AlekseyKorshuk commited on
Commit
98fedb0
1 Parent(s): 56179bd

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/slava-kpss
5
+ tags:
6
+ - huggingartists
7
+ - lyrics
8
+ - lm-head
9
+ - causal-lm
10
+ widget:
11
+ - text: "I am"
12
+ ---
13
+
14
+ <div class="inline-flex flex-col" style="line-height: 1.5;">
15
+ <div class="flex">
16
+ <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/e63e3a804916ed71bf2941ac4e190063.847x847x1.jpg&#39;)">
18
+ </div>
19
+ </div>
20
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
21
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Слава КПСС (Slava KPSS)</div>
22
+ <a href="https://genius.com/artists/slava-kpss">
23
+ <div style="text-align: center; font-size: 14px;">@slava-kpss</div>
24
+ </a>
25
+ </div>
26
+
27
+ I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
28
+
29
+ Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
30
+
31
+ ## How does it work?
32
+
33
+ To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
34
+
35
+ ## Training data
36
+
37
+ The model was trained on lyrics from Слава КПСС (Slava KPSS).
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/slava-kpss).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/slava-kpss")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/foqrsz9e/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
+
50
+ ## Training procedure
51
+
52
+ The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Слава КПСС (Slava KPSS)'s lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1w16q2jl) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1w16q2jl/artifacts) is logged and versioned.
57
+
58
+ ## How to use
59
+
60
+ You can use this model directly with a pipeline for text generation:
61
+
62
+ ```python
63
+ from transformers import pipeline
64
+ generator = pipeline('text-generation',
65
+ model='huggingartists/slava-kpss')
66
+ generator("I am", num_return_sequences=5)
67
+ ```
68
+
69
+ Or with Transformers library:
70
+
71
+ ```python
72
+ from transformers import AutoTokenizer, AutoModelWithLMHead
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained("huggingartists/slava-kpss")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/slava-kpss")
77
+ ```
78
+
79
+ ## Limitations and bias
80
+
81
+ The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
82
+
83
+ In addition, the data present in the user's tweets further affects the text generated by the model.
84
+
85
+ ## About
86
+
87
+ *Built by Aleksey Korshuk*
88
+
89
+ [![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
90
+
91
+ [![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
92
+
93
+ [![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
94
+
95
+ For more details, visit the project repository.
96
+
97
+ [![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 200,
32
+ "min_length": 100,
33
+ "temperature": 1.0,
34
+ "top_p": 0.95
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.10.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 1.7264798879623413, "eval_runtime": 80.0703, "eval_samples_per_second": 20.482, "eval_steps_per_second": 2.56, "epoch": 1.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337deda3e932cb8b9f9f45178fc4d42a4910182f8b2421baf2b41f81f8b5ed78
3
+ size 497764120
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b98963ca82fe7af24587df78468bdd55174ccee367ffeb555b4c0f8139cb2bc
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b79b39a5680447ab02ef00986c994924e2e55dbc55860448f00a8a0e01a1b45
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8613dacebf19a39d9111a86da44f69693a925419e314a219b17a1de0c3c2ef8f
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa1d50b5048030f9eea3f4e31d95b58aad9c69608bc50ec31c69b287312d0da
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,1140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.7264798879623413,
3
