Hugging Face's logo

clejordan
/
MNLP_M3_quantized_model

Text Generation
Transformers
Safetensors
qwen3
conversational
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
 Community
clejordan commited on
Commit
85d1b38
·
verified ·
1 Parent(s): b58813c

Initial commit: MNLP M3 quantized model

Browse files
Files changed (27) hide show
  1. checkpoint-11502/README.md +202 -0
  2. checkpoint-11502/adapter_config.json +39 -0
  3. checkpoint-11502/adapter_model.safetensors +3 -0
  4. checkpoint-11502/optimizer.pt +3 -0
  5. checkpoint-11502/rng_state.pth +3 -0
  6. checkpoint-11502/scaler.pt +3 -0
  7. checkpoint-11502/scheduler.pt +3 -0
  8. checkpoint-11502/trainer_state.json +211 -0
  9. checkpoint-11502/training_args.bin +3 -0
  10. checkpoint-17253/README.md +202 -0
  11. checkpoint-17253/adapter_config.json +39 -0
  12. checkpoint-17253/adapter_model.safetensors +3 -0
  13. checkpoint-17253/optimizer.pt +3 -0
  14. checkpoint-17253/rng_state.pth +3 -0
  15. checkpoint-17253/scaler.pt +3 -0
  16. checkpoint-17253/scheduler.pt +3 -0
  17. checkpoint-17253/trainer_state.json +296 -0
  18. checkpoint-17253/training_args.bin +3 -0
  19. checkpoint-5751/README.md +202 -0
  20. checkpoint-5751/adapter_config.json +39 -0
  21. checkpoint-5751/adapter_model.safetensors +3 -0
  22. checkpoint-5751/optimizer.pt +3 -0
  23. checkpoint-5751/rng_state.pth +3 -0
  24. checkpoint-5751/scaler.pt +3 -0
  25. checkpoint-5751/scheduler.pt +3 -0
  26. checkpoint-5751/trainer_state.json +119 -0
  27. checkpoint-5751/training_args.bin +3 -0
checkpoint-11502/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B-Base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-11502/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "q_proj",
32
+ "down_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-11502/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd4b585c0f3e4ef60ac9f6bff3371e0b58bc43f74a7247fca02259b59f10cdb
3
+ size 20243136
checkpoint-11502/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79090d2c55e4e99e4ae06262c00e9f2ce1bf8182109e3a269113fdeacc963eb6
3
+ size 40699434
checkpoint-11502/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28736a80102fab43bcf5c1d1e9dc6a88947e46af459cca97238dc9bbbdf5bc4b
3
+ size 14244
checkpoint-11502/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f46162db17e079a9706c2a4123deafc07ff4dfb26b47d7134cfd5a81094f13
3
+ size 988
checkpoint-11502/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf0678c8431c32ee488ef33c659bd02feb2088d7e6423f432b09a05eab0958d
3
+ size 1064
checkpoint-11502/trainer_state.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 11502,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0869414014953921,
14
+ "grad_norm": 0.2196940779685974,
15
+ "learning_rate": 0.00019426186750130412,
16
+ "loss": 0.2606,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.1738828029907842,
21
+ "grad_norm": 0.2677164673805237,
22
+ "learning_rate": 0.000188465774068278,
23
+ "loss": 0.1763,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2608242044861763,
28
+ "grad_norm": 0.21263259649276733,
29
+ "learning_rate": 0.00018266968063525185,
30
+ "loss": 0.1714,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3477656059815684,
35
+ "grad_norm": 0.275687575340271,
36
+ "learning_rate": 0.0001768735872022257,
37
+ "loss": 0.1693,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4347070074769605,
42
+ "grad_norm": 0.21894076466560364,
43
+ "learning_rate": 0.00017107749376919957,
44
+ "loss": 0.1719,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5216484089723527,
49
+ "grad_norm": 0.23001301288604736,
50
+ "learning_rate": 0.00016528140033617342,
51
+ "loss": 0.1691,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6085898104677447,
56
+ "grad_norm": 0.23900070786476135,
57
+ "learning_rate": 0.0001594853069031473,
58
+ "loss": 0.167,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.6955312119631368,
63
+ "grad_norm": 0.2820037603378296,
64
+ "learning_rate": 0.00015368921347012115,
65
+ "loss": 0.1678,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.7824726134585289,
70
+ "grad_norm": 0.3206230700016022,
71
+ "learning_rate": 0.00014789312003709503,
72
+ "loss": 0.1675,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.869414014953921,
77
+ "grad_norm": 0.20400723814964294,
78
+ "learning_rate": 0.00014209702660406887,
79
+ "loss": 0.1658,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.9563554164493132,
84
+ "grad_norm": 0.31783542037010193,
85
+ "learning_rate": 0.00013630093317104272,
86
+ "loss": 0.1643,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.0,
91
+ "eval_loss": 0.16573764383792877,
92
+ "eval_runtime": 80.6587,
93
+ "eval_samples_per_second": 31.689,
94
+ "eval_steps_per_second": 7.922,
95
+ "step": 5751
96
+ },
97
+ {
98
+ "epoch": 1.0432968179447053,
99
+ "grad_norm": 0.3012489676475525,
100
+ "learning_rate": 0.0001305048397380166,
101
+ "loss": 0.1588,
102
+ "step": 6000
103
+ },
104
+ {
105
+ "epoch": 1.1302382194400973,
106
+ "grad_norm": 0.2865125238895416,
107
+ "learning_rate": 0.00012470874630499042,
108
+ "loss": 0.1474,
109
+ "step": 6500
110
+ },
111
+ {
112
+ "epoch": 1.2171796209354895,
113
+ "grad_norm": 0.2503669857978821,
114
+ "learning_rate": 0.0001189126528719643,
115
+ "loss": 0.1489,
116
+ "step": 7000
117
+ },
118
+ {
119
+ "epoch": 1.3041210224308815,
120
+ "grad_norm": 0.2573595643043518,
121
+ "learning_rate": 0.00011311655943893815,
122
+ "loss": 0.1488,
123
+ "step": 7500
124
+ },
125
+ {
126
+ "epoch": 1.3910624239262737,
127
+ "grad_norm": 0.2882978916168213,
128
+ "learning_rate": 0.00010732046600591201,
129
+ "loss": 0.1465,
130
+ "step": 8000
131
+ },
132
+ {
133
+ "epoch": 1.4780038254216659,
134
+ "grad_norm": 0.33109399676322937,
135
+ "learning_rate": 0.00010152437257288587,
136
+ "loss": 0.1503,
137
+ "step": 8500
138
+ },
139
+ {
140
+ "epoch": 1.5649452269170578,
141
+ "grad_norm": 0.5740349888801575,
142
+ "learning_rate": 9.572827913985975e-05,
143
+ "loss": 0.1493,
144
+ "step": 9000
145
+ },
146
+ {
147
+ "epoch": 1.65188662841245,
148
+ "grad_norm": 0.298555463552475,
149
+ "learning_rate": 8.99321857068336e-05,
150
+ "loss": 0.1483,
151
+ "step": 9500
152
+ },
153
+ {
154
+ "epoch": 1.7388280299078422,
155
+ "grad_norm": 0.333500474691391,
156
+ "learning_rate": 8.413609227380746e-05,
157
+ "loss": 0.1469,
158
+ "step": 10000
159
+ },
160
+ {
161
+ "epoch": 1.8257694314032342,
162
+ "grad_norm": 0.30120372772216797,
163
+ "learning_rate": 7.833999884078131e-05,
164
+ "loss": 0.1493,
165
+ "step": 10500
166
+ },
167
+ {
168
+ "epoch": 1.9127108328986262,
169
+ "grad_norm": 0.28990960121154785,
170
+ "learning_rate": 7.254390540775517e-05,
171
+ "loss": 0.1458,
172
+ "step": 11000
173
+ },
174
+ {
175
+ "epoch": 1.9996522343940184,
176
+ "grad_norm": 0.5824082493782043,
