07067970314524678,
49
+ "grad_norm": 1.6474590301513672,
50
+ "learning_rate": 1.9039806996381183e-05,
51
+ "loss": 1.1585,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.08245965366945458,
56
+ "grad_norm": 1.7290133237838745,
57
+ "learning_rate": 1.879855247285887e-05,
58
+ "loss": 1.1395,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.09423960419366238,
63
+ "grad_norm": 1.5090484619140625,
64
+ "learning_rate": 1.855729794933655e-05,
65
+ "loss": 1.1484,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.10601955471787018,
70
+ "grad_norm": 1.5769039392471313,
71
+ "learning_rate": 1.8316043425814237e-05,
72
+ "loss": 1.1172,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.11779950524207798,
77
+ "grad_norm": 1.869503378868103,
78
+ "learning_rate": 1.807478890229192e-05,
79
+ "loss": 1.1302,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.1295794557662858,
84
+ "grad_norm": 1.4532737731933594,
85
+ "learning_rate": 1.7833534378769604e-05,
86
+ "loss": 1.1165,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.14135940629049357,
91
+ "grad_norm": 1.5250763893127441,
92
+ "learning_rate": 1.7592279855247287e-05,
93
+ "loss": 1.1043,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.15313935681470137,
98
+ "grad_norm": 1.5375722646713257,
99
+ "learning_rate": 1.7351025331724972e-05,
100
+ "loss": 1.1322,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.16491930733890917,
105
+ "grad_norm": 1.4326726198196411,
106
+ "learning_rate": 1.7109770808202654e-05,
107
+ "loss": 1.0999,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.17669925786311697,
112
+ "grad_norm": 1.5550315380096436,
113
+ "learning_rate": 1.686851628468034e-05,
114
+ "loss": 1.0914,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.18847920838732476,
119
+ "grad_norm": 1.5411320924758911,
120
+ "learning_rate": 1.6627261761158022e-05,
121
+ "loss": 1.1068,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.20025915891153256,
126
+ "grad_norm": 1.581898808479309,
127
+ "learning_rate": 1.6386007237635704e-05,
128
+ "loss": 1.1076,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.21203910943574036,
133
+ "grad_norm": 1.3629993200302124,
134
+ "learning_rate": 1.6144752714113393e-05,
135
+ "loss": 1.0853,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.22381905995994816,
140
+ "grad_norm": 1.5700671672821045,
141
+ "learning_rate": 1.5903498190591076e-05,
142
+ "loss": 1.0833,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.23559901048415596,
147
+ "grad_norm": 1.6526682376861572,
148
+ "learning_rate": 1.5662243667068758e-05,
149
+ "loss": 1.1049,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.24737896100836376,
154
+ "grad_norm": 1.663944125175476,
155
+ "learning_rate": 1.5420989143546443e-05,
156
+ "loss": 1.0847,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.2591589115325716,
161
+ "grad_norm": 1.4961705207824707,
162
+ "learning_rate": 1.5179734620024127e-05,
163
+ "loss": 1.0914,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.27093886205677936,
168
+ "grad_norm": 1.76039457321167,
169
+ "learning_rate": 1.4938480096501811e-05,
170
+ "loss": 1.1108,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.28271881258098713,
175
+ "grad_norm": 1.7683743238449097,
176
+ "learning_rate": 1.4697225572979495e-05,
177
+ "loss": 1.0982,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.29449876310519496,
182
+ "grad_norm": 1.540376901626587,
183
+ "learning_rate": 1.4455971049457179e-05,
184
+ "loss": 1.0766,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.30627871362940273,
189
+ "grad_norm": 1.3952268362045288,
190
+ "learning_rate": 1.4214716525934861e-05,
191
+ "loss": 1.0792,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.31805866415361056,
196
+ "grad_norm": 1.5013277530670166,
197
+ "learning_rate": 1.3973462002412545e-05,
198
+ "loss": 1.0843,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.32983861467781833,
203
+ "grad_norm": 1.506777048110962,
204
+ "learning_rate": 1.3732207478890229e-05,
205
+ "loss": 1.0981,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.34161856520202616,
210
+ "grad_norm": 1.3855302333831787,
211
+ "learning_rate": 1.3490952955367914e-05,
212
+ "loss": 1.1056,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.35339851572623393,
217
+ "grad_norm": 1.5296212434768677,
218
+ "learning_rate": 1.3249698431845598e-05,
219
+ "loss": 1.0776,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.36517846625044176,
