jash6 devchuriwala commited on
Commit
aff49e1
·
verified ·
1 Parent(s): 72615d2

full icliniq dataset finetune (#1)

Browse files

- full icliniq dataset finetune (a88e5ee09d3661b68808b35bd5d4ea9cee480b2a)


Co-authored-by: Dev <devchuriwala@users.noreply.huggingface.co>

README.md CHANGED
@@ -1,57 +1,202 @@
1
  ---
2
  base_model: google/gemma-2b
3
- library_name: transformers
4
- model_name: gemma2b-ft-iclinq
5
- tags:
6
- - generated_from_trainer
7
- - trl
8
- - sft
9
- licence: license
10
  ---
11
 
12
- # Model Card for gemma2b-ft-iclinq
13
 
14
- This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b).
15
- It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
- ## Quick start
18
 
19
- ```python
20
- from transformers import pipeline
21
 
22
- question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
- generator = pipeline("text-generation", model="jash6/results-2", device="cuda")
24
- output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
- print(output["generated_text"])
26
- ```
27
 
28
- ## Training procedure
29
 
 
30
 
31
 
32
- This model was trained with SFT.
33
 
34
- ### Framework versions
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
- - TRL: 0.12.1
37
- - Transformers: 4.46.3
38
- - Pytorch: 2.2.0
39
- - Datasets: 3.1.0
40
- - Tokenizers: 0.20.4
41
 
42
- ## Citations
43
 
 
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
 
46
- Cite TRL as:
47
-
48
- ```bibtex
49
- @misc{vonwerra2022trl,
50
- title = {{TRL: Transformer Reinforcement Learning}},
51
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
52
- year = 2020,
53
- journal = {GitHub repository},
54
- publisher = {GitHub},
55
- howpublished = {\url{https://github.com/huggingface/trl}}
56
- }
57
- ```
 
1
  ---
2
  base_model: google/gemma-2b
3
+ library_name: peft
 
 
 
 
 
 
4
  ---
5
 
6
+ # Model Card for Model ID
7
 
8
+ <!-- Provide a quick summary of what the model is/does. -->
 
9
 
 
10
 
 
 
11
 
12
+ ## Model Details
 
 
 
 
13
 
14
+ ### Model Description
15
 
16
+ <!-- Provide a longer summary of what this model is. -->
17
 
18
 
 
19
 
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
 
111
+ <!-- This should link to a Dataset Card if possible. -->
 
 
 
 
112
 
113
+ [More Information Needed]
114
 
115
+ #### Factors
116
 
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
 
202
+ - PEFT 0.13.2
 
 
 
 
 
 
 
 
 
 
 
adapter_config.json CHANGED
@@ -20,11 +20,11 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "gate_proj",
24
  "v_proj",
25
- "up_proj",
26
- "k_proj",
27
  "q_proj",
 
 
 
