AlekseyKorshuk commited on
Commit
2466af3
1 Parent(s): c6a92ba

huggingartists

Browse files
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ datasets:
4
+ - huggingartists/bruce-springsteen
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/6dfe4b89b895b331f09c6b136a0705e5.807x807x1.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">Bruce Springsteen</div>
22
+ <a href="https://genius.com/artists/bruce-springsteen">
23
+ <div style="text-align: center; font-size: 14px;">@bruce-springsteen</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 Bruce Springsteen.
38
+
39
+ Dataset is available [here](https://huggingface.co/datasets/huggingartists/bruce-springsteen).
40
+ And can be used with:
41
+
42
+ ```python
43
+ from datasets import load_dataset
44
+
45
+ dataset = load_dataset("huggingartists/bruce-springsteen")
46
+ ```
47
+
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/28yd4w57/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 Bruce Springsteen's lyrics.
53
+
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/6qq7wbab) for full transparency and reproducibility.
55
+
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/6qq7wbab/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/bruce-springsteen')
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/bruce-springsteen")
75
+
76
+ model = AutoModelWithLMHead.from_pretrained("huggingartists/bruce-springsteen")
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": "4.9.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 2.562410593032837, "eval_runtime": 8.7547, "eval_samples_per_second": 21.131, "eval_steps_per_second": 2.741, "epoch": 20.0}
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d10dc81d9b50d874f93e8e68c4a2e4a00b0b2f3e187fe376625f32002ad0a67
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:b30ee3bcbb932cf5c052ba491db6f76b87cd13d2dc6bc7f12181c952ce31414c
3
+ size 995604017
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c4a675b660cc1ef7e9771491c8952638c54464549303776f270b68e4d6d468
3
+ size 510403817
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec33686a6d52a730b75fcda652fb2671b551225d74f8c0fab5e5e5f2e22ede81
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cd62b0c7892b777db0b867c23158b58538d7056ca9b90f535f64528ae00eb8
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 +1,1212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.562410593032837,
3
+ "best_model_checkpoint": "output/bruce-springsteen/checkpoint-952",
4
+ "epoch": 7.0,
5
+ "global_step": 952,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 0.00013674294000958298,
13
+ "loss": 3.78,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 0.00013537785052914354,
19
+ "loss": 3.4816,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "learning_rate": 0.00013312292187310875,
25
+ "loss": 3.3352,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.15,
30
+ "learning_rate": 0.0001300082017869573,
31
+ "loss": 3.354,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.18,
36
+ "learning_rate": 0.00012607519505006897,
37
+ "loss": 3.4425,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.22,
42
+ "learning_rate": 0.0001213763104094255,
43
+ "loss": 3.4175,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "learning_rate": 0.00011597416221397217,
49
+ "loss": 3.1509,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.29,
54
+ "learning_rate": 0.000109940736055617,
55
+ "loss": 3.3062,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.33,
60
