projecti7 commited on
Commit
4e3bb3c
·
verified ·
1 Parent(s): e9a49af

Upload folder using huggingface_hub

Browse files
checkpoint-4800/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.18.0
checkpoint-4800/adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Wav2Vec2ForCTC",
7
+ "parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
8
+ },
9
+ "base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 32,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.05,
25
+ "megatron_config": null,
26
+ "megatron_core": "megatron.core",
27
+ "modules_to_save": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.18.0",
30
+ "qalora_group_size": 16,
31
+ "r": 16,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "fc2",
36
+ "q_proj",
37
+ "fc1",
38
+ "k_proj",
39
+ "out_proj",
40
+ "v_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": null,
44
+ "trainable_token_indices": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
checkpoint-4800/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
3
+ size 12610664
checkpoint-4800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b6ec12866348d3bf718c52dd3cf239a75990f52ab7aa86d1aa9e4805ec6b53
3
+ size 25327034
checkpoint-4800/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-4800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3525b75218401e73865cc0270e8bd606b853f31756a6d9e8b511c58565e06000
3
+ size 14308
checkpoint-4800/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b2448f0914773f32921479c4246fc3dea33103c48c01f24891857705a0882d
3
+ size 988
checkpoint-4800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52d9fa1cfb486c7935854e059b6f28c5f346e2723a9a65bddf87ba2351f0607
3
+ size 1064
checkpoint-4800/trainer_state.json ADDED
@@ -0,0 +1,706 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.96,
6
+ "eval_steps": 500,
7
+ "global_step": 4800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01,
14
+ "grad_norm": 2.4969277381896973,
15
+ "learning_rate": 1.76e-05,
16
+ "loss": 19.5898,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02,
21
+ "grad_norm": 8.099705696105957,
22
+ "learning_rate": 3.76e-05,
23
+ "loss": 17.8223,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 11.919422149658203,
29
+ "learning_rate": 5.72e-05,
30
+ "loss": 10.8995,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "grad_norm": 6.321387767791748,
36
+ "learning_rate": 7.64e-05,
37
+ "loss": 3.1441,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "grad_norm": 1.5579607486724854,
43
+ "learning_rate": 9.64e-05,
44
+ "loss": 1.0788,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "grad_norm": 2.1052896976470947,
50
+ "learning_rate": 0.0001164,
51
+ "loss": 0.3291,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.07,
56
+ "grad_norm": 1.402535319328308,
57
+ "learning_rate": 0.0001364,
58
+ "loss": 0.3073,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.08,
63
+ "grad_norm": 1.533136248588562,
64
+ "learning_rate": 0.00015600000000000002,
65
+ "loss": 0.4065,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.09,
70
+ "grad_norm": 2.3747737407684326,
71
+ "learning_rate": 0.00017600000000000002,
72
+ "loss": 0.294,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.1,
77
+ "grad_norm": 6.622051239013672,
78
+ "learning_rate": 0.000196,
79
+ "loss": 0.2311,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "grad_norm": 1.6454269886016846,
85
+ "learning_rate": 0.00019822222222222225,
86
+ "loss": 0.3515,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "grad_norm": 10.714489936828613,
92
+ "learning_rate": 0.000196,
93
+ "loss": 0.1957,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.13,
98
+ "grad_norm": 1.3993964195251465,
99
+ "learning_rate": 0.0001937777777777778,
100
+ "loss": 0.2028,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.14,
105
+ "grad_norm": 0.7649514675140381,
106
+ "learning_rate": 0.0001916,
107
+ "loss": 0.2995,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.15,
112
+ "grad_norm": 0.5896079540252686,
113
+ "learning_rate": 0.0001893777777777778,
114
+ "loss": 0.1876,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.16,
119
+ "grad_norm": 0.6604533791542053,
120
+ "learning_rate": 0.00018715555555555557,
121
+ "loss": 0.19,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "grad_norm": 2.047614097595215,
127
+ "learning_rate": 0.00018493333333333335,
128
+ "loss": 0.0988,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.18,
133
+ "grad_norm": 1.374024748802185,
134
+ "learning_rate": 0.00018271111111111112,
135
+ "loss": 0.1355,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.19,
140
+ "grad_norm": 1.4950742721557617,
141
+ "learning_rate": 0.0001804888888888889,
142
+ "loss": 0.1303,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2,
147
+ "grad_norm": 2.006479024887085,
148
+ "learning_rate": 0.00017826666666666667,
149
+ "loss": 0.1999,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.21,
154
+ "grad_norm": 1.1253306865692139,
155
+ "learning_rate": 0.00017604444444444445,
156
+ "loss": 0.152,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.22,
161
+ "grad_norm": 0.8224861025810242,
162
+ "learning_rate": 0.00017382222222222222,
163
+ "loss": 0.1444,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "grad_norm": 0.523875892162323,
169
+ "learning_rate": 0.0001716,
170
+ "loss": 0.155,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.24,
175
+ "grad_norm": 1.7560786008834839,
176
+ "learning_rate": 0.0001693777777777778,
177
+ "loss": 0.1934,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.25,
182
+ "grad_norm": 0.6891859173774719,
183
+ "learning_rate": 0.00016715555555555555,
184
+ "loss": 0.1062,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.26,
189
+ "grad_norm": 3.0257561206817627,
190
+ "learning_rate": 0.00016493333333333335,
191
+ "loss": 0.1132,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.27,
196
+ "grad_norm": 0.0,
197
+ "learning_rate": 0.00016351111111111112,
198
+ "loss": 0.3971,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.28,
203
+ "grad_norm": 0.0,
204
+ "learning_rate": 0.0001612888888888889,
205
+ "loss": 0.2656,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "grad_norm": 0.0,
211
+ "learning_rate": 0.00015924444444444447,
212
+ "loss": 0.4477,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.3,
217
+ "grad_norm": 0.0,
218
+ "learning_rate": 0.00015706666666666667,
219
+ "loss": 0.3441,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.31,
224
+ "grad_norm": 0.0,
225
+ "learning_rate": 0.00015484444444444445,
226
+ "loss": 0.1985,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.32,
231
+ "grad_norm": 0.0,
232
+ "learning_rate": 0.00015262222222222222,
233
+ "loss": 0.2074,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.33,
238
+ "grad_norm": 0.0,
239
+ "learning_rate": 0.00015066666666666668,
240
+ "loss": 0.481,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.34,
245
+ "grad_norm": 0.0,
246
+ "learning_rate": 0.00014857777777777778,
247
+ "loss": 0.2268,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "grad_norm": 0.0,
253
+ "learning_rate": 0.00014635555555555556,
254
+ "loss": 0.1873,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.36,
259
+ "grad_norm": 0.0,
260
+ "learning_rate": 0.00014413333333333333,
261
+ "loss": 0.2051,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.37,
266
+ "grad_norm": 0.0,
267
+ "learning_rate": 0.00014191111111111113,
268
+ "loss": 0.2184,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.38,
273
+ "grad_norm": 0.0,
274
+ "learning_rate": 0.00013968888888888888,
275
+ "loss": 0.112,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.39,
280
+ "grad_norm": 0.0,
281
+ "learning_rate": 0.00013751111111111113,
282
+ "loss": 0.2867,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4,
287
+ "grad_norm": 0.0,
288
+ "learning_rate": 0.00013528888888888888,
289
+ "loss": 0.1132,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "grad_norm": 0.0,
295
+ "learning_rate": 0.00013306666666666668,
296
+ "loss": 0.2804,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.42,
301
+ "grad_norm": 0.0,
302
+ "learning_rate": 0.00013084444444444446,
303
+ "loss": 0.1317,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.43,
308
+ "grad_norm": 0.0,
309
+ "learning_rate": 0.00012862222222222223,
310
+ "loss": 0.1032,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.44,
315
+ "grad_norm": 0.0,
316
+ "learning_rate": 0.0001264,
317
+ "loss": 0.1184,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.45,
322
+ "grad_norm": 0.0,
323
+ "learning_rate": 0.00012417777777777778,
324
+ "loss": 0.1207,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.46,
329
+ "grad_norm": 0.0,
330
+ "learning_rate": 0.00012195555555555556,
331
+ "loss": 0.1269,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.47,
336
+ "grad_norm": 0.0,
337
+ "learning_rate": 0.00011973333333333335,
338
+ "loss": 0.1391,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.48,
343
+ "grad_norm": 0.0,
344
+ "learning_rate": 0.00011773333333333334,
345
+ "loss": 0.2337,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.49,
350
+ "grad_norm": 0.0,
351
+ "learning_rate": 0.00011586666666666667,
352
+ "loss": 0.3983,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5,
357
+ "grad_norm": 0.0,
358
+ "learning_rate": 0.00011373333333333334,
359
+ "loss": 0.1904,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.51,
364
+ "grad_norm": 0.0,
365
+ "learning_rate": 0.00011160000000000002,
366
+ "loss": 0.2106,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.52,
371
+ "grad_norm": 0.0,
372
+ "learning_rate": 0.00010942222222222223,
373
+ "loss": 0.1193,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.53,
378
+ "grad_norm": 0.0,
379
+ "learning_rate": 0.00010720000000000002,
380
+ "loss": 0.1406,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.54,
385
+ "grad_norm": 0.0,
386
+ "learning_rate": 0.00010497777777777778,
387
+ "loss": 0.1312,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.55,
392
+ "grad_norm": 0.0,
393
+ "learning_rate": 0.00010275555555555557,
394
+ "loss": 0.1193,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.56,
399
+ "grad_norm": 0.0,
400
+ "learning_rate": 0.00010053333333333334,
401
+ "loss": 0.1838,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.57,
406
+ "grad_norm": 0.0,
407
+ "learning_rate": 9.831111111111112e-05,
408
+ "loss": 0.1306,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.58,
413
+ "grad_norm": 0.0,
414
+ "learning_rate": 9.608888888888889e-05,
415
+ "loss": 0.1127,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.59,
420
+ "grad_norm": 0.0,
421
+ "learning_rate": 9.386666666666667e-05,
422
+ "loss": 0.1963,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.6,
427
+ "grad_norm": 0.0,
428
+ "learning_rate": 9.164444444444444e-05,
429
+ "loss": 0.1813,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.61,
434
+ "grad_norm": 0.0,
435
+ "learning_rate": 8.942222222222223e-05,
436
+ "loss": 0.2901,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.62,
441
+ "grad_norm": 0.0,
442
+ "learning_rate": 8.72e-05,
443
+ "loss": 0.0905,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.63,
448
+ "grad_norm": 0.0,
449
+ "learning_rate": 8.497777777777778e-05,
450
+ "loss": 0.1058,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.64,
455
+ "grad_norm": 0.0,
456
+ "learning_rate": 8.275555555555557e-05,
457
+ "loss": 0.0965,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.65,
462
+ "grad_norm": 0.0,
463
+ "learning_rate": 8.053333333333334e-05,
464
+ "loss": 0.0936,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.66,
469
+ "grad_norm": 0.0,
470
+ "learning_rate": 7.831111111111112e-05,
471
+ "loss": 0.1093,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.67,
476
+ "grad_norm": 0.0,
477
+ "learning_rate": 7.613333333333333e-05,
478
+ "loss": 0.1311,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.68,
483
+ "grad_norm": 0.0,
484
+ "learning_rate": 7.391111111111112e-05,
485
+ "loss": 0.1027,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.69,
490
+ "grad_norm": 0.0,
491
+ "learning_rate": 7.16888888888889e-05,
492
+ "loss": 0.0657,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.7,
497
+ "grad_norm": 0.0,
498
+ "learning_rate": 6.946666666666667e-05,
499
+ "loss": 0.0836,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.71,
504
+ "grad_norm": 0.0,
505
+ "learning_rate": 6.724444444444445e-05,
506
+ "loss": 0.0843,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.72,
511
+ "grad_norm": 0.0,
512
+ "learning_rate": 6.502222222222223e-05,
513
+ "loss": 0.0796,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.73,
518
+ "grad_norm": 0.0,
519
+ "learning_rate": 6.280000000000001e-05,
520
+ "loss": 0.0975,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.74,
525
+ "grad_norm": 0.0,
526
+ "learning_rate": 6.057777777777778e-05,
527
+ "loss": 0.0945,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.75,
532
+ "grad_norm": 0.0,
533
+ "learning_rate": 5.8355555555555565e-05,
534
+ "loss": 0.128,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.76,
539
+ "grad_norm": 0.0,
540
+ "learning_rate": 5.613333333333334e-05,
541
+ "loss": 0.0835,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.77,
546
+ "grad_norm": 0.0,
547
+ "learning_rate": 5.3911111111111115e-05,
548
+ "loss": 0.0689,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.78,
553
+ "grad_norm": 0.0,
554
+ "learning_rate": 5.1688888888888883e-05,
555
+ "loss": 0.0727,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.79,
560
+ "grad_norm": 0.0,
561
+ "learning_rate": 4.9466666666666665e-05,
562
+ "loss": 0.0858,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.8,
567
+ "grad_norm": 0.0,
568
+ "learning_rate": 4.724444444444445e-05,
569
+ "loss": 0.133,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.81,
574
+ "grad_norm": 0.0,
575
+ "learning_rate": 4.502222222222223e-05,
576
+ "loss": 0.1415,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.82,
581
+ "grad_norm": 0.0,
582
+ "learning_rate": 4.2800000000000004e-05,
583
+ "loss": 0.084,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.83,
588
+ "grad_norm": 0.0,
589
+ "learning_rate": 4.057777777777778e-05,
590
+ "loss": 0.0646,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.84,
595
+ "grad_norm": 0.0,
