cryptobiosis commited on
Commit
dc75d2b
·
verified ·
1 Parent(s): 653b06b

Publish sanitized Stage 2 SFT1000 release

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
LICENSE ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "{}"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright {yyyy} {name of copyright owner}
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
NOTICE ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Kakeya OProver LoRA derivative, 2026 FluffyAIcode.
2
+ Base model: m-a-p/OProver-8B, Apache-2.0, revision cd9ffd383b584d95bf00e04b88b35b05928b211c.
3
+ Training material derives from leanprover-community/mathlib4, Apache-2.0, revision 360da6fa66c1273b76b6b2d8c5666fd5ac2e3b56.
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: m-a-p/OProver-8B
4
+ library_name: peft
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - lean
8
+ - lean4
9
+ - theorem-proving
10
+ - lora
11
+ - peft
12
+ ---
13
+
14
+ # Kakeya OProver Stage 2 — SFT1000
15
+
16
+ > **Status: MATCHED BASELINE**
17
+
18
+ ## Summary
19
+
20
+ This is an independent PEFT LoRA checkpoint in the Kakeya OProver training journey. It is a proof-advisor research artifact, not an autonomous proof or mathematical truth claim.
21
+
22
+ ## Training Data
23
+
24
+ Public data config: [`sft-1000`](https://huggingface.co/datasets/FluffyAIcode/Kakeya-OProver-Training). Artifact SHA-256: `5ebec3f7ed71d0af202924ea9d5ca12a857c5363b89b028dbf74268bf2e32f24`. Only Mathlib Apache-2.0 material and explicitly derived training negatives are included; provenance-incomplete OProofs mixtures were excluded.
25
+
26
+ ## Method
27
+
28
+ QLoRA supervised fine-tuning on 700 Mathlib examples, with 100 validation and 200 excluded holdout examples.
29
+
30
+ ## Strict Lean Evaluation
31
+
32
+ All matched Stage2–Stage4 evaluations used 22 tasks (18 holdout + 4 canary), one frozen task order, seed, temperature, token budget, and context policy. Parser rate was 22/22 and unsafe generations were 0 for matched evaluations.
33
+
34
+ ```json
35
+ {
36
+ "status": "MATCHED BASELINE",
37
+ "all22": {
38
+ "exact": 9,
39
+ "n": 22,
40
+ "parser": 22,
41
+ "unsafe": 0
42
+ },
43
+ "holdout18": {
44
+ "exact": 5,
45
+ "n": 18
46
+ },
47
+ "canary4": {
48
+ "exact": 4,
49
+ "n": 4
50
+ },
51
+ "audit_sha256": "5e0f757353ffe17315c9b78c60bb46de9ae34e736f9460e69ec26ca1d6213f9c",
52
+ "protocol_root": "6047aa9e4f3ff9594f7913e943cf40dc050b49328b7a42a80a72beefe5c641d7"
53
+ }
54
+ ```
55
+
56
+ ## Safety
57
+
58
+ No private chain-of-thought, production prompts, Jensen candidate proof bodies, credentials, or raw candidate-bearing signed audits are published. Stage status constrains use; Stage4 is **PROOF-ADVISOR-ONLY**.
59
+
60
+ ## Known Failures
61
+
62
+ 5/18 holdout tasks failed exact Lean validation. Warning-bearing outputs and one length stop were observed; unsafe outputs were zero.
63
+
64
+ ## Intended Use
65
+
66
+ Research on Lean proof suggestion, evaluation, and repair. Every generated proof must be compiled and independently reviewed. Not intended for unsupervised theorem claims or production deployment without separate authorization.
67
+
68
+ ## Reproducibility
69
+
70
+ - Base: [`m-a-p/OProver-8B`](https://huggingface.co/m-a-p/OProver-8B) at `cd9ffd383b584d95bf00e04b88b35b05928b211c`
71
+ - Immutable source revision: `8eead931f4b090bca2421fead7d0c64191bea116`
72
+ - Adapter SHA-256: `5e5399518c0741140a14d2cca2fade8ec3eb95fb587139c5c9894d5e297a3b55`
73
+ - Dataset artifact SHA-256: `5ebec3f7ed71d0af202924ea9d5ca12a857c5363b89b028dbf74268bf2e32f24`
74
+ - Sanitized machine-readable files: `evaluation/results.json`, `training/metrics.jsonl`, `training/trainer_state.json`, `provenance/manifest.json`
75
+ - Evaluation/audit digest references are in `evaluation/results.json`; raw candidate-bearing artifacts remain private.
76
+
77
+ ## Limitations
78
+
79
+ Small, single-seed strict suites cannot establish broad theorem-proving capability. Exact Lean rates have wide confidence intervals. Stage4 did not significantly outperform Stage2 in the matched paired test. Jensen remained `SEARCH_EXHAUSTED` with 0/6 Lean-valid candidates. **RH PROVED: NO.**
80
+
81
+ ## Attribution
82
+
83
+ Base model: m-a-p/OProver-8B (Apache-2.0). Training data derives from Mathlib at `360da6fa66c1273b76b6b2d8c5666fd5ac2e3b56` (Apache-2.0). See `NOTICE`.
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "m-a-p/OProver-8B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 32,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "o_proj",
35
+ "k_proj",
36
+ "gate_proj",
37
+ "up_proj",
38
+ "q_proj",
39
+ "v_proj",
40
+ "down_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_bdlora": null,
46
+ "use_dora": false,
47
+ "use_qalora": false,
48
+ "use_rslora": false,
49
+ "velora_config": null
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5399518c0741140a14d2cca2fade8ec3eb95fb587139c5c9894d5e297a3b55
3
+ size 174656040
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 message.content is string 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.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
evaluation/results.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "status": "MATCHED BASELINE",
3
+ "all22": {
4
+ "exact": 9,
5
+ "n": 22,
6
+ "parser": 22,
7
+ "unsafe": 0
8
+ },
9
+ "holdout18": {
10
+ "exact": 5,
11
+ "n": 18
12
+ },
13
+ "canary4": {
14
+ "exact": 4,
15
+ "n": 4
16
+ },
17
+ "audit_sha256": "5e0f757353ffe17315c9b78c60bb46de9ae34e736f9460e69ec26ca1d6213f9c",
18
+ "protocol_root": "6047aa9e4f3ff9594f7913e943cf40dc050b49328b7a42a80a72beefe5c641d7"
19
+ }
provenance/manifest.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema_version": 1,
3
+ "public_repo": "FluffyAIcode/Kakeya-OProver-Stage2-SFT1000",
4
+ "base_model": "m-a-p/OProver-8B",
5
+ "base_revision": "cd9ffd383b584d95bf00e04b88b35b05928b211c",
6
+ "source_private_repo": "FluffyAIcode/oprover-8b-mathlib-lora-stage1",
7
+ "source_immutable_revision": "8eead931f4b090bca2421fead7d0c64191bea116",
8
+ "adapter_sha256": "5e5399518c0741140a14d2cca2fade8ec3eb95fb587139c5c9894d5e297a3b55",
9
+ "dataset_artifact_sha256": "5ebec3f7ed71d0af202924ea9d5ca12a857c5363b89b028dbf74268bf2e32f24",
10
+ "public_private_boundary": {
11
+ "public": [
12
+ "adapter",
13
+ "tokenizer",
14
+ "sanitized metrics/trainer state",
15
+ "aggregate strict evaluation",
16
+ "hashes/signatures/config"
17
+ ],
18
+ "private": [
19
+ "chain-of-thought",
20
+ "production prompts",
21
+ "Jensen candidate proof bodies",
22
+ "raw candidate-bearing signed audits",
23
+ "optimizer and RNG checkpoints"
24
+ ]
25
+ }
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab5a866c748c81fe21eb29faa5c87c5f6448415348e5ab984ba2d69c6d68b36
3
+ size 11428194
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 131072,
11
+ "pad_token": "<|endoftext|>",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }
training/metrics.jsonl ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"entropy": 0.571594450622797, "epoch": 0.022857142857142857, "grad_norm": 2.03125, "learning_rate": 0.0, "loss": 1.892868161201477, "mean_token_accuracy": 0.6494692210108042, "num_tokens": 28665.0, "step": 1}