+ "learning_rate": 0.00010335642953500487,
61
+ "loss": 3.2804,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.37,
66
+ "learning_rate": 9.630898093421199e-05,
67
+ "loss": 2.9747,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.4,
72
+ "learning_rate": 8.889230007218717e-05,
73
+ "loss": 3.4039,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.44,
78
+ "learning_rate": 8.120521692221673e-05,
79
+ "loss": 3.3281,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.48,
84
+ "learning_rate": 7.335016466654156e-05,
85
+ "loss": 3.1832,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.51,
90
+ "learning_rate": 6.543181473690228e-05,
91
+ "loss": 3.0942,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.55,
96
+ "learning_rate": 5.7555682029595066e-05,
97
+ "loss": 3.2014,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.59,
102
+ "learning_rate": 4.982671888105512e-05,
103
+ "loss": 2.9804,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.62,
108
+ "learning_rate": 4.2347916539754844e-05,
109
+ "loss": 2.9935,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.66,
114
+ "learning_rate": 3.5218932770313667e-05,
115
+ "loss": 3.0304,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.7,
120
+ "learning_rate": 2.8534763877493803e-05,
121
+ "loss": 3.0939,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.74,
126
+ "learning_rate": 2.2384478845846175e-05,
127
+ "loss": 3.2979,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.77,
132
+ "learning_rate": 1.6850032463056755e-05,
133
+ "loss": 3.1302,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.81,
138
+ "learning_rate": 1.200517324255647e-05,
139
+ "loss": 2.9578,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.85,
144
+ "learning_rate": 7.914460697724135e-06,
145
+ "loss": 3.1475,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.88,
150
+ "learning_rate": 4.6324050628611986e-06,
151
+ "loss": 3.0137,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.92,
156
+ "learning_rate": 2.202740924469675e-06,
157
+ "loss": 2.9044,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.96,
162
+ "learning_rate": 6.578444419609313e-07,
163
+ "loss": 3.0162,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.99,
168
+ "learning_rate": 1.8301923541685384e-08,
169
+ "loss": 3.0899,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 1.0,
174
+ "eval_loss": 2.968862771987915,
175
+ "eval_runtime": 8.6913,
176
+ "eval_samples_per_second": 21.286,
177
+ "eval_steps_per_second": 2.761,
178
+ "step": 136
179
+ },
180
+ {
181
+ "epoch": 1.03,
182
+ "learning_rate": 2.926355061606279e-07,
183
+ "loss": 3.099,
184
+ "step": 140
185
+ },
186
+ {
187
+ "epoch": 1.07,
188
+ "learning_rate": 1.4771895949302213e-06,
189
+ "loss": 2.9362,
190
+ "step": 145
191
+ },
192
+ {
193
+ "epoch": 1.1,
194
+ "learning_rate": 3.55617957525975e-06,
195
+ "loss": 2.8939,
196
+ "step": 150
197
+ },
198
+ {
199
+ "epoch": 1.14,
200
+ "learning_rate": 6.5019021485927275e-06,
201
+ "loss": 2.8441,
202
+ "step": 155
203
+ },
204
+ {
205
+ "epoch": 1.18,
206
+ "learning_rate": 1.0275104488948473e-05,
207
+ "loss": 2.7526,
208
+ "step": 160
209
+ },
210
+ {
211
+ "epoch": 1.21,
212
+ "learning_rate": 1.4825507301122139e-05,
213
+ "loss": 3.0343,
214
+ "step": 165
215
+ },
216
+ {
217
+ "epoch": 1.25,
218
+ "learning_rate": 2.009247481060283e-05,
219
+ "loss": 2.8204,
220
+ "step": 170
221
+ },
222
+ {
223
+ "epoch": 1.29,
224
+ "learning_rate": 2.600582275734942e-05,
225
+ "loss": 2.8892,