596
+ "learning_rate": 3.8355555555555553e-05,
597
+ "loss": 0.0846,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.85,
602
+ "grad_norm": 0.0,
603
+ "learning_rate": 3.6133333333333335e-05,
604
+ "loss": 0.0827,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.86,
609
+ "grad_norm": 0.0,
610
+ "learning_rate": 3.391111111111111e-05,
611
+ "loss": 0.0659,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.87,
616
+ "grad_norm": 0.0,
617
+ "learning_rate": 3.168888888888889e-05,
618
+ "loss": 0.0723,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.88,
623
+ "grad_norm": 0.0,
624
+ "learning_rate": 2.946666666666667e-05,
625
+ "loss": 0.0909,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.89,
630
+ "grad_norm": 0.0,
631
+ "learning_rate": 2.7244444444444445e-05,
632
+ "loss": 0.0962,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.9,
637
+ "grad_norm": 0.0,
638
+ "learning_rate": 2.5022222222222224e-05,
639
+ "loss": 0.0838,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.91,
644
+ "grad_norm": 0.0,
645
+ "learning_rate": 2.2800000000000002e-05,
646
+ "loss": 0.137,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.92,
651
+ "grad_norm": 0.0,
652
+ "learning_rate": 2.062222222222222e-05,
653
+ "loss": 0.151,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.93,
658
+ "grad_norm": 0.0,
659
+ "learning_rate": 1.84e-05,
660
+ "loss": 0.1,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.94,
665
+ "grad_norm": 0.0,
666
+ "learning_rate": 1.617777777777778e-05,
667
+ "loss": 0.0763,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.95,
672
+ "grad_norm": 0.0,
673
+ "learning_rate": 1.3955555555555555e-05,
674
+ "loss": 0.2048,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.96,
679
+ "grad_norm": 0.0,
680
+ "learning_rate": 1.1733333333333333e-05,
681
+ "loss": 0.1829,
682
+ "step": 4800
683
+ }
684
+ ],
685
+ "logging_steps": 50,
686
+ "max_steps": 5000,
687
+ "num_input_tokens_seen": 0,
688
+ "num_train_epochs": 9223372036854775807,
689
+ "save_steps": 200,
690
+ "stateful_callbacks": {
691
+ "TrainerControl": {
692
+ "args": {
693
+ "should_epoch_stop": false,
694
+ "should_evaluate": false,
695
+ "should_log": false,
696
+ "should_save": true,
697
+ "should_training_stop": false
698
+ },
699
+ "attributes": {}
700
+ }
701
+ },
702
+ "total_flos": 5.622660590999084e+18,
703
+ "train_batch_size": 1,
704
+ "trial_name": null,
705
+ "trial_params": null
706
+ }
checkpoint-4800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c914d1162d969be07a28866d27b70136a6145fb226e21fdb5ca172fa8cc238d
3
+ size 5368
checkpoint-5000/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.18.0
checkpoint-5000/adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Wav2Vec2ForCTC",
7
+ "parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
8
+ },
9
+ "base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 32,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.05,
25
+ "megatron_config": null,
26
+ "megatron_core": "megatron.core",
27
+ "modules_to_save": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.18.0",
30
+ "qalora_group_size": 16,
31
+ "r": 16,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "fc2",
36
+ "q_proj",
37
+ "fc1",
38
+ "k_proj",
39
+ "out_proj",
40
+ "v_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": null,
44
+ "trainable_token_indices": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
checkpoint-5000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
3
+ size 12610664
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc09ebe8d77cac1a1e53048182f106ea6de38cedd5f5771a5a98de74edd67e36
3
+ size 25327034
checkpoint-5000/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2659cb4e60e37a9bb37150e55e3cd20a5f33a9d703b53ff7cbfe2e0807285e52
3
+ size 14308
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd303ddfd62eb46548aabbf09bda78c123534cdd76aeec496e88f6edf6a6d84
3
+ size 988
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81296d7a42b175767c4064a500d9c3b456ca12efa1938516551ad5dfc47353cb
3
+ size 1064
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01,
14
+ "grad_norm": 2.4969277381896973,
15
+ "learning_rate": 1.76e-05,
16
+ "loss": 19.5898,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02,
21
+ "grad_norm": 8.099705696105957,
22
+ "learning_rate": 3.76e-05,
23
+ "loss": 17.8223,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 11.919422149658203,
29
+ "learning_rate": 5.72e-05,
30
+ "loss": 10.8995,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "grad_norm": 6.321387767791748,
36
+ "learning_rate": 7.64e-05,
37
+ "loss": 3.1441,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "grad_norm": 1.5579607486724854,
43
+ "learning_rate": 9.64e-05,
44
+ "loss": 1.0788,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "grad_norm": 2.1052896976470947,
50
+ "learning_rate": 0.0001164,
51
+ "loss": 0.3291,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.07,
56
+ "grad_norm": 1.402535319328308,
57
+ "learning_rate": 0.0001364,
58
+ "loss": 0.3073,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.08,
63
+ "grad_norm": 1.533136248588562,
64
+ "learning_rate": 0.00015600000000000002,
65
+ "loss": 0.4065,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.09,
70
+ "grad_norm": 2.3747737407684326,
71
+ "learning_rate": 0.00017600000000000002,
72
+ "loss": 0.294,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.1,
77
+ "grad_norm": 6.622051239013672,
78
+ "learning_rate": 0.000196,
79
+ "loss": 0.2311,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "grad_norm": 1.6454269886016846,
85
+ "learning_rate": 0.00019822222222222225,
86
+ "loss": 0.3515,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "grad_norm": 10.714489936828613,
92
+ "learning_rate": 0.000196,
93
+ "loss": 0.1957,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.13,
98
+ "grad_norm": 1.3993964195251465,
99
+ "learning_rate": 0.0001937777777777778,
100
+ "loss": 0.2028,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.14,
105
+ "grad_norm": 0.7649514675140381,
106
+ "learning_rate": 0.0001916,
107
+ "loss": 0.2995,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.15,
112
+ "grad_norm": 0.5896079540252686,
113
+ "learning_rate": 0.0001893777777777778,
114
+ "loss": 0.1876,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.16,
119
+ "grad_norm": 0.6604533791542053,
120
+ "learning_rate": 0.00018715555555555557,
121
+ "loss": 0.19,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "grad_norm": 2.047614097595215,
127
+ "learning_rate": 0.00018493333333333335,
128
+ "loss": 0.0988,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.18,
133
+ "grad_norm": 1.374024748802185,
134
+ "learning_rate": 0.00018271111111111112,
135
+ "loss": 0.1355,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.19,
140
+ "grad_norm": 1.4950742721557617,
141
+ "learning_rate": 0.0001804888888888889,
142
+ "loss": 0.1303,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2,
147
+ "grad_norm": 2.006479024887085,
148
+ "learning_rate": 0.00017826666666666667,
149
+ "loss": 0.1999,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.21,
154
+ "grad_norm": 1.1253306865692139,
155