2
+ {"entropy": 0.5400022976100445, "epoch": 0.045714285714285714, "grad_norm": 1.953125, "learning_rate": 5e-05, "loss": 1.3431090116500854, "mean_token_accuracy": 0.6841957792639732, "num_tokens": 56298.0, "step": 2}
3
+ {"entropy": 0.5547708570957184, "epoch": 0.06857142857142857, "grad_norm": 2.046875, "learning_rate": 0.0001, "loss": 1.7731074094772339, "mean_token_accuracy": 0.6730335894972086, "num_tokens": 87134.0, "step": 3}
4
+ {"entropy": 0.6138171833008528, "epoch": 0.09142857142857143, "grad_norm": 1.890625, "learning_rate": 0.00015000000000000001, "loss": 1.6849099397659302, "mean_token_accuracy": 0.7163603082299232, "num_tokens": 110491.0, "step": 4}
5
+ {"entropy": 0.713952723890543, "epoch": 0.11428571428571428, "grad_norm": 1.609375, "learning_rate": 0.0002, "loss": 1.6369731426239014, "mean_token_accuracy": 0.6762979347258806, "num_tokens": 138858.0, "step": 5}
6
+ {"entropy": 0.9489956572651863, "epoch": 0.13714285714285715, "grad_norm": 1.609375, "learning_rate": 0.00019993007047883988, "loss": 1.6043992042541504, "mean_token_accuracy": 0.6542574372142553, "num_tokens": 164666.0, "step": 6}
7
+ {"entropy": 1.2052904553711414, "epoch": 0.16, "grad_norm": 2.046875, "learning_rate": 0.00019972037971811802, "loss": 1.1030031442642212, "mean_token_accuracy": 0.7115810438990593, "num_tokens": 198168.0, "step": 7}
8
+ {"entropy": 1.5162354111671448, "epoch": 0.18285714285714286, "grad_norm": 2.609375, "learning_rate": 0.00019937122098932428, "loss": 1.338626503944397, "mean_token_accuracy": 0.7028692364692688, "num_tokens": 229142.0, "step": 8}
9
+ {"entropy": 1.6831717118620872, "epoch": 0.2057142857142857, "grad_norm": 1.203125, "learning_rate": 0.00019888308262251285, "loss": 1.5491583347320557, "mean_token_accuracy": 0.669173551723361, "num_tokens": 257334.0, "step": 9}
10
+ {"entropy": 1.2227612249553204, "epoch": 0.22857142857142856, "grad_norm": 0.6328125, "learning_rate": 0.00019825664732332884, "loss": 1.0137903690338135, "mean_token_accuracy": 0.7204974591732025, "num_tokens": 286904.0, "step": 10}
11
+ {"entropy": 1.1638432145118713, "epoch": 0.25142857142857145, "grad_norm": 0.83984375, "learning_rate": 0.00019749279121818235, "loss": 1.0442439317703247, "mean_token_accuracy": 0.7225705273449421, "num_tokens": 313566.0, "step": 11}
12
+ {"entropy": 1.090791016817093, "epoch": 0.2742857142857143, "grad_norm": 0.75, "learning_rate": 0.00019659258262890683, "loss": 1.2202626466751099, "mean_token_accuracy": 0.6869607474654913, "num_tokens": 343912.0, "step": 12}
13
+ {"entropy": 1.100559327751398, "epoch": 0.29714285714285715, "grad_norm": 0.73046875, "learning_rate": 0.0001955572805786141, "loss": 1.4237300157546997, "mean_token_accuracy": 0.7026770114898682, "num_tokens": 367824.0, "step": 13}
14
+ {"entropy": 1.0772063918411732, "epoch": 0.32, "grad_norm": 0.734375, "learning_rate": 0.00019438833303083678, "loss": 1.3612886667251587, "mean_token_accuracy": 0.7167600486427546, "num_tokens": 397629.0, "step": 14}
15
+ {"entropy": 1.0418964736163616, "epoch": 0.34285714285714286, "grad_norm": 0.76171875, "learning_rate": 0.00019308737486442045, "loss": 1.2377914190292358, "mean_token_accuracy": 0.7337369881570339, "num_tokens": 426172.0, "step": 15}
16
+ {"entropy": 1.02627420052886, "epoch": 0.3657142857142857, "grad_norm": 0.640625, "learning_rate": 0.00019165622558699763, "loss": 1.043224811553955, "mean_token_accuracy": 0.757489874958992, "num_tokens": 455884.0, "step": 16}
17
+ {"entropy": 1.0985115952789783, "epoch": 0.38857142857142857, "grad_norm": 0.75390625, "learning_rate": 0.0001900968867902419, "loss": 1.0292891263961792, "mean_token_accuracy": 0.7834405265748501, "num_tokens": 479943.0, "step": 17}
18
+ {"entropy": 0.9926935620605946, "epoch": 0.4114285714285714, "grad_norm": 0.5234375, "learning_rate": 0.00018841153935046098, "loss": 1.0027269124984741, "mean_token_accuracy": 0.7445859499275684, "num_tokens": 512401.0, "step": 18}
19
+ {"entropy": 1.184921432286501, "epoch": 0.4342857142857143, "grad_norm": 0.6953125, "learning_rate": 0.00018660254037844388, "loss": 0.8860166072845459, "mean_token_accuracy": 0.7711772620677948, "num_tokens": 532314.0, "step": 19}
20
+ {"entropy": 1.0456415861845016, "epoch": 0.45714285714285713, "grad_norm": 0.578125, "learning_rate": 0.00018467241992282843, "loss": 0.821132242679596, "mean_token_accuracy": 0.7591653987765312, "num_tokens": 560611.0, "step": 20}
21
+ {"entropy": 1.0742540583014488, "epoch": 0.48, "grad_norm": 0.6640625, "learning_rate": 0.0001826238774315995, "loss": 1.1304452419281006, "mean_token_accuracy": 0.7381897754967213, "num_tokens": 582239.0, "step": 21}
22
+ {"entropy": 1.0069492012262344, "epoch": 0.5028571428571429, "grad_norm": 0.83203125, "learning_rate": 0.00018045977797666684, "loss": 1.0569063425064087, "mean_token_accuracy": 0.7475782930850983, "num_tokens": 605785.0, "step": 22}
23
+ {"epoch": 0.5028571428571429, "eval_entropy": 1.0555952689051629, "eval_loss": 1.0447686910629272, "eval_mean_token_accuracy": 0.75280682772398, "eval_num_tokens": 605785.0, "eval_runtime": 77.2364, "eval_samples_per_second": 1.295, "eval_steps_per_second": 1.295, "step": 22}
24
+ {"entropy": 1.0209653116762638, "epoch": 0.5257142857142857, "grad_norm": 0.6953125, "learning_rate": 0.000178183148246803, "loss": 0.9215176105499268, "mean_token_accuracy": 0.7393636666238308, "num_tokens": 630668.0, "step": 23}
25
+ {"entropy": 1.1484412215650082, "epoch": 0.5485714285714286, "grad_norm": 0.63671875, "learning_rate": 0.0001757971723145453, "loss": 1.0585880279541016, "mean_token_accuracy": 0.6772188358008862, "num_tokens": 651568.0, "step": 24}
26
+ {"entropy": 1.022590946406126, "epoch": 0.5714285714285714, "grad_norm": 0.6640625, "learning_rate": 0.00017330518718298264, "loss": 0.8019014596939087, "mean_token_accuracy": 0.7844364829361439, "num_tokens": 677010.0, "step": 25}
27
+ {"entropy": 1.1501350328326225, "epoch": 0.5942857142857143, "grad_norm": 0.578125, "learning_rate": 0.00017071067811865476, "loss": 1.1763538122177124, "mean_token_accuracy": 0.7165477126836777, "num_tokens": 699559.0, "step": 26}
28
+ {"entropy": 1.1520305536687374, "epoch": 0.6171428571428571, "grad_norm": 0.84765625, "learning_rate": 0.00016801727377709194, "loss": 1.3568904399871826, "mean_token_accuracy": 0.7278081495314837, "num_tokens": 723860.0, "step": 27}
29
+ {"entropy": 1.1409958936274052, "epoch": 0.64, "grad_norm": 0.73828125, "learning_rate": 0.00016522874112781213, "loss": 1.2788770198822021, "mean_token_accuracy": 0.688488058745861, "num_tokens": 743869.0, "step": 28}
30
+ {"entropy": 1.06721768155694, "epoch": 0.6628571428571428, "grad_norm": 0.796875, "learning_rate": 0.00016234898018587337, "loss": 0.9878795742988586, "mean_token_accuracy": 0.7843082323670387, "num_tokens": 767668.0, "step": 29}
31
+ {"entropy": 0.9738106857985258, "epoch": 0.6857142857142857, "grad_norm": 0.578125, "learning_rate": 0.00015938201855735014, "loss": 0.7424539923667908, "mean_token_accuracy": 0.7907082177698612, "num_tokens": 796481.0, "step": 30}