226
+ "step": 175
227
+ },
228
+ {
229
+ "epoch": 1.32,
230
+ "learning_rate": 3.2486753626613365e-05,
231
+ "loss": 3.0241,
232
+ "step": 180
233
+ },
234
+ {
235
+ "epoch": 1.36,
236
+ "learning_rate": 3.9448906654517264e-05,
237
+ "loss": 2.9835,
238
+ "step": 185
239
+ },
240
+ {
241
+ "epoch": 1.4,
242
+ "learning_rate": 4.679950861668151e-05,
243
+ "loss": 2.8951,
244
+ "step": 190
245
+ },
246
+ {
247
+ "epoch": 1.43,
248
+ "learning_rate": 5.444061006522326e-05,
249
+ "loss": 2.9979,
250
+ "step": 195
251
+ },
252
+ {
253
+ "epoch": 1.47,
254
+ "learning_rate": 6.227039054081748e-05,
255
+ "loss": 2.8296,
256
+ "step": 200
257
+ },
258
+ {
259
+ "epoch": 1.51,
260
+ "learning_rate": 7.018451536739584e-05,
261
+ "loss": 2.9173,
262
+ "step": 205
263
+ },
264
+ {
265
+ "epoch": 1.54,
266
+ "learning_rate": 7.807752594969911e-05,
267
+ "loss": 2.821,
268
+ "step": 210
269
+ },
270
+ {
271
+ "epoch": 1.58,
272
+ "learning_rate": 8.58442450474616e-05,
273
+ "loss": 2.8064,
274
+ "step": 215
275
+ },
276
+ {
277
+ "epoch": 1.62,
278
+ "learning_rate": 9.338117830043867e-05,
279
+ "loss": 2.8823,
280
+ "step": 220
281
+ },
282
+ {
283
+ "epoch": 1.65,
284
+ "learning_rate": 0.00010058789332844422,
285
+ "loss": 2.9615,
286
+ "step": 225
287
+ },
288
+ {
289
+ "epoch": 1.69,
290
+ "learning_rate": 0.00010736835802938978,
291
+ "loss": 2.8424,
292
+ "step": 230
293
+ },
294
+ {
295
+ "epoch": 1.73,
296
+ "learning_rate": 0.0001136322202420147,
297
+ "loss": 2.9272,
298
+ "step": 235
299
+ },
300
+ {
301
+ "epoch": 1.76,
302
+ "learning_rate": 0.00011929601172133719,
303
+ "loss": 2.7972,
304
+ "step": 240
305
+ },
306
+ {
307
+ "epoch": 1.8,
308
+ "learning_rate": 0.00012428426038341373,
309
+ "loss": 2.6514,
310
+ "step": 245
311
+ },
312
+ {
313
+ "epoch": 1.84,
314
+ "learning_rate": 0.00012853049599834097,
315
+ "loss": 2.966,
316
+ "step": 250
317
+ },
318
+ {
319
+ "epoch": 1.88,
320
+ "learning_rate": 0.00013197813593027427,
321
+ "loss": 3.0045,
322
+ "step": 255
323
+ },
324
+ {
325
+ "epoch": 1.91,
326
+ "learning_rate": 0.00013458123912165538,
327
+ "loss": 2.6775,
328
+ "step": 260
329
+ },
330
+ {
331
+ "epoch": 1.95,
332
+ "learning_rate": 0.00013630511827453364,
333
+ "loss": 2.6298,
334
+ "step": 265
335
+ },
336
+ {
337
+ "epoch": 1.99,
338
+ "learning_rate": 0.00013712680207144277,
339
+ "loss": 2.6688,
340
+ "step": 270
341
+ },
342
+ {
343
+ "epoch": 2.0,
344
+ "eval_loss": 2.839606523513794,
345
+ "eval_runtime": 8.7347,
346
+ "eval_samples_per_second": 21.18,
347
+ "eval_steps_per_second": 2.748,
348
+ "step": 272
349
+ },
350
+ {
351
+ "epoch": 2.02,
352
+ "learning_rate": 0.00013703534127657097,
353
+ "loss": 2.81,
354
+ "step": 275
355
+ },
356
+ {
357
+ "epoch": 2.06,
358
+ "learning_rate": 0.00013603195463831566,
359
+ "loss": 2.4255,
360
+ "step": 280
361
+ },
362
+ {
363
+ "epoch": 2.1,
364
+ "learning_rate": 0.00013413001264901686,
365
+ "loss": 2.5457,
366
+ "step": 285
367
+ },
368
+ {
369
+ "epoch": 2.13,
370
+ "learning_rate": 0.00013135485937827823,
371
+ "loss": 2.3628,
372
+ "step": 290
373
+ },
374
+ {
375
+ "epoch": 2.17,
376
+ "learning_rate": 0.0001277434747540102,
377
+ "loss": 2.6079,
378
+ "step": 295
379
+ },
380
+ {
381
+ "epoch": 2.21,
382
+ "learning_rate": 0.0001233439817914244,
383
+ "loss": 2.6005,
384
+ "step": 300
385
+ },
386
+ {
387
+ "epoch": 2.24,
388
+ "learning_rate": 0.00011821500533633198,
389
+ "loss": 2.3133,
390
+ "step": 305
391
+ },
392
+ {
393
+ "epoch": 2.28,
394