+ "learning_rate": 0.00017604444444444445,
156
+ "loss": 0.152,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.22,
161
+ "grad_norm": 0.8224861025810242,
162
+ "learning_rate": 0.00017382222222222222,
163
+ "loss": 0.1444,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "grad_norm": 0.523875892162323,
169
+ "learning_rate": 0.0001716,
170
+ "loss": 0.155,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.24,
175
+ "grad_norm": 1.7560786008834839,
176
+ "learning_rate": 0.0001693777777777778,
177
+ "loss": 0.1934,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.25,
182
+ "grad_norm": 0.6891859173774719,
183
+ "learning_rate": 0.00016715555555555555,
184
+ "loss": 0.1062,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.26,
189
+ "grad_norm": 3.0257561206817627,
190
+ "learning_rate": 0.00016493333333333335,
191
+ "loss": 0.1132,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.27,
196
+ "grad_norm": 0.0,
197
+ "learning_rate": 0.00016351111111111112,
198
+ "loss": 0.3971,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.28,
203
+ "grad_norm": 0.0,
204
+ "learning_rate": 0.0001612888888888889,
205
+ "loss": 0.2656,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "grad_norm": 0.0,
211
+ "learning_rate": 0.00015924444444444447,
212
+ "loss": 0.4477,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.3,
217
+ "grad_norm": 0.0,
218
+ "learning_rate": 0.00015706666666666667,
219
+ "loss": 0.3441,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.31,
224
+ "grad_norm": 0.0,
225
+ "learning_rate": 0.00015484444444444445,
226
+ "loss": 0.1985,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.32,
231
+ "grad_norm": 0.0,
232
+ "learning_rate": 0.00015262222222222222,
233
+ "loss": 0.2074,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.33,
238
+ "grad_norm": 0.0,
239
+ "learning_rate": 0.00015066666666666668,
240
+ "loss": 0.481,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.34,
245
+ "grad_norm": 0.0,
246
+ "learning_rate": 0.00014857777777777778,
247
+ "loss": 0.2268,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "grad_norm": 0.0,
253
+ "learning_rate": 0.00014635555555555556,
254
+ "loss": 0.1873,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.36,
259
+ "grad_norm": 0.0,
260
+ "learning_rate": 0.00014413333333333333,
261
+ "loss": 0.2051,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.37,
266
+ "grad_norm": 0.0,
267
+ "learning_rate": 0.00014191111111111113,
268
+ "loss": 0.2184,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.38,
273
+ "grad_norm": 0.0,
274
+ "learning_rate": 0.00013968888888888888,
275
+ "loss": 0.112,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.39,
280
+ "grad_norm": 0.0,
281
+ "learning_rate": 0.00013751111111111113,
282
+ "loss": 0.2867,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4,
287
+ "grad_norm": 0.0,
288
+ "learning_rate": 0.00013528888888888888,
289
+ "loss": 0.1132,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "grad_norm": 0.0,
295
+ "learning_rate": 0.00013306666666666668,
296
+ "loss": 0.2804,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.42,
301
+ "grad_norm": 0.0,
302
+ "learning_rate": 0.00013084444444444446,
303
+ "loss": 0.1317,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.43,
308
+ "grad_norm": 0.0,
309
+ "learning_rate": 0.00012862222222222223,
310
+ "loss": 0.1032,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.44,
315
+ "grad_norm": 0.0,
316
+ "learning_rate": 0.0001264,
317
+ "loss": 0.1184,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.45,
322
+ "grad_norm": 0.0,
323
+ "learning_rate": 0.00012417777777777778,
324
+ "loss": 0.1207,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.46,
329
+ "grad_norm": 0.0,
330
+ "learning_rate": 0.00012195555555555556,
331
+ "loss": 0.1269,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.47,
336
+ "grad_norm": 0.0,
337
+ "learning_rate": 0.00011973333333333335,
338
+ "loss": 0.1391,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.48,
343
+ "grad_norm": 0.0,
344
+ "learning_rate": 0.00011773333333333334,
345
+ "loss": 0.2337,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.49,
350
+ "grad_norm": 0.0,
351
+ "learning_rate": 0.00011586666666666667,
352
+ "loss": 0.3983,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5,
357
+ "grad_norm": 0.0,
358
+ "learning_rate": 0.00011373333333333334,
359
+ "loss": 0.1904,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.51,
364
+ "grad_norm": 0.0,
365
+ "learning_rate": 0.00011160000000000002,
366
+ "loss": 0.2106,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.52,
371
+ "grad_norm": 0.0,
372
+ "learning_rate": 0.00010942222222222223,
373
+ "loss": 0.1193,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.53,
378
+ "grad_norm": 0.0,
379
+ "learning_rate": 0.00010720000000000002,
380
+ "loss": 0.1406,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.54,
385
+ "grad_norm": 0.0,
386
+ "learning_rate": 0.00010497777777777778,
387
+ "loss": 0.1312,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.55,
392
+ "grad_norm": 0.0,
393
+ "learning_rate": 0.00010275555555555557,
394
+ "loss": 0.1193,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.56,
399
+ "grad_norm": 0.0,
400
+ "learning_rate": 0.00010053333333333334,
401
+ "loss": 0.1838,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.57,
406
+ "grad_norm": 0.0,
407
+ "learning_rate": 9.831111111111112e-05,
408
+ "loss": 0.1306,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.58,
413
+ "grad_norm": 0.0,
414
+ "learning_rate": 9.608888888888889e-05,
415
+ "loss": 0.1127,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.59,
420
+ "grad_norm": 0.0,
421
+ "learning_rate": 9.386666666666667e-05,
422
+ "loss": 0.1963,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.6,
427
+ "grad_norm": 0.0,
428
+ "learning_rate": 9.164444444444444e-05,
429
+ "loss": 0.1813,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.61,
434
+ "grad_norm": 0.0,
435
+ "learning_rate": 8.942222222222223e-05,
436
+ "loss": 0.2901,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.62,
441
+ "grad_norm": 0.0,
442
+ "learning_rate": 8.72e-05,
443
+ "loss": 0.0905,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.63,
448
+ "grad_norm": 0.0,
449
+ "learning_rate": 8.497777777777778e-05,
450
+ "loss": 0.1058,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.64,
455
+ "grad_norm": 0.0,
456
+ "learning_rate": 8.275555555555557e-05,
457
+ "loss": 0.0965,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.65,
462
+ "grad_norm": 0.0,
463
+ "learning_rate": 8.053333333333334e-05,
464
+ "loss": 0.0936,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.66,
469
+ "grad_norm": 0.0,
470
+ "learning_rate": 7.831111111111112e-05,
471
+ "loss": 0.1093,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.67,
476
+ "grad_norm": 0.0,
477
+ "learning_rate": 7.613333333333333e-05,
478
+ "loss": 0.1311,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.68,
483
+ "grad_norm": 0.0,
484
+ "learning_rate": 7.391111111111112e-05,
485
+ "loss": 0.1027,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.69,
490
+ "grad_norm": 0.0,
491