28
  "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "v_proj",
 
 
24
  "q_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "up_proj",
28
  "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e03debe290b3c389df502b6c0d95d58a9d55f2b9b9ce594c534e4ca80041e55
3
  size 14331480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ec9512d068cc5c7f2376de462eaf86f3678a7ef989d959fd464ad562ced5bd
3
  size 14331480
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65481820a18e53afd9b92fa8ed1ef317a6b48ce02a409c7a018ae0552b46ac81
3
+ size 28734458
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ff545097dd45f4e0976ceb12627a2db85a8cda9404b0b67df2f4c97490e22c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa275e0c3e75f7e8222fcb1c9374e42a40ab63cd9b97d2e82dc002aa81170f4b
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4180,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005980861244019139,
13
+ "grad_norm": 3.412325382232666,
14
+ "learning_rate": 0.0002,
15
+ "loss": 3.3895,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.011961722488038277,
20
+ "grad_norm": 9.85770034790039,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.6708,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.017942583732057416,
27
+ "grad_norm": 1.8022898435592651,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.4984,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.023923444976076555,
34
+ "grad_norm": 1.3909275531768799,
35
+ "learning_rate": 0.0002,
36
+ "loss": 2.4433,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.029904306220095694,
41
+ "grad_norm": 1.3175278902053833,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.4068,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03588516746411483,
48
+ "grad_norm": 2.1698503494262695,
49
+ "learning_rate": 0.0002,
50
+ "loss": 2.3572,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.041866028708133975,
55
+ "grad_norm": 3.156744956970215,
56
+ "learning_rate": 0.0002,
57
+ "loss": 2.3665,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04784688995215311,
62
+ "grad_norm": 1.0966124534606934,
63
+ "learning_rate": 0.0002,
64
+ "loss": 2.3631,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.05382775119617225,
69
+ "grad_norm": 1.5008922815322876,
70
+ "learning_rate": 0.0002,
71
+ "loss": 2.3375,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.05980861244019139,
76
+ "grad_norm": 1.0263694524765015,
77
+ "learning_rate": 0.0002,
78
+ "loss": 2.3668,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.06578947368421052,
83
+ "grad_norm": 0.9050750136375427,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.2953,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.07177033492822966,
90
+ "grad_norm": 1.1184417009353638,
91
+ "learning_rate": 0.0002,
92
+ "loss": 2.3101,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07775119617224881,
97
+ "grad_norm": 1.2090150117874146,
98
+ "learning_rate": 0.0002,
99
+ "loss": 2.3292,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.08373205741626795,
104
+ "grad_norm": 2.347069263458252,
105
+ "learning_rate": 0.0002,
106
+ "loss": 2.3108,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08971291866028708,
111
+ "grad_norm": 1.3362812995910645,
112
+ "learning_rate": 0.0002,
113
+ "loss": 2.2901,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.09569377990430622,
118
+ "grad_norm": 0.906521201133728,
119
+ "learning_rate": 0.0002,
120
+ "loss": 2.3137,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.10167464114832536,
125
+ "grad_norm": 0.8491584658622742,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.2915,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.1076555023923445,
132
+ "grad_norm": 0.9403386116027832,
133
+ "learning_rate": 0.0002,
134
+ "loss": 2.2874,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.11363636363636363,
139
+ "grad_norm": 0.7675734758377075,
140
+ "learning_rate": 0.0002,
141
+ "loss": 2.2536,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11961722488038277,
146
+ "grad_norm": 0.8333762288093567,
147
+ "learning_rate": 0.0002,
148
+ "loss": 2.3332,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.1255980861244019,
153
+ "grad_norm": 0.8489273190498352,
154
+ "learning_rate": 0.0002,
155
+ "loss": 2.3112,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.13157894736842105,
160
+ "grad_norm": 1.2032957077026367,
161
+ "learning_rate": 0.0002,
162
+ "loss": 2.2614,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.1375598086124402,
167
+ "grad_norm": 0.8014360070228577,
168
+ "learning_rate": 0.0002,
169
+ "loss": 2.3014,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.14354066985645933,
174
+ "grad_norm": 0.8756849765777588,
175
+ "learning_rate": 0.0002,
176
+ "loss": 2.2626,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.14952153110047847,
181
+ "grad_norm": 1.0479413270950317,
182
+ "learning_rate": 0.0002,
183
+ "loss": 2.2487,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.15550239234449761,
188
+ "grad_norm": 1.6525335311889648,
189
+ "learning_rate": 0.0002,
190
+ "loss": 2.2643,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.16148325358851676,
195
+ "grad_norm": 0.7974942922592163,
196
+ "learning_rate": 0.0002,
197
+ "loss": 2.2983,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.1674641148325359,
202
+ "grad_norm": 0.8229785561561584,
203
+ "learning_rate": 0.0002,
204
+ "loss": 2.27,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.173444976076555,
209
+ "grad_norm": 0.9374330639839172,
210
+ "learning_rate": 0.0002,
211
+ "loss": 2.2322,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.17942583732057416,
216
+ "grad_norm": 0.8249229788780212,
217
+ "learning_rate": 0.0002,
218
+ "loss": 2.3029,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.1854066985645933,
223
+ "grad_norm": 0.8934934735298157,
224
+ "learning_rate": 0.0002,
225
+ "loss": 2.2204,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.19138755980861244,
230
+ "grad_norm": 0.8451672196388245,
231
+ "learning_rate": 0.0002,
232
+ "loss": 2.2576,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.19736842105263158,
237
+ "grad_norm": 0.8721255660057068,
238
+ "learning_rate": 0.0002,
239
+ "loss": 2.2357,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.20334928229665072,
244
+ "grad_norm": 0.9069824814796448,
245
+ "learning_rate": 0.0002,
246
+ "loss": 2.2624,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.20933014354066987,
251
+ "grad_norm": 0.8029842972755432,
252
+ "learning_rate": 0.0002,
253
+ "loss": 2.2697,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.215311004784689,
258
+ "grad_norm": 3.0026650428771973,
259
+ "learning_rate": 0.0002,
260
+ "loss": 2.2058,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.22129186602870812,
265
+ "grad_norm": 0.8026193380355835,
266
+ "learning_rate": 0.0002,
267
+ "loss": 2.2537,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.22727272727272727,
272
+ "grad_norm": 0.770354688167572,
273
+ "learning_rate": 0.0002,
274
+ "loss": 2.3118,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.2332535885167464,
279
+ "grad_norm": 0.822100043296814,
280
+ "learning_rate": 0.0002,
281
+ "loss": 2.2443,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.23923444976076555,
286
+ "grad_norm": 0.8492611050605774,
287
+ "learning_rate": 0.0002,
288
+ "loss": 2.2295,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.2452153110047847,
293
+ "grad_norm": 0.7530927658081055,
294
+ "learning_rate": 0.0002,
295
+ "loss": 2.2321,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.2511961722488038,
300
+ "grad_norm": 0.7999204993247986,
301
+ "learning_rate": 0.0002,
302
+ "loss": 2.2462,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.25717703349282295,
307
+ "grad_norm": 0.765783965587616,
308
+ "learning_rate": 0.0002,
309
+ "loss": 2.2362,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.2631578947368421,
314
+ "grad_norm": 1.9569802284240723,
315
+ "learning_rate": 0.0002,
316
+ "loss": 2.2309,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.26913875598086123,
321
+ "grad_norm": 0.8249408602714539,
322
+ "learning_rate": 0.0002,
323
+ "loss": 2.2433,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.2751196172248804,
328
+ "grad_norm": 0.848108172416687,
329
+ "learning_rate": 0.0002,
330
+ "loss": 2.2013,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.2811004784688995,
335
+ "grad_norm": 0.8488432765007019,
336
+ "learning_rate": 0.0002,
337
+ "loss": 2.2393,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.28708133971291866,
342
+ "grad_norm": 0.7786160111427307,
343
+ "learning_rate": 0.0002,
344
+ "loss": 2.2247,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.2930622009569378,
349
+ "grad_norm": 2.2969539165496826,
350
+ "learning_rate": 0.0002,
351
+ "loss": 2.2523,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.29904306220095694,
356
+ "grad_norm": 0.8230640292167664,
357
+ "learning_rate": 0.0002,
358
+ "loss": 2.2327,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.3050239234449761,
363
+ "grad_norm": 0.8330740928649902,
364
+ "learning_rate": 0.0002,
365
+ "loss": 2.2306,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.31100478468899523,
370
+ "grad_norm": 0.8412021994590759,
371
+ "learning_rate": 0.0002,
372
+ "loss": 2.2299,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.31698564593301437,
377
+ "grad_norm": 0.8107555508613586,
378
+ "learning_rate": 0.0002,
379
+ "loss": 2.264,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.3229665071770335,
384
+ "grad_norm": 2.283083200454712,
385
+ "learning_rate": 0.0002,
386
