Training in progress, epoch 2
Browse files- checkpoint-405/added_tokens.json +1 -0
- checkpoint-405/config.json +28 -0
- checkpoint-405/optimizer.pt +3 -0
- checkpoint-405/pytorch_model.bin +3 -0
- checkpoint-405/rng_state.pth +3 -0
- checkpoint-405/scaler.pt +3 -0
- checkpoint-405/scheduler.pt +3 -0
- checkpoint-405/special_tokens_map.json +1 -0
- checkpoint-405/spiece.model +3 -0
- checkpoint-405/tokenizer.json +0 -0
- checkpoint-405/tokenizer_config.json +1 -0
- checkpoint-405/trainer_state.json +58 -0
- checkpoint-405/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-405/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 32100}
|
checkpoint-405/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/t5-v1_1-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"num_decoder_layers": 12,
|
18 |
+
"num_heads": 12,
|
19 |
+
"num_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_num_buckets": 32,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.16.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32101
|
28 |
+
}
|
checkpoint-405/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f50de1629ea4e53a65bff6b322ec1b4e6bfcdd148e357f39d35cb95b052393
|
3 |
+
size 1980455257
|
checkpoint-405/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220212430f44d7eb2c6cabf6934d9e4b0203835a31ea897738f797c94e65512d
|
3 |
+
size 990272461
|
checkpoint-405/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:887237cd938b2e6f7ea832a8846246d4009547f25fe2efda6e407f5096ea7f6e
|
3 |
+
size 14503
|
checkpoint-405/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ffa040a21ec017e5ea54c9032cf626519fb2b7b7f3a6115d289bd42d3f21a66
|
3 |
+
size 559
|
checkpoint-405/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:361b412c6099209dd7c32c3cf59809aa5d7b27574edb1597b9b27827ea576a15
|
3 |
+
size 623
|
checkpoint-405/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
checkpoint-405/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-405/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-405/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "google/t5-v1_1-base", "special_tokens_map_file": "/home/chris-zeng/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
checkpoint-405/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.43842175602912903,
|
3 |
+
"best_model_checkpoint": "outputs/t5-v1_1-base-detox/checkpoint-405",
|
4 |
+
"epoch": 2.9953917050691246,
|
5 |
+
"global_step": 405,
|
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": 9e-05,
|
13 |
+
"loss": 8.9719,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.031940221786499,
|
19 |
+
"eval_runtime": 22.7196,
|
20 |
+
"eval_samples_per_second": 136.446,
|
21 |
+
"eval_steps_per_second": 17.078,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 1.9438,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.6424035429954529,
|
33 |
+
"eval_runtime": 22.8507,
|
34 |
+
"eval_samples_per_second": 135.663,
|
35 |
+
"eval_steps_per_second": 16.98,
|
36 |
+
"step": 270
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7e-05,
|
41 |
+
"loss": 0.8941,
|
42 |
+
"step": 405
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.43842175602912903,
|
47 |
+
"eval_runtime": 22.8845,
|
48 |
+
"eval_samples_per_second": 135.463,
|
49 |
+
"eval_steps_per_second": 16.955,
|
50 |
+
"step": 405
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 1350,
|
54 |
+
"num_train_epochs": 10,
|
55 |
+
"total_flos": 3944252667580416.0,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
checkpoint-405/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:839084c79c487b59c2c5870b0257ed8fb82211fae1f0295222d556827c5f599c
|
3 |
+
size 3247
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990272461
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220212430f44d7eb2c6cabf6934d9e4b0203835a31ea897738f797c94e65512d
|
3 |
size 990272461
|