32
+ {"entropy": 0.9771843180060387, "epoch": 0.7085714285714285, "grad_norm": 0.75, "learning_rate": 0.0001563320058063622, "loss": 0.9626051187515259, "mean_token_accuracy": 0.7523193173110485, "num_tokens": 829764.0, "step": 31}
33
+ {"entropy": 1.151510078459978, "epoch": 0.7314285714285714, "grad_norm": 0.78125, "learning_rate": 0.00015320320765153367, "loss": 1.270058512687683, "mean_token_accuracy": 0.6807492543011904, "num_tokens": 855562.0, "step": 32}
34
+ {"entropy": 0.9595269281417131, "epoch": 0.7542857142857143, "grad_norm": 0.5625, "learning_rate": 0.00015000000000000001, "loss": 0.9262505173683167, "mean_token_accuracy": 0.7448003850877285, "num_tokens": 886448.0, "step": 33}
35
+ {"entropy": 0.9837835170328617, "epoch": 0.7771428571428571, "grad_norm": 0.82421875, "learning_rate": 0.0001467268628273062, "loss": 0.7896201014518738, "mean_token_accuracy": 0.7692355290055275, "num_tokens": 909179.0, "step": 34}
36
+ {"entropy": 1.0101780369877815, "epoch": 0.8, "grad_norm": 0.9375, "learning_rate": 0.00014338837391175582, "loss": 1.1079224348068237, "mean_token_accuracy": 0.743992704898119, "num_tokens": 932293.0, "step": 35}
37
+ {"entropy": 1.124088928103447, "epoch": 0.8228571428571428, "grad_norm": 0.84375, "learning_rate": 0.00013998920243197407, "loss": 1.2773886919021606, "mean_token_accuracy": 0.7306922785937786, "num_tokens": 953785.0, "step": 36}
38
+ {"entropy": 1.0273678377270699, "epoch": 0.8457142857142858, "grad_norm": 0.765625, "learning_rate": 0.00013653410243663952, "loss": 1.0014641284942627, "mean_token_accuracy": 0.7343494817614555, "num_tokens": 983541.0, "step": 37}
39
+ {"entropy": 1.1427535712718964, "epoch": 0.8685714285714285, "grad_norm": 0.671875, "learning_rate": 0.00013302790619551674, "loss": 1.1199904680252075, "mean_token_accuracy": 0.7464530095458031, "num_tokens": 1009431.0, "step": 38}
40
+ {"entropy": 1.1668125055730343, "epoch": 0.8914285714285715, "grad_norm": 0.6015625, "learning_rate": 0.00012947551744109043, "loss": 0.9645350575447083, "mean_token_accuracy": 0.780300073325634, "num_tokens": 1027701.0, "step": 39}
41
+ {"entropy": 1.1839856766164303, "epoch": 0.9142857142857143, "grad_norm": 0.62109375, "learning_rate": 0.00012588190451025207, "loss": 1.2035199403762817, "mean_token_accuracy": 0.7434030883014202, "num_tokens": 1055642.0, "step": 40}
42
+ {"entropy": 1.103015311062336, "epoch": 0.9371428571428572, "grad_norm": 0.62109375, "learning_rate": 0.00012225209339563145, "loss": 1.0058553218841553, "mean_token_accuracy": 0.7543482556939125, "num_tokens": 1084745.0, "step": 41}
43
+ {"entropy": 1.1135993152856827, "epoch": 0.96, "grad_norm": 0.6953125, "learning_rate": 0.00011859116071629149, "loss": 1.2151912450790405, "mean_token_accuracy": 0.7335421219468117, "num_tokens": 1110320.0, "step": 42}
44
+ {"entropy": 1.1436597369611263, "epoch": 0.9828571428571429, "grad_norm": 0.58203125, "learning_rate": 0.00011490422661761744, "loss": 1.0186842679977417, "mean_token_accuracy": 0.7390037253499031, "num_tokens": 1134964.0, "step": 43}
45
+ {"entropy": 1.078730583190918, "epoch": 1.0, "grad_norm": 0.65625, "learning_rate": 0.00011119644761033078, "loss": 0.8101186752319336, "mean_token_accuracy": 0.7597745011250178, "num_tokens": 1153583.0, "step": 44}
46
+ {"epoch": 1.0, "eval_entropy": 1.0479114320874214, "eval_loss": 0.9729008674621582, "eval_mean_token_accuracy": 0.7565665817260743, "eval_num_tokens": 1153583.0, "eval_runtime": 77.2335, "eval_samples_per_second": 1.295, "eval_steps_per_second": 1.295, "step": 44}
47
+ {"entropy": 1.0368036814033985, "epoch": 1.022857142857143, "grad_norm": 0.56640625, "learning_rate": 0.00010747300935864243, "loss": 0.8468512296676636, "mean_token_accuracy": 0.8111352436244488, "num_tokens": 1174609.0, "step": 45}
48
+ {"entropy": 0.9628574140369892, "epoch": 1.0457142857142858, "grad_norm": 0.5546875, "learning_rate": 0.0001037391194276326, "loss": 0.5208293199539185, "mean_token_accuracy": 0.8187313564121723, "num_tokens": 1201897.0, "step": 46}
49
+ {"entropy": 1.0299121290445328, "epoch": 1.0685714285714285, "grad_norm": 0.765625, "learning_rate": 0.0001, "loss": 0.7912545204162598, "mean_token_accuracy": 0.7928437106311321, "num_tokens": 1230046.0, "step": 47}
50
+ {"entropy": 1.0342555530369282, "epoch": 1.0914285714285714, "grad_norm": 0.74609375, "learning_rate": 9.626088057236745e-05, "loss": 0.9557701349258423, "mean_token_accuracy": 0.7545025758445263, "num_tokens": 1257406.0, "step": 48}
51
+ {"entropy": 0.9161418825387955, "epoch": 1.1142857142857143, "grad_norm": 0.7109375, "learning_rate": 9.252699064135758e-05, "loss": 1.0390901565551758, "mean_token_accuracy": 0.7715597599744797, "num_tokens": 1291055.0, "step": 49}
52
+ {"entropy": 0.8812923058867455, "epoch": 1.1371428571428572, "grad_norm": 0.625, "learning_rate": 8.880355238966923e-05, "loss": 0.6828033328056335, "mean_token_accuracy": 0.8140444047749043, "num_tokens": 1318257.0, "step": 50}
53
+ {"entropy": 1.0039622746407986, "epoch": 1.16, "grad_norm": 0.546875, "learning_rate": 8.509577338238255e-05, "loss": 0.7247803807258606, "mean_token_accuracy": 0.7645618040114641, "num_tokens": 1341106.0, "step": 51}
54
+ {"entropy": 0.905966442078352, "epoch": 1.1828571428571428, "grad_norm": 0.5625, "learning_rate": 8.140883928370855e-05, "loss": 0.7403977513313293, "mean_token_accuracy": 0.8016074895858765, "num_tokens": 1369760.0, "step": 52}
55
+ {"entropy": 0.9338806178420782, "epoch": 1.2057142857142857, "grad_norm": 0.490234375, "learning_rate": 7.774790660436858e-05, "loss": 0.6406869888305664, "mean_token_accuracy": 0.7956290915608406, "num_tokens": 1392567.0, "step": 53}
56
+ {"entropy": 0.8846337422728539, "epoch": 1.2285714285714286, "grad_norm": 0.69921875, "learning_rate": 7.411809548974792e-05, "loss": 0.8057032823562622, "mean_token_accuracy": 0.7973924726247787, "num_tokens": 1419324.0, "step": 54}
57
+ {"entropy": 0.9206812232732773, "epoch": 1.2514285714285713, "grad_norm": 0.8125, "learning_rate": 7.052448255890957e-05, "loss": 0.6728847026824951, "mean_token_accuracy": 0.8473470285534859, "num_tokens": 1446756.0, "step": 55}
58
+ {"entropy": 0.9307001233100891, "epoch": 1.2742857142857142, "grad_norm": 0.8515625, "learning_rate": 6.697209380448333e-05, "loss": 0.7187720537185669, "mean_token_accuracy": 0.8393540307879448, "num_tokens": 1468062.0, "step": 56}
59
+ {"entropy": 0.8503624759614468, "epoch": 1.2971428571428572, "grad_norm": 0.64453125, "learning_rate": 6.34658975633605e-05, "loss": 0.6491850018501282, "mean_token_accuracy": 0.834420669823885, "num_tokens": 1497763.0, "step": 57}
60
+ {"entropy": 0.8430384919047356, "epoch": 1.32, "grad_norm": 0.62890625, "learning_rate": 6.001079756802592e-05, "loss": 0.7592802047729492, "mean_token_accuracy": 0.7834662459790707, "num_tokens": 1523103.0, "step": 58}
61
+ {"entropy": 1.0481715574860573, "epoch": 1.342857142857143, "grad_norm": 1.15625, "learning_rate": 5.6611626088244194e-05, "loss": 0.8737943768501282, "mean_token_accuracy": 0.7567208111286163, "num_tokens": 1540582.0, "step": 59}
