lmg-anon commited on
Commit
a064569
1 Parent(s): 2727c10

Upload folder using huggingface_hub

Browse files
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: rinna/llama-3-youko-8b
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 0.11.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rinna/llama-3-youko-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": "unsloth",
25
+ "target_modules": [
26
+ "o_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "q_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": true
37
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d0d05e06bc25d8773d0aa7bbc424759b00d64f07846de5f4ee86d30789bb2b
3
+ size 11849545016
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de29957f8d3d72eed4eb3644acf58321a0f5415f54ccf366858e348d55d880c
3
+ size 2778493596
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af34d41a387513fe16d2f526704002f5f5013be898bf20077d67118a76362740
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da542b8958b1a0b8a043729d035cfc7e974b103881eaa9132c25d65d52bd503
3
+ size 1064
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.20128824476650564,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002012882447665056,
13
+ "grad_norm": 22.921390533447266,
14
+ "learning_rate": 6.5e-06,
15
+ "loss": 1.3427,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004025764895330112,
20
+ "grad_norm": 14.772722244262695,
21
+ "learning_rate": 1.3e-05,
22
+ "loss": 1.3647,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.006038647342995169,
27
+ "grad_norm": 11.458742141723633,
28
+ "learning_rate": 1.9499999999999996e-05,
29
+ "loss": 1.2841,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.008051529790660225,
34
+ "grad_norm": 4.747677326202393,
35
+ "learning_rate": 2.6e-05,
36
+ "loss": 1.1644,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.010064412238325281,
41
+ "grad_norm": 3.687121629714966,
42
+ "learning_rate": 3.25e-05,
43
+ "loss": 1.1084,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.012077294685990338,
48
+ "grad_norm": 3.178232431411743,
49
+ "learning_rate": 3.899999999999999e-05,
50
+ "loss": 1.0753,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.014090177133655395,
55
+ "grad_norm": 2.476033926010132,
56
+ "learning_rate": 4.5499999999999995e-05,
57
+ "loss": 1.075,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01610305958132045,
62
+ "grad_norm": 1.9162139892578125,
63
+ "learning_rate": 5.2e-05,
64
+ "loss": 1.0195,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.018115942028985508,
69
+ "grad_norm": 1.797377109527588,
70
+ "learning_rate": 5.85e-05,
71
+ "loss": 0.9884,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.020128824476650563,
76
+ "grad_norm": 1.816100835800171,
77
+ "learning_rate": 6.5e-05,
78
+ "loss": 0.9945,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.02214170692431562,
83
+ "grad_norm": 1.843664526939392,
84
+ "learning_rate": 6.499932098548219e-05,
85
+ "loss": 0.8802,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.024154589371980676,
90
+ "grad_norm": 1.7202250957489014,
91
+ "learning_rate": 6.49972839703017e-05,
92
+ "loss": 0.9833,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.026167471819645734,
97
+ "grad_norm": 1.4981484413146973,
98
+ "learning_rate": 6.499388903957628e-05,
99
+ "loss": 0.9481,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02818035426731079,
104
+ "grad_norm": 1.4716213941574097,
105
+ "learning_rate": 6.498913633516483e-05,
106
+ "loss": 0.8809,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.030193236714975844,
111
+ "grad_norm": 1.3817026615142822,
112
+ "learning_rate": 6.498302605566152e-05,
113
+ "loss": 0.9264,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0322061191626409,
118
+ "grad_norm": 1.509097695350647,
119
+ "learning_rate": 6.497555845638748e-05,
120
+ "loss": 0.8829,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.03421900161030596,
125
+ "grad_norm": 1.5498337745666504,
126
+ "learning_rate": 6.496673384938014e-05,
127
+ "loss": 0.9227,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.036231884057971016,
132
+ "grad_norm": 1.527828574180603,
133
+ "learning_rate": 6.49565526033802e-05,
134
+ "loss": 0.9488,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.038244766505636074,
