Jellyfish042 commited on
Commit
e79f0d2
1 Parent(s): 1cf41e9

Delete checkpoint-2500

Browse files
checkpoint-2500/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_name_or_path": "./models/checkpoint-22500",
3
- "architectures": [
4
- "MT5ForConditionalGeneration"
5
- ],
6
- "d_ff": 1024,
7
- "d_kv": 64,
8
- "d_model": 512,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "gelu_new",
11
- "dropout_rate": 0.1,
12
- "eos_token_id": 1,
13
- "feed_forward_proj": "gated-gelu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": true,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "mt5",
19
- "num_decoder_layers": 8,
20
- "num_heads": 6,
21
- "num_layers": 8,
22
- "pad_token_id": 0,
23
- "relative_attention_max_distance": 128,
24
- "relative_attention_num_buckets": 32,
25
- "tie_word_embeddings": false,
26
- "tokenizer_class": "T5Tokenizer",
27
- "torch_dtype": "float32",
28
- "transformers_version": "4.28.0",
29
- "use_cache": true,
30
- "vocab_size": 250112
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2500/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.28.0"
7
- }
 
 
 
 
 
 
 
 
checkpoint-2500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdf6ee8329a445302adc5a0e633d9e4142cf1e0ac22254e1173da8a372b7708f
3
- size 2401525449
 
 
 
 
checkpoint-2500/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:375d72eabd9f2e338e87fe4bc5b63a17ada2ccfd0181e43db06d24493bb398f5
3
- size 1200770757
 
 
 
 
checkpoint-2500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01be8c45e8e5cf69b55716ce9f97f9e3cfe57e779d0d9801332b138f2b9fd576
3
- size 14503
 
 
 
 
checkpoint-2500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b90cf9de8f5f63de88c7aaa375d4c34594bdabdd77f57d89d3a50c32e02fe8cf
3
- size 623
 
 
 
 
checkpoint-2500/trainer_state.json DELETED
@@ -1,96 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.15242392141022612,
5
- "global_step": 2500,
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": 1.9951222486433756e-05,
13
- "loss": 0.0754,
14
- "step": 200
15
- },
16
- {
17
- "epoch": 0.02,
18
- "learning_rate": 1.990244497286751e-05,
19
- "loss": 0.0747,
20
- "step": 400
21
- },
22
- {
23
- "epoch": 0.04,
24
- "learning_rate": 1.9853667459301263e-05,
25
- "loss": 0.0737,
26
- "step": 600
27
- },
28
- {
29
- "epoch": 0.05,
30
- "learning_rate": 1.9804889945735017e-05,
31
- "loss": 0.073,
32
- "step": 800
33
- },
34
- {
35
- "epoch": 0.06,
36
- "learning_rate": 1.975611243216877e-05,
37
- "loss": 0.0723,
38
- "step": 1000
39
- },
40
- {
41
- "epoch": 0.07,
42
- "learning_rate": 1.9707334918602525e-05,
43
- "loss": 0.072,
44
- "step": 1200
45
- },
46
- {
47
- "epoch": 0.09,
48
- "learning_rate": 1.965855740503628e-05,
49
- "loss": 0.0709,
50
- "step": 1400
51
- },
52
- {
53
- "epoch": 0.1,
54
- "learning_rate": 1.9609779891470033e-05,
55
- "loss": 0.0703,
56
- "step": 1600
57
- },
58
- {
59
- "epoch": 0.11,
60
- "learning_rate": 1.9561002377903787e-05,
61
- "loss": 0.0708,
62
- "step": 1800
63
- },
64
- {
65
- "epoch": 0.12,
66
- "learning_rate": 1.951222486433754e-05,
67
- "loss": 0.0711,
68
- "step": 2000
69
- },
70
- {
71
- "epoch": 0.13,
72
- "learning_rate": 1.9463447350771295e-05,
73
- "loss": 0.0699,
74
- "step": 2200
75
- },
76
- {
77
- "epoch": 0.15,
78
- "learning_rate": 1.941466983720505e-05,
79
- "loss": 0.0701,
80
- "step": 2400
81
- },
82
- {
83
- "epoch": 0.15,
84
- "eval_loss": 0.055753033608198166,
85
- "eval_runtime": 1008.1775,
86
- "eval_samples_per_second": 82.199,
87
- "eval_steps_per_second": 13.7,
88
- "step": 2500
89
- }
90
- ],
91
- "max_steps": 82005,
92
- "num_train_epochs": 5,
93
- "total_flos": 1.268999258112e+17,
94
- "trial_name": null,
95
- "trial_params": null
96
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:69cea6267551e6c3db2312cb16b8e111ea7cc82c9a729b741a0cc0164750a77c
3
- size 3695