Montalte commited on
Commit
bfd8cf9
·
verified ·
1 Parent(s): 2496517

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": 151643,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.2.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": false,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "max_new_tokens": 2048,
8
+ "pad_token_id": 151643,
9
+ "transformers_version": "5.2.0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78eefb26b998b290177a8455afb8c1c8edfb6ef101080f635842dbadb5d8d82
3
+ size 2384234968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc630b4060a09ef2c20251f53d03ce9d164848b1862da95ec1ea3f99226ad8ae
3
+ size 4768669395
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdde1a524b981925b2a7c3979d750b1be1ffab0ffc8345621787881a5039540e
3
+ size 1465
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "padding_side": "right",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
trainer_state.json ADDED
@@ -0,0 +1,657 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 200,
7
+ "global_step": 891,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03368421052631579,
14
+ "grad_norm": 0.39124977588653564,
15
+ "learning_rate": 4.000000000000001e-06,
16
+ "loss": 0.6411091327667237,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06736842105263158,
21
+ "grad_norm": 0.292263388633728,
22
+ "learning_rate": 8.444444444444446e-06,
23
+ "loss": 0.5484030246734619,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.10105263157894737,
28
+ "grad_norm": 0.25442785024642944,
29
+ "learning_rate": 1.288888888888889e-05,
30
+ "loss": 0.5427792072296143,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.13473684210526315,
35
+ "grad_norm": 0.2947239875793457,
36
+ "learning_rate": 1.7333333333333336e-05,
37
+ "loss": 0.5606600761413574,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.16842105263157894,
42
+ "grad_norm": 0.2775092124938965,
43
+ "learning_rate": 1.9998896833611603e-05,
44
+ "loss": 0.5333517074584961,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.20210526315789473,
49
+ "grad_norm": 0.29785287380218506,
50
+ "learning_rate": 1.9986489006814454e-05,
51
+ "loss": 0.5225426197052002,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.23578947368421052,
56
+ "grad_norm": 0.2655927836894989,
57
+ "learning_rate": 1.9960311560501457e-05,
58
+ "loss": 0.5233192920684815,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.2694736842105263,
63
+ "grad_norm": 0.26086923480033875,
64
+ "learning_rate": 1.99204005887869e-05,
65
+ "loss": 0.5474831581115722,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.3031578947368421,
70
+ "grad_norm": 0.28363120555877686,
71
+ "learning_rate": 1.986681112191161e-05,
72
+ "loss": 0.5189789772033692,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3368421052631579,
77
+ "grad_norm": 0.27852076292037964,
78
+ "learning_rate": 1.979961705036587e-05,
79
+ "loss": 0.5073096752166748,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3705263157894737,
84
+ "grad_norm": 0.2481539398431778,
85
+ "learning_rate": 1.9718911023007382e-05,
86
+ "loss": 0.5242129325866699,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.40421052631578946,
91
+ "grad_norm": 0.29133835434913635,
92
+ "learning_rate": 1.9624804319314704e-05,
93
+ "loss": 0.5255519866943359,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.4378947368421053,
98
+ "grad_norm": 0.24475380778312683,
99
+ "learning_rate": 1.9517426695952358e-05,
100
+ "loss": 0.5238783836364747,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.47157894736842104,
105
+ "grad_norm": 0.20989426970481873,
106
+ "learning_rate": 1.9396926207859085e-05,
107
+ "loss": 0.5111160278320312,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.5052631578947369,
112
+ "grad_norm": 0.26935264468193054,
113
+ "learning_rate": 1.926346900410604e-05,
114
+ "loss": 0.5124940872192383,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5389473684210526,
119
+ "grad_norm": 0.2176002562046051,
120
+ "learning_rate": 1.9117239098806296e-05,
121
+ "loss": 0.5246289253234864,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5726315789473684,
126
+ "grad_norm": 0.24210523068904877,
127
+ "learning_rate": 1.895843811739162e-05,
128
+ "loss": 0.5537409305572509,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.6063157894736843,
133
+ "grad_norm": 0.257548451423645,
134
+ "learning_rate": 1.87872850186063e-05,
135
+ "loss": 0.513533639907837,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.64,
140
+ "grad_norm": 0.23951275646686554,
141
+ "learning_rate": 1.8604015792601395e-05,
142
+ "loss": 0.48828821182250975,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6736842105263158,