+ "best_model_checkpoint": "output/slava-kpss/checkpoint-933",
4
+ "epoch": 1.0,
5
+ "global_step": 933,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0001371902778945302,
13
+ "loss": 2.663,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.00013716111433378645,
19
+ "loss": 2.4309,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 0.00013711251758398495,
25
+ "loss": 2.2912,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 0.0001370445014195492,
31
+ "loss": 2.3384,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 0.00013695708511920587,
37
+ "loss": 2.2697,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 0.0001368502934605203,
43
+ "loss": 2.2379,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 0.00013672415671287354,
49
+ "loss": 2.1656,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 0.00013657871062888258,
55
+ "loss": 2.1628,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00013641399643426666,
61
+ "loss": 2.1289,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.000136230060816162,
67
+ "loss": 2.09,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.00013602695590988865,
73
+ "loss": 2.0049,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 0.0001358047392841732,
79
+ "loss": 2.2023,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.00013556347392483116,
85
+ "loss": 2.1472,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "learning_rate": 0.00013530322821691406,
91
+ "loss": 2.0605,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 0.00013502407592532636,
97
+ "loss": 2.1713,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 0.00013472609617391705,
103
+ "loss": 2.0815,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 0.0001344093734230526,
109
+ "loss": 1.998,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 0.00013407399744567734,
115
+ "loss": 1.9623,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 0.00013372006330186772,
121
+ "loss": 2.0139,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 0.00013334767131188837,
127
+ "loss": 2.0258,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "learning_rate": 0.00013295692702775685,
133
+ "loss": 1.9965,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 0.00013254794120332568,
139
+ "loss": 2.0578,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 0.00013212082976288994,
145
+ "loss": 1.9713,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 0.00013167571376832926,
151
+ "loss": 2.0398,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.13,
156
+ "learning_rate": 0.00013121271938479367,
157
+ "loss": 1.9906,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.14,
162
+ "learning_rate": 0.00013073197784494285,
163
+ "loss": 1.9652,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.14,
168
+ "learning_rate": 0.0001302336254117493,
169
+ "loss": 1.9658,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "learning_rate": 0.00012971780333987523,
175
+ "loss": 2.0634,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.16,
180
+ "learning_rate": 0.00012918465783563518,
181
+ "loss": 2.0384,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.16,
186
+ "learning_rate": 0.00012863434001555456,
187
+ "loss": 1.9783,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 0.00012806700586353683,
193
+ "loss": 2.0149,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.17,
198
+ "learning_rate": 0.00012748281618665092,
199
+ "loss": 1.9433,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 0.00012688193656955137,
205
+ "loss": 2.0019,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.18,
210
+ "learning_rate": 0.0001262645373275447,
211
+ "loss": 2.036,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "learning_rate": 0.0001256307934583145,
217
+ "loss": 1.9862,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.19,
222
+ "learning_rate": 0.00012498088459231957,
223
