Hugging Face's logo

utpalendu
/
banglish-model

Safetensors
Model card Files
xet
 Community
utpalendu commited on
Commit
400c8a3
·
verified ·
1 Parent(s): 65431b3

Uploading my trained Banglish model from Colab!

Browse files
Files changed (18) hide show
  1. checkpoint-6/config.json +42 -0
  2. checkpoint-6/generation_config.json +7 -0
  3. checkpoint-6/model.safetensors +3 -0
  4. checkpoint-6/optimizer.pt +3 -0
  5. checkpoint-6/rng_state.pth +3 -0
  6. checkpoint-6/scheduler.pt +3 -0
  7. checkpoint-6/tokenizer.json +0 -0
  8. checkpoint-6/tokenizer_config.json +13 -0
  9. checkpoint-6/trainer_state.json +41 -0
  10. checkpoint-6/training_args.bin +3 -0
  11. final_model/config.json +42 -0
  12. final_model/generation_config.json +7 -0
  13. final_model/model.safetensors +3 -0
  14. final_model/tokenizer.json +0 -0
  15. final_model/tokenizer_config.json +13 -0
  16. final_model/training_args.bin +3 -0
  17. final_model/training_config.json +1 -0
  18. trainer_state.json +50 -0
checkpoint-6/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "dtype": "bfloat16",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 50256,
12
+ "gradient_checkpointing": false,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "gpt2",
16
+ "n_ctx": 1024,
17
+ "n_embd": 768,
18
+ "n_head": 12,
19
+ "n_inner": null,
20
+ "n_layer": 12,
21
+ "n_positions": 1024,
22
+ "pad_token_id": null,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.0,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "task_specific_params": {
33
+ "text-generation": {
34
+ "do_sample": true,
35
+ "max_length": 50
36
+ }
37
+ },
38
+ "tie_word_embeddings": true,
39
+ "transformers_version": "5.10.2",
40
+ "use_cache": false,
41
+ "vocab_size": 50257
42
+ }
checkpoint-6/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "5.10.2",
6
+ "use_cache": true
7
+ }
checkpoint-6/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624008c5c8c6c1571751a29255cad39cb7fd180ef4051c22ab905e91450bd59e
3
+ size 248894656
checkpoint-6/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81a5bb5067fe1d3d2e2d493aa0f183364e35e97787c86fafc5a90343ec976ac
3
+ size 497885643
checkpoint-6/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-6/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb06ab36f20358ef2ecd950a3293dab9c67b6955ddcd81b0409674d6a0a7761
3
+ size 1465
checkpoint-6/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
checkpoint-6/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6153846153846154,
14
+ "grad_norm": 4.0625,
15
+ "learning_rate": 0.0,
16
+ "loss": 6.574719429016113,
17
+ "step": 1
18
+ }
19
+ ],
20
+ "logging_steps": 10,
21
+ "max_steps": 6,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 3,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": true
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 322956951552000.0,
38
+ "train_batch_size": 16,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43fddbb1760dfb603ffe6f01784fc5420493c25abfb894ea0f66e3eea52c754
3
+ size 5201
final_model/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "dtype": "bfloat16",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 50256,
12
+ "gradient_checkpointing": false,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "gpt2",
16
+ "n_ctx": 1024,
17
+ "n_embd": 768,
18
+ "n_head": 12,
19
+ "n_inner": null,
20
+ "n_layer": 12,
21
+ "n_positions": 1024,
22
+ "pad_token_id": null,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.0,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "task_specific_params": {
33
+ "text-generation": {
34
+ "do_sample": true,
35
+ "max_length": 50
36
+ }
37
+ },
38
+ "tie_word_embeddings": true,
39
+ "transformers_version": "5.10.2",
40
+ "use_cache": false,
41
+ "vocab_size": 50257
42
+ }
final_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "5.10.2",
6
+ "use_cache": true
7
+ }
final_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624008c5c8c6c1571751a29255cad39cb7fd180ef4051c22ab905e91450bd59e
3
+ size 248894656
final_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final_model/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
final_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43fddbb1760dfb603ffe6f01784fc5420493c25abfb894ea0f66e3eea52c754
3
+ size 5201
final_model/training_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6153846153846154,
14
+ "grad_norm": 4.0625,
15
+ "learning_rate": 0.0,
16
+ "loss": 6.574719429016113,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 3.0,
21
+ "step": 6,
22
+ "total_flos": 322956951552000.0,
23
+ "train_loss": 6.582550207773845,
24
+ "train_runtime": 332.0555,
25
+ "train_samples_per_second": 1.861,
26
+ "train_steps_per_second": 0.018
27
+ }
28
+ ],
29
+ "logging_steps": 10,
30
+ "max_steps": 6,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 3,
33
+ "save_steps": 500,
34
+ "stateful_callbacks": {
35
+ "TrainerControl": {
36
+ "args": {
37
+ "should_epoch_stop": false,
38
+ "should_evaluate": false,
39
+ "should_log": false,
40
+ "should_save": true,
41
+ "should_training_stop": true
42
+ },
43
+ "attributes": {}
44
+ }
45
+ },
46
+ "total_flos": 322956951552000.0,
47
+ "train_batch_size": 16,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }