gchhablani commited on
Commit
07e78fa
1 Parent(s): 655b5ea

Training in progress, epoch 2

Browse files
checkpoint-80/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "architectures": [
4
+ "FNetForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "finetuning_task": "wnli",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "not_entailment",
14
+ "1": "entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "entailment": 1,
20
+ "not_entailment": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "torch_dtype": "float32",
28
+ "tpu_short_seq_length": 512,
29
+ "transformers_version": "4.11.0.dev0",
30
+ "type_vocab_size": 4,
31
+ "use_tpu_fourier_optimizations": false,
32
+ "vocab_size": 32000
33
+ }
checkpoint-80/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74b6bedbe5e912c72eacb7ec69538aa9ca54861c6c71bbdc78cf4d1a59e8537
3
+ size 662962197
checkpoint-80/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f52617c88be8134677066f67b8a7f0aa9167d5bfdc5b1da1594afa37f6142e2
3
+ size 331497705
checkpoint-80/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67246c9b868c242e4f4868c36f92225e18db89642a3dcdfba1702cf1c227be0
3
+ size 14503
checkpoint-80/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b87f8ba4c0cc97d1cb84e99916436cfd692e67e4a2573bfe57ee6abcbd84bd1
3
+ size 623
checkpoint-80/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-80/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-80/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": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}
checkpoint-80/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": 80,
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": 1.6000000000000003e-05,
13
+ "loss": 0.7052,
14
+ "step": 40
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5633802816901409,
19
+ "eval_loss": 0.6902039051055908,
20
+ "eval_runtime": 0.5271,
21
+ "eval_samples_per_second": 134.707,
22
+ "eval_steps_per_second": 17.076,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 1.2e-05,
28
+ "loss": 0.6957,
29
+ "step": 80
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.43661971830985913,
34
+ "eval_loss": 0.7012577056884766,
35
+ "eval_runtime": 0.5221,
36
+ "eval_samples_per_second": 135.995,
37
+ "eval_steps_per_second": 17.239,
38
+ "step": 80
39
+ }
40
+ ],
41
+ "max_steps": 200,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 225855555440640.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-80/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0018d0bd5493d2abb91a78e7fe6494461f7f4d10944b54be5c94d6f6c54f5859
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:626ed3907402fd980be0cc276f022708d4128336ce7bbacd26826eaf5ad4444a
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f52617c88be8134677066f67b8a7f0aa9167d5bfdc5b1da1594afa37f6142e2
3
  size 331497705
runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e67b981c3c5ff96cef1ccb162a2f05ad1aa5111c255953faebaab3533315db
3
- size 3655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644536cc6608207ee4a31006af505383b7ce5c21112e60a84807da966727be02
3
+ size 4126