+ "loss": 1.9842,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.2,
228
+ "learning_rate": 0.00012431499494187896,
229
+ "loss": 2.0212,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.2,
234
+ "learning_rate": 0.000123633313248958,
235
+ "loss": 1.8205,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.21,
240
+ "learning_rate": 0.00012293603273167084,
241
+ "loss": 2.0015,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.21,
246
+ "learning_rate": 0.00012222335102951405,
247
+ "loss": 1.8653,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.22,
252
+ "learning_rate": 0.00012149547014734692,
253
+ "loss": 2.0522,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.23,
258
+ "learning_rate": 0.00012075259639813464,
259
+ "loss": 1.8885,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.23,
264
+ "learning_rate": 0.00011999494034447026,
265
+ "loss": 1.8864,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.24,
270
+ "learning_rate": 0.00011922271673889206,
271
+ "loss": 1.9415,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.24,
276
+ "learning_rate": 0.00011843614446301341,
277
+ "loss": 1.9542,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.25,
282
+ "learning_rate": 0.00011763544646548234,
283
+ "loss": 1.8528,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.25,
288
+ "learning_rate": 0.00011682084969878809,
289
+ "loss": 1.8431,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.26,
294
+ "learning_rate": 0.00011599258505493302,
295
+ "loss": 1.9018,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "learning_rate": 0.0001151508872999878,
301
+ "loss": 1.8971,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.27,
306
+ "learning_rate": 0.00011429599500754859,
307
+ "loss": 1.9842,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.27,
312
+ "learning_rate": 0.00011342815049111488,
313
+ "loss": 1.8397,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.28,
318
+ "learning_rate": 0.00011254759973540735,
319
+ "loss": 1.854,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.28,
324
+ "learning_rate": 0.0001116545923266452,
325
+ "loss": 1.9264,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.29,
330
+ "learning_rate": 0.00011074938138180258,
331
+ "loss": 1.833,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.29,
336
+ "learning_rate": 0.00010983222347686431,
337
+ "loss": 1.8783,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "learning_rate": 0.00010890337857410102,
343
+ "loss": 1.8777,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.31,
348
+ "learning_rate": 0.00010796310994838476,
349
+ "loss": 1.8851,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.31,
354
+ "learning_rate": 0.00010701168411256533,
355
+ "loss": 1.8735,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.32,
360
+ "learning_rate": 0.0001060493707419291,
361
+ "loss": 1.9696,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.32,
366
+ "learning_rate": 0.00010507644259776136,
367
+ "loss": 1.8878,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 0.33,
372
+ "learning_rate": 0.00010409317545003389,
373
+ "loss": 1.8279,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 0.33,
378
+ "learning_rate": 0.0001030998479992398,
379
+ "loss": 1.9672,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "learning_rate": 0.00010209674179739785,
385
+ "loss": 1.889,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 0.34,
390
+ "learning_rate": 0.00010108414116824834,
391
+ "loss": 1.8617,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "learning_rate": 0.00010006233312666341,
397
+ "loss": 1.9077,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 0.35,
402
+ "learning_rate": 9.90316072972947e-05,
403
+ "loss": 1.8912,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 0.36,
408
+ "learning_rate": 9.79922558324811e-05,
409