+ "learning_rate": 0.00011242489086772457,
395
+ "loss": 2.691,
396
+ "step": 310
397
+ },
398
+ {
399
+ "epoch": 2.32,
400
+ "learning_rate": 0.00010605079376937858,
401
+ "loss": 2.4907,
402
+ "step": 315
403
+ },
404
+ {
405
+ "epoch": 2.35,
406
+ "learning_rate": 9.917765120627052e-05,
407
+ "loss": 2.614,
408
+ "step": 320
409
+ },
410
+ {
411
+ "epoch": 2.39,
412
+ "learning_rate": 9.189705030592299e-05,
413
+ "loss": 2.5114,
414
+ "step": 325
415
+ },
416
+ {
417
+ "epoch": 2.43,
418
+ "learning_rate": 8.430600772657927e-05,
419
+ "loss": 2.3745,
420
+ "step": 330
421
+ },
422
+ {
423
+ "epoch": 2.46,
424
+ "learning_rate": 7.650567687490305e-05,
425
+ "loss": 2.6594,
426
+ "step": 335
427
+ },
428
+ {
429
+ "epoch": 2.5,
430
+ "learning_rate": 6.860000000000001e-05,
431
+ "loss": 2.6282,
432
+ "step": 340
433
+ },
434
+ {
435
+ "epoch": 2.54,
436
+ "learning_rate": 6.0694323125097e-05,
437
+ "loss": 2.4007,
438
+ "step": 345
439
+ },
440
+ {
441
+ "epoch": 2.57,
442
+ "learning_rate": 5.289399227342078e-05,
443
+ "loss": 2.61,
444
+ "step": 350
445
+ },
446
+ {
447
+ "epoch": 2.61,
448
+ "learning_rate": 4.530294969407699e-05,
449
+ "loss": 2.4243,
450
+ "step": 355
451
+ },
452
+ {
453
+ "epoch": 2.65,
454
+ "learning_rate": 3.8022348793729525e-05,
455
+ "loss": 2.6903,
456
+ "step": 360
457
+ },
458
+ {
459
+ "epoch": 2.68,
460
+ "learning_rate": 3.11492062306214e-05,
461
+ "loss": 2.4129,
462
+ "step": 365
463
+ },
464
+ {
465
+ "epoch": 2.72,
466
+ "learning_rate": 2.4775109132275458e-05,
467
+ "loss": 2.5884,
468
+ "step": 370
469
+ },
470
+ {
471
+ "epoch": 2.76,
472
+ "learning_rate": 1.8984994663667992e-05,
473
+ "loss": 2.5451,
474
+ "step": 375
475
+ },
476
+ {
477
+ "epoch": 2.79,
478
+ "learning_rate": 1.3856018208575617e-05,
479
+ "loss": 2.3267,
480
+ "step": 380
481
+ },
482
+ {
483
+ "epoch": 2.83,
484
+ "learning_rate": 9.45652524598977e-06,
485
+ "loss": 2.6289,
486
+ "step": 385
487
+ },
488
+ {
489
+ "epoch": 2.87,
490
+ "learning_rate": 5.845140621721773e-06,
491
+ "loss": 2.6761,
492
+ "step": 390
493
+ },
494
+ {
495
+ "epoch": 2.9,
496
+ "learning_rate": 3.069987350983113e-06,
497
+ "loss": 2.548,
498
+ "step": 395
499
+ },
500
+ {
501
+ "epoch": 2.94,
502
+ "learning_rate": 1.1680453616843376e-06,
503
+ "loss": 2.2025,
504
+ "step": 400
505
+ },
506
+ {
507
+ "epoch": 2.98,
508
+ "learning_rate": 1.646587234290122e-07,
509
+ "loss": 2.4811,
510
+ "step": 405
511
+ },
512
+ {
513
+ "epoch": 3.0,
514
+ "eval_loss": 2.697875499725342,
515
+ "eval_runtime": 8.7457,
516
+ "eval_samples_per_second": 21.153,
517
+ "eval_steps_per_second": 2.744,
518
+ "step": 408
519
+ },
520
+ {
521
+ "epoch": 3.01,
522
+ "learning_rate": 7.319792855724439e-08,
523
+ "loss": 2.3981,
524
+ "step": 410
525
+ },
526
+ {
527
+ "epoch": 3.05,
528
+ "learning_rate": 8.948817254663383e-07,
529
+ "loss": 2.4304,
530
+ "step": 415
531
+ },
532
+ {
533
+ "epoch": 3.09,
534
+ "learning_rate": 2.618760878344606e-06,
535
+ "loss": 2.3479,
536
+ "step": 420
537
+ },
538
+ {
539
+ "epoch": 3.12,
540
+ "learning_rate": 5.22186406972573e-06,
541
+ "loss": 2.2508,
542
+ "step": 425
543
+ },
544
+ {
545
+ "epoch": 3.16,
546
+ "learning_rate": 8.669504001659e-06,
547
+ "loss": 2.2017,
548
+ "step": 430
549
+ },
550
+ {
551
+ "epoch": 3.2,
552
+ "learning_rate": 1.2915739616586271e-05,
553
+ "loss": 2.3098,
554
+ "step": 435
555
+ },
556
+ {
557
+ "epoch": 3.24,
558
+ "learning_rate": 1.7903988278662747e-05,
559
+ "loss": 2.325,
560
+ "step": 440
561
+ },
562
+ {
563
+ "epoch": 3.27,
564
+ "learning_rate": 2.3567779757985262e-05,
565
+ "loss": 2.331,
566
+ "step": 445
567
+ },
568
+ {
569
+ "epoch": 3.31,
570
+ "learning_rate": 2.983164197061009e-05,
571
+ "loss": 2.2929,
572
+ "step": 450
573
+ },
574
+ {
575
+ "epoch": 3.35,
576
+ "learning_rate": 3.6612106671555745e-05,
577
+ "loss": 2.2436,
578
+ "step": 455
579
+ },
580
+ {
581
+ "epoch": 3.38,
582
+ "learning_rate": 4.381882169956124e-05,
583
+ "loss": 2.4438,
584
+ "step": 460
585
+ },
586
+ {
587
+ "epoch": 3.42,
588
+ "learning_rate": 5.135575495253831e-05,
589
+ "loss": 2.1411,
590
+ "step": 465
591
+ },
592
+ {
593
+ "epoch": 3.46,
594
+ "learning_rate": 5.9122474050300846e-05,
595
+ "loss": 2.2244,
596
+ "step": 470
597
+ },
598
+ {
599
+ "epoch": 3.49,
600
+ "learning_rate": 6.701548463260412e-05,
601
+ "loss": 2.2979,
602
+ "step": 475
603
+ },
604
+ {
605
+ "epoch": 3.53,
606
+ "learning_rate": 7.492960945918241e-05,
607
+ "loss": 2.188,
608
+ "step": 480
609
+ },
610
+ {
611
+ "epoch": 3.57,
612
+ "learning_rate": 8.275938993477677e-05,
613
+ "loss": 2.0263,
614
+ "step": 485
615
+ },
616
+ {
617
+ "epoch": 3.6,
618
+ "learning_rate": 9.04004913833184e-05,
619
+ "loss": 2.4795,
620
+ "step": 490
621
+ },
622
+ {
623
+ "epoch": 3.64,
624
+ "learning_rate": 9.77510933454827e-05,
625
+ "loss": 2.287,
626
+ "step": 495
627
+ },
628
+ {
629
+ "epoch": 3.68,
630
+ "learning_rate": 0.0001047132463733866,
631
+ "loss": 2.2963,
632
+ "step": 500
633
+ },
634
+ {
635
+ "epoch": 3.71,
636
+ "learning_rate": 0.0001111941772426506,
637
+ "loss": 2.2048,
638
+ "step": 505
639
+ },
640
+ {
641
+ "epoch": 3.75,
642
+ "learning_rate": 0.0001171075251893971,
643
+ "loss": 2.416,
644
+ "step": 510
645
+ },
646
+ {
647
+ "epoch": 3.79,
648
+ "learning_rate": 0.00012237449269887778,
649
+ "loss": 2.3413,
650
+ "step": 515
651
+ },
652
+ {
653
+ "epoch": 3.82,
654
+ "learning_rate": 0.0001269248955110515,
655
+ "loss": 2.3194,
656
+ "step": 520
657
+ },
658
+ {
659
+ "epoch": 3.86,
660
+ "learning_rate": 0.00013069809785140726,
661
+ "loss": 2.3466,
662
+ "step": 525
663
+ },
664
+ {
665
+ "epoch": 3.9,
666
+ "learning_rate": 0.00013364382042474026,
667
+ "loss": 2.5401,
668
+ "step": 530
669
+ },
670
+ {
671
+ "epoch": 3.93,
672
+ "learning_rate": 0.00013572281040506975,
673
+ "loss": 2.2886,
674
+ "step": 535
675
+ },
676
+ {
677
+ "epoch": 3.97,
678
+ "learning_rate": 0.00013690736449383938,
679
+ "loss": 2.4436,
680
+ "step": 540
681
+ },
682
+ {
683
+ "epoch": 4.0,
684
+ "eval_loss": 2.6544318199157715,
685
+ "eval_runtime": 8.682,
686
+ "eval_samples_per_second": 21.308,
687
+ "eval_steps_per_second": 2.764,
688
+ "step": 544
689
+ },
690
+ {
691
+ "epoch": 4.01,
692
+ "learning_rate": 0.00013718169807645832,
693
+ "loss": 2.2455,
694
+ "step": 545
695
+ },
696
+ {
697
+ "epoch": 4.04,
698
+ "learning_rate": 0.00013654215555803907,
699
+ "loss": 2.2189,
700
+ "step": 550
701
+ },
702
+ {
703
+ "epoch": 4.08,
704
+ "learning_rate": 0.00013499725907553032,
705
+ "loss": 2.0464,
706
+ "step": 555
707
+ },
708
+ {
709
+ "epoch": 4.12,
710
+ "learning_rate": 0.00013256759493713885,
711
+ "loss": 2.0255,
712
+ "step": 560
713
+ },
714
+ {
715
+ "epoch": 4.15,
716
+ "learning_rate": 0.00012928553930227594,
717
+ "loss": 1.9056,
718
+ "step": 565
719
+ },
720
+ {
721
+ "epoch": 4.19,
722
+ "learning_rate": 0.0001251948267574435,
723
+ "loss": 2.1303,
724
+ "step": 570
725
+ },
726
+ {
727
+ "epoch": 4.23,
728
+ "learning_rate": 0.00012034996753694334,
729
+ "loss": 2.1789,
730
+ "step": 575
731
+ },
732
+ {
733
+ "epoch": 4.26,
734
+ "learning_rate": 0.00011481552115415383,
735
+ "loss": 2.1376,
736
+ "step": 580
737
+ },
738
+ {
739
+ "epoch": 4.3,
740
+ "learning_rate": 0.00010866523612250621,
741
+ "loss": 2.1059,
742
+ "step": 585
743
+ },
744
+ {
745
+ "epoch": 4.34,
746
+ "learning_rate": 0.00010198106722968643,
747
+ "loss": 2.3021,
748
+ "step": 590
749
+ },
750
+ {
751
+ "epoch": 4.38,
752
+ "learning_rate": 9.485208346024522e-05,
753
+ "loss": 2.096,
754
+ "step": 595
755
+ },
756
+ {
757
+ "epoch": 4.41,
758
+ "learning_rate": 8.73732811189448e-05,
759
+ "loss": 2.1222,
760
+ "step": 600
761
+ },
762
+ {
763
+ "epoch": 4.45,
764
+ "learning_rate": 7.964431797040506e-05,
765
+ "loss": 2.1479,
766
+ "step": 605
767
+ },
768
+ {
769
+ "epoch": 4.49,
770
+ "learning_rate": 7.176818526309773e-05,
771
+ "loss": 2.112,
772
+ "step": 610
773
+ },
774
+ {
775
+ "epoch": 4.52,
776
+ "learning_rate": 6.384983533345843e-05,
777
+ "loss": 1.9858,
778
+ "step": 615
779
+ },
780
+ {
781
+ "epoch": 4.56,
782
+ "learning_rate": 5.599478307778335e-05,
783
+ "loss": 2.0653,
784
+ "step": 620
785
+ },
786
+ {
787
+ "epoch": 4.6,
788
+ "learning_rate": 4.83076999278129e-05,
789
+ "loss": 2.3118,
790
+ "step": 625
791
+ },
792
+ {
793
+ "epoch": 4.63,
794
+ "learning_rate": 4.089101906578792e-05,
795
+ "loss": 2.1364,
796
+ "step": 630
797
+ },
798
+ {
799
+ "epoch": 4.67,
800
+ "learning_rate": 3.3843570464995244e-05,
801
+ "loss": 1.9424,
802
+ "step": 635
803
+ },
804
+ {
805
+ "epoch": 4.71,
806
+ "learning_rate": 2.7259263944382997e-05,
807
+ "loss": 2.0466,
808
+ "step": 640
809
+ },
810
+ {
811
+ "epoch": 4.74,
812
+ "learning_rate": 2.12258377860279e-05,
813
+ "loss": 2.2663,
814
+ "step": 645
815
+ },
816
+ {
817
+ "epoch": 4.78,
818
+ "learning_rate": 1.5823689590574545e-05,
819
+ "loss": 2.1516,
820
+ "step": 650
821
+ },
822
+ {
823
+ "epoch": 4.82,
824
+ "learning_rate": 1.112480494993106e-05,
825
+ "loss": 2.0252,
826
+ "step": 655
827
+ },
828
+ {
829
+ "epoch": 4.85,
830
+ "learning_rate": 7.191798213042784e-06,
831
+ "loss": 2.1763,
832
+ "step": 660
833
+ },
834
+ {
835
+ "epoch": 4.89,
836
+ "learning_rate": 4.077078126891299e-06,
837
+ "loss": 1.8925,
838
+ "step": 665
839
+ },
840
+ {
841
+ "epoch": 4.93,
842
+ "learning_rate": 1.822149470856462e-06,
843
+ "loss": 2.0655,
844
+ "step": 670
845
+ },
846
+ {
847
+ "epoch": 4.96,
848
+ "learning_rate": 4.570599904170397e-07,
849
+ "loss": 2.0477,
850
+ "step": 675
851
+ },
852
+ {
853
+ "epoch": 5.0,
854
+ "learning_rate": 0.0,
855
+ "loss": 1.8207,
856
+ "step": 680
857
+ },
858
+ {
859
+ "epoch": 5.0,
860
+ "eval_loss": 2.601478338241577,
861
+ "eval_runtime": 8.6457,
862
+ "eval_samples_per_second": 21.398,
863
+ "eval_steps_per_second": 2.776,
864
+ "step": 680
865
+ },
866
+ {
867
+ "epoch": 5.04,
868
+ "learning_rate": 4.570599904170321e-07,
869
+ "loss": 1.6645,
870
+ "step": 685
871
+ },
872
+ {
873
+ "epoch": 5.07,
874
+ "learning_rate": 1.8221494708564468e-06,
875
+ "loss": 1.9202,
876
+ "step": 690
877
+ },
878
+ {
879
+ "epoch": 5.11,
880
+ "learning_rate": 4.0770781268912235e-06,
881
+ "loss": 1.761,
882
+ "step": 695
883
+ },
884
+ {
885
+ "epoch": 5.15,
886
+ "learning_rate": 7.191798213042746e-06,
887
+ "loss": 1.877,
888
+ "step": 700
889
+ },
890
+ {
891
+ "epoch": 5.18,
892
+ "learning_rate": 1.1124804949931014e-05,
893
+ "loss": 1.7914,
894
+ "step": 705
895
+ },
896
+ {
897
+ "epoch": 5.22,
898
