Hugging Face's logo

shanthi-323
/
lora-flan-t5-base-chatbot

Transformers
TensorBoard
Safetensors
t5
text2text-generation
text-generation-inference
Model card Files
xet
 Metrics Community
shanthi-323 commited on
Commit
998e40f
·
verified ·
1 Parent(s): 69fff20

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-1840/config.json +62 -0
  2. checkpoint-1840/generation_config.json +7 -0
  3. checkpoint-1840/model.safetensors +3 -0
  4. checkpoint-1840/optimizer.pt +3 -0
  5. checkpoint-1840/rng_state.pth +3 -0
  6. checkpoint-1840/scheduler.pt +3 -0
  7. checkpoint-1840/trainer_state.json +40 -0
  8. checkpoint-1840/training_args.bin +3 -0
  9. config.json +1 -1
  10. logs/events.out.tfevents.1733863440.713e82b928c4.10782.0 +3 -0
  11. model.safetensors +2 -2
  12. training_args.bin +3 -0
checkpoint-1840/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
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": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.46.3",
60
+ "use_cache": false,
61
+ "vocab_size": 32128
62
+ }
checkpoint-1840/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": "4.46.3"
7
+ }
checkpoint-1840/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fefc39b4ec978dcbeb3d45bfac26f04a777f2ba4e526593f3c3da1aebeec868
3
+ size 990345064
checkpoint-1840/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8280ed2c1f51e2a715d6d31ed39d5524fc55894befc14b6538ea8ef15c8dba
3
+ size 1980860410
checkpoint-1840/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72212f9e7079f5d78c1347aeeaf339fae7a6304530aca3c08cf11444b0b603f
3
+ size 14244
checkpoint-1840/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381467b304922e6e183dcab945b3b25fca1375cfceb56860bf86ad36fcb9ed4c
3
+ size 1064
checkpoint-1840/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1840,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 0.7821058034896851,
14
+ "learning_rate": 0.0,
15
+ "loss": 1.8154,
16
+ "step": 1840
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 1840,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 1,
23
+ "save_steps": 500,
24
+ "stateful_callbacks": {
25
+ "TrainerControl": {
26
+ "args": {
27
+ "should_epoch_stop": false,
28
+ "should_evaluate": false,
29
+ "should_log": false,
30
+ "should_save": true,
31
+ "should_training_stop": true
32
+ },
33
+ "attributes": {}
34
+ }
35
+ },
36
+ "total_flos": 2519907057008640.0,
37
+ "train_batch_size": 4,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-1840/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a50bec8b4a36e7986ad135551a0c96e51188679691def4916f939328a57dd8
3
+ size 5432
config.json CHANGED
@@ -57,6 +57,6 @@
57
  "tie_word_embeddings": false,
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.46.3",
60
- "use_cache": false,
61
  "vocab_size": 32128
62
  }
 
57
  "tie_word_embeddings": false,
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.46.3",
60
+ "use_cache": true,
61
  "vocab_size": 32128
62
  }
logs/events.out.tfevents.1733863440.713e82b928c4.10782.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65eb8d278c3b509313a75fcf4071c19d93c821cf844bdcd8bc75a1c272c22223
3
+ size 6643
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fefc39b4ec978dcbeb3d45bfac26f04a777f2ba4e526593f3c3da1aebeec868
3
- size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d091c3c12cb0fd70641cd6a5910f650ebc3925dbec21ababe10a69ba6789602
3
+ size 993904016
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a50bec8b4a36e7986ad135551a0c96e51188679691def4916f939328a57dd8
3
+ size 5432