224
+ "grad_norm": 1.3882752656936646,
225
+ "learning_rate": 1.3008443908323282e-05,
226
+ "loss": 1.0834,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.37695841677464953,
231
+ "grad_norm": 1.5645182132720947,
232
+ "learning_rate": 1.2767189384800966e-05,
233
+ "loss": 1.0751,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.38873836729885736,
238
+ "grad_norm": 1.42621910572052,
239
+ "learning_rate": 1.252593486127865e-05,
240
+ "loss": 1.0736,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.40051831782306513,
245
+ "grad_norm": 1.6674786806106567,
246
+ "learning_rate": 1.2284680337756334e-05,
247
+ "loss": 1.0872,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.41229826834727296,
252
+ "grad_norm": 1.2423211336135864,
253
+ "learning_rate": 1.2043425814234018e-05,
254
+ "loss": 1.0522,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.4240782188714807,
259
+ "grad_norm": 1.6971081495285034,
260
+ "learning_rate": 1.1802171290711702e-05,
261
+ "loss": 1.0585,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.43585816939568855,
266
+ "grad_norm": 1.5267912149429321,
267
+ "learning_rate": 1.1560916767189386e-05,
268
+ "loss": 1.0765,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.4476381199198963,
273
+ "grad_norm": 1.5102652311325073,
274
+ "learning_rate": 1.131966224366707e-05,
275
+ "loss": 1.0361,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.45941807044410415,
280
+ "grad_norm": 1.1953086853027344,
281
+ "learning_rate": 1.1078407720144753e-05,
282
+ "loss": 1.056,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4711980209683119,
287
+ "grad_norm": 1.5494145154953003,
288
+ "learning_rate": 1.0837153196622439e-05,
289
+ "loss": 1.0614,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.48297797149251975,
294
+ "grad_norm": 1.424010157585144,
295
+ "learning_rate": 1.0595898673100123e-05,
296
+ "loss": 1.0784,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.4947579220167275,
301
+ "grad_norm": 1.547558307647705,
302
+ "learning_rate": 1.0354644149577807e-05,
303
+ "loss": 1.063,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.5065378725409353,
308
+ "grad_norm": 1.4514057636260986,
309
+ "learning_rate": 1.0113389626055489e-05,
310
+ "loss": 1.062,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.5183178230651432,
315
+ "grad_norm": 1.283713936805725,
316
+ "learning_rate": 9.872135102533173e-06,
317
+ "loss": 1.0691,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.530097773589351,
322
+ "grad_norm": 1.5060367584228516,
323
+ "learning_rate": 9.630880579010857e-06,
324
+ "loss": 1.0622,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.5418777241135587,
329
+ "grad_norm": 1.7280113697052002,
330
+ "learning_rate": 9.38962605548854e-06,
331
+ "loss": 1.0568,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.5536576746377665,
336
+ "grad_norm": 1.4609959125518799,
337
+ "learning_rate": 9.148371531966225e-06,
338
+ "loss": 1.0405,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.5654376251619743,
343
+ "grad_norm": 1.46717369556427,
344
+ "learning_rate": 8.90711700844391e-06,
345
+ "loss": 1.087,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.5772175756861821,
350
+ "grad_norm": 1.513267159461975,
351
+ "learning_rate": 8.665862484921594e-06,
352
+ "loss": 1.0413,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5889975262103899,
357
+ "grad_norm": 1.4865115880966187,
358
+ "learning_rate": 8.424607961399276e-06,
359
+ "loss": 1.0488,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.6007774767345977,
364
+ "grad_norm": 1.6761298179626465,
365
+ "learning_rate": 8.18335343787696e-06,
366
+ "loss": 1.0709,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.6125574272588055,
371
+ "grad_norm": 1.3326189517974854,
372
+ "learning_rate": 7.942098914354644e-06,
373
+ "loss": 1.0548,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.6243373777830133,
378
+ "grad_norm": 1.6205568313598633,
379
+ "learning_rate": 7.700844390832328e-06,
380
+ "loss": 1.0557,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.6361173283072211,
385
+ "grad_norm": 1.7094571590423584,
386
+ "learning_rate": 7.4595898673100135e-06,
387
+ "loss": 1.0392,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.6478972788314289,
392
+ "grad_norm": 1.4315111637115479,
393
+ "learning_rate": 7.2183353437876966e-06,
394
+ "loss": 1.0542,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.6596772293556367,
399
+ "grad_norm": 1.6000643968582153,