+ "learning_rate": 1.5823689590574568e-05,
899
+ "loss": 1.9094,
900
+ "step": 710
901
+ },
902
+ {
903
+ "epoch": 5.26,
904
+ "learning_rate": 2.122583778602784e-05,
905
+ "loss": 1.8799,
906
+ "step": 715
907
+ },
908
+ {
909
+ "epoch": 5.29,
910
+ "learning_rate": 2.7259263944382926e-05,
911
+ "loss": 1.625,
912
+ "step": 720
913
+ },
914
+ {
915
+ "epoch": 5.33,
916
+ "learning_rate": 3.384357046499517e-05,
917
+ "loss": 1.673,
918
+ "step": 725
919
+ },
920
+ {
921
+ "epoch": 5.37,
922
+ "learning_rate": 4.089101906578795e-05,
923
+ "loss": 1.7023,
924
+ "step": 730
925
+ },
926
+ {
927
+ "epoch": 5.4,
928
+ "learning_rate": 4.8307699927812706e-05,
929
+ "loss": 1.9625,
930
+ "step": 735
931
+ },
932
+ {
933
+ "epoch": 5.44,
934
+ "learning_rate": 5.599478307778327e-05,
935
+ "loss": 1.8095,
936
+ "step": 740
937
+ },
938
+ {
939
+ "epoch": 5.48,
940
+ "learning_rate": 6.384983533345835e-05,
941
+ "loss": 2.0594,
942
+ "step": 745
943
+ },
944
+ {
945
+ "epoch": 5.51,
946
+ "learning_rate": 7.176818526309777e-05,
947
+ "loss": 1.9059,
948
+ "step": 750
949
+ },
950
+ {
951
+ "epoch": 5.55,
952
+ "learning_rate": 7.964431797040486e-05,
953
+ "loss": 1.8821,
954
+ "step": 755
955
+ },
956
+ {
957
+ "epoch": 5.59,
958
+ "learning_rate": 8.737328111894472e-05,
959
+ "loss": 2.187,
960
+ "step": 760
961
+ },
962
+ {
963
+ "epoch": 5.62,
964
+ "learning_rate": 9.485208346024515e-05,
965
+ "loss": 2.0599,
966
+ "step": 765
967
+ },
968
+ {
969
+ "epoch": 5.66,
970
+ "learning_rate": 0.00010198106722968646,
971
+ "loss": 1.9395,
972
+ "step": 770
973
+ },
974
+ {
975
+ "epoch": 5.7,
976
+ "learning_rate": 0.00010866523612250605,
977
+ "loss": 1.8671,
978
+ "step": 775
979
+ },
980
+ {
981
+ "epoch": 5.74,
982
+ "learning_rate": 0.00011481552115415377,
983
+ "loss": 2.1133,
984
+ "step": 780
985
+ },
986
+ {
987
+ "epoch": 5.77,
988
+ "learning_rate": 0.0001203499675369433,
989
+ "loss": 1.9346,
990
+ "step": 785
991
+ },
992
+ {
993
+ "epoch": 5.81,
994
+ "learning_rate": 0.00012519482675744353,
995
+ "loss": 2.0467,
996
+ "step": 790
997
+ },
998
+ {
999
+ "epoch": 5.85,
1000
+ "learning_rate": 0.00012928553930227583,
1001
+ "loss": 1.8789,
1002
+ "step": 795
1003
+ },
1004
+ {
1005
+ "epoch": 5.88,
1006
+ "learning_rate": 0.00013256759493713883,
1007
+ "loss": 1.8932,
1008
+ "step": 800
1009
+ },
1010
+ {
1011
+ "epoch": 5.92,
1012
+ "learning_rate": 0.0001349972590755303,
1013
+ "loss": 1.8909,
1014
+ "step": 805
1015
+ },
1016
+ {
1017
+ "epoch": 5.96,
1018
+ "learning_rate": 0.00013654215555803907,
1019
+ "loss": 2.1403,
1020
+ "step": 810
1021
+ },
1022
+ {
1023
+ "epoch": 5.99,
1024
+ "learning_rate": 0.00013718169807645832,
1025
+ "loss": 1.8803,
1026
+ "step": 815
1027
+ },
1028
+ {
1029
+ "epoch": 6.0,
1030
+ "eval_loss": 2.6078295707702637,
1031
+ "eval_runtime": 8.6964,
1032
+ "eval_samples_per_second": 21.273,
1033
+ "eval_steps_per_second": 2.76,
1034
+ "step": 816
1035
+ },
1036
+ {
1037
+ "epoch": 6.03,
1038
+ "learning_rate": 0.00013690736449383938,
1039
+ "loss": 1.7367,
1040
+ "step": 820
1041
+ },
1042
+ {
1043
+ "epoch": 6.07,
1044
+ "learning_rate": 0.00013572281040506978,
1045
+ "loss": 1.8923,
1046
+ "step": 825
1047
+ },
1048
+ {
1049
+ "epoch": 6.1,
1050
+ "learning_rate": 0.0001336438204247403,
1051
+ "loss": 1.7941,
1052
+ "step": 830
1053
+ },
1054
+ {
1055
+ "epoch": 6.14,
1056
+ "learning_rate": 0.00013069809785140734,
1057
+ "loss": 1.733,
1058
+ "step": 835
1059
+ },
1060
+ {
1061
+ "epoch": 6.18,
1062
+ "learning_rate": 0.00012692489551105156,
1063
+ "loss": 1.6456,
1064
+ "step": 840
1065
+ },
1066
+ {
1067
+ "epoch": 6.21,
1068
+ "learning_rate": 0.00012237449269887794,
1069
+ "loss": 1.7817,
1070
+ "step": 845
1071
+ },
1072
+ {
1073
+ "epoch": 6.25,
1074
+ "learning_rate": 0.00011710752518939715,
1075
+ "loss": 1.8526,
1076
+ "step": 850
1077
+ },
1078
+ {
1079
+ "epoch": 6.29,
1080
+ "learning_rate": 0.00011119417724265067,
1081
+ "loss": 1.6085,
1082
+ "step": 855
1083
+ },
1084
+ {
1085
+ "epoch": 6.32,
1086
+ "learning_rate": 0.00010471324637338676,
1087
+ "loss": 1.7472,
1088
+ "step": 860
1089
+ },
1090
+ {
1091
+ "epoch": 6.36,
1092
+ "learning_rate": 9.775109334548278e-05,
1093
+ "loss": 1.7182,
1094
+ "step": 865
1095
+ },
1096
+ {
1097
+ "epoch": 6.4,
1098
+ "learning_rate": 9.040049138331835e-05,
1099
+ "loss": 1.7503,
1100
+ "step": 870
1101
+ },
1102
+ {
1103
+ "epoch": 6.43,
1104
+ "learning_rate": 8.275938993477671e-05,
1105
+ "loss": 1.7068,
1106
+ "step": 875
1107
+ },
1108
+ {
1109
+ "epoch": 6.47,
1110
+ "learning_rate": 7.492960945918261e-05,
1111
+ "loss": 1.6923,
1112
+ "step": 880
1113
+ },
1114
+ {
1115
+ "epoch": 6.51,
1116
+ "learning_rate": 6.701548463260408e-05,
1117
+ "loss": 1.6817,
1118
+ "step": 885
1119
+ },
1120
+ {
1121
+ "epoch": 6.54,
1122
+ "learning_rate": 5.912247405030094e-05,
1123
+ "loss": 1.6556,
1124
+ "step": 890
1125
+ },
1126
+ {
1127
+ "epoch": 6.58,
1128
+ "learning_rate": 5.135575495253826e-05,
1129
+ "loss": 1.7865,
1130
+ "step": 895
1131
+ },
1132
+ {
1133
+ "epoch": 6.62,
1134
+ "learning_rate": 4.3818821699561535e-05,
1135
+ "loss": 1.9308,
1136
+ "step": 900
1137
+ },
1138
+ {
1139
+ "epoch": 6.65,
1140
+ "learning_rate": 3.661210667155582e-05,
1141
+ "loss": 1.7407,
1142
+ "step": 905
1143
+ },
1144
+ {
1145
+ "epoch": 6.69,
1146
+ "learning_rate": 2.9831641970610168e-05,
1147
+ "loss": 1.5858,
1148
+ "step": 910
1149
+ },
1150
+ {
1151
+ "epoch": 6.73,
1152
+ "learning_rate": 2.3567779757985323e-05,
1153
+ "loss": 1.6857,
1154
+ "step": 915
1155
+ },
1156
+ {
1157
+ "epoch": 6.76,
1158
+ "learning_rate": 1.7903988278662893e-05,
1159
+ "loss": 1.6211,
1160
+ "step": 920
1161
+ },
1162
+ {
1163
+ "epoch": 6.8,
1164
+ "learning_rate": 1.2915739616586247e-05,
1165
+ "loss": 1.6546,
1166
+ "step": 925
1167
+ },
1168
+ {
1169
+ "epoch": 6.84,
1170
+ "learning_rate": 8.669504001659107e-06,
1171
+ "loss": 1.9644,
1172
+ "step": 930
1173
+ },
1174
+ {
1175
+ "epoch": 6.88,
1176
+ "learning_rate": 5.221864069725715e-06,
1177
+ "loss": 1.6495,
1178
+ "step": 935
1179
+ },
1180
+ {
1181
+ "epoch": 6.91,
1182
+ "learning_rate": 2.618760878344629e-06,
1183
+ "loss": 1.7503,
1184
+ "step": 940
1185
+ },
1186
+ {
1187
+ "epoch": 6.95,
1188
+ "learning_rate": 8.948817254663764e-07,
1189
+ "loss": 1.9784,
1190
+ "step": 945
1191
+ },
1192
+ {
1193
+ "epoch": 6.99,
1194
+ "learning_rate": 7.3197928557252e-08,
1195
+ "loss": 1.7477,
1196
+ "step": 950
1197
+ },
1198
+ {
1199
+ "epoch": 7.0,
1200
+ "eval_loss": 2.562410593032837,
1201
+ "eval_runtime": 8.7008,
1202
+ "eval_samples_per_second": 21.262,
1203
+ "eval_steps_per_second": 2.758,
1204
+ "step": 952
1205
+ }
1206
+ ],
1207
+ "max_steps": 2720,
1208
+ "num_train_epochs": 20,
1209
+ "total_flos": 991341969408000.0,
1210
+ "trial_name": null,
1211
+ "trial_params": null
1212
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c870882292272d33b62b9ef881bad4f77a261fd8fb28315858dfc9592f2134
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff