gchhablani commited on
Commit
d8c4ceb
1 Parent(s): 51f3ff0

Training in progress, epoch 2

Browse files

checkpoint-4276/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-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6416ed8efe769e294c75fdd53d1b2f5b815c971bfc243e25ea79abb7648de8c7
3
+ size 1895696981
checkpoint-4276/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd2a61ad0bd04c9345bd003f3bb6f31921df35cb8a9bce4ce9846d548d54c595
3
+ size 947877033
checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80f4e51d0774e913c158ad9a68063ca4f06f003e867db601b7d10c16da1ac88
3
+ size 14503
checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff13071a1bf1959d894c84324cbde923b25da6300eafd5a0a660477cfd507b4f
3
+ size 623
checkpoint-4276/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-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
checkpoint-4276/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-4276/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 4276,
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
+ "max_steps": 10690,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 1.0699286530707456e+16,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-4276/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:b9d82febb017cf4214879c89b80126cff7354534c6d783536d58a1c9b209e0a3
3
  size 947877033
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd2a61ad0bd04c9345bd003f3bb6f31921df35cb8a9bce4ce9846d548d54c595
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 sha256:49d0504c3fccc94b0b8abaa703cdad70c5d8acf48e718ae7d99fcdbff75ee5b3
3
- size 3768
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620ad799c1fb0da3e6d5c6fc29a8db69a520a1688ec280e50fd4dd2fb851772d
3
+ size 4260