+ "learning_rate": 7.16888888888889e-05,
492
+ "loss": 0.0657,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.7,
497
+ "grad_norm": 0.0,
498
+ "learning_rate": 6.946666666666667e-05,
499
+ "loss": 0.0836,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.71,
504
+ "grad_norm": 0.0,
505
+ "learning_rate": 6.724444444444445e-05,
506
+ "loss": 0.0843,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.72,
511
+ "grad_norm": 0.0,
512
+ "learning_rate": 6.502222222222223e-05,
513
+ "loss": 0.0796,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.73,
518
+ "grad_norm": 0.0,
519
+ "learning_rate": 6.280000000000001e-05,
520
+ "loss": 0.0975,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.74,
525
+ "grad_norm": 0.0,
526
+ "learning_rate": 6.057777777777778e-05,
527
+ "loss": 0.0945,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.75,
532
+ "grad_norm": 0.0,
533
+ "learning_rate": 5.8355555555555565e-05,
534
+ "loss": 0.128,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.76,
539
+ "grad_norm": 0.0,
540
+ "learning_rate": 5.613333333333334e-05,
541
+ "loss": 0.0835,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.77,
546
+ "grad_norm": 0.0,
547
+ "learning_rate": 5.3911111111111115e-05,
548
+ "loss": 0.0689,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.78,
553
+ "grad_norm": 0.0,
554
+ "learning_rate": 5.1688888888888883e-05,
555
+ "loss": 0.0727,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.79,
560
+ "grad_norm": 0.0,
561
+ "learning_rate": 4.9466666666666665e-05,
562
+ "loss": 0.0858,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.8,
567
+ "grad_norm": 0.0,
568
+ "learning_rate": 4.724444444444445e-05,
569
+ "loss": 0.133,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.81,
574
+ "grad_norm": 0.0,
575
+ "learning_rate": 4.502222222222223e-05,
576
+ "loss": 0.1415,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.82,
581
+ "grad_norm": 0.0,
582
+ "learning_rate": 4.2800000000000004e-05,
583
+ "loss": 0.084,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.83,
588
+ "grad_norm": 0.0,
589
+ "learning_rate": 4.057777777777778e-05,
590
+ "loss": 0.0646,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.84,
595
+ "grad_norm": 0.0,
596
+ "learning_rate": 3.8355555555555553e-05,
597
+ "loss": 0.0846,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.85,
602
+ "grad_norm": 0.0,
603
+ "learning_rate": 3.6133333333333335e-05,
604
+ "loss": 0.0827,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.86,
609
+ "grad_norm": 0.0,
610
+ "learning_rate": 3.391111111111111e-05,
611
+ "loss": 0.0659,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.87,
616
+ "grad_norm": 0.0,
617
+ "learning_rate": 3.168888888888889e-05,
618
+ "loss": 0.0723,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.88,
623
+ "grad_norm": 0.0,
624
+ "learning_rate": 2.946666666666667e-05,
625
+ "loss": 0.0909,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.89,
630
+ "grad_norm": 0.0,
631
+ "learning_rate": 2.7244444444444445e-05,
632
+ "loss": 0.0962,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.9,
637
+ "grad_norm": 0.0,
638
+ "learning_rate": 2.5022222222222224e-05,
639
+ "loss": 0.0838,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.91,
644
+ "grad_norm": 0.0,
645
+ "learning_rate": 2.2800000000000002e-05,
646
+ "loss": 0.137,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.92,
651
+ "grad_norm": 0.0,
652
+ "learning_rate": 2.062222222222222e-05,
653
+ "loss": 0.151,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.93,
658
+ "grad_norm": 0.0,
659
+ "learning_rate": 1.84e-05,
660
+ "loss": 0.1,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.94,
665
+ "grad_norm": 0.0,
666
+ "learning_rate": 1.617777777777778e-05,
667
+ "loss": 0.0763,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.95,
672
+ "grad_norm": 0.0,
673
+ "learning_rate": 1.3955555555555555e-05,
674
+ "loss": 0.2048,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.96,
679
+ "grad_norm": 0.0,
680
+ "learning_rate": 1.1733333333333333e-05,
681
+ "loss": 0.1829,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.97,
686
+ "grad_norm": 0.0,
687
+ "learning_rate": 9.511111111111112e-06,
688
+ "loss": 0.1028,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.98,
693
+ "grad_norm": 0.0,
694
+ "learning_rate": 7.288888888888889e-06,
695
+ "loss": 0.1039,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.99,
700
+ "grad_norm": 0.0,
701
+ "learning_rate": 5.066666666666667e-06,
702
+ "loss": 0.0719,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 1.0,
707
+ "grad_norm": 0.0,
708
+ "learning_rate": 2.8444444444444446e-06,
709
+ "loss": 0.0712,
710
+ "step": 5000
711
+ }
712
+ ],
713
+ "logging_steps": 50,
714
+ "max_steps": 5000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 9223372036854775807,
717
+ "save_steps": 200,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": true
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 5.965059712153151e+18,
731
+ "train_batch_size": 1,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c914d1162d969be07a28866d27b70136a6145fb226e21fdb5ca172fa8cc238d
3
+ size 5368
checkpoint-5001/README.md ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tinkvu/wav2vec2-large-xlsr-amharic-healthcare
3
+ library_name: peft
4
+ tags:
5
+ - base_model:adapter:tinkvu/wav2vec2-large-xlsr-amharic-healthcare
6
+ - lora
7
+ - transformers
8
+ ---
9
+
10
+ # Model Card for Model ID
11
+
12
+ <!-- Provide a quick summary of what the model is/does. -->
13
+
14
+
15
+
16
+ ## Model Details
17
+
18
+ ### Model Description
19
+
20
+ <!-- Provide a longer summary of what this model is. -->
21
+
22
+
23
+
24
+ - **Developed by:** [More Information Needed]
25
+ - **Funded by [optional]:** [More Information Needed]
26
+ - **Shared by [optional]:** [More Information Needed]
27
+ - **Model type:** [More Information Needed]
28
+ - **Language(s) (NLP):** [More Information Needed]
29
+ - **License:** [More Information Needed]
30
+ - **Finetuned from model [optional]:** [More Information Needed]
31
+
32
+ ### Model Sources [optional]
33
+
34
+ <!-- Provide the basic links for the model. -->
35
+
36
+ - **Repository:** [More Information Needed]
37
+ - **Paper [optional]:** [More Information Needed]
38
+ - **Demo [optional]:** [More Information Needed]
39
+
40
+ ## Uses
41
+
42
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
43
+
44
+ ### Direct Use
45
+
46
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
47
+
48
+ [More Information Needed]
49
+
50
+ ### Downstream Use [optional]
51
+
52
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
53
+
54
+ [More Information Needed]
55
+
56
+ ### Out-of-Scope Use
57
+
58
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
59
+
60
+ [More Information Needed]
61
+
62
+ ## Bias, Risks, and Limitations
63
+
64
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
65
+
66
+ [More Information Needed]
67
+
68
+ ### Recommendations
69
+
70
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
71
+
72
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
73
+
74
+ ## How to Get Started with the Model
75
+
76
+ Use the code below to get started with the model.
