Weyaxi commited on
Commit
75bcb9b
1 Parent(s): 9725414

Upload folder using huggingface_hub

Browse files
checkpoint-140/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-v0.1
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
+
201
+
202
+ ## Training procedure
203
+
204
+
205
+ The following `bitsandbytes` quantization config was used during training:
206
+ - quant_method: bitsandbytes
207
+ - load_in_8bit: False
208
+ - load_in_4bit: True
209
+ - llm_int8_threshold: 6.0
210
+ - llm_int8_skip_modules: None
211
+ - llm_int8_enable_fp32_cpu_offload: False
212
+ - llm_int8_has_fp16_weight: False
213
+ - bnb_4bit_quant_type: nf4
214
+ - bnb_4bit_use_double_quant: True
215
+ - bnb_4bit_compute_dtype: float16
216
+
217
+ ### Framework versions
218
+
219
+
220
+ - PEFT 0.6.3.dev0
checkpoint-140/adapter_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "up_proj",
20
+ "gate_proj",
21
+ "down_proj"
22
+ ],
23
+ "task_type": "CAUSAL_LM"
24
+ }
checkpoint-140/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085a9dfa1c86851bf457206ec9843cfe817938ebcc3396cd0b5e1bc4cb3e2487
3
+ size 226517904
checkpoint-140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e4bd152f043ce44b9328e4a5cb841f30b48a5547b3691e1a5387484335fc8e
3
+ size 453146810
checkpoint-140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639eab3df5d0c2b0bf83ce7ea5da1e1c8272bd19f751902fb967d34c8594fee1
3
+ size 14244
checkpoint-140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dba903a5561c312a931c4efb15ea6342dffc4e61ffd7628e3968f3d73ef536c
3
+ size 1064
checkpoint-140/trainer_state.json ADDED
@@ -0,0 +1,860 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.3164426059979317,
5
+ "eval_steps": 500,
6
+ "global_step": 140,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.000000000000001e-06,
14
+ "loss": 0.643,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 8.000000000000001e-06,
20
+ "loss": 0.6409,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "learning_rate": 1.2e-05,
26
+ "loss": 0.5779,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.07,
31
+ "learning_rate": 1.6000000000000003e-05,
32
+ "loss": 0.6641,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.08,
37
+ "learning_rate": 2e-05,
38
+ "loss": 0.61,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "learning_rate": 2.4e-05,
44
+ "loss": 0.6653,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "learning_rate": 2.8000000000000003e-05,
50
+ "loss": 0.6101,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.13,
55
+ "learning_rate": 3.2000000000000005e-05,
56
+ "loss": 0.7479,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.15,
61
+ "learning_rate": 3.6e-05,
62
+ "loss": 0.6357,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.17,
67
+ "learning_rate": 4e-05,
68
+ "loss": 0.6214,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.18,
73
+ "learning_rate": 4.4000000000000006e-05,
74
+ "loss": 0.6257,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.2,
79
+ "learning_rate": 4.8e-05,
80
+ "loss": 0.6228,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.22,
85
+ "learning_rate": 5.2000000000000004e-05,
86
+ "loss": 0.6295,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.23,
91
+ "learning_rate": 5.6000000000000006e-05,
92
+ "loss": 0.6345,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.25,
97
+ "learning_rate": 6e-05,
98
+ "loss": 0.6282,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.26,
103
+ "learning_rate": 6.400000000000001e-05,
104
+ "loss": 0.6231,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.28,
109
+ "learning_rate": 6.800000000000001e-05,
110
+ "loss": 0.6282,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.3,
115
+ "learning_rate": 7.2e-05,
116
+ "loss": 0.6423,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.31,
121
+ "learning_rate": 7.6e-05,
122
+ "loss": 0.6055,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.33,
127
+ "learning_rate": 8e-05,
128
+ "loss": 0.6244,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.35,
133
+ "learning_rate": 8.4e-05,
134
+ "loss": 0.5443,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.36,
139
+ "learning_rate": 8.800000000000001e-05,
140
+ "loss": 0.6479,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.38,
145
+ "learning_rate": 9.200000000000001e-05,
146
+ "loss": 0.5565,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.4,
151
+ "learning_rate": 9.6e-05,
152
+ "loss": 0.6131,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.41,
157
+ "learning_rate": 0.0001,
158
+ "loss": 0.6696,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.43,
163
+ "learning_rate": 0.00010400000000000001,
164
+ "loss": 0.5886,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.45,
169
+ "learning_rate": 0.00010800000000000001,
170
+ "loss": 0.5999,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.46,
175
+ "learning_rate": 0.00011200000000000001,
176
+ "loss": 0.7083,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.48,
181
+ "learning_rate": 0.000116,
182
+ "loss": 0.6178,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.5,
187
+ "learning_rate": 0.00012,
188
+ "loss": 0.6466,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.51,
193
+ "learning_rate": 0.000124,
194
+ "loss": 0.5462,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.53,
199
+ "learning_rate": 0.00012800000000000002,
200
+ "loss": 0.6239,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.55,
205
+ "learning_rate": 0.000132,
206
+ "loss": 0.6646,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.56,
211
+ "learning_rate": 0.00013600000000000003,
212
+ "loss": 0.6293,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.58,
217
+ "learning_rate": 0.00014,
218
+ "loss": 0.5853,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.6,
223
+ "learning_rate": 0.000144,
224
+ "loss": 0.6881,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.61,
229
+ "learning_rate": 0.000148,
230
+ "loss": 0.6398,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.63,
235
+ "learning_rate": 0.000152,
236
+ "loss": 0.6054,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.65,
241
+ "learning_rate": 0.00015600000000000002,
242
+ "loss": 0.6332,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.66,
247
+ "learning_rate": 0.00016,
248
+ "loss": 0.5941,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.68,
253
+ "learning_rate": 0.000164,
254
+ "loss": 0.6127,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.69,
259
+ "learning_rate": 0.000168,
260
+ "loss": 0.6475,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.71,
265
+ "learning_rate": 0.000172,
266
+ "loss": 0.5668,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.73,
271
+ "learning_rate": 0.00017600000000000002,
272
+ "loss": 0.6348,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.74,
277
+ "learning_rate": 0.00018,
278
+ "loss": 0.6379,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.76,
283
+ "learning_rate": 0.00018400000000000003,
284
+ "loss": 0.5992,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.78,
289
+ "learning_rate": 0.000188,
290
+ "loss": 0.6435,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.79,
295
+ "learning_rate": 0.000192,
296
+ "loss": 0.5909,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.81,
301
+ "learning_rate": 0.000196,
302
+ "loss": 0.6596,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.83,
307
+ "learning_rate": 0.0002,
308
+ "loss": 0.6426,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.84,
313
+ "learning_rate": 0.00020400000000000003,
314
+ "loss": 0.5908,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.86,
319
+ "learning_rate": 0.00020800000000000001,
320
+ "loss": 0.5486,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.88,
325
+ "learning_rate": 0.00021200000000000003,
326
+ "loss": 0.6184,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.89,
331
+ "learning_rate": 0.00021600000000000002,
332
+ "loss": 0.6977,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.91,
337
+ "learning_rate": 0.00022000000000000003,
338
+ "loss": 0.6308,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.93,
343
+ "learning_rate": 0.00022400000000000002,
344
+ "loss": 0.5394,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.94,
349
+ "learning_rate": 0.00022799999999999999,
350
+ "loss": 0.5426,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.96,
355
+ "learning_rate": 0.000232,
356
+ "loss": 0.5429,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.98,
361
+ "learning_rate": 0.000236,
362
+ "loss": 0.5822,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.99,
367
+ "learning_rate": 0.00024,
368
+ "loss": 0.5793,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 1.01,
373
+ "learning_rate": 0.000244,
374
+ "loss": 0.5906,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 1.03,
379
+ "learning_rate": 0.000248,
380
+ "loss": 0.4957,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 1.04,
385
+ "learning_rate": 0.000252,
386
+ "loss": 0.5421,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 1.06,
391
+ "learning_rate": 0.00025600000000000004,
392
+ "loss": 0.5444,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 1.08,
397
+ "learning_rate": 0.00026000000000000003,
398
+ "loss": 0.5618,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 1.09,
403
+ "learning_rate": 0.000264,
404
+ "loss": 0.5372,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 1.11,
409
+ "learning_rate": 0.000268,
410
+ "loss": 0.5701,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 1.13,
415
+ "learning_rate": 0.00027200000000000005,