139
+ "grad_norm": 1.4578592777252197,
140
+ "learning_rate": 6.494501514381621e-05,
141
+ "loss": 0.8845,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.040257648953301126,
146
+ "grad_norm": 1.4198046922683716,
147
+ "learning_rate": 6.493212195278678e-05,
148
+ "loss": 0.8809,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.042270531400966184,
153
+ "grad_norm": 1.4455400705337524,
154
+ "learning_rate": 6.491787356904047e-05,
155
+ "loss": 0.8686,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04428341384863124,
160
+ "grad_norm": 1.5711616277694702,
161
+ "learning_rate": 6.490227058795323e-05,
162
+ "loss": 0.96,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.046296296296296294,
167
+ "grad_norm": 1.4603729248046875,
168
+ "learning_rate": 6.488531366150359e-05,
169
+ "loss": 0.9026,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04830917874396135,
174
+ "grad_norm": 1.4184608459472656,
175
+ "learning_rate": 6.48670034982453e-05,
176
+ "loss": 0.9426,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.05032206119162641,
181
+ "grad_norm": 1.4080291986465454,
182
+ "learning_rate": 6.484734086327788e-05,
183
+ "loss": 0.8857,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05233494363929147,
188
+ "grad_norm": 1.4739091396331787,
189
+ "learning_rate": 6.482632657821454e-05,
190
+ "loss": 0.8897,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05434782608695652,
195
+ "grad_norm": 1.320746898651123,
196
+ "learning_rate": 6.480396152114787e-05,
197
+ "loss": 0.8512,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05636070853462158,
202
+ "grad_norm": 1.4142905473709106,
203
+ "learning_rate": 6.478024662661315e-05,
204
+ "loss": 0.9459,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05837359098228664,
209
+ "grad_norm": 1.3830432891845703,
210
+ "learning_rate": 6.47551828855493e-05,
211
+ "loss": 0.8605,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.06038647342995169,
216
+ "grad_norm": 1.3653528690338135,
217
+ "learning_rate": 6.472877134525753e-05,
218
+ "loss": 0.8446,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06239935587761675,
223
+ "grad_norm": 1.3041807413101196,
224
+ "learning_rate": 6.470101310935746e-05,
225
+ "loss": 0.8407,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.0644122383252818,
230
+ "grad_norm": 1.3803820610046387,
231
+ "learning_rate": 6.467190933774112e-05,
232
+ "loss": 0.8505,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.06642512077294686,
237
+ "grad_norm": 1.3407087326049805,
238
+ "learning_rate": 6.464146124652441e-05,
239
+ "loss": 0.794,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06843800322061191,
244
+ "grad_norm": 1.4283268451690674,
245
+ "learning_rate": 6.460967010799629e-05,
246
+ "loss": 0.9139,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.07045088566827697,
251
+ "grad_norm": 1.3512784242630005,
252
+ "learning_rate": 6.457653725056568e-05,
253
+ "loss": 0.807,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.07246376811594203,
258
+ "grad_norm": 1.3088512420654297,
259
+ "learning_rate": 6.454206405870587e-05,
260
+ "loss": 0.8968,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07447665056360708,
265
+ "grad_norm": 1.2908034324645996,
266
+ "learning_rate": 6.450625197289675e-05,
267
+ "loss": 0.8447,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07648953301127215,
272
+ "grad_norm": 1.3444992303848267,
273
+ "learning_rate": 6.446910248956453e-05,
274
+ "loss": 0.8891,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0785024154589372,
279
+ "grad_norm": 1.2567275762557983,
280
+ "learning_rate": 6.443061716101926e-05,
281
+ "loss": 0.8134,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.08051529790660225,
286
+ "grad_norm": 1.3401930332183838,
287
+ "learning_rate": 6.439079759539e-05,
288
+ "loss": 0.8751,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08252818035426732,
293
+ "grad_norm": 1.3348793983459473,
294
+ "learning_rate": 6.434964545655754e-05,
295
+ "loss": 0.7942,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08454106280193237,
300
+ "grad_norm": 1.311357021331787,
301
+ "learning_rate": 6.430716246408493e-05,
302
+ "loss": 0.8461,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08655394524959742,