+ "loss": 1.7622,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 0.36,
414
+ "learning_rate": 9.694457332944009e-05,
415
+ "loss": 1.8778,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 0.37,
420
+ "learning_rate": 9.588885674676624e-05,
421
+ "loss": 1.8761,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 0.38,
426
+ "learning_rate": 9.482540532026027e-05,
427
+ "loss": 1.8225,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 0.38,
432
+ "learning_rate": 9.37545204781125e-05,
433
+ "loss": 1.7817,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 0.39,
438
+ "learning_rate": 9.26765057554653e-05,
439
+ "loss": 1.7633,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 0.39,
444
+ "learning_rate": 9.159166670837789e-05,
445
+ "loss": 1.8406,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 0.4,
450
+ "learning_rate": 9.05003108272186e-05,
451
+ "loss": 1.9374,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 0.4,
456
+ "learning_rate": 8.940274744950875e-05,
457
+ "loss": 1.8444,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 0.41,
462
+ "learning_rate": 8.829928767224302e-05,
463
+ "loss": 1.8098,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 0.41,
468
+ "learning_rate": 8.71902442637111e-05,
469
+ "loss": 1.822,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 0.42,
474
+ "learning_rate": 8.607593157484563e-05,
475
+ "loss": 1.87,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 0.42,
480
+ "learning_rate": 8.495666545012144e-05,
481
+ "loss": 1.8821,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 0.43,
486
+ "learning_rate": 8.383276313803162e-05,
487
+ "loss": 1.8619,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 0.43,
492
+ "learning_rate": 8.270454320116558e-05,
493
+ "loss": 1.896,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 0.44,
498
+ "learning_rate": 8.157232542591454e-05,
499
+ "loss": 1.776,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 0.44,
504
+ "learning_rate": 8.043643073183026e-05,
505
+ "loss": 1.8886,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "learning_rate": 7.92971810806626e-05,
511
+ "loss": 1.8725,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 0.46,
516
+ "learning_rate": 7.815489938510145e-05,
517
+ "loss": 1.8305,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 0.46,
522
+ "learning_rate": 7.700990941724947e-05,
523
+ "loss": 1.8383,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 0.47,
528
+ "learning_rate": 7.586253571685095e-05,
529
+ "loss": 1.872,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 0.47,
534
+ "learning_rate": 7.471310349930326e-05,
535
+ "loss": 1.8617,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 0.48,
540
+ "learning_rate": 7.356193856347655e-05,
541
+ "loss": 1.8118,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 0.48,
546
+ "learning_rate": 7.24093671993686e-05,
547
+ "loss": 1.8363,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "learning_rate": 7.125571609561963e-05,
553
+ "loss": 1.7498,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 0.49,
558
+ "learning_rate": 7.010131224691501e-05,
559
+ "loss": 1.8902,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 0.5,
564
+ "learning_rate": 6.894648286130055e-05,
565
+ "loss": 1.9075,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 0.5,
570
+ "learning_rate": 6.779155526743765e-05,
571
+ "loss": 1.8081,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 0.51,
576
+ "learning_rate": 6.66368568218242e-05,
577
+ "loss": 1.8239,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 0.51,
582
+ "learning_rate": 6.548271481600758e-05,
583
+ "loss": 1.8584,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 0.52,
588
+ "learning_rate": 6.432945638381598e-05,
589
+ "loss": 1.9037,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 0.53,
594
+ "learning_rate": 6.317740840863456e-05,
595