62
+ {"entropy": 0.849721547216177, "epoch": 1.3657142857142857, "grad_norm": 0.8984375, "learning_rate": 5.32731371726938e-05, "loss": 0.7518897652626038, "mean_token_accuracy": 0.8164225146174431, "num_tokens": 1562096.0, "step": 60}
63
+ {"entropy": 0.7319265194237232, "epoch": 1.3885714285714286, "grad_norm": 0.76953125, "learning_rate": 5.000000000000002e-05, "loss": 0.5088726282119751, "mean_token_accuracy": 0.8368714712560177, "num_tokens": 1588869.0, "step": 61}
64
+ {"entropy": 0.7714136429131031, "epoch": 1.4114285714285715, "grad_norm": 0.515625, "learning_rate": 4.6796792348466356e-05, "loss": 0.5990605354309082, "mean_token_accuracy": 0.8109956867992878, "num_tokens": 1618753.0, "step": 62}
65
+ {"entropy": 0.8922704569995403, "epoch": 1.4342857142857142, "grad_norm": 0.7265625, "learning_rate": 4.3667994193637796e-05, "loss": 0.7471989393234253, "mean_token_accuracy": 0.8137485198676586, "num_tokens": 1639035.0, "step": 63}
66
+ {"entropy": 0.8474112637341022, "epoch": 1.457142857142857, "grad_norm": 0.9375, "learning_rate": 4.0617981442649855e-05, "loss": 0.9250304102897644, "mean_token_accuracy": 0.7889886423945427, "num_tokens": 1667695.0, "step": 64}
67
+ {"entropy": 0.8302664868533611, "epoch": 1.48, "grad_norm": 0.8984375, "learning_rate": 3.7651019814126654e-05, "loss": 0.9558159112930298, "mean_token_accuracy": 0.7763096019625664, "num_tokens": 1691022.0, "step": 65}
68
+ {"entropy": 0.8031172640621662, "epoch": 1.502857142857143, "grad_norm": 0.79296875, "learning_rate": 3.477125887218792e-05, "loss": 0.801313042640686, "mean_token_accuracy": 0.8177301362156868, "num_tokens": 1724435.0, "step": 66}
69
+ {"epoch": 1.502857142857143, "eval_entropy": 0.8457768812775612, "eval_loss": 0.9875430464744568, "eval_mean_token_accuracy": 0.756916128396988, "eval_num_tokens": 1724435.0, "eval_runtime": 77.2316, "eval_samples_per_second": 1.295, "eval_steps_per_second": 1.295, "step": 66}
70
+ {"entropy": 0.841597568243742, "epoch": 1.5257142857142858, "grad_norm": 0.8359375, "learning_rate": 3.198272622290804e-05, "loss": 0.8447511196136475, "mean_token_accuracy": 0.7982683703303337, "num_tokens": 1752489.0, "step": 67}
71
+ {"entropy": 0.873002614825964, "epoch": 1.5485714285714285, "grad_norm": 0.68359375, "learning_rate": 2.9289321881345254e-05, "loss": 0.8038796782493591, "mean_token_accuracy": 0.8067350275814533, "num_tokens": 1784291.0, "step": 68}
72
+ {"entropy": 0.9177370071411133, "epoch": 1.5714285714285714, "grad_norm": 0.6796875, "learning_rate": 2.669481281701739e-05, "loss": 0.8557254672050476, "mean_token_accuracy": 0.8137136548757553, "num_tokens": 1804179.0, "step": 69}
73
+ {"entropy": 0.8276135660707951, "epoch": 1.5942857142857143, "grad_norm": 0.73828125, "learning_rate": 2.420282768545469e-05, "loss": 0.6800186634063721, "mean_token_accuracy": 0.8346021547913551, "num_tokens": 1831612.0, "step": 70}
74
+ {"entropy": 0.9364416636526585, "epoch": 1.617142857142857, "grad_norm": 0.75390625, "learning_rate": 2.181685175319702e-05, "loss": 0.7834956049919128, "mean_token_accuracy": 0.7997728437185287, "num_tokens": 1853595.0, "step": 71}
75
+ {"entropy": 0.8710121884942055, "epoch": 1.6400000000000001, "grad_norm": 0.765625, "learning_rate": 1.9540222023333166e-05, "loss": 0.6057661771774292, "mean_token_accuracy": 0.8205794207751751, "num_tokens": 1882408.0, "step": 72}
76
+ {"entropy": 0.8379442691802979, "epoch": 1.6628571428571428, "grad_norm": 0.7734375, "learning_rate": 1.7376122568400532e-05, "loss": 0.7106757760047913, "mean_token_accuracy": 0.8180459216237068, "num_tokens": 1904944.0, "step": 73}
77
+ {"entropy": 0.8745108097791672, "epoch": 1.6857142857142857, "grad_norm": 1.2109375, "learning_rate": 1.5327580077171587e-05, "loss": 0.9369223713874817, "mean_token_accuracy": 0.8044208958745003, "num_tokens": 1933402.0, "step": 74}
78
+ {"entropy": 0.8298410475254059, "epoch": 1.7085714285714286, "grad_norm": 0.8828125, "learning_rate": 1.339745962155613e-05, "loss": 0.6346684694290161, "mean_token_accuracy": 0.8335375674068928, "num_tokens": 1960093.0, "step": 75}
79
+ {"entropy": 0.8175692446529865, "epoch": 1.7314285714285713, "grad_norm": 0.91796875, "learning_rate": 1.1588460649539035e-05, "loss": 0.9119294285774231, "mean_token_accuracy": 0.8193050436675549, "num_tokens": 1986339.0, "step": 76}
80
+ {"entropy": 0.8975704163312912, "epoch": 1.7542857142857144, "grad_norm": 0.859375, "learning_rate": 9.903113209758096e-06, "loss": 0.7237526178359985, "mean_token_accuracy": 0.7882252000272274, "num_tokens": 2011176.0, "step": 77}
81
+ {"entropy": 0.8363670147955418, "epoch": 1.7771428571428571, "grad_norm": 0.74609375, "learning_rate": 8.343774413002381e-06, "loss": 0.6269868016242981, "mean_token_accuracy": 0.8103100657463074, "num_tokens": 2041289.0, "step": 78}
82
+ {"entropy": 0.8557109721004963, "epoch": 1.8, "grad_norm": 0.6171875, "learning_rate": 6.9126251355795864e-06, "loss": 0.5580326914787292, "mean_token_accuracy": 0.8539069853723049, "num_tokens": 2069418.0, "step": 79}
83
+ {"entropy": 0.790475644171238, "epoch": 1.822857142857143, "grad_norm": 0.984375, "learning_rate": 5.611666969163243e-06, "loss": 0.6902757287025452, "mean_token_accuracy": 0.8313734903931618, "num_tokens": 2101162.0, "step": 80}
84
+ {"entropy": 0.8487820513546467, "epoch": 1.8457142857142856, "grad_norm": 0.7265625, "learning_rate": 4.442719421385922e-06, "loss": 0.6248161792755127, "mean_token_accuracy": 0.8196811378002167, "num_tokens": 2129262.0, "step": 81}
85
+ {"entropy": 0.8948404788970947, "epoch": 1.8685714285714285, "grad_norm": 0.87890625, "learning_rate": 3.40741737109318e-06, "loss": 0.8848119378089905, "mean_token_accuracy": 0.7821721211075783, "num_tokens": 2152597.0, "step": 82}
86
+ {"entropy": 0.9239097908139229, "epoch": 1.8914285714285715, "grad_norm": 0.7421875, "learning_rate": 2.5072087818176382e-06, "loss": 0.7065685987472534, "mean_token_accuracy": 0.807807132601738, "num_tokens": 2177161.0, "step": 83}
87
+ {"entropy": 0.7839450426399708, "epoch": 1.9142857142857141, "grad_norm": 0.77734375, "learning_rate": 1.7433526766711728e-06, "loss": 0.7359437942504883, "mean_token_accuracy": 0.8403091952204704, "num_tokens": 2209858.0, "step": 84}
88
+ {"entropy": 0.843034666031599, "epoch": 1.9371428571428573, "grad_norm": 0.765625, "learning_rate": 1.1169173774871478e-06, "loss": 0.7045976519584656, "mean_token_accuracy": 0.7968335002660751, "num_tokens": 2238762.0, "step": 85}
89
+ {"entropy": 0.8172502107918262, "epoch": 1.96, "grad_norm": 0.73046875, "learning_rate": 6.287790106757396e-07, "loss": 0.7153176665306091, "mean_token_accuracy": 0.8268864750862122, "num_tokens": 2266000.0, "step": 86}
90
+ {"entropy": 0.9393381252884865, "epoch": 1.9828571428571429, "grad_norm": 0.8046875, "learning_rate": 2.7962028188198706e-07, "loss": 0.7222880721092224, "mean_token_accuracy": 0.8043639399111271, "num_tokens": 2291896.0, "step": 87}
91
+ {"entropy": 0.9007064700126648, "epoch": 2.0, "grad_norm": 0.9453125, "learning_rate": 6.992952116013918e-08, "loss": 0.9412174224853516, "mean_token_accuracy": 0.7673612783352534, "num_tokens": 2307166.0, "step": 88}
