Vikaspandey582003 commited on
Commit
3d90663
·
verified ·
1 Parent(s): b9dae38

checkpoint step 50

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
+ checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-50/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Qwen2.5-7B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/Qwen2.5-7B-Instruct
7
+ - grpo
8
+ - lora
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.19.1
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
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": 16,
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
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "down_proj",
34
+ "up_proj",
35
+ "k_proj",
36
+ "v_proj",
37
+ "gate_proj",
38
+ "q_proj",
39
+ "o_proj"
40
+ ],
41
+ "target_parameters": null,
42
+ "task_type": "CAUSAL_LM",
43
+ "trainable_token_indices": null,
44
+ "use_bdlora": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
checkpoint-50/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8774212fba617daa40bef4cef915e047bc2e6feee4ceebd5580bf1ee2fb50370
3
+ size 80792880
checkpoint-50/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f91af0fa995043cb9e216dca74e80d09ee819a9d274a9dcf260d0411a6b48ed
3
+ size 161816251
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c8957cbd17b37e5391f10035f189ea0492f94bda207d033f16b09cc832dbcf
3
+ size 14645
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:259b1303d82fa78c2e55eeb7df6096e0b57593f81a8f6658f2d1675d51e39965
3
+ size 1465
checkpoint-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32768,
11
+ "pad_token": "<|vision_pad|>",
12
+ "padding_side": "left",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null
16
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0021551724137931034,
6
+ "eval_steps": 500,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.0,
19
+ "completions/max_length": 130.0,
20
+ "completions/max_terminated_length": 130.0,
21
+ "completions/mean_length": 68.5,
22
+ "completions/mean_terminated_length": 68.5,
23
+ "completions/min_length": 26.8,
24
+ "completions/min_terminated_length": 26.8,
25
+ "entropy": 0.25826080311089755,
26
+ "epoch": 0.00021551724137931034,
27
+ "frac_reward_zero_std": 0.1,
28
+ "grad_norm": 0.28125,
29
+ "learning_rate": 1.0000000000000002e-06,
30
+ "loss": 0.10238287448883057,
31
+ "num_tokens": 12064.0,
32
+ "reward": 0.3290319949388504,
33
+ "reward_std": 0.40028320252895355,
34
+ "rewards/reward_fn/mean": 0.3290319949388504,
35
+ "rewards/reward_fn/std": 0.400283208489418,
36
+ "step": 5,
37
+ "step_time": 22.194597821800016
38
+ },
39
+ {
40
+ "clip_ratio/high_max": 0.0,
41
+ "clip_ratio/high_mean": 0.0,
42
+ "clip_ratio/low_mean": 0.0,
43
+ "clip_ratio/low_min": 0.0,
44
+ "clip_ratio/region_mean": 0.0,
45
+ "completions/clipped_ratio": 0.0,
46
+ "completions/max_length": 87.6,
47
+ "completions/max_terminated_length": 87.6,
48
+ "completions/mean_length": 48.525,
49
+ "completions/mean_terminated_length": 48.525,
50
+ "completions/min_length": 17.0,
51
+ "completions/min_terminated_length": 17.0,
52
+ "entropy": 0.2673827801831067,
53
+ "epoch": 0.0004310344827586207,
54
+ "frac_reward_zero_std": 0.1,
55
+ "grad_norm": 0.484375,
56
+ "learning_rate": 2.25e-06,
57
+ "loss": 0.05849265456199646,
58
+ "num_tokens": 23089.0,
59
+ "reward": 0.45969198942184447,
60
+ "reward_std": 0.2795014828443527,
61
+ "rewards/reward_fn/mean": 0.45969198942184447,
62
+ "rewards/reward_fn/std": 0.27950150668621065,
63
+ "step": 10,
64
+ "step_time": 16.331819552399928
65
+ },
66
+ {
67
+ "clip_ratio/high_max": 0.0,
68
+ "clip_ratio/high_mean": 0.0,
69
+ "clip_ratio/low_mean": 0.0,
70
+ "clip_ratio/low_min": 0.0,
71
+ "clip_ratio/region_mean": 0.0,
72
+ "completions/clipped_ratio": 0.0,
73
+ "completions/max_length": 85.6,
74
+ "completions/max_terminated_length": 85.6,
75
+ "completions/mean_length": 47.35,
76
+ "completions/mean_terminated_length": 47.35,
77
+ "completions/min_length": 25.0,
78
+ "completions/min_terminated_length": 25.0,