400
+ "learning_rate": 6.9770808202653805e-06,
401
+ "loss": 1.0567,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.6714571798798445,
406
+ "grad_norm": 1.821889877319336,
407
+ "learning_rate": 6.735826296743064e-06,
408
+ "loss": 1.0469,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.6832371304040523,
413
+ "grad_norm": 1.4687271118164062,
414
+ "learning_rate": 6.494571773220748e-06,
415
+ "loss": 1.0614,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.6950170809282601,
420
+ "grad_norm": 1.4694554805755615,
421
+ "learning_rate": 6.253317249698433e-06,
422
+ "loss": 1.0456,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.7067970314524679,
427
+ "grad_norm": 1.5050467252731323,
428
+ "learning_rate": 6.012062726176117e-06,
429
+ "loss": 1.0649,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.7185769819766757,
434
+ "grad_norm": 1.3030104637145996,
435
+ "learning_rate": 5.770808202653801e-06,
436
+ "loss": 1.049,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.7303569325008835,
441
+ "grad_norm": 1.426845669746399,
442
+ "learning_rate": 5.529553679131484e-06,
443
+ "loss": 1.064,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.7421368830250913,
448
+ "grad_norm": 1.4176698923110962,
449
+ "learning_rate": 5.288299155609168e-06,
450
+ "loss": 1.0423,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.7539168335492991,
455
+ "grad_norm": 1.7557893991470337,
456
+ "learning_rate": 5.047044632086852e-06,
457
+ "loss": 1.047,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.7656967840735069,
462
+ "grad_norm": 1.4390746355056763,
463
+ "learning_rate": 4.8057901085645355e-06,
464
+ "loss": 1.0585,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.7774767345977147,
469
+ "grad_norm": 1.5117220878601074,
470
+ "learning_rate": 4.56453558504222e-06,
471
+ "loss": 1.0498,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.7892566851219225,
476
+ "grad_norm": 1.2958707809448242,
477
+ "learning_rate": 4.323281061519904e-06,
478
+ "loss": 1.0385,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.8010366356461303,
483
+ "grad_norm": 1.5557655096054077,
484
+ "learning_rate": 4.082026537997588e-06,
485
+ "loss": 1.059,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.8128165861703381,
490
+ "grad_norm": 1.4961349964141846,
491
+ "learning_rate": 3.840772014475272e-06,
492
+ "loss": 1.0299,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.8245965366945459,
497
+ "grad_norm": 1.2806799411773682,
498
+ "learning_rate": 3.599517490952956e-06,
499
+ "loss": 1.0688,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.8363764872187537,
504
+ "grad_norm": 1.4575563669204712,
505
+ "learning_rate": 3.3582629674306393e-06,
506
+ "loss": 1.0623,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.8481564377429615,
511
+ "grad_norm": 1.2596416473388672,
512
+ "learning_rate": 3.1170084439083236e-06,
513
+ "loss": 1.0534,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.8599363882671692,
518
+ "grad_norm": 1.479817509651184,
519
+ "learning_rate": 2.8757539203860075e-06,
520
+ "loss": 1.043,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.8717163387913771,
525
+ "grad_norm": 1.3471312522888184,
526
+ "learning_rate": 2.634499396863691e-06,
527
+ "loss": 1.0453,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.8834962893155849,
532
+ "grad_norm": 1.2828015089035034,
533
+ "learning_rate": 2.3932448733413753e-06,
534
+ "loss": 1.0441,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.8952762398397927,
539
+ "grad_norm": 1.610693097114563,
540
+ "learning_rate": 2.151990349819059e-06,
541
+ "loss": 1.0739,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.9070561903640004,
546
+ "grad_norm": 1.4694626331329346,
547
+ "learning_rate": 1.910735826296743e-06,
548
+ "loss": 1.0341,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.9188361408882083,
553
+ "grad_norm": 1.4196053743362427,
554
+ "learning_rate": 1.6694813027744272e-06,
555
+ "loss": 1.0441,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.9306160914124161,
560
+ "grad_norm": 1.558480978012085,
561
+ "learning_rate": 1.4282267792521113e-06,
562
+ "loss": 1.0646,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.9423960419366239,
567
+ "grad_norm": 1.602553129196167,
568
+ "learning_rate": 1.186972255729795e-06,
569
+ "loss": 1.061,
570
+ "step": 4000
571
+ }
572
+ ],
573
+ "logging_steps": 50,
574
+ "max_steps": 4245,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 1,