77
+
78
+ [More Information Needed]
79
+
80
+ ## Training Details
81
+
82
+ ### Training Data
83
+
84
+ <!-- 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. -->
85
+
86
+ [More Information Needed]
87
+
88
+ ### Training Procedure
89
+
90
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
91
+
92
+ #### Preprocessing [optional]
93
+
94
+ [More Information Needed]
95
+
96
+
97
+ #### Training Hyperparameters
98
+
99
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
100
+
101
+ #### Speeds, Sizes, Times [optional]
102
+
103
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
104
+
105
+ [More Information Needed]
106
+
107
+ ## Evaluation
108
+
109
+ <!-- This section describes the evaluation protocols and provides the results. -->
110
+
111
+ ### Testing Data, Factors & Metrics
112
+
113
+ #### Testing Data
114
+
115
+ <!-- This should link to a Dataset Card if possible. -->
116
+
117
+ [More Information Needed]
118
+
119
+ #### Factors
120
+
121
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
122
+
123
+ [More Information Needed]
124
+
125
+ #### Metrics
126
+
127
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
128
+
129
+ [More Information Needed]
130
+
131
+ ### Results
132
+
133
+ [More Information Needed]
134
+
135
+ #### Summary
136
+
137
+
138
+
139
+ ## Model Examination [optional]
140
+
141
+ <!-- Relevant interpretability work for the model goes here -->
142
+
143
+ [More Information Needed]
144
+
145
+ ## Environmental Impact
146
+
147
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
148
+
149
+ 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).
150
+
151
+ - **Hardware Type:** [More Information Needed]
152
+ - **Hours used:** [More Information Needed]
153
+ - **Cloud Provider:** [More Information Needed]
154
+ - **Compute Region:** [More Information Needed]
155
+ - **Carbon Emitted:** [More Information Needed]
156
+
157
+ ## Technical Specifications [optional]
158
+
159
+ ### Model Architecture and Objective
160
+
161
+ [More Information Needed]
162
+
163
+ ### Compute Infrastructure
164
+
165
+ [More Information Needed]
166
+
167
+ #### Hardware
168
+
169
+ [More Information Needed]
170
+
171
+ #### Software
172
+
173
+ [More Information Needed]
174
+
175
+ ## Citation [optional]
176
+
177
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
178
+
179
+ **BibTeX:**
180
+
181
+ [More Information Needed]
182
+
183
+ **APA:**
184
+
185
+ [More Information Needed]
186
+
187
+ ## Glossary [optional]
188
+
189
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
190
+
191
+ [More Information Needed]
192
+
193
+ ## More Information [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Authors [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Contact
202
+
203
+ [More Information Needed]
204
+ ### Framework versions
205
+
206
+ - PEFT 0.18.0
checkpoint-5001/adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Wav2Vec2ForCTC",
7
+ "parent_library": "transformers.models.wav2vec2.modeling_wav2vec2"
8
+ },
9
+ "base_model_name_or_path": "tinkvu/wav2vec2-large-xlsr-amharic-healthcare",
10
+ "bias": "none",
11
+ "corda_config": null,
12
+ "ensure_weight_tying": false,
13
+ "eva_config": null,
14
+ "exclude_modules": null,
15
+ "fan_in_fan_out": false,
16
+ "inference_mode": true,
17
+ "init_lora_weights": true,
18
+ "layer_replication": null,
19
+ "layers_pattern": null,
20
+ "layers_to_transform": null,
21
+ "loftq_config": {},
22
+ "lora_alpha": 32,
23
+ "lora_bias": false,
24
+ "lora_dropout": 0.05,
25
+ "megatron_config": null,
26
+ "megatron_core": "megatron.core",
27
+ "modules_to_save": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.18.0",
30
+ "qalora_group_size": 16,
31
+ "r": 16,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "fc2",
36
+ "q_proj",
37
+ "fc1",
38
+ "k_proj",
39
+ "out_proj",
40
+ "v_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": null,
44
+ "trainable_token_indices": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
checkpoint-5001/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94833f7953f32ef49bc33486828f0294e6f1d4c8e21970687c840f2c832b1e0
3
+ size 12610664
checkpoint-5001/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d8e12a90994f2184ba088e8090c659526e3b75cfe02ccca2dceac264300c7c
3
+ size 25327034
checkpoint-5001/preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
checkpoint-5001/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e756890108a8f741a185bce7f0602c3aa17eba79f6f5512073164be496d80b2
3
+ size 14308
checkpoint-5001/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91d19f4eff6d661e3ac8e6d859a592e95afaa30622db0085dba164eafa44de2
3
+ size 988
checkpoint-5001/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33af232a099127febd9ad133ed35db3a358842052c8ba5d0301120dc3429f3c
3
+ size 1064
checkpoint-5001/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0002,
6
+ "eval_steps": 500,
7
+ "global_step": 5001,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01,
14
+ "grad_norm": 2.4969277381896973,
15
+ "learning_rate": 1.76e-05,
16
+ "loss": 19.5898,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02,
21
+ "grad_norm": 8.099705696105957,
22
+ "learning_rate": 3.76e-05,
23
+ "loss": 17.8223,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 11.919422149658203,
29
+ "learning_rate": 5.72e-05,
30
+ "loss": 10.8995,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "grad_norm": 6.321387767791748,
36
+ "learning_rate": 7.64e-05,
37
+ "loss": 3.1441,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "grad_norm": 1.5579607486724854,
43
+ "learning_rate": 9.64e-05,
44
+ "loss": 1.0788,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "grad_norm": 2.1052896976470947,
50
+ "learning_rate": 0.0001164,
51
+ "loss": 0.3291,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.07,
56
+ "grad_norm": 1.402535319328308,
57
+ "learning_rate": 0.0001364,
58
+ "loss": 0.3073,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.08,
63
+ "grad_norm": 1.533136248588562,
64
+ "learning_rate": 0.00015600000000000002,
65
+ "loss": 0.4065,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.09,
70
+ "grad_norm": 2.3747737407684326,
71
+ "learning_rate": 0.00017600000000000002,
72
+ "loss": 0.294,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.1,
77
+ "grad_norm": 6.622051239013672,
78
+ "learning_rate": 0.000196,
79
+ "loss": 0.2311,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "grad_norm": 1.6454269886016846,
85
+ "learning_rate": 0.00019822222222222225,
86
+ "loss": 0.3515,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "grad_norm": 10.714489936828613,
92
+ "learning_rate": 0.000196,
93
+ "loss": 0.1957,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.13,
98
+ "grad_norm": 1.3993964195251465,
99
+ "learning_rate": 0.0001937777777777778,
100