416
+ "loss": 0.5257,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 1.14,
421
+ "learning_rate": 0.000276,
422
+ "loss": 0.5237,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 1.16,
427
+ "learning_rate": 0.00028,
428
+ "loss": 0.4729,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 1.17,
433
+ "learning_rate": 0.000284,
434
+ "loss": 0.5142,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 1.19,
439
+ "learning_rate": 0.000288,
440
+ "loss": 0.5365,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 1.21,
445
+ "learning_rate": 0.000292,
446
+ "loss": 0.5288,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 1.22,
451
+ "learning_rate": 0.000296,
452
+ "loss": 0.5095,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 1.24,
457
+ "learning_rate": 0.00030000000000000003,
458
+ "loss": 0.5229,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 1.26,
463
+ "learning_rate": 0.000304,
464
+ "loss": 0.5355,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 1.27,
469
+ "learning_rate": 0.000308,
470
+ "loss": 0.5626,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 1.29,
475
+ "learning_rate": 0.00031200000000000005,
476
+ "loss": 0.5548,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 1.31,
481
+ "learning_rate": 0.00031600000000000004,
482
+ "loss": 0.5404,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 1.32,
487
+ "learning_rate": 0.00032,
488
+ "loss": 0.5686,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 1.34,
493
+ "learning_rate": 0.000324,
494
+ "loss": 0.5242,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 1.36,
499
+ "learning_rate": 0.000328,
500
+ "loss": 0.52,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 1.37,
505
+ "learning_rate": 0.000332,
506
+ "loss": 0.5481,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 1.39,
511
+ "learning_rate": 0.000336,
512
+ "loss": 0.5321,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 1.41,
517
+ "learning_rate": 0.00034,
518
+ "loss": 0.603,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 1.42,
523
+ "learning_rate": 0.000344,
524
+ "loss": 0.4836,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 1.44,
529
+ "learning_rate": 0.000348,
530
+ "loss": 0.5583,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 1.46,
535
+ "learning_rate": 0.00035200000000000005,
536
+ "loss": 0.5336,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 1.47,
541
+ "learning_rate": 0.00035600000000000003,
542
+ "loss": 0.4061,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 1.49,
547
+ "learning_rate": 0.00036,
548
+ "loss": 0.5555,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 1.51,
553
+ "learning_rate": 0.000364,
554
+ "loss": 0.5216,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 1.52,
559
+ "learning_rate": 0.00036800000000000005,
560
+ "loss": 0.4991,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 1.54,
565
+ "learning_rate": 0.00037200000000000004,
566
+ "loss": 0.5601,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 1.56,
571
+ "learning_rate": 0.000376,
572
+ "loss": 0.4857,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 1.57,
577
+ "learning_rate": 0.00038,
578
+ "loss": 0.5439,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.59,
583
+ "learning_rate": 0.000384,
584
+ "loss": 0.5817,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 1.6,
589
+ "learning_rate": 0.000388,
590
+ "loss": 0.5179,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 1.62,
595
+ "learning_rate": 0.000392,
596
+ "loss": 0.5464,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.64,
601
+ "learning_rate": 0.00039600000000000003,
602
+ "loss": 0.513,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.65,
607
+ "learning_rate": 0.0004,
608
+ "loss": 0.4899,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.67,
613
+ "learning_rate": 0.0003998458072481446,
614
+ "loss": 0.5715,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.69,
619
+ "learning_rate": 0.0003993834667466256,
620
+ "loss": 0.5312,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.7,
625
+ "learning_rate": 0.0003986136913909853,
626
+ "loss": 0.5066,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.72,
631
+ "learning_rate": 0.00039753766811902755,
632
+ "loss": 0.5407,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.74,
637
+ "learning_rate": 0.0003961570560806461,
638
+ "loss": 0.5281,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.75,
643
+ "learning_rate": 0.0003944739840795353,
644
+ "loss": 0.4873,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.77,
649
+ "learning_rate": 0.00039249104729072946,
650
+ "loss": 0.5336,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.79,
655
+ "learning_rate": 0.00039021130325903074,
656