177
+ "learning_rate": 6.674781197472903e-05,
178
+ "loss": 0.1504,
179
+ "step": 11500
180
+ },
181
+ {
182
+ "epoch": 2.0,
183
+ "eval_loss": 0.1634208858013153,
184
+ "eval_runtime": 80.8075,
185
+ "eval_samples_per_second": 31.631,
186
+ "eval_steps_per_second": 7.908,
187
+ "step": 11502
188
+ }
189
+ ],
190
+ "logging_steps": 500,
191
+ "max_steps": 17253,
192
+ "num_input_tokens_seen": 0,
193
+ "num_train_epochs": 3,
194
+ "save_steps": 500,
195
+ "stateful_callbacks": {
196
+ "TrainerControl": {
197
+ "args": {
198
+ "should_epoch_stop": false,
199
+ "should_evaluate": false,
200
+ "should_log": false,
201
+ "should_save": true,
202
+ "should_training_stop": false
203
+ },
204
+ "attributes": {}
205
+ }
206
+ },
207
+ "total_flos": 6.29646476401705e+16,
208
+ "train_batch_size": 4,
209
+ "trial_name": null,
210
+ "trial_params": null
211
+ }
checkpoint-11502/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb590c3405bb321e9c77b1f2243981f8f41d35f037852c7fac86c1191f3b93d
3
+ size 5240
checkpoint-17253/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B-Base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-17253/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "q_proj",
32
+ "down_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-17253/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45693b9cd8afbb41d58108077fcf4359946130c8044f6e8b257a7650afdb702a
3
+ size 20243136
checkpoint-17253/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9c11ab10a9a068eb7be4ba5d55d24764197c51d4356aa0299c1c02a573e367
3
+ size 40699434
checkpoint-17253/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82169739e50e874f2f26da7d4d29a03b185e25b3179c2c76acfb6c1d9adb1a97
3
+ size 14244
checkpoint-17253/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5ad3b693be99a5dac611e0456760165d5a6c761ca4a2bdb14da83cb70ac609
3
+ size 988
checkpoint-17253/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400d96f8001902fcdfb4263517a92d19497f1ed5d512b07f5da1ea66c847616f
3
+ size 1064
checkpoint-17253/trainer_state.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 17253,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0869414014953921,
14
+ "grad_norm": 0.2196940779685974,
15
+ "learning_rate": 0.00019426186750130412,
16
+ "loss": 0.2606,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.1738828029907842,
21
+ "grad_norm": 0.2677164673805237,
22
+ "learning_rate": 0.000188465774068278,
23
+ "loss": 0.1763,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2608242044861763,
28
+ "grad_norm": 0.21263259649276733,
29
+ "learning_rate": 0.00018266968063525185,
30
+ "loss": 0.1714,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3477656059815684,
35
+ "grad_norm": 0.275687575340271,
36
+ "learning_rate": 0.0001768735872022257,
37
+ "loss": 0.1693,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4347070074769605,
42
+ "grad_norm": 0.21894076466560364,
43
+ "learning_rate": 0.00017107749376919957,
44
+ "loss": 0.1719,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5216484089723527,
49
+ "grad_norm": 0.23001301288604736,
50
+ "learning_rate": 0.00016528140033617342,
51
+ "loss": 0.1691,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6085898104677447,
56
+ "grad_norm": 0.23900070786476135,
57
+ "learning_rate": 0.0001594853069031473,
58
+ "loss": 0.167,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.6955312119631368,
63