+ "loss": 2.2085,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.32894736842105265,
391
+ "grad_norm": 0.7781470417976379,
392
+ "learning_rate": 0.0002,
393
+ "loss": 2.2123,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.3349282296650718,
398
+ "grad_norm": 0.7660220265388489,
399
+ "learning_rate": 0.0002,
400
+ "loss": 2.2525,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.3409090909090909,
405
+ "grad_norm": 0.8373708724975586,
406
+ "learning_rate": 0.0002,
407
+ "loss": 2.2142,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.34688995215311,
412
+ "grad_norm": 0.7727882862091064,
413
+ "learning_rate": 0.0002,
414
+ "loss": 2.1824,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.35287081339712917,
419
+ "grad_norm": 0.9092174768447876,
420
+ "learning_rate": 0.0002,
421
+ "loss": 2.1939,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.3588516746411483,
426
+ "grad_norm": 0.8021971583366394,
427
+ "learning_rate": 0.0002,
428
+ "loss": 2.2175,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.36483253588516745,
433
+ "grad_norm": 0.7922872304916382,
434
+ "learning_rate": 0.0002,
435
+ "loss": 2.2079,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.3708133971291866,
440
+ "grad_norm": 1.0842111110687256,
441
+ "learning_rate": 0.0002,
442
+ "loss": 2.1879,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.37679425837320574,
447
+ "grad_norm": 0.9562531113624573,
448
+ "learning_rate": 0.0002,
449
+ "loss": 2.1896,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.3827751196172249,
454
+ "grad_norm": 0.8320727348327637,
455
+ "learning_rate": 0.0002,
456
+ "loss": 2.2254,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.388755980861244,
461
+ "grad_norm": 0.80451899766922,
462
+ "learning_rate": 0.0002,
463
+ "loss": 2.2144,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.39473684210526316,
468
+ "grad_norm": 0.7288826704025269,
469
+ "learning_rate": 0.0002,
470
+ "loss": 2.2349,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.4007177033492823,
475
+ "grad_norm": 0.8023431897163391,
476
+ "learning_rate": 0.0002,
477
+ "loss": 2.2037,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.40669856459330145,
482
+ "grad_norm": 0.8532123565673828,
483
+ "learning_rate": 0.0002,
484
+ "loss": 2.2314,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.4126794258373206,
489
+ "grad_norm": 0.7851171493530273,
490
+ "learning_rate": 0.0002,
491
+ "loss": 2.185,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.41866028708133973,
496
+ "grad_norm": 0.8515769243240356,
497
+ "learning_rate": 0.0002,
498
+ "loss": 2.232,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.4246411483253589,
503
+ "grad_norm": 0.782311201095581,
504
+ "learning_rate": 0.0002,
505
+ "loss": 2.1859,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.430622009569378,
510
+ "grad_norm": 0.7590478658676147,
511
+ "learning_rate": 0.0002,
512
+ "loss": 2.1837,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.4366028708133971,
517
+ "grad_norm": 0.7843049168586731,
518
+ "learning_rate": 0.0002,
519
+ "loss": 2.2069,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.44258373205741625,
524
+ "grad_norm": 0.7173344492912292,
525
+ "learning_rate": 0.0002,
526
+ "loss": 2.1989,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.4485645933014354,
531
+ "grad_norm": 0.8669169545173645,
532
+ "learning_rate": 0.0002,
533
+ "loss": 2.1941,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.45454545454545453,
538
+ "grad_norm": 1.45564603805542,
539
+ "learning_rate": 0.0002,
540
+ "loss": 2.2045,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.4605263157894737,
545
+ "grad_norm": 0.8243363499641418,
546
+ "learning_rate": 0.0002,
547
+ "loss": 2.1819,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.4665071770334928,
552
+ "grad_norm": 0.8817090392112732,
553
+ "learning_rate": 0.0002,
554
+ "loss": 2.1533,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.47248803827751196,
559
+ "grad_norm": 0.82022625207901,
560
+ "learning_rate": 0.0002,
561
+ "loss": 2.243,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.4784688995215311,
566
+ "grad_norm": 0.8863716721534729,
567
+ "learning_rate": 0.0002,
568
+ "loss": 2.1638,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.48444976076555024,
573
+ "grad_norm": 0.7413605451583862,
574
+ "learning_rate": 0.0002,
575
+ "loss": 2.2107,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.4904306220095694,
580
+ "grad_norm": 0.8566731810569763,
581
+ "learning_rate": 0.0002,
582
+ "loss": 2.148,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.4964114832535885,
587
+ "grad_norm": 0.9010487794876099,
588
+ "learning_rate": 0.0002,
589
+ "loss": 2.1828,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.5023923444976076,
594
+ "grad_norm": 0.8197215795516968,
595
+ "learning_rate": 0.0002,
596
+ "loss": 2.1683,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.5083732057416268,
601
+ "grad_norm": 0.9159034490585327,
602
+ "learning_rate": 0.0002,
603
+ "loss": 2.2269,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.5143540669856459,
608
+ "grad_norm": 0.8410281538963318,
609
+ "learning_rate": 0.0002,
610
+ "loss": 2.2111,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.5203349282296651,
615
+ "grad_norm": 1.8926668167114258,
616
+ "learning_rate": 0.0002,
617
+ "loss": 2.1884,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.5263157894736842,
622
+ "grad_norm": 1.0006904602050781,
623
+ "learning_rate": 0.0002,
624
+ "loss": 2.192,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.5322966507177034,
629
+ "grad_norm": 0.7826078534126282,
630
+ "learning_rate": 0.0002,
631
+ "loss": 2.1894,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.5382775119617225,
636
+ "grad_norm": 0.8574744462966919,
637
+ "learning_rate": 0.0002,
638
+ "loss": 2.1854,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.5442583732057417,
643
+ "grad_norm": 0.9018279314041138,
644
+ "learning_rate": 0.0002,
645
+ "loss": 2.1725,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.5502392344497608,
650
+ "grad_norm": 1.3028662204742432,
651
+ "learning_rate": 0.0002,
652
+ "loss": 2.1944,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.55622009569378,
657
+ "grad_norm": 0.8321689367294312,
658
+ "learning_rate": 0.0002,
659
+ "loss": 2.1652,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.562200956937799,
664
+ "grad_norm": 0.7999281287193298,
665
+ "learning_rate": 0.0002,
666
+ "loss": 2.2041,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.5681818181818182,
671
+ "grad_norm": 4.9575629234313965,
672
+ "learning_rate": 0.0002,
673
+ "loss": 2.2154,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.5741626794258373,
678
+ "grad_norm": 0.7689957022666931,
679
+ "learning_rate": 0.0002,
680
+ "loss": 2.1695,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.5801435406698564,
685
+ "grad_norm": 0.9012035131454468,
686
+ "learning_rate": 0.0002,
687
+ "loss": 2.1557,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.5861244019138756,
692
+ "grad_norm": 0.8276737928390503,
693
+ "learning_rate": 0.0002,
694
+ "loss": 2.1906,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.5921052631578947,
699
+ "grad_norm": 0.9128056168556213,
700
+ "learning_rate": 0.0002,
701
+ "loss": 2.1445,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.5980861244019139,
706
+ "grad_norm": 0.8623008131980896,
707
+ "learning_rate": 0.0002,
708
+ "loss": 2.1852,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.604066985645933,
713
+ "grad_norm": 0.7866010665893555,
714
+ "learning_rate": 0.0002,
715
+ "loss": 2.173,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.6100478468899522,
720
+ "grad_norm": 0.8097877502441406,
721
+ "learning_rate": 0.0002,
722
+ "loss": 2.1324,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.6160287081339713,
727
+ "grad_norm": 0.8153032660484314,
728
+ "learning_rate": 0.0002,
729
+ "loss": 2.1271,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.6220095693779905,
734
+ "grad_norm": 0.7427578568458557,
735
+ "learning_rate": 0.0002,
736
+ "loss": 2.1617,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.6279904306220095,
741
+ "grad_norm": 0.8749725222587585,
742
+ "learning_rate": 0.0002,
743
+ "loss": 2.1961,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.6339712918660287,
748
+ "grad_norm": 0.7804417610168457,
749
+ "learning_rate": 0.0002,
750
+ "loss": 2.1782,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.6399521531100478,
755
+ "grad_norm": 0.8692734837532043,
756
+ "learning_rate": 0.0002,
757
+ "loss": 2.1852,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.645933014354067,
762
+ "grad_norm": 0.8000411987304688,
763
+ "learning_rate": 0.0002,
764
+ "loss": 2.1628,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.6519138755980861,
769
+ "grad_norm": 0.9027504324913025,
770
+ "learning_rate": 0.0002,
771
+ "loss": 2.1666,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.6578947368421053,
776
+ "grad_norm": 0.8674067854881287,
777
+ "learning_rate": 0.0002,
778
+ "loss": 2.1394,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.6638755980861244,
783
+ "grad_norm": 1.3791645765304565,
784
+ "learning_rate": 0.0002,
785
+ "loss": 2.1626,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.6698564593301436,
790
+ "grad_norm": 0.8177993297576904,
791
+ "learning_rate": 0.0002,
792
+ "loss": 2.1664,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.6758373205741627,
797
+ "grad_norm": 0.8040952682495117,
798
+ "learning_rate": 0.0002,
799
+ "loss": 2.1603,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.6818181818181818,
804