+ "loss": 0.2028,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.14,
105
+ "grad_norm": 0.7649514675140381,
106
+ "learning_rate": 0.0001916,
107
+ "loss": 0.2995,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.15,
112
+ "grad_norm": 0.5896079540252686,
113
+ "learning_rate": 0.0001893777777777778,
114
+ "loss": 0.1876,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.16,
119
+ "grad_norm": 0.6604533791542053,
120
+ "learning_rate": 0.00018715555555555557,
121
+ "loss": 0.19,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "grad_norm": 2.047614097595215,
127
+ "learning_rate": 0.00018493333333333335,
128
+ "loss": 0.0988,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.18,
133
+ "grad_norm": 1.374024748802185,
134
+ "learning_rate": 0.00018271111111111112,
135
+ "loss": 0.1355,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.19,
140
+ "grad_norm": 1.4950742721557617,
141
+ "learning_rate": 0.0001804888888888889,
142
+ "loss": 0.1303,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2,
147
+ "grad_norm": 2.006479024887085,
148
+ "learning_rate": 0.00017826666666666667,
149
+ "loss": 0.1999,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.21,
154
+ "grad_norm": 1.1253306865692139,
155
+ "learning_rate": 0.00017604444444444445,
156
+ "loss": 0.152,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.22,
161
+ "grad_norm": 0.8224861025810242,
162
+ "learning_rate": 0.00017382222222222222,
163
+ "loss": 0.1444,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "grad_norm": 0.523875892162323,
169
+ "learning_rate": 0.0001716,
170
+ "loss": 0.155,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.24,
175
+ "grad_norm": 1.7560786008834839,
176
+ "learning_rate": 0.0001693777777777778,
177
+ "loss": 0.1934,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.25,
182
+ "grad_norm": 0.6891859173774719,
183
+ "learning_rate": 0.00016715555555555555,
184
+ "loss": 0.1062,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.26,
189
+ "grad_norm": 3.0257561206817627,
190
+ "learning_rate": 0.00016493333333333335,
191
+ "loss": 0.1132,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.27,
196
+ "grad_norm": 0.0,
197
+ "learning_rate": 0.00016351111111111112,
198
+ "loss": 0.3971,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.28,
203
+ "grad_norm": 0.0,
204
+ "learning_rate": 0.0001612888888888889,
205
+ "loss": 0.2656,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "grad_norm": 0.0,
211
+ "learning_rate": 0.00015924444444444447,
212
+ "loss": 0.4477,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.3,
217
+ "grad_norm": 0.0,
218
+ "learning_rate": 0.00015706666666666667,
219
+ "loss": 0.3441,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.31,
224
+ "grad_norm": 0.0,
225
+ "learning_rate": 0.00015484444444444445,
226
+ "loss": 0.1985,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.32,
231
+ "grad_norm": 0.0,
232
+ "learning_rate": 0.00015262222222222222,
233
+ "loss": 0.2074,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.33,
238
+ "grad_norm": 0.0,
239
+ "learning_rate": 0.00015066666666666668,
240
+ "loss": 0.481,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.34,
245
+ "grad_norm": 0.0,
246
+ "learning_rate": 0.00014857777777777778,
247
+ "loss": 0.2268,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "grad_norm": 0.0,
253
+ "learning_rate": 0.00014635555555555556,
254
+ "loss": 0.1873,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.36,
259
+ "grad_norm": 0.0,
260
+ "learning_rate": 0.00014413333333333333,
261
+ "loss": 0.2051,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.37,
266
+ "grad_norm": 0.0,
267
+ "learning_rate": 0.00014191111111111113,
268
+ "loss": 0.2184,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.38,
273
+ "grad_norm": 0.0,
274
+ "learning_rate": 0.00013968888888888888,
275
+ "loss": 0.112,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.39,
280
+ "grad_norm": 0.0,
281
+ "learning_rate": 0.00013751111111111113,
282
+ "loss": 0.2867,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4,
287
+ "grad_norm": 0.0,
288
+ "learning_rate": 0.00013528888888888888,
289
+ "loss": 0.1132,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "grad_norm": 0.0,
295
+ "learning_rate": 0.00013306666666666668,
296
+ "loss": 0.2804,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.42,
301
+ "grad_norm": 0.0,
302
+ "learning_rate": 0.00013084444444444446,
303
+ "loss": 0.1317,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.43,
308
+ "grad_norm": 0.0,
309
+ "learning_rate": 0.00012862222222222223,
310
+ "loss": 0.1032,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.44,
315
+ "grad_norm": 0.0,
316
+ "learning_rate": 0.0001264,
317
+ "loss": 0.1184,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.45,
322
+ "grad_norm": 0.0,
323
+ "learning_rate": 0.00012417777777777778,
324
+ "loss": 0.1207,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.46,
329
+ "grad_norm": 0.0,
330
+ "learning_rate": 0.00012195555555555556,
331
+ "loss": 0.1269,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.47,
336
+ "grad_norm": 0.0,
337
+ "learning_rate": 0.00011973333333333335,
338
+ "loss": 0.1391,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.48,
343
+ "grad_norm": 0.0,
344
+ "learning_rate": 0.00011773333333333334,
345
+ "loss": 0.2337,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.49,
350
+ "grad_norm": 0.0,
351
+ "learning_rate": 0.00011586666666666667,
352
+ "loss": 0.3983,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5,
357
+ "grad_norm": 0.0,
358
+ "learning_rate": 0.00011373333333333334,
359
+ "loss": 0.1904,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.51,
364
+ "grad_norm": 0.0,
365
+ "learning_rate": 0.00011160000000000002,
366
+ "loss": 0.2106,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.52,
371
+ "grad_norm": 0.0,
372
+ "learning_rate": 0.00010942222222222223,
373
+ "loss": 0.1193,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.53,
378
+ "grad_norm": 0.0,
379
+ "learning_rate": 0.00010720000000000002,
380
+ "loss": 0.1406,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.54,
385
+ "grad_norm": 0.0,
386
+ "learning_rate": 0.00010497777777777778,
387
+ "loss": 0.1312,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.55,
392
+ "grad_norm": 0.0,
393
+ "learning_rate": 0.00010275555555555557,
394
+ "loss": 0.1193,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.56,
399
+ "grad_norm": 0.0,
400
+ "learning_rate": 0.00010053333333333334,
401
+ "loss": 0.1838,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.57,
406
+ "grad_norm": 0.0,
407
+ "learning_rate": 9.831111111111112e-05,
408
+ "loss": 0.1306,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.58,
413
+ "grad_norm": 0.0,
414
+ "learning_rate": 9.608888888888889e-05,