92
+ {"epoch": 2.0, "eval_entropy": 0.8574838742613793, "eval_loss": 0.9815174341201782, "eval_mean_token_accuracy": 0.7545835164189338, "eval_num_tokens": 2307166.0, "eval_runtime": 77.2359, "eval_samples_per_second": 1.295, "eval_steps_per_second": 1.295, "step": 88}
training/trainer_state.json ADDED
@@ -0,0 +1,963 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_steps": 88,
3
+ "save_steps": 22,
4
+ "is_world_process_zero": true,
5
+ "train_batch_size": 1,
6
+ "stateful_callbacks": {
7
+ "TrainerControl": {
8
+ "args": {
9
+ "should_epoch_stop": false,
10
+ "should_evaluate": false,
11
+ "should_log": false,
12
+ "should_save": true,
13
+ "should_training_stop": true
14
+ },
15
+ "attributes": {}
16
+ }
17
+ },
18
+ "is_hyper_param_search": false,
19
+ "num_input_tokens_seen": 0,
20
+ "log_history": [
21
+ {
22
+ "entropy": 0.571594450622797,
23
+ "epoch": 0.022857142857142857,
24
+ "grad_norm": 2.03125,
25
+ "learning_rate": 0.0,
26
+ "loss": 1.892868161201477,
27
+ "mean_token_accuracy": 0.6494692210108042,
28
+ "num_tokens": 28665.0,
29
+ "step": 1
30
+ },
31
+ {
32
+ "entropy": 0.5400022976100445,
33
+ "epoch": 0.045714285714285714,
34
+ "grad_norm": 1.953125,
35
+ "learning_rate": 5e-05,
36
+ "loss": 1.3431090116500854,
37
+ "mean_token_accuracy": 0.6841957792639732,
38
+ "num_tokens": 56298.0,
39
+ "step": 2
40
+ },
41
+ {
42
+ "entropy": 0.5547708570957184,
43
+ "epoch": 0.06857142857142857,
44
+ "grad_norm": 2.046875,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.7731074094772339,
47
+ "mean_token_accuracy": 0.6730335894972086,
48
+ "num_tokens": 87134.0,
49
+ "step": 3
50
+ },
51
+ {
52
+ "entropy": 0.6138171833008528,
53
+ "epoch": 0.09142857142857143,
54
+ "grad_norm": 1.890625,
55
+ "learning_rate": 0.00015000000000000001,
56
+ "loss": 1.6849099397659302,
57
+ "mean_token_accuracy": 0.7163603082299232,
58
+ "num_tokens": 110491.0,
59
+ "step": 4
60
+ },
61
+ {
62
+ "entropy": 0.713952723890543,
63
+ "epoch": 0.11428571428571428,
64
+ "grad_norm": 1.609375,
65
+ "learning_rate": 0.0002,
66
+ "loss": 1.6369731426239014,
67
+ "mean_token_accuracy": 0.6762979347258806,
68
+ "num_tokens": 138858.0,
69
+ "step": 5
70
+ },
71
+ {
72
+ "entropy": 0.9489956572651863,
73
+ "epoch": 0.13714285714285715,
74
+ "grad_norm": 1.609375,
75
+ "learning_rate": 0.00019993007047883988,
76
+ "loss": 1.6043992042541504,
77
+ "mean_token_accuracy": 0.6542574372142553,
78
+ "num_tokens": 164666.0,
79
+ "step": 6
80
+ },
81
+ {
82
+ "entropy": 1.2052904553711414,
83
+ "epoch": 0.16,
84
+ "grad_norm": 2.046875,
85
+ "learning_rate": 0.00019972037971811802,
86
+ "loss": 1.1030031442642212,
87
+ "mean_token_accuracy": 0.7115810438990593,
88
+ "num_tokens": 198168.0,
89
+ "step": 7
90
+ },
91
+ {
92
+ "entropy": 1.5162354111671448,
93
+ "epoch": 0.18285714285714286,
94
+ "grad_norm": 2.609375,
95
+ "learning_rate": 0.00019937122098932428,
96
+ "loss": 1.338626503944397,
97
+ "mean_token_accuracy": 0.7028692364692688,
98
+ "num_tokens": 229142.0,
99
+ "step": 8
100
+ },
101
+ {
102
+ "entropy": 1.6831717118620872,
103
+ "epoch": 0.2057142857142857,
104
+ "grad_norm": 1.203125,
105
+ "learning_rate": 0.00019888308262251285,
106
+ "loss": 1.5491583347320557,
107
+ "mean_token_accuracy": 0.669173551723361,
108
+ "num_tokens": 257334.0,
109
+ "step": 9
110
+ },
111
+ {
112
+ "entropy": 1.2227612249553204,
113
+ "epoch": 0.22857142857142856,
114
+ "grad_norm": 0.6328125,
115
+ "learning_rate": 0.00019825664732332884,
116
+ "loss": 1.0137903690338135,
117
+ "mean_token_accuracy": 0.7204974591732025,
118
+ "num_tokens": 286904.0,
119
+ "step": 10
120
+ },
121
+ {
122
+ "entropy": 1.1638432145118713,
123
+ "epoch": 0.25142857142857145,
124
+ "grad_norm": 0.83984375,
125
+ "learning_rate": 0.00019749279121818235,
126
+ "loss": 1.0442439317703247,
127
+ "mean_token_accuracy": 0.7225705273449421,
128
+ "num_tokens": 313566.0,
129
+ "step": 11
130
+ },
131
+ {
132
+ "entropy": 1.090791016817093,
133
+ "epoch": 0.2742857142857143,
134
+ "grad_norm": 0.75,
135
+ "learning_rate": 0.00019659258262890683,
136
+ "loss": 1.2202626466751099,
137
+ "mean_token_accuracy": 0.6869607474654913,
138
+ "num_tokens": 343912.0,
139
+ "step": 12
140
+ },
141
+ {
142
+ "entropy": 1.100559327751398,
143
+ "epoch": 0.29714285714285715,
144
+ "grad_norm": 0.73046875,
145
+ "learning_rate": 0.0001955572805786141,
146
+ "loss": 1.4237300157546997,
147
+ "mean_token_accuracy": 0.7026770114898682,
148
+ "num_tokens": 367824.0,
149
+ "step": 13
150
+ },
151
+ {
152
+ "entropy": 1.0772063918411732,
153
+ "epoch": 0.32,
154
+ "grad_norm": 0.734375,
155
+ "learning_rate": 0.00019438833303083678,
156
+ "loss": 1.3612886667251587,
157
+ "mean_token_accuracy": 0.7167600486427546,
158
+ "num_tokens": 397629.0,
159
+ "step": 14
160
+ },
161
+ {
162
+ "entropy": 1.0418964736163616,
163
+ "epoch": 0.34285714285714286,
164
+ "grad_norm": 0.76171875,
165
+ "learning_rate": 0.00019308737486442045,
166
+ "loss": 1.2377914190292358,
167
+ "mean_token_accuracy": 0.7337369881570339,
168
+ "num_tokens": 426172.0,
169
+ "step": 15
170
+ },
171
+ {
172
+ "entropy": 1.02627420052886,
173
+ "epoch": 0.3657142857142857,
174
+ "grad_norm": 0.640625,
175
+ "learning_rate": 0.00019165622558699763,
176
+ "loss": 1.043224811553955,
177
+ "mean_token_accuracy": 0.757489874958992,
178
+ "num_tokens": 455884.0,
179
+ "step": 16
180
+ },
181
+ {
182
+ "entropy": 1.0985115952789783,
183
+ "epoch": 0.38857142857142857,
184
+ "grad_norm": 0.75390625,
185
+ "learning_rate": 0.0001900968867902419,
186
+ "loss": 1.0292891263961792,
187
+ "mean_token_accuracy": 0.7834405265748501,
188
+ "num_tokens": 479943.0,
189
+ "step": 17
190
+ },
191
+ {
192
+ "entropy": 0.9926935620605946,
193
+ "epoch": 0.4114285714285714,
194
+ "grad_norm": 0.5234375,
195
+ "learning_rate": 0.00018841153935046098,
196
+ "loss": 1.0027269124984741,
197
+ "mean_token_accuracy": 0.7445859499275684,
198
+ "num_tokens": 512401.0,
199
+ "step": 18
200
+ },
201
+ {
202
+ "entropy": 1.184921432286501,
203
+ "epoch": 0.4342857142857143,
204
+ "grad_norm": 0.6953125,
205
+ "learning_rate": 0.00018660254037844388,
206
+ "loss": 0.8860166072845459,
207
+ "mean_token_accuracy": 0.7711772620677948,
208
+ "num_tokens": 532314.0,
209
+ "step": 19
210
+ },
211
+ {
212
+ "entropy": 1.0456415861845016,
213
+ "epoch": 0.45714285714285713,
214
+ "grad_norm": 0.578125,
215
+ "learning_rate": 0.00018467241992282843,
216
+ "loss": 0.821132242679596,
217
+ "mean_token_accuracy": 0.7591653987765312,
218
+ "num_tokens": 560611.0,
219
+ "step": 20
220
+ },
221
+ {
222
+ "entropy": 1.0742540583014488,
223
+ "epoch": 0.48,
224
+ "grad_norm": 0.6640625,
225
+ "learning_rate": 0.0001826238774315995,
226
+ "loss": 1.1304452419281006,
227
+ "mean_token_accuracy": 0.7381897754967213,
228
+ "num_tokens": 582239.0,
229
+ "step": 21
230
+ },
231
+ {
232
+ "entropy": 1.0069492012262344,
233
+ "epoch": 0.5028571428571429,
234
+ "grad_norm": 0.83203125,
235
+ "learning_rate": 0.00018045977797666684,
236
+ "loss": 1.0569063425064087,
237