+ "loss": 1.7551,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 0.53,
600
+ "learning_rate": 6.202689743075261e-05,
601
+ "loss": 1.8329,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 0.54,
606
+ "learning_rate": 6.0878249554807756e-05,
607
+ "loss": 1.7776,
608
+ "step": 500
609
+ },
610
+ {
611
+ "epoch": 0.54,
612
+ "learning_rate": 5.9731790357353845e-05,
613
+ "loss": 1.8987,
614
+ "step": 505
615
+ },
616
+ {
617
+ "epoch": 0.55,
618
+ "learning_rate": 5.8587844794578496e-05,
619
+ "loss": 1.6097,
620
+ "step": 510
621
+ },
622
+ {
623
+ "epoch": 0.55,
624
+ "learning_rate": 5.744673711019635e-05,
625
+ "loss": 1.8081,
626
+ "step": 515
627
+ },
628
+ {
629
+ "epoch": 0.56,
630
+ "learning_rate": 5.630879074354446e-05,
631
+ "loss": 1.8023,
632
+ "step": 520
633
+ },
634
+ {
635
+ "epoch": 0.56,
636
+ "learning_rate": 5.517432823790546e-05,
637
+ "loss": 1.709,
638
+ "step": 525
639
+ },
640
+ {
641
+ "epoch": 0.57,
642
+ "learning_rate": 5.404367114908498e-05,
643
+ "loss": 1.7632,
644
+ "step": 530
645
+ },
646
+ {
647
+ "epoch": 0.57,
648
+ "learning_rate": 5.291713995426862e-05,
649
+ "loss": 1.796,
650
+ "step": 535
651
+ },
652
+ {
653
+ "epoch": 0.58,
654
+ "learning_rate": 5.179505396118502e-05,
655
+ "loss": 1.7405,
656
+ "step": 540
657
+ },
658
+ {
659
+ "epoch": 0.58,
660
+ "learning_rate": 5.067773121760007e-05,
661
+ "loss": 1.8264,
662
+ "step": 545
663
+ },
664
+ {
665
+ "epoch": 0.59,
666
+ "learning_rate": 4.9565488421168504e-05,
667
+ "loss": 1.8083,
668
+ "step": 550
669
+ },
670
+ {
671
+ "epoch": 0.59,
672
+ "learning_rate": 4.8458640829668e-05,
673
+ "loss": 1.7488,
674
+ "step": 555
675
+ },
676
+ {
677
+ "epoch": 0.6,
678
+ "learning_rate": 4.735750217164156e-05,
679
+ "loss": 1.8385,
680
+ "step": 560
681
+ },
682
+ {
683
+ "epoch": 0.61,
684
+ "learning_rate": 4.6262384557473104e-05,
685
+ "loss": 1.8445,
686
+ "step": 565
687
+ },
688
+ {
689
+ "epoch": 0.61,
690
+ "learning_rate": 4.517359839092207e-05,
691
+ "loss": 1.7808,
692
+ "step": 570
693
+ },
694
+ {
695
+ "epoch": 0.62,
696
+ "learning_rate": 4.409145228114133e-05,
697
+ "loss": 1.7932,
698
+ "step": 575
699
+ },
700
+ {
701
+ "epoch": 0.62,
702
+ "learning_rate": 4.3016252955204197e-05,
703
+ "loss": 1.7931,
704
+ "step": 580
705
+ },
706
+ {
707
+ "epoch": 0.63,
708
+ "learning_rate": 4.1948305171164515e-05,
709
+ "loss": 1.7508,
710
+ "step": 585
711
+ },
712
+ {
713
+ "epoch": 0.63,
714
+ "learning_rate": 4.08879116316751e-05,
715
+ "loss": 1.7877,
716
+ "step": 590
717
+ },
718
+ {
719
+ "epoch": 0.64,
720
+ "learning_rate": 3.98353728981888e-05,
721
+ "loss": 1.8233,
722
+ "step": 595
723
+ },
724
+ {
725
+ "epoch": 0.64,
726
+ "learning_rate": 3.879098730576618e-05,
727
+ "loss": 1.8181,
728
+ "step": 600
729
+ },
730
+ {
731
+ "epoch": 0.65,
732
+ "learning_rate": 3.7755050878514536e-05,
733
+ "loss": 1.6906,
734
+ "step": 605
735
+ },
736
+ {
737
+ "epoch": 0.65,
738
+ "learning_rate": 3.672785724568185e-05,
739
+ "loss": 1.7465,
740
+ "step": 610
741
+ },
742
+ {
743
+ "epoch": 0.66,
744
+ "learning_rate": 3.570969755842952e-05,
745
+ "loss": 1.7276,
746
+ "step": 615
747
+ },
748
+ {
749
+ "epoch": 0.66,
750
+ "learning_rate": 3.4700860407307565e-05,
751
+ "loss": 1.7561,
752
+ "step": 620
753
+ },
754
+ {
755
+ "epoch": 0.67,
756
+ "learning_rate": 3.3701631740455454e-05,
757
+ "loss": 1.8063,
758
+ "step": 625
759
+ },
760
+ {
761
+ "epoch": 0.68,
762
+ "learning_rate": 3.271229478255218e-05,
763
+ "loss": 1.6319,
764
+ "step": 630
765
+ },
766
+ {
767
+ "epoch": 0.68,
768
+ "learning_rate": 3.173312995453793e-05,
769
+ "loss": 1.7234,
770
+ "step": 635
771
+ },
772
+ {
773
+ "epoch": 0.69,
774
+ "learning_rate": 3.07644147941308e-05,
775
+ "loss": 1.811,
776
+ "step": 640
777
+ },
778
+ {
779
+ "epoch": 0.69,
780
+ "learning_rate": 2.9806423877160492e-05,
781
+ "loss": 1.8344,
782
+ "step": 645
783
+ },
784