577
+ "save_steps": 2000,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": false
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 3709549928028672.0,
591
+ "train_batch_size": 4,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f20a3b02b00239ae2899f66eebf8dcf57fa94f04a1164c46967c63200582c3
3
+ size 5777
checkpoint-4000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4245/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-4245/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "4.57.1",
28
+ "use_cache": true,
29
+ "vocab_size": 49152
30
+ }
checkpoint-4245/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "max_new_tokens": 40,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.57.1"
10
+ }
checkpoint-4245/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4245/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c216ce7fbb29c7f41e1988417a0ff9726e921168b125239c8eabf255c5949258
3
+ size 538090408
checkpoint-4245/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece67dc2523f0155eaa987b2b9dbe238871ae5bfbcad7868d11578ef479c3e40
3
+ size 1076353291
checkpoint-4245/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-4245/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
3
+ size 1383
checkpoint-4245/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd804538ca37343c88588206425d0dee8559dd4257d26744a8add56713b1bcf
3
+ size 1465
checkpoint-4245/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-4245/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4245/tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "clean_up_tokenization_spaces": false,
147
+ "eos_token": "<|im_end|>",
148
+ "extra_special_tokens": {},
149
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
checkpoint-4245/trainer_state.json ADDED
@@ -0,0 +1,622 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4245,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011779950524207798,
14
+ "grad_norm": 2.4857845306396484,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 1.8343,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.023559901048415596,
21
+ "grad_norm": 1.9041292667388916,
22
+ "learning_rate": 1.98e-05,
23
+ "loss": 1.2675,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03533985157262339,
28
+ "grad_norm": 1.7534877061843872,
29
+ "learning_rate": 1.976357056694813e-05,
30
+ "loss": 1.2149,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04711980209683119,
35
+ "grad_norm": 1.2397135496139526,
36
+ "learning_rate": 1.9522316043425815e-05,
37
+ "loss": 1.1763,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05889975262103899,
42
+ "grad_norm": 1.390807032585144,
43
+ "learning_rate": 1.9281061519903498e-05,
44
+ "loss": 1.1537,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.07067970314524678,
49
+ "grad_norm": 1.6474590301513672,
50
+ "learning_rate": 1.9039806996381183e-05,
51
+ "loss": 1.1585,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.08245965366945458,
56
+ "grad_norm": 1.7290133237838745,
57
+ "learning_rate": 1.879855247285887e-05,
58
+ "loss": 1.1395,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.09423960419366238,
63
+ "grad_norm": 1.5090484619140625,
64
+ "learning_rate": 1.855729794933655e-05,
65
+ "loss": 1.1484,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.10601955471787018,
70
+ "grad_norm": 1.5769039392471313,
71
+ "learning_rate": 1.8316043425814237e-05,
72
+ "loss": 1.1172,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.11779950524207798,
77
+ "grad_norm": 1.869503378868103,
78
+ "learning_rate": 1.807478890229192e-05,
79
+ "loss": 1.1302,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.1295794557662858,
84
+ "grad_norm": 1.4532737731933594,
85
+ "learning_rate": 1.7833534378769604e-05,
86
+ "loss": 1.1165,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.14135940629049357,
91
+ "grad_norm": 1.5250763893127441,
92
+ "learning_rate": 1.7592279855247287e-05,
93
+ "loss": 1.1043,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.15313935681470137,
98
+ "grad_norm": 1.5375722646713257,
99
+ "learning_rate": 1.7351025331724972e-05,
100
+ "loss": 1.1322,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.16491930733890917,
105
+ "grad_norm": 1.4326726198196411,
106
+ "learning_rate": 1.7109770808202654e-05,
107
+ "loss": 1.0999,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.17669925786311697,
112
+ "grad_norm": 1.5550315380096436,
113
+ "learning_rate": 1.686851628468034e-05,
114
