Upload config.json
Browse files- config.json +28 -85
config.json
CHANGED
@@ -3,88 +3,31 @@
|
|
3 |
"description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
|
4 |
"training_timestamp": "Sat Oct 7 08:52:05 2023",
|
5 |
"training_comments": "cerebras-1.3b-base",
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
"torchscript": false,
|
35 |
-
"torch_dtype": null,
|
36 |
-
"use_bfloat16": false,
|
37 |
-
"tf_legacy_loss": false,
|
38 |
-
"pruned_heads": {},
|
39 |
-
"tie_word_embeddings": true,
|
40 |
-
"is_encoder_decoder": false,
|
41 |
-
"is_decoder": false,
|
42 |
-
"cross_attention_hidden_size": null,
|
43 |
-
"add_cross_attention": false,
|
44 |
-
"tie_encoder_decoder": false,
|
45 |
-
"max_length": 20,
|
46 |
-
"min_length": 0,
|
47 |
-
"do_sample": false,
|
48 |
-
"early_stopping": false,
|
49 |
-
"num_beams": 1,
|
50 |
-
"num_beam_groups": 1,
|
51 |
-
"diversity_penalty": 0.0,
|
52 |
-
"temperature": 1.0,
|
53 |
-
"top_k": 50,
|
54 |
-
"top_p": 1.0,
|
55 |
-
"typical_p": 1.0,
|
56 |
-
"repetition_penalty": 1.0,
|
57 |
-
"length_penalty": 1.0,
|
58 |
-
"no_repeat_ngram_size": 0,
|
59 |
-
"encoder_no_repeat_ngram_size": 0,
|
60 |
-
"bad_words_ids": null,
|
61 |
-
"num_return_sequences": 1,
|
62 |
-
"chunk_size_feed_forward": 0,
|
63 |
-
"output_scores": false,
|
64 |
-
"return_dict_in_generate": false,
|
65 |
-
"forced_bos_token_id": null,
|
66 |
-
"forced_eos_token_id": null,
|
67 |
-
"remove_invalid_values": false,
|
68 |
-
"exponential_decay_length_penalty": null,
|
69 |
-
"suppress_tokens": null,
|
70 |
-
"begin_suppress_tokens": null,
|
71 |
-
"architectures": null,
|
72 |
-
"finetuning_task": null,
|
73 |
-
"id2label": {
|
74 |
-
"0": "LABEL_0",
|
75 |
-
"1": "LABEL_1"
|
76 |
-
},
|
77 |
-
"label2id": {
|
78 |
-
"LABEL_0": 0,
|
79 |
-
"LABEL_1": 1
|
80 |
-
},
|
81 |
-
"tokenizer_class": null,
|
82 |
-
"prefix": null,
|
83 |
-
"pad_token_id": null,
|
84 |
-
"sep_token_id": null,
|
85 |
-
"decoder_start_token_id": null,
|
86 |
-
"task_specific_params": null,
|
87 |
-
"problem_type": null,
|
88 |
-
"transformers_version": "4.28.1",
|
89 |
-
"trained": "custom training"
|
90 |
-
}
|
|
|
3 |
"description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
|
4 |
"training_timestamp": "Sat Oct 7 08:52:05 2023",
|
5 |
"training_comments": "cerebras-1.3b-base",
|
6 |
+
"_name_or_path": "cerebras/Cerebras-GPT-1.3B",
|
7 |
+
"activation_function": "gelu",
|
8 |
+
"attn_pdrop": 0.0,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.0,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_embd": 2048,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": 8192,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 2048,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.0,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"transformers_version": "4.33.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50257
|
32 |
+
}
|
33 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|