gchhablani commited on
Commit
ea76033
1 Parent(s): 091f97b

Training in progress, epoch 2

Browse files
checkpoint-312/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": "rte",
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "entailment",
14
+ "1": "not_entailment"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "entailment": 0,
20
+ "not_entailment": 1
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-312/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:717a49dc4b139c6321cf5a2fd6365b9a1656fc75625ed14343ca9dedb2dbfcf0
3
+ size 662962261
checkpoint-312/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703325ffcce92834a555de711f8d2ea5175af28d0cb351b6d0eb917c1e40a72e
3
+ size 331497705
checkpoint-312/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86c5bbf2695c97ebbb4d1435a327e520f687d51ffe49395e5b3065784c70958
3
+ size 14503
checkpoint-312/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c73dfb7abd19508ad56a6440748f5143d455937855467685a268634550bc8d3
3
+ size 623
checkpoint-312/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-312/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-312/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-312/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": 312,
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": 1.3333333333333333e-05,
13
+ "loss": 0.6829,
14
+ "step": 156
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5703971119133574,
19
+ "eval_loss": 0.6657100915908813,
20
+ "eval_runtime": 2.0131,
21
+ "eval_samples_per_second": 137.6,
22
+ "eval_steps_per_second": 17.386,
23
+ "step": 156
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.6174,
29
+ "step": 312
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.6101083032490975,
34
+ "eval_loss": 0.6784032583236694,
35
+ "eval_runtime": 2.013,
36
+ "eval_samples_per_second": 137.609,
37
+ "eval_steps_per_second": 17.387,
38
+ "step": 312
39
+ }
40
+ ],
41
+ "max_steps": 468,
42
+ "num_train_epochs": 3,
43
+ "total_flos": 885638319759360.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-312/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2785b0a5856d6dcded05366f24390f17de2bc55f955abf2c62f58cd45feda2ba
3
+ size 2735
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fda7052f3995f536c79c4af7fb0a0b4b15b9578629e2550fda87cc8bbcda3e3
3
  size 331497705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703325ffcce92834a555de711f8d2ea5175af28d0cb351b6d0eb917c1e40a72e
3
  size 331497705
runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030438.patrick-general-gpu.457696.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dcf250953a643295f0b083aa6995d62a18c75d3ba3ef02f4b39929017088292
3
- size 3660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38f1de6ffcdbb07eab6c410618378017bdf30f0724ff009108005b33a1ee155
3
+ size 4140