+ "loss": 1.0914,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.18847920838732476,
119
+ "grad_norm": 1.5411320924758911,
120
+ "learning_rate": 1.6627261761158022e-05,
121
+ "loss": 1.1068,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.20025915891153256,
126
+ "grad_norm": 1.581898808479309,
127
+ "learning_rate": 1.6386007237635704e-05,
128
+ "loss": 1.1076,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.21203910943574036,
133
+ "grad_norm": 1.3629993200302124,
134
+ "learning_rate": 1.6144752714113393e-05,
135
+ "loss": 1.0853,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.22381905995994816,
140
+ "grad_norm": 1.5700671672821045,
141
+ "learning_rate": 1.5903498190591076e-05,
142
+ "loss": 1.0833,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.23559901048415596,
147
+ "grad_norm": 1.6526682376861572,
148
+ "learning_rate": 1.5662243667068758e-05,
149
+ "loss": 1.1049,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.24737896100836376,
154
+ "grad_norm": 1.663944125175476,
155
+ "learning_rate": 1.5420989143546443e-05,
156
+ "loss": 1.0847,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.2591589115325716,
161
+ "grad_norm": 1.4961705207824707,
162
+ "learning_rate": 1.5179734620024127e-05,
163
+ "loss": 1.0914,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.27093886205677936,
168
+ "grad_norm": 1.76039457321167,
169
+ "learning_rate": 1.4938480096501811e-05,
170
+ "loss": 1.1108,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.28271881258098713,
175
+ "grad_norm": 1.7683743238449097,
176
+ "learning_rate": 1.4697225572979495e-05,
177
+ "loss": 1.0982,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.29449876310519496,
182
+ "grad_norm": 1.540376901626587,
183
+ "learning_rate": 1.4455971049457179e-05,
184
+ "loss": 1.0766,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.30627871362940273,
189
+ "grad_norm": 1.3952268362045288,
190
+ "learning_rate": 1.4214716525934861e-05,
191
+ "loss": 1.0792,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.31805866415361056,
196
+ "grad_norm": 1.5013277530670166,
197
+ "learning_rate": 1.3973462002412545e-05,
198
+ "loss": 1.0843,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.32983861467781833,
203
+ "grad_norm": 1.506777048110962,
204
+ "learning_rate": 1.3732207478890229e-05,
205
+ "loss": 1.0981,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.34161856520202616,
210
+ "grad_norm": 1.3855302333831787,
211
+ "learning_rate": 1.3490952955367914e-05,
212
+ "loss": 1.1056,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.35339851572623393,
217
+ "grad_norm": 1.5296212434768677,
218
+ "learning_rate": 1.3249698431845598e-05,
219
+ "loss": 1.0776,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.36517846625044176,
224
+ "grad_norm": 1.3882752656936646,
225
+ "learning_rate": 1.3008443908323282e-05,
226
+ "loss": 1.0834,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.37695841677464953,
231
+ "grad_norm": 1.5645182132720947,
232
+ "learning_rate": 1.2767189384800966e-05,
233
+ "loss": 1.0751,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.38873836729885736,
238
+ "grad_norm": 1.42621910572052,
239
+ "learning_rate": 1.252593486127865e-05,
240
+ "loss": 1.0736,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.40051831782306513,
245
+ "grad_norm": 1.6674786806106567,
246
+ "learning_rate": 1.2284680337756334e-05,
247
+ "loss": 1.0872,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.41229826834727296,
252
+ "grad_norm": 1.2423211336135864,
253
+ "learning_rate": 1.2043425814234018e-05,
254
+ "loss": 1.0522,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.4240782188714807,
259
+ "grad_norm": 1.6971081495285034,
260
+ "learning_rate": 1.1802171290711702e-05,
261
+ "loss": 1.0585,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.43585816939568855,
266
+ "grad_norm": 1.5267912149429321,
267
+ "learning_rate": 1.1560916767189386e-05,
268
+ "loss": 1.0765,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.4476381199198963,
273
+ "grad_norm": 1.5102652311325073,
274
+ "learning_rate": 1.131966224366707e-05,
275
+ "loss": 1.0361,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.45941807044410415,
280
+ "grad_norm": 1.1953086853027344,
281
+ "learning_rate": 1.1078407720144753e-05,
282
+ "loss": 1.056,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4711980209683119,
287
+ "grad_norm": 1.5494145154953003,
288
+ "learning_rate": 1.0837153196622439e-05,
289
