gchhablani commited on
Commit
e25e5fd
1 Parent(s): cb5f92c

Training in progress, epoch 4

Browse files

checkpoint-8552/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-large",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "cola",
10
+ "hidden_act": "gelu_new",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "unacceptable",
15
+ "1": "acceptable"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "acceptable": 1,
21
+ "unacceptable": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "fnet",
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 3,
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.11.0.dev0",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
checkpoint-8552/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2ac5c8e3edc06a1348f4f4c5274c3dc78e7e33d1666ce9c900740d3a95180c
3
+ size 1895696981
checkpoint-8552/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2026be213de9e967e07d8a374455c2c3b55a79dd7a7f1acfa394dc003594143
3
+ size 947877033
checkpoint-8552/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f247af074dbaa1be03637760c76d9fc7323467179c4207dd46233699c320ae10
3
+ size 14503
checkpoint-8552/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0226777751c14a204a52d00d817f7bbbb439b5d4f71c2052cc4004db96ca9f9f
3
+ size 623
checkpoint-8552/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
checkpoint-8552/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-8552/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}
checkpoint-8552/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 8552,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 3.5566666666666666e-05,
13
+ "loss": 0.6212,
14
+ "step": 2138
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.6539720296859741,
19
+ "eval_matthews_correlation": 0.0,
20
+ "eval_runtime": 22.7284,
21
+ "eval_samples_per_second": 45.89,
22
+ "eval_steps_per_second": 5.764,
23
+ "step": 2138
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 2.6700000000000002e-05,
28
+ "loss": 0.62,
29
+ "step": 4276
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 0.6409146785736084,
34
+ "eval_matthews_correlation": 0.0,
35
+ "eval_runtime": 22.7182,
36
+ "eval_samples_per_second": 45.91,
37
+ "eval_steps_per_second": 5.766,
38
+ "step": 4276
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 1.783333333333333e-05,
43
+ "loss": 0.6182,
44
+ "step": 6414
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_loss": 0.6234332919120789,
49
+ "eval_matthews_correlation": 0.0,
50
+ "eval_runtime": 22.7216,
51
+ "eval_samples_per_second": 45.904,
52
+ "eval_steps_per_second": 5.765,
53
+ "step": 6414
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 8.966666666666667e-06,
58
+ "loss": 0.6181,
59
+ "step": 8552
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_loss": 0.6234201192855835,
64
+ "eval_matthews_correlation": 0.0,
65
+ "eval_runtime": 22.7101,
66
+ "eval_samples_per_second": 45.927,
67
+ "eval_steps_per_second": 5.768,
68
+ "step": 8552
69
+ }
70
+ ],
71
+ "max_steps": 10690,
72
+ "num_train_epochs": 5,
73
+ "total_flos": 2.139857306141491e+16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-8552/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88518180b48b7d86e915e89c08d25d45c9dd551905fa41d34c4933dfadcb9385
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd40bce63a5c383faa601fcd60966460e58f97aa6d6bfa79c0992789faf8671a
3
  size 947877033
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2026be213de9e967e07d8a374455c2c3b55a79dd7a7f1acfa394dc003594143
3
  size 947877033
runs/Oct10_19-39-15_patrick-general-gpu/events.out.tfevents.1633894776.patrick-general-gpu.131003.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75e58a166d46410eb2b539f0b1117ebb600740ac3cb5320c43121d6051dfa722
3
- size 4752
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a1c6d365b80f31ffc2e589199d8806015dc9bed6170f9211b0a62ce02ebaed
3
+ size 5244