gchhablani commited on
Commit
b4cf6fb
1 Parent(s): 18812d0

Training in progress, epoch 3

Browse files
checkpoint-6414/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-6414/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519d399e171a012994ccce3ab9887e9afc33dd56eff3af2c78c0d813c5a959b5
3
+ size 1895696981
checkpoint-6414/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81249b0d27cddd42b66cc24109ff25d252ca2a434279db734502f0e7da638d69
3
+ size 947877033
checkpoint-6414/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb46f4b7d44eaed90819f3e91fee2f01af644625f3152f3618c58b96dab6a95
3
+ size 14503
checkpoint-6414/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86642ce7c252487cfeeb5babe32f76b49d66747d74e741e5949756c534404d01
3
+ size 623
checkpoint-6414/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-6414/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6414/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-6414/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 6414,
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": 7.408177408177407e-05,
13
+ "loss": 0.6408,
14
+ "step": 2138
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.7329378128051758,
19
+ "eval_matthews_correlation": 0.0,
20
+ "eval_runtime": 22.7321,
21
+ "eval_samples_per_second": 45.882,
22
+ "eval_steps_per_second": 5.763,
23
+ "step": 2138
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 3.704088704088704e-05,
28
+ "loss": 0.6589,
29
+ "step": 4276
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 0.6311050057411194,
34
+ "eval_matthews_correlation": 0.0,
35
+ "eval_runtime": 22.7597,
36
+ "eval_samples_per_second": 45.827,
37
+ "eval_steps_per_second": 5.756,
38
+ "step": 4276
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.6467,
44
+ "step": 6414
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_loss": 0.6554446816444397,
49
+ "eval_matthews_correlation": 0.0,
50
+ "eval_runtime": 22.7256,
51
+ "eval_samples_per_second": 45.895,
52
+ "eval_steps_per_second": 5.764,
53
+ "step": 6414
54
+ }
55
+ ],
56
+ "max_steps": 6414,
57
+ "num_train_epochs": 3,
58
+ "total_flos": 1.6048929796061184e+16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-6414/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86815fd44d40e13e4091bbc8889512f9aedd06f2b30d63cfd01d96a1aa69432c
3
+ size 2799
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c954b9cbf43c9ee57d606144921472345c7a799db2d6917b15d7a5a8906f623a
3
  size 947877033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81249b0d27cddd42b66cc24109ff25d252ca2a434279db734502f0e7da638d69
3
  size 947877033
runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633850743.patrick-general-gpu.98066.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec6099d939377cdc3a0145b35970e18e440a0adc9e10d2c15ae7166e9be6f42e
3
- size 4257
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1cb8e887d24367e8ee7840322d8229673fe9b9a7f57993d6d9b9afc05fce2cd
3
+ size 4749