+ "grad_norm": 0.2820037603378296,
64
+ "learning_rate": 0.00015368921347012115,
65
+ "loss": 0.1678,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.7824726134585289,
70
+ "grad_norm": 0.3206230700016022,
71
+ "learning_rate": 0.00014789312003709503,
72
+ "loss": 0.1675,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.869414014953921,
77
+ "grad_norm": 0.20400723814964294,
78
+ "learning_rate": 0.00014209702660406887,
79
+ "loss": 0.1658,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.9563554164493132,
84
+ "grad_norm": 0.31783542037010193,
85
+ "learning_rate": 0.00013630093317104272,
86
+ "loss": 0.1643,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.0,
91
+ "eval_loss": 0.16573764383792877,
92
+ "eval_runtime": 80.6587,
93
+ "eval_samples_per_second": 31.689,
94
+ "eval_steps_per_second": 7.922,
95
+ "step": 5751
96
+ },
97
+ {
98
+ "epoch": 1.0432968179447053,
99
+ "grad_norm": 0.3012489676475525,
100
+ "learning_rate": 0.0001305048397380166,
101
+ "loss": 0.1588,
102
+ "step": 6000
103
+ },
104
+ {
105
+ "epoch": 1.1302382194400973,
106
+ "grad_norm": 0.2865125238895416,
107
+ "learning_rate": 0.00012470874630499042,
108
+ "loss": 0.1474,
109
+ "step": 6500
110
+ },
111
+ {
112
+ "epoch": 1.2171796209354895,
113
+ "grad_norm": 0.2503669857978821,
114
+ "learning_rate": 0.0001189126528719643,
115
+ "loss": 0.1489,
116
+ "step": 7000
117
+ },
118
+ {
119
+ "epoch": 1.3041210224308815,
120
+ "grad_norm": 0.2573595643043518,
121
+ "learning_rate": 0.00011311655943893815,
122
+ "loss": 0.1488,
123
+ "step": 7500
124
+ },
125
+ {
126
+ "epoch": 1.3910624239262737,
127
+ "grad_norm": 0.2882978916168213,
128
+ "learning_rate": 0.00010732046600591201,
129
+ "loss": 0.1465,
130
+ "step": 8000
131
+ },
132
+ {
133
+ "epoch": 1.4780038254216659,
134
+ "grad_norm": 0.33109399676322937,
135
+ "learning_rate": 0.00010152437257288587,
136
+ "loss": 0.1503,
137
+ "step": 8500
138
+ },
139
+ {
140
+ "epoch": 1.5649452269170578,
141
+ "grad_norm": 0.5740349888801575,
142
+ "learning_rate": 9.572827913985975e-05,
143
+ "loss": 0.1493,
144
+ "step": 9000
145
+ },
146
+ {
147
+ "epoch": 1.65188662841245,
148
+ "grad_norm": 0.298555463552475,
149
+ "learning_rate": 8.99321857068336e-05,
150
+ "loss": 0.1483,
151
+ "step": 9500
152
+ },
153
+ {
154
+ "epoch": 1.7388280299078422,
155
+ "grad_norm": 0.333500474691391,
156
+ "learning_rate": 8.413609227380746e-05,
157
+ "loss": 0.1469,
158
+ "step": 10000
159
+ },
160
+ {
161
+ "epoch": 1.8257694314032342,
162
+ "grad_norm": 0.30120372772216797,
163
+ "learning_rate": 7.833999884078131e-05,
164
+ "loss": 0.1493,
165
+ "step": 10500
166
+ },
167
+ {
168
+ "epoch": 1.9127108328986262,
169
+ "grad_norm": 0.28990960121154785,
170
+ "learning_rate": 7.254390540775517e-05,
171
+ "loss": 0.1458,
172
+ "step": 11000
173
+ },
174
+ {
175
+ "epoch": 1.9996522343940184,
176
+ "grad_norm": 0.5824082493782043,
177
+ "learning_rate": 6.674781197472903e-05,
178
+ "loss": 0.1504,
179
+ "step": 11500
180
+ },
181
+ {
182
+ "epoch": 2.0,
183
+ "eval_loss": 0.1634208858013153,
184
+ "eval_runtime": 80.8075,
185
+ "eval_samples_per_second": 31.631,
186
+ "eval_steps_per_second": 7.908,
187
+ "step": 11502
188
+ },
189
+ {
190
+ "epoch": 2.0865936358894106,
191
+ "grad_norm": 0.4085701107978821,
192
+ "learning_rate": 6.0951718541702897e-05,
193
+ "loss": 0.1307,
194
+ "step": 12000
195
+ },
196
+ {
197
+ "epoch": 2.1735350373848026,
198
+ "grad_norm": 0.32403185963630676,
199
+ "learning_rate": 5.516721729554281e-05,
200
+ "loss": 0.1283,
201
+ "step": 12500
202
+ },
203
+ {
204
+ "epoch": 2.2604764388801946,
205
+ "grad_norm": 0.5084943175315857,
206
+ "learning_rate": 4.9371123862516664e-05,
207
+ "loss": 0.1298,
208
+ "step": 13000
209
+ },
210
+ {
211
+ "epoch": 2.347417840375587,
212
+ "grad_norm": 0.31282761693000793,
213
+ "learning_rate": 4.357503042949053e-05,
214
+ "loss": 0.1292,
215
+ "step": 13500
216
+ },
217
+ {
218
+ "epoch": 2.434359241870979,
219
+ "grad_norm": 0.28461700677871704,
220
+ "learning_rate": 3.777893699646439e-05,
221
+ "loss": 0.1299,
222
+ "step": 14000
223
+ },
224
+ {
225
+ "epoch": 2.521300643366371,
226
+ "grad_norm": 0.4293518364429474,
227
+ "learning_rate": 3.1982843563438245e-05,
228
+ "loss": 0.1312,
229
+ "step": 14500
230
+ },
231
+ {
232
+ "epoch": 2.608242044861763,
233
+ "grad_norm": 0.27910229563713074,
234
+ "learning_rate": 2.6198342317278157e-05,
235
+ "loss": 0.1286,
236
+ "step": 15000
237
+ },
238
+ {
239
+ "epoch": 2.6951834463571553,
240
+ "grad_norm": 0.3739106059074402,
241
+ "learning_rate": 2.0402248884252016e-05,
242
+ "loss": 0.1313,
243
+ "step": 15500
244
+ },
245
+ {
246
+ "epoch": 2.7821248478525473,
247
+ "grad_norm": 0.38641801476478577,
248
+ "learning_rate": 1.4606155451225875e-05,
249
+ "loss": 0.1299,
250
+ "step": 16000
251
+ },
252
+ {
253
+ "epoch": 2.8690662493479397,
254
+ "grad_norm": 0.25568658113479614,
255
+ "learning_rate": 8.810062018199734e-06,
256
+ "loss": 0.1294,
257
+ "step": 16500
258
+ },
259
+ {
260
+ "epoch": 2.9560076508433317,
261
+ "grad_norm": 0.3838019073009491,
262
+ "learning_rate": 3.013968585173593e-06,
263
+ "loss": 0.1304,
264
+ "step": 17000
265
+ },
266
+ {
267
+ "epoch": 3.0,
268
+ "eval_loss": 0.16723191738128662,
269
+ "eval_runtime": 80.6877,
270
+ "eval_samples_per_second": 31.678,
271
+ "eval_steps_per_second": 7.919,
272
+ "step": 17253
273
+ }
274
+ ],
275
+ "logging_steps": 500,
276
+ "max_steps": 17253,
277
+ "num_input_tokens_seen": 0,
278
+ "num_train_epochs": 3,
279
+ "save_steps": 500,
280
+ "stateful_callbacks": {
281
+ "TrainerControl": {
282
+ "args": {
283
+ "should_epoch_stop": false,
284
+ "should_evaluate": false,
285
+ "should_log": false,
286
+ "should_save": true,
287
+ "should_training_stop": true
288
+ },
289
+ "attributes": {}
290
+ }
291
+ },
292
+ "total_flos": 9.444697146025574e+16,
293
+ "train_batch_size": 4,
294
+ "trial_name": null,
295
+ "trial_params": null
296
+ }
checkpoint-17253/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb590c3405bb321e9c77b1f2243981f8f41d35f037852c7fac86c1191f3b93d
3
+ size 5240
checkpoint-5751/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B-Base
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- 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. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ 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).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-5751/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "q_proj",
32
+ "down_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-5751/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4862f3b505031f9b2c55607739804b852b93b6cded6dde5dd975894f6372766a
3
+ size 20243136
checkpoint-5751/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d0682019e9bed4623ac62035f013ab3f9476d0f384d4fd945108357de6f423