+ "loss": 1.0614,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.48297797149251975,
294
+ "grad_norm": 1.424010157585144,
295
+ "learning_rate": 1.0595898673100123e-05,
296
+ "loss": 1.0784,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.4947579220167275,
301
+ "grad_norm": 1.547558307647705,
302
+ "learning_rate": 1.0354644149577807e-05,
303
+ "loss": 1.063,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.5065378725409353,
308
+ "grad_norm": 1.4514057636260986,
309
+ "learning_rate": 1.0113389626055489e-05,
310
+ "loss": 1.062,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.5183178230651432,
315
+ "grad_norm": 1.283713936805725,
316
+ "learning_rate": 9.872135102533173e-06,
317
+ "loss": 1.0691,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.530097773589351,
322
+ "grad_norm": 1.5060367584228516,
323
+ "learning_rate": 9.630880579010857e-06,
324
+ "loss": 1.0622,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.5418777241135587,
329
+ "grad_norm": 1.7280113697052002,
330
+ "learning_rate": 9.38962605548854e-06,
331
+ "loss": 1.0568,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.5536576746377665,
336
+ "grad_norm": 1.4609959125518799,
337
+ "learning_rate": 9.148371531966225e-06,
338
+ "loss": 1.0405,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.5654376251619743,
343
+ "grad_norm": 1.46717369556427,
344
+ "learning_rate": 8.90711700844391e-06,
345
+ "loss": 1.087,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.5772175756861821,
350
+ "grad_norm": 1.513267159461975,
351
+ "learning_rate": 8.665862484921594e-06,
352
+ "loss": 1.0413,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5889975262103899,
357
+ "grad_norm": 1.4865115880966187,
358
+ "learning_rate": 8.424607961399276e-06,
359
+ "loss": 1.0488,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.6007774767345977,
364
+ "grad_norm": 1.6761298179626465,
365
+ "learning_rate": 8.18335343787696e-06,
366
+ "loss": 1.0709,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.6125574272588055,
371
+ "grad_norm": 1.3326189517974854,
372
+ "learning_rate": 7.942098914354644e-06,
373
+ "loss": 1.0548,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.6243373777830133,
378
+ "grad_norm": 1.6205568313598633,
379
+ "learning_rate": 7.700844390832328e-06,
380
+ "loss": 1.0557,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.6361173283072211,
385
+ "grad_norm": 1.7094571590423584,
386
+ "learning_rate": 7.4595898673100135e-06,
387
+ "loss": 1.0392,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.6478972788314289,
392
+ "grad_norm": 1.4315111637115479,
393
+ "learning_rate": 7.2183353437876966e-06,
394
+ "loss": 1.0542,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.6596772293556367,
399
+ "grad_norm": 1.6000643968582153,
400
+ "learning_rate": 6.9770808202653805e-06,
401
+ "loss": 1.0567,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.6714571798798445,
406
+ "grad_norm": 1.821889877319336,
407
+ "learning_rate": 6.735826296743064e-06,
408
+ "loss": 1.0469,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.6832371304040523,
413
+ "grad_norm": 1.4687271118164062,
414
+ "learning_rate": 6.494571773220748e-06,
415
+ "loss": 1.0614,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.6950170809282601,
420
+ "grad_norm": 1.4694554805755615,
421
+ "learning_rate": 6.253317249698433e-06,
422
+ "loss": 1.0456,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.7067970314524679,
427
+ "grad_norm": 1.5050467252731323,
428
+ "learning_rate": 6.012062726176117e-06,
429
+ "loss": 1.0649,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.7185769819766757,
434
+ "grad_norm": 1.3030104637145996,
435
+ "learning_rate": 5.770808202653801e-06,
436
+ "loss": 1.049,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.7303569325008835,
441
+ "grad_norm": 1.426845669746399,
442
+ "learning_rate": 5.529553679131484e-06,
443
+ "loss": 1.064,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.7421368830250913,
448
+ "grad_norm": 1.4176698923110962,
449
+ "learning_rate": 5.288299155609168e-06,
450
+ "loss": 1.0423,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.7539168335492991,
455
+ "grad_norm": 1.7557893991470337,
456
+ "learning_rate": 5.047044632086852e-06,
457
+ "loss": 1.047,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.7656967840735069,
462
+ "grad_norm": 1.4390746355056763,
463
+ "learning_rate": 4.8057901085645355e-06,
464
+ "loss": 1.0585,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.7774767345977147,
469
+ "grad_norm": 1.5117220878601074,
470
+ "learning_rate": 4.56453558504222e-06,
471
+ "loss": 1.0498,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.7892566851219225,
476
+ "grad_norm": 1.2958707809448242,
477
+ "learning_rate": 4.323281061519904e-06,
478
+ "loss": 1.0385,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.8010366356461303,
483
+ "grad_norm": 1.5557655096054077,
484
+ "learning_rate": 4.082026537997588e-06,
485
+ "loss": 1.059,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.8128165861703381,
490
+ "grad_norm": 1.4961349964141846,
491
+ "learning_rate": 3.840772014475272e-06,
492
+ "loss": 1.0299,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.8245965366945459,
497
+ "grad_norm": 1.2806799411773682,
498
+ "learning_rate": 3.599517490952956e-06,
499
+ "loss": 1.0688,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.8363764872187537,
504
+ "grad_norm": 1.4575563669204712,
505
+ "learning_rate": 3.3582629674306393e-06,
506
+ "loss": 1.0623,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.8481564377429615,
511
+ "grad_norm": 1.2596416473388672,
512
+ "learning_rate": 3.1170084439083236e-06,
513
+ "loss": 1.0534,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.8599363882671692,
518
+ "grad_norm": 1.479817509651184,
519
+ "learning_rate": 2.8757539203860075e-06,
520
+ "loss": 1.043,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.8717163387913771,
525
+ "grad_norm": 1.3471312522888184,
526
+ "learning_rate": 2.634499396863691e-06,
527
+ "loss": 1.0453,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.8834962893155849,
532
+ "grad_norm": 1.2828015089035034,
533
+ "learning_rate": 2.3932448733413753e-06,
534
+ "loss": 1.0441,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.8952762398397927,
539
+ "grad_norm": 1.610693097114563,
540
+ "learning_rate": 2.151990349819059e-06,
541
+ "loss": 1.0739,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.9070561903640004,
546
+ "grad_norm": 1.4694626331329346,
547
+ "learning_rate": 1.910735826296743e-06,
548
+ "loss": 1.0341,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.9188361408882083,
553
+ "grad_norm": 1.4196053743362427,
554
+ "learning_rate": 1.6694813027744272e-06,
555
+ "loss": 1.0441,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.9306160914124161,
560
+ "grad_norm": 1.558480978012085,
561
+ "learning_rate": 1.4282267792521113e-06,
562
+ "loss": 1.0646,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.9423960419366239,
567
+ "grad_norm": 1.602553129196167,
568
+ "learning_rate": 1.186972255729795e-06,
569
+ "loss": 1.061,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.9541759924608316,
574
+ "grad_norm": 1.4343607425689697,
575
+ "learning_rate": 9.45717732207479e-07,
576
+ "loss": 1.0353,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.9659559429850395,
581
+ "grad_norm": 1.1924039125442505,
582
+ "learning_rate": 7.044632086851629e-07,
583
+ "loss": 1.0412,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.9777358935092473,
588
+ "grad_norm": 1.7164132595062256,
589
+ "learning_rate": 4.6320868516284687e-07,
590
+ "loss": 1.0474,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.989515844033455,
595
+ "grad_norm": 1.4795231819152832,
596
+ "learning_rate": 2.2195416164053077e-07,
597
+ "loss": 1.0529,
598
+ "step": 4200
599
+ }
600
+ ],
601
+ "logging_steps": 50,
602
+ "max_steps": 4245,
603
+ "num_input_tokens_seen": 0,
604
+ "num_train_epochs": 1,
605
+ "save_steps": 2000,
606
+ "stateful_callbacks": {
607
+ "TrainerControl": {
608
+ "args": {
609
+ "should_epoch_stop": false,
610
+ "should_evaluate": false,
611
+ "should_log": false,
612
+ "should_save": true,
613
+ "should_training_stop": true
614
+ },
615
+ "attributes": {}
616
+ }
617
+ },
618
+ "total_flos": 3934530267184512.0,
619
+ "train_batch_size": 4,
620
+ "trial_name": null,
621
+ "trial_params": null
622
+ }
checkpoint-4245/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f20a3b02b00239ae2899f66eebf8dcf57fa94f04a1164c46967c63200582c3
3
+ size 5777
checkpoint-4245/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "transformers_version": "4.57.1",
28
+ "use_cache": true,
29
+ "vocab_size": 49152
30
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "max_new_tokens": 40,
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.57.1"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c216ce7fbb29c7f41e1988417a0ff9726e921168b125239c8eabf255c5949258
3
+ size 538090408