147
+ "grad_norm": 0.2258734107017517,
148
+ "learning_rate": 1.8408883135545634e-05,
149
+ "loss": 0.5039851188659668,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.7073684210526315,
154
+ "grad_norm": 0.19968342781066895,
155
+ "learning_rate": 1.8202156101201646e-05,
156
+ "loss": 0.521153450012207,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7410526315789474,
161
+ "grad_norm": 0.2292439192533493,
162
+ "learning_rate": 1.7984119729947944e-05,
163
+ "loss": 0.5093928337097168,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7747368421052632,
168
+ "grad_norm": 0.2542964518070221,
169
+ "learning_rate": 1.7755074655758174e-05,
170
+ "loss": 0.5263922691345215,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.8084210526315789,
175
+ "grad_norm": 0.2533174455165863,
176
+ "learning_rate": 1.7515336691679478e-05,
177
+ "loss": 0.49692983627319337,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.8421052631578947,
182
+ "grad_norm": 0.2821718156337738,
183
+ "learning_rate": 1.7265236394381634e-05,
184
+ "loss": 0.518037223815918,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8757894736842106,
189
+ "grad_norm": 0.2320486307144165,
190
+ "learning_rate": 1.7005118608377288e-05,
191
+ "loss": 0.49869470596313475,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.9094736842105263,
196
+ "grad_norm": 0.23216022551059723,
197
+ "learning_rate": 1.6735341990541766e-05,
198
+ "loss": 0.496633243560791,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.9431578947368421,
203
+ "grad_norm": 0.23232285678386688,
204
+ "learning_rate": 1.6456278515588023e-05,
205
+ "loss": 0.4894012451171875,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9768421052631578,
210
+ "grad_norm": 0.23754945397377014,
211
+ "learning_rate": 1.61683129631787e-05,
212
+ "loss": 0.4862018585205078,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.0101052631578948,
217
+ "grad_norm": 0.23209305107593536,
218
+ "learning_rate": 1.5871842387382307e-05,
219
+ "loss": 0.4496741771697998,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 1.0437894736842106,
224
+ "grad_norm": 0.230687215924263,
225
+ "learning_rate": 1.5567275569205216e-05,
226
+ "loss": 0.3736781120300293,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0774736842105264,
231
+ "grad_norm": 0.26011544466018677,
232
+ "learning_rate": 1.5255032452954246e-05,
233
+ "loss": 0.3811728239059448,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.1111578947368421,
238
+ "grad_norm": 0.2397359162569046,
239
+ "learning_rate": 1.4935543567206984e-05,
240
+ "loss": 0.3847402572631836,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.1448421052631579,
245
+ "grad_norm": 0.24537348747253418,
246
+ "learning_rate": 1.460924943118828e-05,
247
+ "loss": 0.4140181541442871,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1785263157894736,
252
+ "grad_norm": 0.29034218192100525,
253
+ "learning_rate": 1.4276599947371388e-05,
254
+ "loss": 0.40039353370666503,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.2122105263157894,
259
+ "grad_norm": 0.23461507260799408,
260
+ "learning_rate": 1.3938053781141224e-05,
261
+ "loss": 0.38444128036499026,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.2458947368421052,
266
+ "grad_norm": 0.278699666261673,
267
+ "learning_rate": 1.3594077728375129e-05,
268
+ "loss": 0.4034078598022461,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.279578947368421,
273
+ "grad_norm": 0.2430262416601181,
274
+ "learning_rate": 1.3245146071813114e-05,
275
+ "loss": 0.3933774471282959,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.313263157894737,
280
+ "grad_norm": 0.24822789430618286,
281
+ "learning_rate": 1.2891739927104992e-05,
282
+ "loss": 0.37237229347229006,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.3469473684210527,
287
+ "grad_norm": 0.23200945556163788,
288
+ "learning_rate": 1.2534346579436158e-05,
289
+ "loss": 0.3913832187652588,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3806315789473684,
294
+ "grad_norm": 0.22769705951213837,
295
+ "learning_rate": 1.217345881164667e-05,
296
+ "loss": 0.3784568071365356,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.4143157894736842,
301
+ "grad_norm": 0.24226728081703186,
302
+ "learning_rate": 1.1809574224769983e-05,
303
+ "loss": 0.39284965991973875,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.448,
308
+ "grad_norm": 0.25648000836372375,
309
+ "learning_rate": 1.1443194551928267e-05,
310
+ "loss": 0.38346447944641116,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4816842105263157,
315
+ "grad_norm": 0.26635488867759705,
316
+ "learning_rate": 1.1074824966530312e-05,