79
+ "entropy": 0.20174795808270574,
80
+ "epoch": 0.000646551724137931,
81
+ "frac_reward_zero_std": 0.4,
82
+ "grad_norm": 0.66015625,
83
+ "learning_rate": 3.5e-06,
84
+ "loss": -0.03555725216865539,
85
+ "num_tokens": 34239.0,
86
+ "reward": 0.5545999944210053,
87
+ "reward_std": 0.32832055240869523,
88
+ "rewards/reward_fn/mean": 0.5545999944210053,
89
+ "rewards/reward_fn/std": 0.3283205583691597,
90
+ "step": 15,
91
+ "step_time": 16.44816417159991
92
+ },
93
+ {
94
+ "clip_ratio/high_max": 0.0,
95
+ "clip_ratio/high_mean": 0.0,
96
+ "clip_ratio/low_mean": 0.0,
97
+ "clip_ratio/low_min": 0.0,
98
+ "clip_ratio/region_mean": 0.0,
99
+ "completions/clipped_ratio": 0.0,
100
+ "completions/max_length": 98.2,
101
+ "completions/max_terminated_length": 98.2,
102
+ "completions/mean_length": 53.6,
103
+ "completions/mean_terminated_length": 53.6,
104
+ "completions/min_length": 25.0,
105
+ "completions/min_terminated_length": 25.0,
106
+ "entropy": 0.2620095924474299,
107
+ "epoch": 0.0008620689655172414,
108
+ "frac_reward_zero_std": 0.2,
109
+ "grad_norm": 0.5390625,
110
+ "learning_rate": 4.75e-06,
111
+ "loss": 0.017401468753814698,
112
+ "num_tokens": 45399.0,
113
+ "reward": 0.4466240078210831,
114
+ "reward_std": 0.27573536019772293,
115
+ "rewards/reward_fn/mean": 0.4466240078210831,
116
+ "rewards/reward_fn/std": 0.27573537137359383,
117
+ "step": 20,
118
+ "step_time": 17.988385831799953
119
+ },
120
+ {
121
+ "clip_ratio/high_max": 0.0,
122
+ "clip_ratio/high_mean": 0.0,
123
+ "clip_ratio/low_mean": 0.0,
124
+ "clip_ratio/low_min": 0.0,
125
+ "clip_ratio/region_mean": 0.0,
126
+ "completions/clipped_ratio": 0.0,
127
+ "completions/max_length": 123.8,
128
+ "completions/max_terminated_length": 123.8,
129
+ "completions/mean_length": 59.15,
130
+ "completions/mean_terminated_length": 59.15,
131
+ "completions/min_length": 21.8,
132
+ "completions/min_terminated_length": 21.8,
133
+ "entropy": 0.33701689867302775,
134
+ "epoch": 0.0010775862068965517,
135
+ "frac_reward_zero_std": 0.0,
136
+ "grad_norm": 0.74609375,
137
+ "learning_rate": 4.965517241379311e-06,
138
+ "loss": -0.02674364447593689,
139
+ "num_tokens": 56993.0,
140
+ "reward": 0.5006439983844757,
141
+ "reward_std": 0.2351181447505951,
142
+ "rewards/reward_fn/mean": 0.5006439983844757,
143
+ "rewards/reward_fn/std": 0.23511814773082734,
144
+ "step": 25,
145
+ "step_time": 21.11461545459997
146
+ },
147
+ {
148
+ "clip_ratio/high_max": 0.0,
149
+ "clip_ratio/high_mean": 0.0,
150
+ "clip_ratio/low_mean": 0.0,
151
+ "clip_ratio/low_min": 0.0,
152
+ "clip_ratio/region_mean": 0.0,
153
+ "completions/clipped_ratio": 0.0,
154
+ "completions/max_length": 110.2,
155
+ "completions/max_terminated_length": 110.2,
156
+ "completions/mean_length": 47.95,
157
+ "completions/mean_terminated_length": 47.95,
158
+ "completions/min_length": 15.8,
159
+ "completions/min_terminated_length": 15.8,
160
+ "entropy": 0.24504410615190864,
161
+ "epoch": 0.001293103448275862,
162
+ "frac_reward_zero_std": 0.4,
163
+ "grad_norm": 0.92578125,
164
+ "learning_rate": 4.922413793103449e-06,
165
+ "loss": -0.05023183822631836,
166
+ "num_tokens": 67659.0,
167
+ "reward": 0.6457239985466003,
168
+ "reward_std": 0.11179900387069211,
169
+ "rewards/reward_fn/mean": 0.6457239985466003,
170
+ "rewards/reward_fn/std": 0.11179901438299567,
171
+ "step": 30,
172
+ "step_time": 19.134268762199827
173
+ },
174
+ {
175
+ "clip_ratio/high_max": 0.0,
176
+ "clip_ratio/high_mean": 0.0,
177
+ "clip_ratio/low_mean": 0.0,
178
+ "clip_ratio/low_min": 0.0,
179
+ "clip_ratio/region_mean": 0.0,
180
+ "completions/clipped_ratio": 0.1,
181
+ "completions/max_length": 150.8,
182
+ "completions/max_terminated_length": 120.2,
183
+ "completions/mean_length": 73.375,
184
+ "completions/mean_terminated_length": 54.36666717529297,
185
+ "completions/min_length": 15.2,
186
+ "completions/min_terminated_length": 15.2,
187
+ "entropy": 0.23285924410447478,
188
+ "epoch": 0.0015086206896551724,
189
+ "frac_reward_zero_std": 0.3,