3
+ size 40699434
checkpoint-5751/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4394136fb64eb98f651f75ef940681d780caab4c23a847d316298109499168bd
3
+ size 14244
checkpoint-5751/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5820fb9a9c4841034c6fda9b374e822e5e9f63c5394403d4618580fb13b469d8
3
+ size 988
checkpoint-5751/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005bbd780391869e7961f515cfb7223f41a929b03950c9ee31e174d339bd5ada
3
+ size 1064
checkpoint-5751/trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5751,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0869414014953921,
14
+ "grad_norm": 0.2196940779685974,
15
+ "learning_rate": 0.00019426186750130412,
16
+ "loss": 0.2606,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.1738828029907842,
21
+ "grad_norm": 0.2677164673805237,
22
+ "learning_rate": 0.000188465774068278,
23
+ "loss": 0.1763,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2608242044861763,
28
+ "grad_norm": 0.21263259649276733,
29
+ "learning_rate": 0.00018266968063525185,
30
+ "loss": 0.1714,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3477656059815684,
35
+ "grad_norm": 0.275687575340271,
36
+ "learning_rate": 0.0001768735872022257,
37
+ "loss": 0.1693,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4347070074769605,
42
+ "grad_norm": 0.21894076466560364,
43
+ "learning_rate": 0.00017107749376919957,
44
+ "loss": 0.1719,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5216484089723527,
49
+ "grad_norm": 0.23001301288604736,
50
+ "learning_rate": 0.00016528140033617342,
51
+ "loss": 0.1691,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6085898104677447,
56
+ "grad_norm": 0.23900070786476135,
57
+ "learning_rate": 0.0001594853069031473,
58
+ "loss": 0.167,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.6955312119631368,
63
+ "grad_norm": 0.2820037603378296,
64
+ "learning_rate": 0.00015368921347012115,
65
+ "loss": 0.1678,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.7824726134585289,
70
+ "grad_norm": 0.3206230700016022,
71
+ "learning_rate": 0.00014789312003709503,
72
+ "loss": 0.1675,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.869414014953921,
77
+ "grad_norm": 0.20400723814964294,
78
+ "learning_rate": 0.00014209702660406887,
79
+ "loss": 0.1658,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.9563554164493132,
84
+ "grad_norm": 0.31783542037010193,
85
+ "learning_rate": 0.00013630093317104272,
86
+ "loss": 0.1643,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.0,
91
+ "eval_loss": 0.16573764383792877,
92
+ "eval_runtime": 80.6587,
93
+ "eval_samples_per_second": 31.689,
94
+ "eval_steps_per_second": 7.922,
95
+ "step": 5751
96
+ }
97
+ ],
98
+ "logging_steps": 500,
99
+ "max_steps": 17253,
100
+ "num_input_tokens_seen": 0,
101
+ "num_train_epochs": 3,
102
+ "save_steps": 500,
103
+ "stateful_callbacks": {
104
+ "TrainerControl": {
105
+ "args": {
106
+ "should_epoch_stop": false,
107
+ "should_evaluate": false,
108
+ "should_log": false,
109
+ "should_save": true,
110
+ "should_training_stop": false
111
+ },
112
+ "attributes": {}
113
+ }
114
+ },
115
+ "total_flos": 3.148232382008525e+16,
116
+ "train_batch_size": 4,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }
checkpoint-5751/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb590c3405bb321e9c77b1f2243981f8f41d35f037852c7fac86c1191f3b93d
3
+ size 5240