+ "grad_norm": 0.8698276281356812,
805
+ "learning_rate": 0.0002,
806
+ "loss": 2.2068,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.687799043062201,
811
+ "grad_norm": 0.8038722276687622,
812
+ "learning_rate": 0.0002,
813
+ "loss": 2.1528,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.69377990430622,
818
+ "grad_norm": 0.8705615401268005,
819
+ "learning_rate": 0.0002,
820
+ "loss": 2.1538,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.6997607655502392,
825
+ "grad_norm": 0.9985973834991455,
826
+ "learning_rate": 0.0002,
827
+ "loss": 2.1686,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.7057416267942583,
832
+ "grad_norm": 0.7473865747451782,
833
+ "learning_rate": 0.0002,
834
+ "loss": 2.2257,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.7117224880382775,
839
+ "grad_norm": 0.8028366565704346,
840
+ "learning_rate": 0.0002,
841
+ "loss": 2.1712,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.7177033492822966,
846
+ "grad_norm": 0.767857551574707,
847
+ "learning_rate": 0.0002,
848
+ "loss": 2.1782,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.7236842105263158,
853
+ "grad_norm": 0.7830066680908203,
854
+ "learning_rate": 0.0002,
855
+ "loss": 2.1488,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.7296650717703349,
860
+ "grad_norm": 0.8238586783409119,
861
+ "learning_rate": 0.0002,
862
+ "loss": 2.1588,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.7356459330143541,
867
+ "grad_norm": 0.7727087140083313,
868
+ "learning_rate": 0.0002,
869
+ "loss": 2.1398,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.7416267942583732,
874
+ "grad_norm": 0.8918077945709229,
875
+ "learning_rate": 0.0002,
876
+ "loss": 2.1829,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.7476076555023924,
881
+ "grad_norm": 1.202504277229309,
882
+ "learning_rate": 0.0002,
883
+ "loss": 2.1784,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.7535885167464115,
888
+ "grad_norm": 0.8316906094551086,
889
+ "learning_rate": 0.0002,
890
+ "loss": 2.1806,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.7595693779904307,
895
+ "grad_norm": 0.7766339182853699,
896
+ "learning_rate": 0.0002,
897
+ "loss": 2.1577,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.7655502392344498,
902
+ "grad_norm": 0.9902828931808472,
903
+ "learning_rate": 0.0002,
904
+ "loss": 2.1519,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.7715311004784688,
909
+ "grad_norm": 0.895126461982727,
910
+ "learning_rate": 0.0002,
911
+ "loss": 2.1712,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.777511961722488,
916
+ "grad_norm": 0.8055546879768372,
917
+ "learning_rate": 0.0002,
918
+ "loss": 2.1814,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.7834928229665071,
923
+ "grad_norm": 0.7867780327796936,
924
+ "learning_rate": 0.0002,
925
+ "loss": 2.1507,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.7894736842105263,
930
+ "grad_norm": 0.8065791726112366,
931
+ "learning_rate": 0.0002,
932
+ "loss": 2.2211,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.7954545454545454,
937
+ "grad_norm": 1.5913640260696411,
938
+ "learning_rate": 0.0002,
939
+ "loss": 2.2257,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.8014354066985646,
944
+ "grad_norm": 0.7849767208099365,
945
+ "learning_rate": 0.0002,
946
+ "loss": 2.1893,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.8074162679425837,
951
+ "grad_norm": 0.7633355855941772,
952
+ "learning_rate": 0.0002,
953
+ "loss": 2.1956,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.8133971291866029,
958
+ "grad_norm": 0.8164528608322144,
959
+ "learning_rate": 0.0002,
960
+ "loss": 2.2224,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.819377990430622,
965
+ "grad_norm": 0.7906235456466675,
966
+ "learning_rate": 0.0002,
967
+ "loss": 2.1833,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.8253588516746412,
972
+ "grad_norm": 0.8774910569190979,
973
+ "learning_rate": 0.0002,
974
+ "loss": 2.1471,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.8313397129186603,
979
+ "grad_norm": 0.8200404644012451,
980
+ "learning_rate": 0.0002,
981
+ "loss": 2.1554,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.8373205741626795,
986
+ "grad_norm": 0.7728098630905151,
987
+ "learning_rate": 0.0002,
988
+ "loss": 2.2009,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.8433014354066986,
993
+ "grad_norm": 0.7523846626281738,
994
+ "learning_rate": 0.0002,
995
+ "loss": 2.2052,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.8492822966507177,
1000
+ "grad_norm": 0.8525931239128113,
1001
+ "learning_rate": 0.0002,
1002
+ "loss": 2.1811,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.8552631578947368,
1007
+ "grad_norm": 0.7875164747238159,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 2.1308,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.861244019138756,