190
+ "grad_norm": 0.58203125,
191
+ "learning_rate": 4.879310344827586e-06,
192
+ "loss": -0.05149807929992676,
193
+ "num_tokens": 79734.0,
194
+ "reward": 0.46414998471736907,
195
+ "reward_std": 0.4071369742392562,
196
+ "rewards/reward_fn/mean": 0.46414998471736907,
197
+ "rewards/reward_fn/std": 0.40713699695188554,
198
+ "step": 35,
199
+ "step_time": 24.679699858600042
200
+ },
201
+ {
202
+ "clip_ratio/high_max": 0.0,
203
+ "clip_ratio/high_mean": 0.0,
204
+ "clip_ratio/low_mean": 0.0,
205
+ "clip_ratio/low_min": 0.0,
206
+ "clip_ratio/region_mean": 0.0,
207
+ "completions/clipped_ratio": 0.0,
208
+ "completions/max_length": 125.4,
209
+ "completions/max_terminated_length": 125.4,
210
+ "completions/mean_length": 68.925,
211
+ "completions/mean_terminated_length": 68.925,
212
+ "completions/min_length": 26.0,
213
+ "completions/min_terminated_length": 26.0,
214
+ "entropy": 0.3110098702833056,
215
+ "epoch": 0.0017241379310344827,
216
+ "frac_reward_zero_std": 0.1,
217
+ "grad_norm": 0.419921875,
218
+ "learning_rate": 4.836206896551724e-06,
219
+ "loss": 0.030162644386291505,
220
+ "num_tokens": 91695.0,
221
+ "reward": 0.5143539935350419,
222
+ "reward_std": 0.2790891878306866,
223
+ "rewards/reward_fn/mean": 0.5143539935350419,
224
+ "rewards/reward_fn/std": 0.279089218378067,
225
+ "step": 40,
226
+ "step_time": 21.565513409599998
227
+ },
228
+ {
229
+ "clip_ratio/high_max": 0.0,
230
+ "clip_ratio/high_mean": 0.0,
231
+ "clip_ratio/low_mean": 0.0,
232
+ "clip_ratio/low_min": 0.0,
233
+ "clip_ratio/region_mean": 0.0,
234
+ "completions/clipped_ratio": 0.0,
235
+ "completions/max_length": 100.0,
236
+ "completions/max_terminated_length": 100.0,
237
+ "completions/mean_length": 53.875,
238
+ "completions/mean_terminated_length": 53.875,
239
+ "completions/min_length": 16.6,
240
+ "completions/min_terminated_length": 16.6,
241
+ "entropy": 0.23047098610550165,
242
+ "epoch": 0.001939655172413793,
243
+ "frac_reward_zero_std": 0.4,
244
+ "grad_norm": 1.15625,
245
+ "learning_rate": 4.793103448275862e-06,
246
+ "loss": -0.04350074529647827,
247
+ "num_tokens": 102994.0,
248
+ "reward": 0.6398920059204102,
249
+ "reward_std": 0.2279826147481799,
250
+ "rewards/reward_fn/mean": 0.6398920059204102,
251
+ "rewards/reward_fn/std": 0.22798261437565087,
252
+ "step": 45,
253
+ "step_time": 18.23975218899968
254
+ },
255
+ {
256
+ "clip_ratio/high_max": 0.0,
257
+ "clip_ratio/high_mean": 0.0,
258
+ "clip_ratio/low_mean": 0.0,
259
+ "clip_ratio/low_min": 0.0,
260
+ "clip_ratio/region_mean": 0.0,
261
+ "completions/clipped_ratio": 0.0,
262
+ "completions/max_length": 133.4,
263
+ "completions/max_terminated_length": 133.4,
264
+ "completions/mean_length": 75.975,
265
+ "completions/mean_terminated_length": 75.975,
266
+ "completions/min_length": 23.8,
267
+ "completions/min_terminated_length": 23.8,
268
+ "entropy": 0.34613882582634686,
269
+ "epoch": 0.0021551724137931034,
270
+ "frac_reward_zero_std": 0.2,
271
+ "grad_norm": 0.1318359375,
272
+ "learning_rate": 4.75e-06,
273
+ "loss": -0.03668657541275024,
274
+ "num_tokens": 115289.0,
275
+ "reward": 0.33042599707841874,
276
+ "reward_std": 0.5918701648712158,
277
+ "rewards/reward_fn/mean": 0.33042599707841874,
278
+ "rewards/reward_fn/std": 0.5918702006340026,
279
+ "step": 50,
280
+ "step_time": 22.43372436519985
281
+ }
282
+ ],
283
+ "logging_steps": 5,
284
+ "max_steps": 600,
285
+ "num_input_tokens_seen": 115289,
286
+ "num_train_epochs": 1,
287
+ "save_steps": 50,
288
+ "stateful_callbacks": {
289
+ "TrainerControl": {
290
+ "args": {
291
+ "should_epoch_stop": false,
292
+ "should_evaluate": false,
293
+ "should_log": false,
294
+ "should_save": true,
295
+ "should_training_stop": false
296
+ },
297
+ "attributes": {}
298
+ }
299
+ },
300
+ "total_flos": 0.0,
301
+ "train_batch_size": 1,
302
+ "trial_name": null,
303
+ "trial_params": null
304
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf50531ca359d39fbfa05dc0896e03532a83d53b029182b6d7f757efab0c97a
3
+ size 7185