+ "mean_token_accuracy": 0.7475782930850983,
238
+ "num_tokens": 605785.0,
239
+ "step": 22
240
+ },
241
+ {
242
+ "epoch": 0.5028571428571429,
243
+ "eval_entropy": 1.0555952689051629,
244
+ "eval_loss": 1.0447686910629272,
245
+ "eval_mean_token_accuracy": 0.75280682772398,
246
+ "eval_num_tokens": 605785.0,
247
+ "eval_runtime": 77.2364,
248
+ "eval_samples_per_second": 1.295,
249
+ "eval_steps_per_second": 1.295,
250
+ "step": 22
251
+ },
252
+ {
253
+ "entropy": 1.0209653116762638,
254
+ "epoch": 0.5257142857142857,
255
+ "grad_norm": 0.6953125,
256
+ "learning_rate": 0.000178183148246803,
257
+ "loss": 0.9215176105499268,
258
+ "mean_token_accuracy": 0.7393636666238308,
259
+ "num_tokens": 630668.0,
260
+ "step": 23
261
+ },
262
+ {
263
+ "entropy": 1.1484412215650082,
264
+ "epoch": 0.5485714285714286,
265
+ "grad_norm": 0.63671875,
266
+ "learning_rate": 0.0001757971723145453,
267
+ "loss": 1.0585880279541016,
268
+ "mean_token_accuracy": 0.6772188358008862,
269
+ "num_tokens": 651568.0,
270
+ "step": 24
271
+ },
272
+ {
273
+ "entropy": 1.022590946406126,
274
+ "epoch": 0.5714285714285714,
275
+ "grad_norm": 0.6640625,
276
+ "learning_rate": 0.00017330518718298264,
277
+ "loss": 0.8019014596939087,
278
+ "mean_token_accuracy": 0.7844364829361439,
279
+ "num_tokens": 677010.0,
280
+ "step": 25
281
+ },
282
+ {
283
+ "entropy": 1.1501350328326225,
284
+ "epoch": 0.5942857142857143,
285
+ "grad_norm": 0.578125,
286
+ "learning_rate": 0.00017071067811865476,
287
+ "loss": 1.1763538122177124,
288
+ "mean_token_accuracy": 0.7165477126836777,
289
+ "num_tokens": 699559.0,
290
+ "step": 26
291
+ },
292
+ {
293
+ "entropy": 1.1520305536687374,
294
+ "epoch": 0.6171428571428571,
295
+ "grad_norm": 0.84765625,
296
+ "learning_rate": 0.00016801727377709194,
297
+ "loss": 1.3568904399871826,
298
+ "mean_token_accuracy": 0.7278081495314837,
299
+ "num_tokens": 723860.0,
300
+ "step": 27
301
+ },
302
+ {
303
+ "entropy": 1.1409958936274052,
304
+ "epoch": 0.64,
305
+ "grad_norm": 0.73828125,
306
+ "learning_rate": 0.00016522874112781213,
307
+ "loss": 1.2788770198822021,
308
+ "mean_token_accuracy": 0.688488058745861,
309
+ "num_tokens": 743869.0,
310
+ "step": 28
311
+ },
312
+ {
313
+ "entropy": 1.06721768155694,
314
+ "epoch": 0.6628571428571428,
315
+ "grad_norm": 0.796875,
316
+ "learning_rate": 0.00016234898018587337,
317
+ "loss": 0.9878795742988586,
318
+ "mean_token_accuracy": 0.7843082323670387,
319
+ "num_tokens": 767668.0,
320
+ "step": 29
321
+ },
322
+ {
323
+ "entropy": 0.9738106857985258,
324
+ "epoch": 0.6857142857142857,
325
+ "grad_norm": 0.578125,
326
+ "learning_rate": 0.00015938201855735014,
327
+ "loss": 0.7424539923667908,
328
+ "mean_token_accuracy": 0.7907082177698612,
329
+ "num_tokens": 796481.0,
330
+ "step": 30
331
+ },
332
+ {
333
+ "entropy": 0.9771843180060387,
334
+ "epoch": 0.7085714285714285,
335
+ "grad_norm": 0.75,
336
+ "learning_rate": 0.0001563320058063622,
337
+ "loss": 0.9626051187515259,
338
+ "mean_token_accuracy": 0.7523193173110485,
339
+ "num_tokens": 829764.0,
340
+ "step": 31
341
+ },
342
+ {
343
+ "entropy": 1.151510078459978,
344
+ "epoch": 0.7314285714285714,
345
+ "grad_norm": 0.78125,
346
+ "learning_rate": 0.00015320320765153367,
347
+ "loss": 1.270058512687683,
348
+ "mean_token_accuracy": 0.6807492543011904,
349
+ "num_tokens": 855562.0,
350
+ "step": 32
351
+ },
352
+ {
353
+ "entropy": 0.9595269281417131,
354
+ "epoch": 0.7542857142857143,
355
+ "grad_norm": 0.5625,
356
+ "learning_rate": 0.00015000000000000001,
357
+ "loss": 0.9262505173683167,
358
+ "mean_token_accuracy": 0.7448003850877285,
359
+ "num_tokens": 886448.0,
360
+ "step": 33
361
+ },
362
+ {
363
+ "entropy": 0.9837835170328617,
364
+ "epoch": 0.7771428571428571,
365
+ "grad_norm": 0.82421875,
366
+ "learning_rate": 0.0001467268628273062,
367
+ "loss": 0.7896201014518738,
368
+ "mean_token_accuracy": 0.7692355290055275,
369
+ "num_tokens": 909179.0,
370
+ "step": 34
371
+ },
372
+ {
373
+ "entropy": 1.0101780369877815,
374
+ "epoch": 0.8,
375
+ "grad_norm": 0.9375,
376
+ "learning_rate": 0.00014338837391175582,
377
+ "loss": 1.1079224348068237,
378
+ "mean_token_accuracy": 0.743992704898119,
379
+ "num_tokens": 932293.0,
380
+ "step": 35
381
+ },
382
+ {
383
+ "entropy": 1.124088928103447,
384
+ "epoch": 0.8228571428571428,
385
+ "grad_norm": 0.84375,
386
+ "learning_rate": 0.00013998920243197407,
387
+ "loss": 1.2773886919021606,
388
+ "mean_token_accuracy": 0.7306922785937786,
389
+ "num_tokens": 953785.0,
390
+ "step": 36
391
+ },
392
+ {
393
+ "entropy": 1.0273678377270699,
394
+ "epoch": 0.8457142857142858,
395
+ "grad_norm": 0.765625,
396
+ "learning_rate": 0.00013653410243663952,
397
+ "loss": 1.0014641284942627,
398
+ "mean_token_accuracy": 0.7343494817614555,
399
+ "num_tokens": 983541.0,
400
+ "step": 37
401
+ },
402
+ {
403
+ "entropy": 1.1427535712718964,
404
+ "epoch": 0.8685714285714285,
405
+ "grad_norm": 0.671875,
406
+ "learning_rate": 0.00013302790619551674,
407
+ "loss": 1.1199904680252075,
408
+ "mean_token_accuracy": 0.7464530095458031,
409
+ "num_tokens": 1009431.0,
410
+ "step": 38
411
+ },
412
+ {
413
+ "entropy": 1.1668125055730343,
414
+ "epoch": 0.8914285714285715,
415
+ "grad_norm": 0.6015625,
416
+ "learning_rate": 0.00012947551744109043,
417
+ "loss": 0.9645350575447083,
418
+ "mean_token_accuracy": 0.780300073325634,
419
+ "num_tokens": 1027701.0,
420
+ "step": 39
421
+ },
422
+ {
423
+ "entropy": 1.1839856766164303,
424
+ "epoch": 0.9142857142857143,
425
+ "grad_norm": 0.62109375,
426
+ "learning_rate": 0.00012588190451025207,
427
+ "loss": 1.2035199403762817,
428
+ "mean_token_accuracy": 0.7434030883014202,
429
+ "num_tokens": 1055642.0,
430
+ "step": 40
431
+ },
432
+ {
433
+ "entropy": 1.103015311062336,
434
+ "epoch": 0.9371428571428572,
435
+ "grad_norm": 0.62109375,
436
+ "learning_rate": 0.00012225209339563145,
437
+ "loss": 1.0058553218841553,
438
+ "mean_token_accuracy": 0.7543482556939125,
439
+ "num_tokens": 1084745.0,
440
+ "step": 41
441
+ },
442
+ {
443
+ "entropy": 1.1135993152856827,
444
+ "epoch": 0.96,
445
+ "grad_norm": 0.6953125,
446
+ "learning_rate": 0.00011859116071629149,
447
+ "loss": 1.2151912450790405,
448
+ "mean_token_accuracy": 0.7335421219468117,
449
+ "num_tokens": 1110320.0,
450
+ "step": 42
451
+ },
452
+ {
453
+ "entropy": 1.1436597369611263,
454
+ "epoch": 0.9828571428571429,
455
+ "grad_norm": 0.58203125,
456
+ "learning_rate": 0.00011490422661761744,
457
+ "loss": 1.0186842679977417,
458
+ "mean_token_accuracy": 0.7390037253499031,
459
+ "num_tokens": 1134964.0,
460
+ "step": 43
461
+ },
462
+ {
463
+ "entropy": 1.078730583190918,
464
+ "epoch": 1.0,
465
+ "grad_norm": 0.65625,
466
+ "learning_rate": 0.00011119644761033078,
467
+ "loss": 0.8101186752319336,
468
+ "mean_token_accuracy": 0.7597745011250178,
469
+ "num_tokens": 1153583.0,
470
+ "step": 44
471
+ },
472
+ {
473
+ "epoch": 1.0,
474
+ "eval_entropy": 1.0479114320874214,
475
+ "eval_loss": 0.9729008674621582,
476
+ "eval_mean_token_accuracy": 0.7565665817260743,
477
+ "eval_num_tokens": 1153583.0,
478
+ "eval_runtime": 77.2335,
479