1014
+ "grad_norm": 0.7879646420478821,
1015
+ "learning_rate": 0.0002,
1016
+ "loss": 2.1665,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.8672248803827751,
1021
+ "grad_norm": 0.7715153694152832,
1022
+ "learning_rate": 0.0002,
1023
+ "loss": 2.1593,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.8732057416267942,
1028
+ "grad_norm": 0.8685998320579529,
1029
+ "learning_rate": 0.0002,
1030
+ "loss": 2.18,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.8791866028708134,
1035
+ "grad_norm": 0.8396874666213989,
1036
+ "learning_rate": 0.0002,
1037
+ "loss": 2.1639,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.8851674641148325,
1042
+ "grad_norm": 0.8163192272186279,
1043
+ "learning_rate": 0.0002,
1044
+ "loss": 2.1742,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.8911483253588517,
1049
+ "grad_norm": 0.8341553211212158,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 2.1569,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.8971291866028708,
1056
+ "grad_norm": 0.7632786631584167,
1057
+ "learning_rate": 0.0002,
1058
+ "loss": 2.1596,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.90311004784689,
1063
+ "grad_norm": 0.7861719131469727,
1064
+ "learning_rate": 0.0002,
1065
+ "loss": 2.1853,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.9090909090909091,
1070
+ "grad_norm": 0.8243244886398315,
1071
+ "learning_rate": 0.0002,
1072
+ "loss": 2.1695,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.9150717703349283,
1077
+ "grad_norm": 0.760749876499176,
1078
+ "learning_rate": 0.0002,
1079
+ "loss": 2.1501,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.9210526315789473,
1084
+ "grad_norm": 0.9622604250907898,
1085
+ "learning_rate": 0.0002,
1086
+ "loss": 2.1256,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.9270334928229665,
1091
+ "grad_norm": 0.7732083797454834,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 2.1433,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.9330143540669856,
1098
+ "grad_norm": 0.7828539609909058,
1099
+ "learning_rate": 0.0002,
1100
+ "loss": 2.1356,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.9389952153110048,
1105
+ "grad_norm": 0.8860824704170227,
1106
+ "learning_rate": 0.0002,
1107
+ "loss": 2.1525,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.9449760765550239,
1112
+ "grad_norm": 0.8569679260253906,
1113
+ "learning_rate": 0.0002,
1114
+ "loss": 2.1501,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.9509569377990431,
1119
+ "grad_norm": 0.7966086864471436,
1120
+ "learning_rate": 0.0002,
1121
+ "loss": 2.1484,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.9569377990430622,
1126
+ "grad_norm": 0.7861948609352112,
1127
+ "learning_rate": 0.0002,
1128
+ "loss": 2.1461,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.9629186602870813,
1133
+ "grad_norm": 0.8073152303695679,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 2.1681,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.9688995215311005,
1140
+ "grad_norm": 0.8233998417854309,
1141
+ "learning_rate": 0.0002,
1142
+ "loss": 2.1513,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.9748803827751196,
1147
+ "grad_norm": 0.836236834526062,
1148
+ "learning_rate": 0.0002,
1149
+ "loss": 2.1665,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.9808612440191388,
1154
+ "grad_norm": 0.7221957445144653,
1155
+ "learning_rate": 0.0002,
1156
+ "loss": 2.1079,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.9868421052631579,
1161
+ "grad_norm": 0.7149819731712341,
1162
+ "learning_rate": 0.0002,
1163
+ "loss": 2.1858,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.992822966507177,
1168
+ "grad_norm": 0.7578993439674377,
1169
+ "learning_rate": 0.0002,
1170
+ "loss": 2.1467,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.9988038277511961,
1175
+ "grad_norm": 1.0370241403579712,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 2.1626,
1178
+ "step": 4175
1179
+ }
1180
+ ],
1181
+ "logging_steps": 25,
1182
+ "max_steps": 4180,
1183
+ "num_input_tokens_seen": 0,
1184
+ "num_train_epochs": 1,
1185
+ "save_steps": 25,
1186
+ "stateful_callbacks": {
1187
+ "TrainerControl": {
1188
+ "args": {
1189
+ "should_epoch_stop": false,
1190
+ "should_evaluate": false,
1191
+ "should_log": false,
1192
+ "should_save": true,
1193
+ "should_training_stop": true
1194
+ },
1195
+ "attributes": {}
1196
+ }
1197
+ },
1198
+ "total_flos": 1.194945264893952e+17,
1199
+ "train_batch_size": 16,
1200
+ "trial_name": null,
1201
+ "trial_params": null
1202
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b824497097c522678a8778785e9d54a6abfee1cafad9106a72ffee52ab5983ed
3
- size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ece2cecece1fcae39040b74581428f594292a4f3d733443c4954ce8373a446f
3
+ size 5496