415
+ "loss": 0.1127,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.59,
420
+ "grad_norm": 0.0,
421
+ "learning_rate": 9.386666666666667e-05,
422
+ "loss": 0.1963,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.6,
427
+ "grad_norm": 0.0,
428
+ "learning_rate": 9.164444444444444e-05,
429
+ "loss": 0.1813,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.61,
434
+ "grad_norm": 0.0,
435
+ "learning_rate": 8.942222222222223e-05,
436
+ "loss": 0.2901,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.62,
441
+ "grad_norm": 0.0,
442
+ "learning_rate": 8.72e-05,
443
+ "loss": 0.0905,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.63,
448
+ "grad_norm": 0.0,
449
+ "learning_rate": 8.497777777777778e-05,
450
+ "loss": 0.1058,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.64,
455
+ "grad_norm": 0.0,
456
+ "learning_rate": 8.275555555555557e-05,
457
+ "loss": 0.0965,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.65,
462
+ "grad_norm": 0.0,
463
+ "learning_rate": 8.053333333333334e-05,
464
+ "loss": 0.0936,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.66,
469
+ "grad_norm": 0.0,
470
+ "learning_rate": 7.831111111111112e-05,
471
+ "loss": 0.1093,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.67,
476
+ "grad_norm": 0.0,
477
+ "learning_rate": 7.613333333333333e-05,
478
+ "loss": 0.1311,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.68,
483
+ "grad_norm": 0.0,
484
+ "learning_rate": 7.391111111111112e-05,
485
+ "loss": 0.1027,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.69,
490
+ "grad_norm": 0.0,
491
+ "learning_rate": 7.16888888888889e-05,
492
+ "loss": 0.0657,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.7,
497
+ "grad_norm": 0.0,
498
+ "learning_rate": 6.946666666666667e-05,
499
+ "loss": 0.0836,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.71,
504
+ "grad_norm": 0.0,
505
+ "learning_rate": 6.724444444444445e-05,
506
+ "loss": 0.0843,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.72,
511
+ "grad_norm": 0.0,
512
+ "learning_rate": 6.502222222222223e-05,
513
+ "loss": 0.0796,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.73,
518
+ "grad_norm": 0.0,
519
+ "learning_rate": 6.280000000000001e-05,
520
+ "loss": 0.0975,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.74,
525
+ "grad_norm": 0.0,
526
+ "learning_rate": 6.057777777777778e-05,
527
+ "loss": 0.0945,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.75,
532
+ "grad_norm": 0.0,
533
+ "learning_rate": 5.8355555555555565e-05,
534
+ "loss": 0.128,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.76,
539
+ "grad_norm": 0.0,
540
+ "learning_rate": 5.613333333333334e-05,
541
+ "loss": 0.0835,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.77,
546
+ "grad_norm": 0.0,
547
+ "learning_rate": 5.3911111111111115e-05,
548
+ "loss": 0.0689,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.78,
553
+ "grad_norm": 0.0,
554
+ "learning_rate": 5.1688888888888883e-05,
555
+ "loss": 0.0727,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.79,
560
+ "grad_norm": 0.0,
561
+ "learning_rate": 4.9466666666666665e-05,
562
+ "loss": 0.0858,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.8,
567
+ "grad_norm": 0.0,
568
+ "learning_rate": 4.724444444444445e-05,
569
+ "loss": 0.133,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.81,
574
+ "grad_norm": 0.0,
575
+ "learning_rate": 4.502222222222223e-05,
576
+ "loss": 0.1415,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.82,
581
+ "grad_norm": 0.0,
582
+ "learning_rate": 4.2800000000000004e-05,
583
+ "loss": 0.084,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.83,
588
+ "grad_norm": 0.0,
589
+ "learning_rate": 4.057777777777778e-05,
590
+ "loss": 0.0646,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.84,
595
+ "grad_norm": 0.0,
596
+ "learning_rate": 3.8355555555555553e-05,
597
+ "loss": 0.0846,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.85,
602
+ "grad_norm": 0.0,
603
+ "learning_rate": 3.6133333333333335e-05,
604
+ "loss": 0.0827,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.86,
609
+ "grad_norm": 0.0,
610
+ "learning_rate": 3.391111111111111e-05,
611
+ "loss": 0.0659,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.87,
616
+ "grad_norm": 0.0,
617
+ "learning_rate": 3.168888888888889e-05,
618
+ "loss": 0.0723,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.88,
623
+ "grad_norm": 0.0,
624
+ "learning_rate": 2.946666666666667e-05,
625
+ "loss": 0.0909,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.89,
630
+ "grad_norm": 0.0,
631
+ "learning_rate": 2.7244444444444445e-05,
632
+ "loss": 0.0962,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.9,
637
+ "grad_norm": 0.0,
638
+ "learning_rate": 2.5022222222222224e-05,
639
+ "loss": 0.0838,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.91,
644
+ "grad_norm": 0.0,
645
+ "learning_rate": 2.2800000000000002e-05,
646
+ "loss": 0.137,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.92,
651
+ "grad_norm": 0.0,
652
+ "learning_rate": 2.062222222222222e-05,
653
+ "loss": 0.151,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.93,
658
+ "grad_norm": 0.0,
659
+ "learning_rate": 1.84e-05,
660
+ "loss": 0.1,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.94,
665
+ "grad_norm": 0.0,
666
+ "learning_rate": 1.617777777777778e-05,
667
+ "loss": 0.0763,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.95,
672
+ "grad_norm": 0.0,
673
+ "learning_rate": 1.3955555555555555e-05,
674
+ "loss": 0.2048,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.96,
679
+ "grad_norm": 0.0,
680
+ "learning_rate": 1.1733333333333333e-05,
681
+ "loss": 0.1829,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.97,
686
+ "grad_norm": 0.0,
687
+ "learning_rate": 9.511111111111112e-06,
688
+ "loss": 0.1028,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.98,
693
+ "grad_norm": 0.0,
694
+ "learning_rate": 7.288888888888889e-06,
695
+ "loss": 0.1039,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.99,
700
+ "grad_norm": 0.0,
701
+ "learning_rate": 5.066666666666667e-06,
702
+ "loss": 0.0719,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 1.0,
707
+ "grad_norm": 0.0,
708
+ "learning_rate": 2.8444444444444446e-06,
709
+ "loss": 0.0712,
710
+ "step": 5000
711
+ }
712
+ ],
713
+ "logging_steps": 50,
714
+ "max_steps": 5000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 9223372036854775807,
717
+ "save_steps": 200,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": true
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 5.966293791739906e+18,
731
+ "train_batch_size": 1,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-5001/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6750694c4eac2ee8f68ff96dd2d091aa195827faf50bac6fb6d68217a85c7a5e
3
+ size 5368