+ "eval_samples_per_second": 1.295,
480
+ "eval_steps_per_second": 1.295,
481
+ "step": 44
482
+ },
483
+ {
484
+ "entropy": 1.0368036814033985,
485
+ "epoch": 1.022857142857143,
486
+ "grad_norm": 0.56640625,
487
+ "learning_rate": 0.00010747300935864243,
488
+ "loss": 0.8468512296676636,
489
+ "mean_token_accuracy": 0.8111352436244488,
490
+ "num_tokens": 1174609.0,
491
+ "step": 45
492
+ },
493
+ {
494
+ "entropy": 0.9628574140369892,
495
+ "epoch": 1.0457142857142858,
496
+ "grad_norm": 0.5546875,
497
+ "learning_rate": 0.0001037391194276326,
498
+ "loss": 0.5208293199539185,
499
+ "mean_token_accuracy": 0.8187313564121723,
500
+ "num_tokens": 1201897.0,
501
+ "step": 46
502
+ },
503
+ {
504
+ "entropy": 1.0299121290445328,
505
+ "epoch": 1.0685714285714285,
506
+ "grad_norm": 0.765625,
507
+ "learning_rate": 0.0001,
508
+ "loss": 0.7912545204162598,
509
+ "mean_token_accuracy": 0.7928437106311321,
510
+ "num_tokens": 1230046.0,
511
+ "step": 47
512
+ },
513
+ {
514
+ "entropy": 1.0342555530369282,
515
+ "epoch": 1.0914285714285714,
516
+ "grad_norm": 0.74609375,
517
+ "learning_rate": 9.626088057236745e-05,
518
+ "loss": 0.9557701349258423,
519
+ "mean_token_accuracy": 0.7545025758445263,
520
+ "num_tokens": 1257406.0,
521
+ "step": 48
522
+ },
523
+ {
524
+ "entropy": 0.9161418825387955,
525
+ "epoch": 1.1142857142857143,
526
+ "grad_norm": 0.7109375,
527
+ "learning_rate": 9.252699064135758e-05,
528
+ "loss": 1.0390901565551758,
529
+ "mean_token_accuracy": 0.7715597599744797,
530
+ "num_tokens": 1291055.0,
531
+ "step": 49
532
+ },
533
+ {
534
+ "entropy": 0.8812923058867455,
535
+ "epoch": 1.1371428571428572,
536
+ "grad_norm": 0.625,
537
+ "learning_rate": 8.880355238966923e-05,
538
+ "loss": 0.6828033328056335,
539
+ "mean_token_accuracy": 0.8140444047749043,
540
+ "num_tokens": 1318257.0,
541
+ "step": 50
542
+ },
543
+ {
544
+ "entropy": 1.0039622746407986,
545
+ "epoch": 1.16,
546
+ "grad_norm": 0.546875,
547
+ "learning_rate": 8.509577338238255e-05,
548
+ "loss": 0.7247803807258606,
549
+ "mean_token_accuracy": 0.7645618040114641,
550
+ "num_tokens": 1341106.0,
551
+ "step": 51
552
+ },
553
+ {
554
+ "entropy": 0.905966442078352,
555
+ "epoch": 1.1828571428571428,
556
+ "grad_norm": 0.5625,
557
+ "learning_rate": 8.140883928370855e-05,
558
+ "loss": 0.7403977513313293,
559
+ "mean_token_accuracy": 0.8016074895858765,
560
+ "num_tokens": 1369760.0,
561
+ "step": 52
562
+ },
563
+ {
564
+ "entropy": 0.9338806178420782,
565
+ "epoch": 1.2057142857142857,
566
+ "grad_norm": 0.490234375,
567
+ "learning_rate": 7.774790660436858e-05,
568
+ "loss": 0.6406869888305664,
569
+ "mean_token_accuracy": 0.7956290915608406,
570
+ "num_tokens": 1392567.0,
571
+ "step": 53
572
+ },
573
+ {
574
+ "entropy": 0.8846337422728539,
575
+ "epoch": 1.2285714285714286,
576
+ "grad_norm": 0.69921875,
577
+ "learning_rate": 7.411809548974792e-05,
578
+ "loss": 0.8057032823562622,
579
+ "mean_token_accuracy": 0.7973924726247787,
580
+ "num_tokens": 1419324.0,
581
+ "step": 54
582
+ },
583
+ {
584
+ "entropy": 0.9206812232732773,
585
+ "epoch": 1.2514285714285713,
586
+ "grad_norm": 0.8125,
587
+ "learning_rate": 7.052448255890957e-05,
588
+ "loss": 0.6728847026824951,
589
+ "mean_token_accuracy": 0.8473470285534859,
590
+ "num_tokens": 1446756.0,
591
+ "step": 55
592
+ },
593
+ {
594
+ "entropy": 0.9307001233100891,
595
+ "epoch": 1.2742857142857142,
596
+ "grad_norm": 0.8515625,
597
+ "learning_rate": 6.697209380448333e-05,
598
+ "loss": 0.7187720537185669,
599
+ "mean_token_accuracy": 0.8393540307879448,
600
+ "num_tokens": 1468062.0,
601
+ "step": 56
602
+ },
603
+ {
604
+ "entropy": 0.8503624759614468,
605
+ "epoch": 1.2971428571428572,
606
+ "grad_norm": 0.64453125,
607
+ "learning_rate": 6.34658975633605e-05,
608
+ "loss": 0.6491850018501282,
609
+ "mean_token_accuracy": 0.834420669823885,
610
+ "num_tokens": 1497763.0,
611
+ "step": 57
612
+ },
613
+ {
614
+ "entropy": 0.8430384919047356,
615
+ "epoch": 1.32,
616
+ "grad_norm": 0.62890625,
617
+ "learning_rate": 6.001079756802592e-05,
618
+ "loss": 0.7592802047729492,
619
+ "mean_token_accuracy": 0.7834662459790707,
620
+ "num_tokens": 1523103.0,
621
+ "step": 58
622
+ },
623
+ {
624
+ "entropy": 1.0481715574860573,
625
+ "epoch": 1.342857142857143,
626
+ "grad_norm": 1.15625,
627
+ "learning_rate": 5.6611626088244194e-05,
628
+ "loss": 0.8737943768501282,
629
+ "mean_token_accuracy": 0.7567208111286163,
630
+ "num_tokens": 1540582.0,
631
+ "step": 59
632
+ },
633
+ {
634
+ "entropy": 0.849721547216177,
635
+ "epoch": 1.3657142857142857,
636
+ "grad_norm": 0.8984375,
637
+ "learning_rate": 5.32731371726938e-05,
638
+ "loss": 0.7518897652626038,
639
+ "mean_token_accuracy": 0.8164225146174431,
640
+ "num_tokens": 1562096.0,
641
+ "step": 60
642
+ },
643
+ {
644
+ "entropy": 0.7319265194237232,
645
+ "epoch": 1.3885714285714286,
646
+ "grad_norm": 0.76953125,
647
+ "learning_rate": 5.000000000000002e-05,
648
+ "loss": 0.5088726282119751,
649
+ "mean_token_accuracy": 0.8368714712560177,
650
+ "num_tokens": 1588869.0,
651
+ "step": 61
652
+ },
653
+ {
654
+ "entropy": 0.7714136429131031,
655
+ "epoch": 1.4114285714285715,
656
+ "grad_norm": 0.515625,
657
+ "learning_rate": 4.6796792348466356e-05,
658
+ "loss": 0.5990605354309082,
659
+ "mean_token_accuracy": 0.8109956867992878,
660
+ "num_tokens": 1618753.0,
661
+ "step": 62
662
+ },
663
+ {
664
+ "entropy": 0.8922704569995403,
665
+ "epoch": 1.4342857142857142,
666
+ "grad_norm": 0.7265625,
667
+ "learning_rate": 4.3667994193637796e-05,
668
+ "loss": 0.7471989393234253,
669
+ "mean_token_accuracy": 0.8137485198676586,
670
+ "num_tokens": 1639035.0,
671
+ "step": 63
672
+ },
673
+ {
674
+ "entropy": 0.8474112637341022,
675
+ "epoch": 1.457142857142857,
676
+ "grad_norm": 0.9375,
677
+ "learning_rate": 4.0617981442649855e-05,
678
+ "loss": 0.9250304102897644,
679
+ "mean_token_accuracy": 0.7889886423945427,
680
+ "num_tokens": 1667695.0,
681
+ "step": 64
682
+ },
683
+ {
684
+ "entropy": 0.8302664868533611,
685
+ "epoch": 1.48,
686
+ "grad_norm": 0.8984375,
687
+ "learning_rate": 3.7651019814126654e-05,
688
+ "loss": 0.9558159112930298,
689
+ "mean_token_accuracy": 0.7763096019625664,
690
+ "num_tokens": 1691022.0,
691
+ "step": 65
692
+ },
693
+ {
694
+ "entropy": 0.8031172640621662,
695
+ "epoch": 1.502857142857143,
696
+ "grad_norm": 0.79296875,
697
+ "learning_rate": 3.477125887218792e-05,
698
+ "loss": 0.801313042640686,
699
+ "mean_token_accuracy": 0.8177301362156868,
700
+ "num_tokens": 1724435.0,
701
+ "step": 66
702
+ },
703
+ {
704
+ "epoch": 1.502857142857143,
705
+ "eval_entropy": 0.8457768812775612,
706
+ "eval_loss": 0.9875430464744568,
707
+ "eval_mean_token_accuracy": 0.756916128396988,
708
+ "eval_num_tokens": 1724435.0,
709
+ "eval_runtime": 77.2316,
710
+ "eval_samples_per_second": 1.295,
711
+ "eval_steps_per_second": 1.295,
712
+ "step": 66
713
+ },
714
+ {
715
+ "entropy": 0.841597568243742,
716
+ "epoch": 1.5257142857142858,
717
+ "grad_norm": 0.8359375,
718
+ "learning_rate": 3.198272622290804e-05,
719
+ "loss": 0.8447511196136475,
720