+ {
785
+ "epoch": 0.7,
786
+ "learning_rate": 2.8859428739741754e-05,
787
+ "loss": 1.7602,
788
+ "step": 650
789
+ },
790
+ {
791
+ "epoch": 0.7,
792
+ "learning_rate": 2.7923697801309092e-05,
793
+ "loss": 1.8365,
794
+ "step": 655
795
+ },
796
+ {
797
+ "epoch": 0.71,
798
+ "learning_rate": 2.699949628853528e-05,
799
+ "loss": 1.7506,
800
+ "step": 660
801
+ },
802
+ {
803
+ "epoch": 0.71,
804
+ "learning_rate": 2.60870861601545e-05,
805
+ "loss": 1.7098,
806
+ "step": 665
807
+ },
808
+ {
809
+ "epoch": 0.72,
810
+ "learning_rate": 2.518672603271192e-05,
811
+ "loss": 1.8215,
812
+ "step": 670
813
+ },
814
+ {
815
+ "epoch": 0.72,
816
+ "learning_rate": 2.429867110726057e-05,
817
+ "loss": 1.8035,
818
+ "step": 675
819
+ },
820
+ {
821
+ "epoch": 0.73,
822
+ "learning_rate": 2.3423173097026407e-05,
823
+ "loss": 1.7455,
824
+ "step": 680
825
+ },
826
+ {
827
+ "epoch": 0.73,
828
+ "learning_rate": 2.25604801560617e-05,
829
+ "loss": 1.8008,
830
+ "step": 685
831
+ },
832
+ {
833
+ "epoch": 0.74,
834
+ "learning_rate": 2.1710836808907555e-05,
835
+ "loss": 1.7584,
836
+ "step": 690
837
+ },
838
+ {
839
+ "epoch": 0.74,
840
+ "learning_rate": 2.0874483881285084e-05,
841
+ "loss": 1.7836,
842
+ "step": 695
843
+ },
844
+ {
845
+ "epoch": 0.75,
846
+ "learning_rate": 2.0051658431834844e-05,
847
+ "loss": 1.7353,
848
+ "step": 700
849
+ },
850
+ {
851
+ "epoch": 0.76,
852
+ "learning_rate": 1.924259368492425e-05,
853
+ "loss": 1.7518,
854
+ "step": 705
855
+ },
856
+ {
857
+ "epoch": 0.76,
858
+ "learning_rate": 1.844751896454173e-05,
859
+ "loss": 1.7968,
860
+ "step": 710
861
+ },
862
+ {
863
+ "epoch": 0.77,
864
+ "learning_rate": 1.766665962929623e-05,
865
+ "loss": 1.751,
866
+ "step": 715
867
+ },
868
+ {
869
+ "epoch": 0.77,
870
+ "learning_rate": 1.6900237008540944e-05,
871
+ "loss": 1.7056,
872
+ "step": 720
873
+ },
874
+ {
875
+ "epoch": 0.78,
876
+ "learning_rate": 1.6148468339638933e-05,
877
+ "loss": 1.7457,
878
+ "step": 725
879
+ },
880
+ {
881
+ "epoch": 0.78,
882
+ "learning_rate": 1.5411566706388707e-05,
883
+ "loss": 1.7712,
884
+ "step": 730
885
+ },
886
+ {
887
+ "epoch": 0.79,
888
+ "learning_rate": 1.4689740978626948e-05,
889
+ "loss": 1.7609,
890
+ "step": 735
891
+ },
892
+ {
893
+ "epoch": 0.79,
894
+ "learning_rate": 1.3983195753025887e-05,
895
+ "loss": 1.7358,
896
+ "step": 740
897
+ },
898
+ {
899
+ "epoch": 0.8,
900
+ "learning_rate": 1.3292131295101604e-05,
901
+ "loss": 1.8011,
902
+ "step": 745
903
+ },
904
+ {
905
+ "epoch": 0.8,
906
+ "learning_rate": 1.2616743482450217e-05,
907
+ "loss": 1.7338,
908
+ "step": 750
909
+ },
910
+ {
911
+ "epoch": 0.81,
912
+ "learning_rate": 1.1957223749227626e-05,
913
+ "loss": 1.7185,
914
+ "step": 755
915
+ },
916
+ {
917
+ "epoch": 0.81,
918
+ "learning_rate": 1.1313759031888791e-05,
919
+ "loss": 1.7987,
920
+ "step": 760
921
+ },
922
+ {
923
+ "epoch": 0.82,
924
+ "learning_rate": 1.0686531716201893e-05,
925
+ "loss": 1.7855,
926
+ "step": 765
927
+ },
928
+ {
929
+ "epoch": 0.83,
930
+ "learning_rate": 1.0075719585552289e-05,
931
+ "loss": 1.755,
932
+ "step": 770
933
+ },
934
+ {
935
+ "epoch": 0.83,
936
+ "learning_rate": 9.481495770550924e-06,
937
+ "loss": 1.7749,
938
+ "step": 775
939
+ },
940
+ {
941
+ "epoch": 0.84,
942
+ "learning_rate": 8.90402869996171e-06,
943
+ "loss": 1.7306,
944
+ "step": 780
945
+ },
946
+ {
947
+ "epoch": 0.84,
948
+ "learning_rate": 8.343482052961487e-06,
949
+ "loss": 1.7385,
950
+ "step": 785
951
+ },
952
+ {
953
+ "epoch": 0.85,
954
+ "learning_rate": 7.800014712746244e-06,
955
+ "loss": 1.8382,
956
+ "step": 790
957
+ },
958
+ {
959
+ "epoch": 0.85,
960
+ "learning_rate": 7.273780721496786e-06,
961
+ "loss": 1.7857,
962
+ "step": 795
963
+ },
964
+ {
965
+ "epoch": 0.86,
966
+ "learning_rate": 6.7649292367164704e-06,
967
+ "loss": 1.7224,
968
+ "step": 800
969
+ },
970
+ {
971
+ "epoch": 0.86,