307
+ "grad_norm": 1.3319345712661743,
308
+ "learning_rate": 6.426335039314566e-05,
309
+ "loss": 0.8821,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08856682769726248,
314
+ "grad_norm": 1.304795742034912,
315
+ "learning_rate": 6.421821107444936e-05,
316
+ "loss": 0.8655,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.09057971014492754,
321
+ "grad_norm": 1.422869086265564,
322
+ "learning_rate": 6.417174639416547e-05,
323
+ "loss": 0.9261,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09259259259259259,
328
+ "grad_norm": 1.2931973934173584,
329
+ "learning_rate": 6.412395829384427e-05,
330
+ "loss": 0.8157,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09460547504025765,
335
+ "grad_norm": 1.2984646558761597,
336
+ "learning_rate": 6.407484877033586e-05,
337
+ "loss": 0.7919,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.0966183574879227,
342
+ "grad_norm": 1.2596486806869507,
343
+ "learning_rate": 6.402441987570665e-05,
344
+ "loss": 0.7682,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09863123993558776,
349
+ "grad_norm": 1.3544796705245972,
350
+ "learning_rate": 6.397267371715368e-05,
351
+ "loss": 0.9084,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.10064412238325282,
356
+ "grad_norm": 1.2623202800750732,
357
+ "learning_rate": 6.391961245691652e-05,
358
+ "loss": 0.8482,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.10265700483091787,
363
+ "grad_norm": 1.320026159286499,
364
+ "learning_rate": 6.386523831218689e-05,
365
+ "loss": 0.8436,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.10466988727858294,
370
+ "grad_norm": 1.4064967632293701,
371
+ "learning_rate": 6.38095535550161e-05,
372
+ "loss": 0.8962,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.10668276972624799,
377
+ "grad_norm": 1.3178116083145142,
378
+ "learning_rate": 6.375256051222009e-05,
379
+ "loss": 0.8064,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.10869565217391304,
384
+ "grad_norm": 1.2729371786117554,
385
+ "learning_rate": 6.369426156528213e-05,
386
+ "loss": 0.8338,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.1107085346215781,
391
+ "grad_norm": 1.2167425155639648,
392
+ "learning_rate": 6.363465915025339e-05,
393
+ "loss": 0.8078,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.11272141706924316,
398
+ "grad_norm": 1.3006845712661743,
399
+ "learning_rate": 6.357375575765108e-05,
400
+ "loss": 0.8462,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.11473429951690821,
405
+ "grad_norm": 1.245822787284851,
406
+ "learning_rate": 6.351155393235449e-05,
407
+ "loss": 0.8394,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.11674718196457327,
412
+ "grad_norm": 1.2608625888824463,
413
+ "learning_rate": 6.34480562734985e-05,
414
+ "loss": 0.8606,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.11876006441223833,
419
+ "grad_norm": 1.2614774703979492,
420
+ "learning_rate": 6.33832654343651e-05,
421
+ "loss": 0.7633,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.12077294685990338,
426
+ "grad_norm": 1.3382893800735474,
427
+ "learning_rate": 6.331718412227247e-05,
428
+ "loss": 0.8514,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.12278582930756844,
433
+ "grad_norm": 1.2239303588867188,
434
+ "learning_rate": 6.324981509846189e-05,
435
+ "loss": 0.8319,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.1247987117552335,
440
+ "grad_norm": 1.3828685283660889,
441
+ "learning_rate": 6.318116117798225e-05,
442
+ "loss": 0.8683,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.12681159420289856,
447
+ "grad_norm": 1.304027795791626,
448
+ "learning_rate": 6.311122522957255e-05,
449
+ "loss": 0.887,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.1288244766505636,
454
+ "grad_norm": 1.3097902536392212,
455
+ "learning_rate": 6.304001017554202e-05,
456
+ "loss": 0.8636,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.13083735909822866,
461
+ "grad_norm": 1.281269907951355,
462
+ "learning_rate": 6.296751899164788e-05,
463
+ "loss": 0.7537,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.13285024154589373,
468
+ "grad_norm": 1.2349010705947876,
469
+ "learning_rate": 6.289375470697116e-05,
470
+ "loss": 0.8451,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.13486312399355876,
475
+ "grad_norm": 1.2939257621765137,
476
+ "learning_rate": 6.281872040379001e-05,
477
+ "loss": 0.8249,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.13687600644122383,
482
+ "grad_norm": 1.308341145515442,
483
+ "learning_rate": 6.274241921745097e-05,
484
+ "loss": 0.8764,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.1388888888888889,
489
+ "grad_norm": 1.311805009841919,
490
+ "learning_rate": 6.266485433623794e-05,
491
+ "loss": 0.8308,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.14090177133655393,
496
+ "grad_norm": 1.6127303838729858,
497
+ "learning_rate": 6.258602900123894e-05,
498
+ "loss": 0.8069,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.142914653784219,
503
+ "grad_norm": 1.292090654373169,
504
+ "learning_rate": 6.250594650621067e-05,
505
+ "loss": 0.8174,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.14492753623188406,
510
+ "grad_norm": 1.256778359413147,
511
+ "learning_rate": 6.2424610197441e-05,
512
+ "loss": 0.7956,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.1469404186795491,
517
+ "grad_norm": 1.2579149007797241,
518
+ "learning_rate": 6.23420234736089e-05,
519
+ "loss": 0.8267,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.14895330112721417,
524
+ "grad_norm": 1.3226171731948853,
525
+ "learning_rate": 6.225818978564269e-05,
526
+ "loss": 0.9322,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.15096618357487923,
531
+ "grad_norm": 1.1891167163848877,
532
+ "learning_rate": 6.217311263657565e-05,
533
+ "loss": 0.7886,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.1529790660225443,
538
+ "grad_norm": 1.2481876611709595,
539
+ "learning_rate": 6.208679558139977e-05,
540
+ "loss": 0.7832,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.15499194847020933,
545
+ "grad_norm": 1.2592449188232422,
546
+ "learning_rate": 6.199924222691707e-05,
547
+ "loss": 0.8061,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.1570048309178744,
552
+ "grad_norm": 1.250359058380127,
553
+ "learning_rate": 6.191045623158907e-05,
554
+ "loss": 0.7942,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.15901771336553946,
559
+ "grad_norm": 1.2406524419784546,
560
+ "learning_rate": 6.182044130538373e-05,
561
+ "loss": 0.7766,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.1610305958132045,
566
+ "grad_norm": 1.2620049715042114,
567
+ "learning_rate": 6.172920120962052e-05,
568
+ "loss": 0.8445,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.16304347826086957,
573
+ "grad_norm": 1.2618622779846191,
574
+ "learning_rate": 6.16367397568133e-05,
575
+ "loss": 0.812,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.16505636070853463,
580
+ "grad_norm": 1.2560168504714966,
581
+ "learning_rate": 6.15430608105109e-05,
582
+ "loss": 0.8331,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.16706924315619967,
587
+ "grad_norm": 1.2386751174926758,
588
+ "learning_rate": 6.144816828513576e-05,
589
+ "loss": 0.7318,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.16908212560386474,
594
+ "grad_norm": 1.3558485507965088,
595
+ "learning_rate": 6.135206614582031e-05,
596
+ "loss": 0.8476,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1710950080515298,
601
+ "grad_norm": 1.2461968660354614,
602
+ "learning_rate": 6.125475840824137e-05,
603
+ "loss": 0.8012,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.17310789049919484,
608
+ "grad_norm": 1.2398920059204102,
609
+ "learning_rate": 6.115624913845225e-05,
610
+ "loss": 0.8033,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1751207729468599,
615
+ "grad_norm": 1.3263791799545288,
616
+ "learning_rate": 6.105654245271292e-05,
617
+ "loss": 0.8511,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.17713365539452497,
622
+ "grad_norm": 1.2072999477386475,
623
+ "learning_rate": 6.095564251731795e-05,
624
+ "loss": 0.7478,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.17914653784219,
629
+ "grad_norm": 1.287801742553711,
630
+ "learning_rate": 6.085355354842249e-05,
631
+ "loss": 0.8152,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.18115942028985507,
636
+ "grad_norm": 1.2826151847839355,
637
+ "learning_rate": 6.0750279811866046e-05,
638
+ "loss": 0.7918,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.18317230273752014,
643
+ "grad_norm": 1.276780605316162,
644
+ "learning_rate": 6.0645825622994254e-05,
645
+ "loss": 0.8774,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.18518518518518517,
650
+ "grad_norm": 1.2205020189285278,
651
+ "learning_rate": 6.0540195346478515e-05,
652
+ "loss": 0.8398,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.18719806763285024,
657
+ "grad_norm": 1.2247477769851685,
658
+ "learning_rate": 6.043339339613371e-05,
659
+ "loss": 0.8322,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.1892109500805153,
664
+ "grad_norm": 1.3282443284988403,
665
+ "learning_rate": 6.0325424234733656e-05,
666
+ "loss": 0.8003,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.19122383252818034,
671
+ "grad_norm": 1.3472024202346802,
672
+ "learning_rate": 6.0216292373824696e-05,
673
+ "loss": 0.8305,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.1932367149758454,
678
+ "grad_norm": 1.2812607288360596,
679
+ "learning_rate": 6.010600237353716e-05,
680
+ "loss": 0.7657,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.19524959742351047,
685
+ "grad_norm": 1.2958053350448608,
686
+ "learning_rate": 5.999455884239483e-05,
687
+ "loss": 0.869,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.1972624798711755,
692
+ "grad_norm": 1.2021034955978394,
693
+ "learning_rate": 5.988196643712235e-05,
694
+ "loss": 0.7798,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.19927536231884058,
699
+ "grad_norm": 1.2430065870285034,
700
+ "learning_rate": 5.976822986245067e-05,
701
+ "loss": 0.7496,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.20128824476650564,
706
+ "grad_norm": 1.2749730348587036,
707
+ "learning_rate": 5.9653353870920434e-05,
708
+ "loss": 0.831,
709
+ "step": 100
710
+ }
711
+ ],
712
+ "logging_steps": 1,
713
+ "max_steps": 496,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 1,
716
+ "save_steps": 50,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": false
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 1.189794361882706e+17,
730
+ "train_batch_size": 6,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d099daa3926570d9e2501eaac78896812191b5c803506c6b4dc9b531482a17b
3
+ size 5112
checkpoint-50/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: rinna/llama-3-youko-8b
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 0.11.1
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rinna/llama-3-youko-8b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "embed_tokens",
19
+ "lm_head"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": "unsloth",
25
+ "target_modules": [
26
+ "o_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "q_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": true
37
+ }
checkpoint-50/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60cdf01103d0d16c917672595466985b1595d46a048d7285282fc6db18f7a654
3
+ size 11849545016
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac1126e459c9c1a3155ebf3054c1cff1aa2f0f61312b9fa19080cfec65d7a13
3
+ size 2778493596
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af34d41a387513fe16d2f526704002f5f5013be898bf20077d67118a76362740
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a604eccd63938d2fa022c2aa991d7744dde2c7bb6dc324fa4f0fac6a7be08e
3
+ size 1064
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.10064412238325282,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002012882447665056,
13
+ "grad_norm": 22.921390533447266,
14
+ "learning_rate": 6.5e-06,
15
+ "loss": 1.3427,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004025764895330112,
20
+ "grad_norm": 14.772722244262695,
21
+ "learning_rate": 1.3e-05,
22
+ "loss": 1.3647,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.006038647342995169,
27
+ "grad_norm": 11.458742141723633,
28
+ "learning_rate": 1.9499999999999996e-05,
29
+ "loss": 1.2841,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.008051529790660225,
34
+ "grad_norm": 4.747677326202393,
35
+ "learning_rate": 2.6e-05,
36
+ "loss": 1.1644,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.010064412238325281,
41
+ "grad_norm": 3.687121629714966,
42
+ "learning_rate": 3.25e-05,
43
+ "loss": 1.1084,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.012077294685990338,
48
+ "grad_norm": 3.178232431411743,
49
+ "learning_rate": 3.899999999999999e-05,
50
+ "loss": 1.0753,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.014090177133655395,
55
+ "grad_norm": 2.476033926010132,
56
+ "learning_rate": 4.5499999999999995e-05,
57
+ "loss": 1.075,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01610305958132045,
62
+ "grad_norm": 1.9162139892578125,
63
+ "learning_rate": 5.2e-05,
64
+ "loss": 1.0195,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.018115942028985508,
69
+ "grad_norm": 1.797377109527588,
70
+ "learning_rate": 5.85e-05,
71
+ "loss": 0.9884,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.020128824476650563,
76
+ "grad_norm": 1.816100835800171,
77
+ "learning_rate": 6.5e-05,
78
+ "loss": 0.9945,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.02214170692431562,
83
+ "grad_norm": 1.843664526939392,
84
+ "learning_rate": 6.499932098548219e-05,
85
+ "loss": 0.8802,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.024154589371980676,
90
+ "grad_norm": 1.7202250957489014,
91
+ "learning_rate": 6.49972839703017e-05,
92
+ "loss": 0.9833,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.026167471819645734,
97
+ "grad_norm": 1.4981484413146973,
98
+ "learning_rate": 6.499388903957628e-05,
99
+ "loss": 0.9481,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.02818035426731079,
104
+ "grad_norm": 1.4716213941574097,
105
+ "learning_rate": 6.498913633516483e-05,
106
+ "loss": 0.8809,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.030193236714975844,
111
+ "grad_norm": 1.3817026615142822,
112
+ "learning_rate": 6.498302605566152e-05,
113
+ "loss": 0.9264,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.0322061191626409,
118
+ "grad_norm": 1.509097695350647,
119
+ "learning_rate": 6.497555845638748e-05,
120
+ "loss": 0.8829,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.03421900161030596,
125
+ "grad_norm": 1.5498337745666504,
126
+ "learning_rate": 6.496673384938014e-05,
127
+ "loss": 0.9227,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.036231884057971016,
132
+ "grad_norm": 1.527828574180603,
133
+ "learning_rate": 6.49565526033802e-05,
134
+ "loss": 0.9488,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.038244766505636074,
139
+ "grad_norm": 1.4578592777252197,
140
+ "learning_rate": 6.494501514381621e-05,
141
+ "loss": 0.8845,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.040257648953301126,
146
+ "grad_norm": 1.4198046922683716,
147
+ "learning_rate": 6.493212195278678e-05,
148
+ "loss": 0.8809,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.042270531400966184,
153
+ "grad_norm": 1.4455400705337524,
154
+ "learning_rate": 6.491787356904047e-05,
155
+ "loss": 0.8686,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04428341384863124,
160
+ "grad_norm": 1.5711616277694702,
161
+ "learning_rate": 6.490227058795323e-05,
162
+ "loss": 0.96,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.046296296296296294,
167
+ "grad_norm": 1.4603729248046875,
168
+ "learning_rate": 6.488531366150359e-05,
169
+ "loss": 0.9026,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04830917874396135,
174
+ "grad_norm": 1.4184608459472656,
175
+ "learning_rate": 6.48670034982453e-05,
176
+ "loss": 0.9426,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.05032206119162641,
181
+ "grad_norm": 1.4080291986465454,
182
+ "learning_rate": 6.484734086327788e-05,
183
+ "loss": 0.8857,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05233494363929147,
188
+ "grad_norm": 1.4739091396331787,
189
+ "learning_rate": 6.482632657821454e-05,
190
+ "loss": 0.8897,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05434782608695652,
195
+ "grad_norm": 1.320746898651123,
196
+ "learning_rate": 6.480396152114787e-05,
197
+ "loss": 0.8512,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05636070853462158,
202
+ "grad_norm": 1.4142905473709106,
203
+ "learning_rate": 6.478024662661315e-05,
204
+ "loss": 0.9459,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05837359098228664,
209
+ "grad_norm": 1.3830432891845703,
210
+ "learning_rate": 6.47551828855493e-05,
211
+ "loss": 0.8605,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.06038647342995169,
216
+ "grad_norm": 1.3653528690338135,
217
+ "learning_rate": 6.472877134525753e-05,
218
+ "loss": 0.8446,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06239935587761675,
223
+ "grad_norm": 1.3041807413101196,
224
+ "learning_rate": 6.470101310935746e-05,
225
+ "loss": 0.8407,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.0644122383252818,
230
+ "grad_norm": 1.3803820610046387,
231
+ "learning_rate": 6.467190933774112e-05,
232
+ "loss": 0.8505,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.06642512077294686,
237
+ "grad_norm": 1.3407087326049805,
238
+ "learning_rate": 6.464146124652441e-05,
239
+ "loss": 0.794,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06843800322061191,
244
+ "grad_norm": 1.4283268451690674,
245
+ "learning_rate": 6.460967010799629e-05,
246
+ "loss": 0.9139,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.07045088566827697,
251
+ "grad_norm": 1.3512784242630005,
252
+ "learning_rate": 6.457653725056568e-05,
253
+ "loss": 0.807,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.07246376811594203,
258
+ "grad_norm": 1.3088512420654297,
259
+ "learning_rate": 6.454206405870587e-05,
260
+ "loss": 0.8968,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07447665056360708,
265
+ "grad_norm": 1.2908034324645996,
266
+ "learning_rate": 6.450625197289675e-05,
267
+ "loss": 0.8447,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07648953301127215,
272
+ "grad_norm": 1.3444992303848267,
273
+ "learning_rate": 6.446910248956453e-05,
274
+ "loss": 0.8891,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0785024154589372,
279
+ "grad_norm": 1.2567275762557983,
280
+ "learning_rate": 6.443061716101926e-05,
281
+ "loss": 0.8134,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.08051529790660225,
286
+ "grad_norm": 1.3401930332183838,
287
+ "learning_rate": 6.439079759539e-05,
288
+ "loss": 0.8751,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08252818035426732,
293
+ "grad_norm": 1.3348793983459473,
294
+ "learning_rate": 6.434964545655754e-05,
295
+ "loss": 0.7942,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08454106280193237,
300
+ "grad_norm": 1.311357021331787,
301
+ "learning_rate": 6.430716246408493e-05,
302
+ "loss": 0.8461,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08655394524959742,
307
+ "grad_norm": 1.3319345712661743,
308
+ "learning_rate": 6.426335039314566e-05,
309
+ "loss": 0.8821,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08856682769726248,
314
+ "grad_norm": 1.304795742034912,
315
+ "learning_rate": 6.421821107444936e-05,
316
+ "loss": 0.8655,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.09057971014492754,
321
+ "grad_norm": 1.422869086265564,
322
+ "learning_rate": 6.417174639416547e-05,
323
+ "loss": 0.9261,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09259259259259259,
328
+ "grad_norm": 1.2931973934173584,
329
+ "learning_rate": 6.412395829384427e-05,
330
+ "loss": 0.8157,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09460547504025765,
335
+ "grad_norm": 1.2984646558761597,
336
+ "learning_rate": 6.407484877033586e-05,
337
+ "loss": 0.7919,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.0966183574879227,
342
+ "grad_norm": 1.2596486806869507,
343
+ "learning_rate": 6.402441987570665e-05,
344
+ "loss": 0.7682,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09863123993558776,
349
+ "grad_norm": 1.3544796705245972,
350
+ "learning_rate": 6.397267371715368e-05,
351
+ "loss": 0.9084,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.10064412238325282,
356
+ "grad_norm": 1.2623202800750732,
357
+ "learning_rate": 6.391961245691652e-05,
358
+ "loss": 0.8482,
359
+ "step": 50
360
+ }
361
+ ],
362
+ "logging_steps": 1,
363
+ "max_steps": 496,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 1,
366
+ "save_steps": 50,
367
+ "stateful_callbacks": {
368
+ "TrainerControl": {
369
+ "args": {
370
+ "should_epoch_stop": false,
371
+ "should_evaluate": false,
372
+ "should_log": false,
373
+ "should_save": true,
374
+ "should_training_stop": false
375
+ },
376
+ "attributes": {}
377
+ }
378
+ },
379
+ "total_flos": 5.877172627557581e+16,
380
+ "train_batch_size": 6,
381
+ "trial_name": null,
382
+ "trial_params": null
383
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d099daa3926570d9e2501eaac78896812191b5c803506c6b4dc9b531482a17b
3
+ size 5112