+ "loss": 0.4842,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.8,
661
+ "learning_rate": 0.00038763826718449685,
662
+ "loss": 0.5136,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.82,
667
+ "learning_rate": 0.0003847759065022574,
668
+ "loss": 0.5359,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.84,
673
+ "learning_rate": 0.0003816286347650163,
674
+ "loss": 0.4766,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.85,
679
+ "learning_rate": 0.0003782013048376736,
680
+ "loss": 0.4896,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.87,
685
+ "learning_rate": 0.00037449920141455944,
686
+ "loss": 0.4977,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.89,
691
+ "learning_rate": 0.00037052803287081844,
692
+ "loss": 0.506,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.9,
697
+ "learning_rate": 0.0003662939224605091,
698
+ "loss": 0.5442,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.92,
703
+ "learning_rate": 0.0003618033988749895,
704
+ "loss": 0.5445,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.94,
709
+ "learning_rate": 0.00035706338617614897,
710
+ "loss": 0.5348,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.95,
715
+ "learning_rate": 0.0003520811931200062,
716
+ "loss": 0.5331,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.97,
721
+ "learning_rate": 0.0003468645018871371,
722
+ "loss": 0.4697,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.99,
727
+ "learning_rate": 0.0003414213562373095,
728
+ "loss": 0.5119,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 2.0,
733
+ "learning_rate": 0.0003357601491065884,
734
+ "loss": 0.4679,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 2.02,
739
+ "learning_rate": 0.0003298896096660367,
740
+ "loss": 0.3522,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 2.04,
745
+ "learning_rate": 0.00032381878986196687,
746
+ "loss": 0.3267,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 2.05,
751
+ "learning_rate": 0.00031755705045849464,
752
+ "loss": 0.3626,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 2.07,
757
+ "learning_rate": 0.00031111404660392046,
758
+ "loss": 0.3274,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 2.08,
763
+ "learning_rate": 0.0003044997129431898,
764
+ "loss": 0.3159,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 2.1,
769
+ "learning_rate": 0.00029772424829939106,
770
+ "loss": 0.3336,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 2.12,
775
+ "learning_rate": 0.00029079809994790937,
776
+ "loss": 0.2973,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 2.13,
781
+ "learning_rate": 0.0002837319475074856,
782
+ "loss": 0.319,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 2.15,
787
+ "learning_rate": 0.000276536686473018,
788
+ "loss": 0.2978,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 2.17,
793
+ "learning_rate": 0.0002692234114154986,
794
+ "loss": 0.3393,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 2.18,
799
+ "learning_rate": 0.00026180339887498953,
800
+ "loss": 0.3318,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 2.2,
805
+ "learning_rate": 0.00025428808997301485,
806
+ "loss": 0.299,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 2.22,
811
+ "learning_rate": 0.00024668907277118114,
812
+ "loss": 0.27,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 2.23,
817
+ "learning_rate": 0.0002390180644032257,
818
+ "loss": 0.2739,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 2.25,
823
+ "learning_rate": 0.0002312868930080462,
824
+ "loss": 0.3041,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 2.27,
829
+ "learning_rate": 0.00022350747949156756,
830
+ "loss": 0.2892,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 2.28,
835
+ "learning_rate": 0.000215691819145569,
836
+ "loss": 0.2659,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 2.3,
841
+ "learning_rate": 0.00020785196315181376,
842
+ "loss": 0.3424,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 2.32,
847
+ "learning_rate": 0.0002,
848
+ "loss": 0.318,
849
+ "step": 140
850
+ }
851
+ ],
852
+ "logging_steps": 1,
853
+ "max_steps": 180,
854
+ "num_input_tokens_seen": 0,
855
+ "num_train_epochs": 3,
856
+ "save_steps": 10,
857
+ "total_flos": 4.852324119379968e+17,
858
+ "trial_name": null,
859
+ "trial_params": null
860
+ }
checkpoint-140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f924836ef21707286fc6978ae0980c72a4e9c41410a8b98d6d3ba75f7357b705
3
+ size 4664
runs/Nov24_16-17-54_924075f44444/events.out.tfevents.1700842675.924075f44444.7554.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8d6237fe967dde5e3c01377356c8f74898806e7db2eaaae6b2f47134c3afa36
3
- size 24750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837df6c913ca114d473af2f6cedd5c7594e1dbe4dd41f1c791880791413ea2dc
3
+ size 26320