972
+ "learning_rate": 6.2736044889534784e-06,
973
+ "loss": 1.7514,
974
+ "step": 805
975
+ },
976
+ {
977
+ "epoch": 0.87,
978
+ "learning_rate": 5.799945740919712e-06,
979
+ "loss": 1.7887,
980
+ "step": 810
981
+ },
982
+ {
983
+ "epoch": 0.87,
984
+ "learning_rate": 5.344087248017646e-06,
985
+ "loss": 1.7605,
986
+ "step": 815
987
+ },
988
+ {
989
+ "epoch": 0.88,
990
+ "learning_rate": 4.906158220286551e-06,
991
+ "loss": 1.7712,
992
+ "step": 820
993
+ },
994
+ {
995
+ "epoch": 0.88,
996
+ "learning_rate": 4.486282785778806e-06,
997
+ "loss": 1.7334,
998
+ "step": 825
999
+ },
1000
+ {
1001
+ "epoch": 0.89,
1002
+ "learning_rate": 4.084579955376559e-06,
1003
+ "loss": 1.749,
1004
+ "step": 830
1005
+ },
1006
+ {
1007
+ "epoch": 0.89,
1008
+ "learning_rate": 3.7011635890589766e-06,
1009
+ "loss": 1.7343,
1010
+ "step": 835
1011
+ },
1012
+ {
1013
+ "epoch": 0.9,
1014
+ "learning_rate": 3.3361423636293224e-06,
1015
+ "loss": 1.7663,
1016
+ "step": 840
1017
+ },
1018
+ {
1019
+ "epoch": 0.91,
1020
+ "learning_rate": 2.989619741911281e-06,
1021
+ "loss": 1.759,
1022
+ "step": 845
1023
+ },
1024
+ {
1025
+ "epoch": 0.91,
1026
+ "learning_rate": 2.6616939434230985e-06,
1027
+ "loss": 1.7025,
1028
+ "step": 850
1029
+ },
1030
+ {
1031
+ "epoch": 0.92,
1032
+ "learning_rate": 2.352457916537921e-06,
1033
+ "loss": 1.7564,
1034
+ "step": 855
1035
+ },
1036
+ {
1037
+ "epoch": 0.92,
1038
+ "learning_rate": 2.0619993121382247e-06,
1039
+ "loss": 1.8452,
1040
+ "step": 860
1041
+ },
1042
+ {
1043
+ "epoch": 0.93,
1044
+ "learning_rate": 1.7904004587717305e-06,
1045
+ "loss": 1.7741,
1046
+ "step": 865
1047
+ },
1048
+ {
1049
+ "epoch": 0.93,
1050
+ "learning_rate": 1.5377383393159132e-06,
1051
+ "loss": 1.7832,
1052
+ "step": 870
1053
+ },
1054
+ {
1055
+ "epoch": 0.94,
1056
+ "learning_rate": 1.3040845691577635e-06,
1057
+ "loss": 1.8237,
1058
+ "step": 875
1059
+ },
1060
+ {
1061
+ "epoch": 0.94,
1062
+ "learning_rate": 1.0895053758948607e-06,
1063
+ "loss": 1.7458,
1064
+ "step": 880
1065
+ },
1066
+ {
1067
+ "epoch": 0.95,
1068
+ "learning_rate": 8.940615805635918e-07,
1069
+ "loss": 1.7009,
1070
+ "step": 885
1071
+ },
1072
+ {
1073
+ "epoch": 0.95,
1074
+ "learning_rate": 7.178085803998752e-07,
1075
+ "loss": 1.725,
1076
+ "step": 890
1077
+ },
1078
+ {
1079
+ "epoch": 0.96,
1080
+ "learning_rate": 5.607963331371593e-07,
1081
+ "loss": 1.7469,
1082
+ "step": 895
1083
+ },
1084
+ {
1085
+ "epoch": 0.96,
1086
+ "learning_rate": 4.2306934284621745e-07,
1087
+ "loss": 1.6719,
1088
+ "step": 900
1089
+ },
1090
+ {
1091
+ "epoch": 0.97,
1092
+ "learning_rate": 3.04666647320803e-07,
1093
+ "loss": 1.8424,
1094
+ "step": 905
1095
+ },
1096
+ {
1097
+ "epoch": 0.98,
1098
+ "learning_rate": 2.0562180701263117e-07,
1099
+ "loss": 1.7483,
1100
+ "step": 910
1101
+ },
1102
+ {
1103
+ "epoch": 0.98,
1104
+ "learning_rate": 1.2596289551889364e-07,
1105
+ "loss": 1.7528,
1106
+ "step": 915
1107
+ },
1108
+ {
1109
+ "epoch": 0.99,
1110
+ "learning_rate": 6.571249162498684e-08,
1111
+ "loss": 1.8179,
1112
+ "step": 920
1113
+ },
1114
+ {
1115
+ "epoch": 0.99,
1116
+ "learning_rate": 2.4887672904708548e-08,
1117
+ "loss": 1.7763,
1118
+ "step": 925
1119
+ },
1120
+ {
1121
+ "epoch": 1.0,
1122
+ "learning_rate": 3.5000108797349717e-09,
1123
+ "loss": 1.7489,
1124
+ "step": 930
1125
+ },
1126
+ {
1127
+ "epoch": 1.0,
1128
+ "eval_loss": 1.7264798879623413,
1129
+ "eval_runtime": 80.022,
1130
+ "eval_samples_per_second": 20.494,
1131
+ "eval_steps_per_second": 2.562,
1132
+ "step": 933
1133
+ }
1134
+ ],
1135
+ "max_steps": 933,
1136
+ "num_train_epochs": 1,
1137
+ "total_flos": 974357987328000.0,
1138
+ "trial_name": null,
1139
+ "trial_params": null
1140
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67df3bd264a71efcb0d01d8192714279a8fc3600ce7fa98693fe3fda12d80b92
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff