arbitropy commited on
Commit
e5ad9a7
1 Parent(s): c1162be

Training in progress, step 7000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ade63866bbc493dfbfb03d439072fb9d488f77db218d611ed1e217f724a99068
3
  size 2329638768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50fcbeac21ddcf83790ff6bbb28d8f29f47fb2d1e4d3dc8a614bfd15b631428
3
  size 2329638768
tmp-checkpoint-2100/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
tmp-checkpoint-2100/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
tmp-checkpoint-2100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c896cc8e11a85906462bbbcbf5be5495407c89ae8edfc1e2222844fbcb0718
3
+ size 2329638768
tmp-checkpoint-2100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e6d9d9a2e4c5f294e10301ad2301712cfe98b2e9cc974fcdbca2f8a8ea1d1d
3
+ size 4115450
tmp-checkpoint-2100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091e061afd413df7ee4b351402ee1ffb8f5a151e211c21f2527afeff29b127a0
3
+ size 14244
tmp-checkpoint-2100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdd58248507e9625744739d70e5d6b634c8d545c721febcd4a79084161273a4
3
+ size 1064
tmp-checkpoint-2100/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tmp-checkpoint-2100/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tmp-checkpoint-2100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ce747f56c3a3abbd1d60f2ce1c6c51decbfbc7ca49247aca30eed62c32d900
3
+ size 16330659
tmp-checkpoint-2100/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": true,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
tmp-checkpoint-2100/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.6017142534255981,
3
+ "best_model_checkpoint": "arbitropy/mt5-base-bcoqa/checkpoint-2100",
4
+ "epoch": 0.060544904137235116,
5
+ "eval_steps": 700,
6
+ "global_step": 2100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 14.746796607971191,
14
+ "learning_rate": 4.9639613665849795e-05,
15
+ "loss": 4.3627,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "eval_loss": 1.7135968208312988,
21
+ "eval_runtime": 62.9933,
22
+ "eval_samples_per_second": 75.183,
23
+ "eval_steps_per_second": 18.796,
24
+ "step": 700
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 3.6309075355529785,
29
+ "learning_rate": 4.927922733169959e-05,
30
+ "loss": 2.2652,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "eval_loss": 1.6376169919967651,
36
+ "eval_runtime": 63.2403,
37
+ "eval_samples_per_second": 74.889,
38
+ "eval_steps_per_second": 18.722,
39
+ "step": 1400
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "grad_norm": 6.434725761413574,
44
+ "learning_rate": 4.891884099754937e-05,
45
+ "loss": 2.0917,
46
+ "step": 1500
47
+ },
48
+ {
49
+ "epoch": 0.06,
50
+ "grad_norm": 10.990394592285156,
51
+ "learning_rate": 4.8558454663399166e-05,
52
+ "loss": 1.9203,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.06,
57
+ "eval_loss": 1.6017142534255981,
58
+ "eval_runtime": 63.1369,
59
+ "eval_samples_per_second": 75.012,
60
+ "eval_steps_per_second": 18.753,
61
+ "step": 2100
62
+ }
63
+ ],
64
+ "logging_steps": 500,
65
+ "max_steps": 69370,
66
+ "num_input_tokens_seen": 0,
67
+ "num_train_epochs": 2,
68
+ "save_steps": 700,
69
+ "total_flos": 1.956696216451891e+16,
70
+ "train_batch_size": 4,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
tmp-checkpoint-2100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd5b87bc40502d3f7df1436b012dd996beac219bdea584487f441f0232b5e11
3
+ size 5048
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bd5b87bc40502d3f7df1436b012dd996beac219bdea584487f441f0232b5e11
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87723fa72dd0500c3ac83696346c3aa13e6f3d19b13e24891f78d7aff97351f8
3
  size 5048