317
+ "loss": 0.4148388385772705,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.5153684210526315,
322
+ "grad_norm": 0.25696197152137756,
323
+ "learning_rate": 1.0704973385725853e-05,
324
+ "loss": 0.37754507064819337,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.5490526315789475,
329
+ "grad_norm": 0.2661338746547699,
330
+ "learning_rate": 1.0334149770076747e-05,
331
+ "loss": 0.3888374090194702,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.582736842105263,
336
+ "grad_norm": 0.26346883177757263,
337
+ "learning_rate": 9.962865420410702e-06,
338
+ "loss": 0.3881821632385254,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.616421052631579,
343
+ "grad_norm": 0.23709534108638763,
344
+ "learning_rate": 9.591632272826935e-06,
345
+ "loss": 0.3894140958786011,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.6501052631578947,
350
+ "grad_norm": 0.2380121797323227,
351
+ "learning_rate": 9.22096219282597e-06,
352
+ "loss": 0.38091790676116943,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.6837894736842105,
357
+ "grad_norm": 0.2552591562271118,
358
+ "learning_rate": 8.85136626953673e-06,
359
+ "loss": 0.3866596698760986,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.7174736842105263,
364
+ "grad_norm": 0.2706044018268585,
365
+ "learning_rate": 8.483354111014142e-06,
366
+ "loss": 0.34658288955688477,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.751157894736842,
371
+ "grad_norm": 0.238291934132576,
372
+ "learning_rate": 8.117433141578865e-06,
373
+ "loss": 0.3751774549484253,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.784842105263158,
378
+ "grad_norm": 0.2516458332538605,
379
+ "learning_rate": 7.75410790216802e-06,
380
+ "loss": 0.3806126356124878,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.8185263157894735,
385
+ "grad_norm": 0.2464667409658432,
386
+ "learning_rate": 7.3938793546615775e-06,
387
+ "loss": 0.3747535705566406,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.8522105263157895,
392
+ "grad_norm": 0.23317350447177887,
393
+ "learning_rate": 7.037244191143662e-06,
394
+ "loss": 0.39618306159973143,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.8858947368421053,
399
+ "grad_norm": 0.23871706426143646,
400
+ "learning_rate": 6.684694149051156e-06,
401
+ "loss": 0.39216933250427244,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.919578947368421,
406
+ "grad_norm": 0.25860607624053955,
407
+ "learning_rate": 6.336715333153869e-06,
408
+ "loss": 0.3773647308349609,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.9532631578947368,
413
+ "grad_norm": 0.24600288271903992,
414
+ "learning_rate": 5.993787545301204e-06,
415
+ "loss": 0.3795567274093628,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.9869473684210526,
420
+ "grad_norm": 0.263887882232666,
421
+ "learning_rate": 5.656383622859418e-06,
422
+ "loss": 0.3699490070343018,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 2.0202105263157897,
427
+ "grad_norm": 0.24102307856082916,
428
+ "learning_rate": 5.3249687867517095e-06,
429
+ "loss": 0.33141674995422366,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 2.053894736842105,
434
+ "grad_norm": 0.2210257202386856,
435
+ "learning_rate": 5.000000000000003e-06,
436
+ "loss": 0.2707043647766113,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 2.087578947368421,
441
+ "grad_norm": 0.25143396854400635,
442
+ "learning_rate": 4.681925337653006e-06,
443
+ "loss": 0.27166755199432374,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.1212631578947367,
448
+ "grad_norm": 0.23633138835430145,
449
+ "learning_rate": 4.371183368969165e-06,
450
+ "loss": 0.28992409706115724,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.1549473684210527,
455
+ "grad_norm": 0.248697429895401,
456
+ "learning_rate": 4.0682025527064486e-06,
457
+ "loss": 0.28457343578338623,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.1886315789473683,
462
+ "grad_norm": 0.26528167724609375,
463
+ "learning_rate": 3.7734006463527695e-06,
464
+ "loss": 0.2810338497161865,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.2223157894736842,
469
+ "grad_norm": 0.28675395250320435,
470
+ "learning_rate": 3.4871841301115615e-06,
471
+ "loss": 0.28777623176574707,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.2560000000000002,
476
+ "grad_norm": 0.24856451153755188,
477
+ "learning_rate": 3.209947646436752e-06,
478
+ "loss": 0.2675544500350952,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.2896842105263158,
483
+ "grad_norm": 0.27366021275520325,
484
+ "learning_rate": 2.9420734558899323e-06,
485
+ "loss": 0.27961390018463134,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.3233684210526317,
490
+ "grad_norm": 0.26319196820259094,
491
+ "learning_rate": 2.6839309100699975e-06,
492
+ "loss": 0.2918535232543945,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.3570526315789473,
497
+ "grad_norm": 0.3220144808292389,
498
+ "learning_rate": 2.4358759423419476e-06,
499
+ "loss": 0.2924020767211914,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.3907368421052633,
504
+ "grad_norm": 0.2410717010498047,
505
+ "learning_rate": 2.1982505770671303e-06,
506
+ "loss": 0.2743253707885742,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.424421052631579,
511
+ "grad_norm": 0.30828380584716797,
512
+ "learning_rate": 1.9713824580115336e-06,
513
+ "loss": 0.27377402782440186,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.458105263157895,
518
+ "grad_norm": 0.20561999082565308,
519
+ "learning_rate": 1.7555843965823992e-06,
520
+ "loss": 0.27103970050811765,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.4917894736842103,
525
+ "grad_norm": 0.26168638467788696,
526
+ "learning_rate": 1.5511539405160824e-06,
527
+ "loss": 0.2865826845169067,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.5254736842105263,
532
+ "grad_norm": 0.27809929847717285,
533
+ "learning_rate": 1.3583729636118359e-06,
534
+ "loss": 0.2839942455291748,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.559157894736842,
539
+ "grad_norm": 0.27653998136520386,
540
+ "learning_rate": 1.1775072770771833e-06,
541
+ "loss": 0.28238811492919924,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.592842105263158,
546
+ "grad_norm": 0.23926998674869537,
547
+ "learning_rate": 1.0088062630208272e-06,
548
+ "loss": 0.2802205324172974,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.626526315789474,
553
+ "grad_norm": 0.23364897072315216,
554
+ "learning_rate": 8.525025305983936e-07,
555
+ "loss": 0.2747425317764282,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.6602105263157894,
560
+ "grad_norm": 0.26213040947914124,
561
+ "learning_rate": 7.088115952851238e-07,
562
+ "loss": 0.264876651763916,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.6938947368421053,
567
+ "grad_norm": 0.23854820430278778,
568
+ "learning_rate": 5.779315817178e-07,
569
+ "loss": 0.27306721210479734,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.7275789473684213,
574
+ "grad_norm": 0.26059138774871826,
575
+ "learning_rate": 4.6004295051554236e-07,
576
+ "loss": 0.27785990238189695,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.761263157894737,
581
+ "grad_norm": 0.22004592418670654,
582
+ "learning_rate": 3.553082494562354e-07,
583
+ "loss": 0.28950111865997313,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.7949473684210524,
588
+ "grad_norm": 0.24607206881046295,
589
+ "learning_rate": 2.638718893515946e-07,
590
+ "loss": 0.28249540328979494,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.8286315789473684,
595
+ "grad_norm": 0.2633419930934906,
596
+ "learning_rate": 1.8585994492995917e-07,
597
+ "loss": 0.2748891353607178,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.8623157894736844,
602
+ "grad_norm": 0.2897525429725647,
603
+ "learning_rate": 1.21379981001305e-07,
604
+ "loss": 0.27536725997924805,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.896,
609
+ "grad_norm": 0.25982382893562317,
610
+ "learning_rate": 7.052090414422119e-08,
611
+ "loss": 0.2835198163986206,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.929684210526316,
616
+ "grad_norm": 0.2790670096874237,
617
+ "learning_rate": 3.335284011929951e-08,
618
+ "loss": 0.2774952411651611,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.9633684210526314,
623
+ "grad_norm": 0.24153731763362885,
624
+ "learning_rate": 9.927037177993593e-09,
625
+ "loss": 0.25984973907470704,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.9970526315789474,
630
+ "grad_norm": 0.215993270277977,
631
+ "learning_rate": 2.75795400255241e-10,
632
+ "loss": 0.28056533336639405,
633
+ "step": 890
634
+ }
635
+ ],
636
+ "logging_steps": 10,
637
+ "max_steps": 891,
638
+ "num_input_tokens_seen": 0,
639
+ "num_train_epochs": 3,
640
+ "save_steps": 200,
641
+ "stateful_callbacks": {
642
+ "TrainerControl": {
643
+ "args": {
644
+ "should_epoch_stop": false,
645
+ "should_evaluate": false,
646
+ "should_log": false,
647
+ "should_save": true,
648
+ "should_training_stop": true
649
+ },
650
+ "attributes": {}
651
+ }
652
+ },
653
+ "total_flos": 4.040324108884378e+16,
654
+ "train_batch_size": 2,
655
+ "trial_name": null,
656
+ "trial_params": null
657
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05796971c2805ec048dc38bacad1233ec744382d97d208f49cf86436e46843f0
3
+ size 5585