+ "mean_token_accuracy": 0.7982683703303337,
721
+ "num_tokens": 1752489.0,
722
+ "step": 67
723
+ },
724
+ {
725
+ "entropy": 0.873002614825964,
726
+ "epoch": 1.5485714285714285,
727
+ "grad_norm": 0.68359375,
728
+ "learning_rate": 2.9289321881345254e-05,
729
+ "loss": 0.8038796782493591,
730
+ "mean_token_accuracy": 0.8067350275814533,
731
+ "num_tokens": 1784291.0,
732
+ "step": 68
733
+ },
734
+ {
735
+ "entropy": 0.9177370071411133,
736
+ "epoch": 1.5714285714285714,
737
+ "grad_norm": 0.6796875,
738
+ "learning_rate": 2.669481281701739e-05,
739
+ "loss": 0.8557254672050476,
740
+ "mean_token_accuracy": 0.8137136548757553,
741
+ "num_tokens": 1804179.0,
742
+ "step": 69
743
+ },
744
+ {
745
+ "entropy": 0.8276135660707951,
746
+ "epoch": 1.5942857142857143,
747
+ "grad_norm": 0.73828125,
748
+ "learning_rate": 2.420282768545469e-05,
749
+ "loss": 0.6800186634063721,
750
+ "mean_token_accuracy": 0.8346021547913551,
751
+ "num_tokens": 1831612.0,
752
+ "step": 70
753
+ },
754
+ {
755
+ "entropy": 0.9364416636526585,
756
+ "epoch": 1.617142857142857,
757
+ "grad_norm": 0.75390625,
758
+ "learning_rate": 2.181685175319702e-05,
759
+ "loss": 0.7834956049919128,
760
+ "mean_token_accuracy": 0.7997728437185287,
761
+ "num_tokens": 1853595.0,
762
+ "step": 71
763
+ },
764
+ {
765
+ "entropy": 0.8710121884942055,
766
+ "epoch": 1.6400000000000001,
767
+ "grad_norm": 0.765625,
768
+ "learning_rate": 1.9540222023333166e-05,
769
+ "loss": 0.6057661771774292,
770
+ "mean_token_accuracy": 0.8205794207751751,
771
+ "num_tokens": 1882408.0,
772
+ "step": 72
773
+ },
774
+ {
775
+ "entropy": 0.8379442691802979,
776
+ "epoch": 1.6628571428571428,
777
+ "grad_norm": 0.7734375,
778
+ "learning_rate": 1.7376122568400532e-05,
779
+ "loss": 0.7106757760047913,
780
+ "mean_token_accuracy": 0.8180459216237068,
781
+ "num_tokens": 1904944.0,
782
+ "step": 73
783
+ },
784
+ {
785
+ "entropy": 0.8745108097791672,
786
+ "epoch": 1.6857142857142857,
787
+ "grad_norm": 1.2109375,
788
+ "learning_rate": 1.5327580077171587e-05,
789
+ "loss": 0.9369223713874817,
790
+ "mean_token_accuracy": 0.8044208958745003,
791
+ "num_tokens": 1933402.0,
792
+ "step": 74
793
+ },
794
+ {
795
+ "entropy": 0.8298410475254059,
796
+ "epoch": 1.7085714285714286,
797
+ "grad_norm": 0.8828125,
798
+ "learning_rate": 1.339745962155613e-05,
799
+ "loss": 0.6346684694290161,
800
+ "mean_token_accuracy": 0.8335375674068928,
801
+ "num_tokens": 1960093.0,
802
+ "step": 75
803
+ },
804
+ {
805
+ "entropy": 0.8175692446529865,
806
+ "epoch": 1.7314285714285713,
807
+ "grad_norm": 0.91796875,
808
+ "learning_rate": 1.1588460649539035e-05,
809
+ "loss": 0.9119294285774231,
810
+ "mean_token_accuracy": 0.8193050436675549,
811
+ "num_tokens": 1986339.0,
812
+ "step": 76
813
+ },
814
+ {
815
+ "entropy": 0.8975704163312912,
816
+ "epoch": 1.7542857142857144,
817
+ "grad_norm": 0.859375,
818
+ "learning_rate": 9.903113209758096e-06,
819
+ "loss": 0.7237526178359985,
820
+ "mean_token_accuracy": 0.7882252000272274,
821
+ "num_tokens": 2011176.0,
822
+ "step": 77
823
+ },
824
+ {
825
+ "entropy": 0.8363670147955418,
826
+ "epoch": 1.7771428571428571,
827
+ "grad_norm": 0.74609375,
828
+ "learning_rate": 8.343774413002381e-06,
829
+ "loss": 0.6269868016242981,
830
+ "mean_token_accuracy": 0.8103100657463074,
831
+ "num_tokens": 2041289.0,
832
+ "step": 78
833
+ },
834
+ {
835
+ "entropy": 0.8557109721004963,
836
+ "epoch": 1.8,
837
+ "grad_norm": 0.6171875,
838
+ "learning_rate": 6.9126251355795864e-06,
839
+ "loss": 0.5580326914787292,
840
+ "mean_token_accuracy": 0.8539069853723049,
841
+ "num_tokens": 2069418.0,
842
+ "step": 79
843
+ },
844
+ {
845
+ "entropy": 0.790475644171238,
846
+ "epoch": 1.822857142857143,
847
+ "grad_norm": 0.984375,
848
+ "learning_rate": 5.611666969163243e-06,
849
+ "loss": 0.6902757287025452,
850
+ "mean_token_accuracy": 0.8313734903931618,
851
+ "num_tokens": 2101162.0,
852
+ "step": 80
853
+ },
854
+ {
855
+ "entropy": 0.8487820513546467,
856
+ "epoch": 1.8457142857142856,
857
+ "grad_norm": 0.7265625,
858
+ "learning_rate": 4.442719421385922e-06,
859
+ "loss": 0.6248161792755127,
860
+ "mean_token_accuracy": 0.8196811378002167,
861
+ "num_tokens": 2129262.0,
862
+ "step": 81
863
+ },
864
+ {
865
+ "entropy": 0.8948404788970947,
866
+ "epoch": 1.8685714285714285,
867
+ "grad_norm": 0.87890625,
868
+ "learning_rate": 3.40741737109318e-06,
869
+ "loss": 0.8848119378089905,
870
+ "mean_token_accuracy": 0.7821721211075783,
871
+ "num_tokens": 2152597.0,
872
+ "step": 82
873
+ },
874
+ {
875
+ "entropy": 0.9239097908139229,
876
+ "epoch": 1.8914285714285715,
877
+ "grad_norm": 0.7421875,
878
+ "learning_rate": 2.5072087818176382e-06,
879
+ "loss": 0.7065685987472534,
880
+ "mean_token_accuracy": 0.807807132601738,
881
+ "num_tokens": 2177161.0,
882
+ "step": 83
883
+ },
884
+ {
885
+ "entropy": 0.7839450426399708,
886
+ "epoch": 1.9142857142857141,
887
+ "grad_norm": 0.77734375,
888
+ "learning_rate": 1.7433526766711728e-06,
889
+ "loss": 0.7359437942504883,
890
+ "mean_token_accuracy": 0.8403091952204704,
891
+ "num_tokens": 2209858.0,
892
+ "step": 84
893
+ },
894
+ {
895
+ "entropy": 0.843034666031599,
896
+ "epoch": 1.9371428571428573,
897
+ "grad_norm": 0.765625,
898
+ "learning_rate": 1.1169173774871478e-06,
899
+ "loss": 0.7045976519584656,
900
+ "mean_token_accuracy": 0.7968335002660751,
901
+ "num_tokens": 2238762.0,
902
+ "step": 85
903
+ },
904
+ {
905
+ "entropy": 0.8172502107918262,
906
+ "epoch": 1.96,
907
+ "grad_norm": 0.73046875,
908
+ "learning_rate": 6.287790106757396e-07,
909
+ "loss": 0.7153176665306091,
910
+ "mean_token_accuracy": 0.8268864750862122,
911
+ "num_tokens": 2266000.0,
912
+ "step": 86
913
+ },
914
+ {
915
+ "entropy": 0.9393381252884865,
916
+ "epoch": 1.9828571428571429,
917
+ "grad_norm": 0.8046875,
918
+ "learning_rate": 2.7962028188198706e-07,
919
+ "loss": 0.7222880721092224,
920
+ "mean_token_accuracy": 0.8043639399111271,
921
+ "num_tokens": 2291896.0,
922
+ "step": 87
923
+ },
924
+ {
925
+ "entropy": 0.9007064700126648,
926
+ "epoch": 2.0,
927
+ "grad_norm": 0.9453125,
928
+ "learning_rate": 6.992952116013918e-08,
929
+ "loss": 0.9412174224853516,
930
+ "mean_token_accuracy": 0.7673612783352534,
931
+ "num_tokens": 2307166.0,
932
+ "step": 88
933
+ },
934
+ {
935
+ "epoch": 2.0,
936
+ "eval_entropy": 0.8574838742613793,
937
+ "eval_loss": 0.9815174341201782,
938
+ "eval_mean_token_accuracy": 0.7545835164189338,
939
+ "eval_num_tokens": 2307166.0,
940
+ "eval_runtime": 77.2359,
941
+ "eval_samples_per_second": 1.295,
942
+ "eval_steps_per_second": 1.295,
943
+ "step": 88
944
+ },
945
+ {
946
+ "epoch": 2.0,
947
+ "step": 88,
948
+ "total_flos": 1.0597781694661018e+17,
949
+ "train_loss": 0.9580497294664383,
950
+ "train_runtime": 4168.6102,
951
+ "train_samples_per_second": 0.336,
952
+ "train_steps_per_second": 0.021
953
+ }
954
+ ],
955
+ "trial_params": null,
956
+ "global_step": 88,
957
+ "is_local_process_zero": true,
958
+ "total_flos": 1.0597781694661018e+17,
959
+ "num_train_epochs": 2,
960
+ "epoch": 2.0,
961
+ "best_metric": null,
962
+ "trial_name": null
963
+ }