Upload folder using huggingface_hub
Browse files- checkpoint-10/config.json +185 -0
- checkpoint-10/generation_config.json +13 -0
- checkpoint-10/model.safetensors +3 -0
- checkpoint-10/optimizer.pt +3 -0
- checkpoint-10/preprocessor_config.json +36 -0
- checkpoint-10/rng_state.pth +3 -0
- checkpoint-10/scheduler.pt +3 -0
- checkpoint-10/trainer_state.json +76 -0
- checkpoint-10/training_args.bin +3 -0
- checkpoint-20/config.json +185 -0
- checkpoint-20/generation_config.json +13 -0
- checkpoint-20/model.safetensors +3 -0
- checkpoint-20/optimizer.pt +3 -0
- checkpoint-20/preprocessor_config.json +36 -0
- checkpoint-20/rng_state.pth +3 -0
- checkpoint-20/scheduler.pt +3 -0
- checkpoint-20/trainer_state.json +119 -0
- checkpoint-20/training_args.bin +3 -0
- config.json +185 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jun11_09-10-35_ip-10-192-12-224/events.out.tfevents.1718097036.ip-10-192-12-224.1762.0 +3 -0
- training_args.bin +3 -0
checkpoint-10/config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BhashaAI/iamgeing-3",
|
3 |
+
"architectures": [
|
4 |
+
"VisionEncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "surajp/gpt2-hindi",
|
8 |
+
"activation_function": "gelu_new",
|
9 |
+
"add_cross_attention": true,
|
10 |
+
"architectures": [
|
11 |
+
"GPT2LMHeadModel"
|
12 |
+
],
|
13 |
+
"attn_pdrop": 0.1,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 50256,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"cross_attention_hidden_size": null,
|
19 |
+
"decoder_start_token_id": null,
|
20 |
+
"diversity_penalty": 0.0,
|
21 |
+
"do_sample": false,
|
22 |
+
"early_stopping": false,
|
23 |
+
"embd_pdrop": 0.1,
|
24 |
+
"encoder_no_repeat_ngram_size": 0,
|
25 |
+
"eos_token_id": 50256,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"is_decoder": true,
|
36 |
+
"is_encoder_decoder": false,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1
|
40 |
+
},
|
41 |
+
"layer_norm_epsilon": 1e-05,
|
42 |
+
"length_penalty": 1.0,
|
43 |
+
"max_length": 20,
|
44 |
+
"min_length": 0,
|
45 |
+
"model_type": "gpt2",
|
46 |
+
"n_ctx": 1024,
|
47 |
+
"n_embd": 768,
|
48 |
+
"n_head": 12,
|
49 |
+
"n_inner": null,
|
50 |
+
"n_layer": 6,
|
51 |
+
"n_positions": 1024,
|
52 |
+
"no_repeat_ngram_size": 0,
|
53 |
+
"num_beam_groups": 1,
|
54 |
+
"num_beams": 1,
|
55 |
+
"num_return_sequences": 1,
|
56 |
+
"output_attentions": false,
|
57 |
+
"output_hidden_states": false,
|
58 |
+
"output_scores": false,
|
59 |
+
"pad_token_id": 50257,
|
60 |
+
"prefix": null,
|
61 |
+
"problem_type": null,
|
62 |
+
"pruned_heads": {},
|
63 |
+
"remove_invalid_values": false,
|
64 |
+
"reorder_and_upcast_attn": false,
|
65 |
+
"repetition_penalty": 1.0,
|
66 |
+
"resid_pdrop": 0.1,
|
67 |
+
"return_dict": true,
|
68 |
+
"return_dict_in_generate": false,
|
69 |
+
"scale_attn_by_inverse_layer_idx": false,
|
70 |
+
"scale_attn_weights": true,
|
71 |
+
"sep_token_id": null,
|
72 |
+
"summary_activation": null,
|
73 |
+
"summary_first_dropout": 0.1,
|
74 |
+
"summary_proj_to_labels": true,
|
75 |
+
"summary_type": "cls_index",
|
76 |
+
"summary_use_proj": true,
|
77 |
+
"suppress_tokens": null,
|
78 |
+
"task_specific_params": null,
|
79 |
+
"temperature": 1.0,
|
80 |
+
"tf_legacy_loss": false,
|
81 |
+
"tie_encoder_decoder": false,
|
82 |
+
"tie_word_embeddings": true,
|
83 |
+
"tokenizer_class": null,
|
84 |
+
"top_k": 50,
|
85 |
+
"top_p": 1.0,
|
86 |
+
"torch_dtype": null,
|
87 |
+
"torchscript": false,
|
88 |
+
"typical_p": 1.0,
|
89 |
+
"use_bfloat16": false,
|
90 |
+
"use_cache": true,
|
91 |
+
"vocab_size": 50258
|
92 |
+
},
|
93 |
+
"decoder_start_token_id": 50257,
|
94 |
+
"device_map": "cuda",
|
95 |
+
"early_stopping": true,
|
96 |
+
"encoder": {
|
97 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
98 |
+
"add_cross_attention": false,
|
99 |
+
"architectures": [
|
100 |
+
"ViTModel"
|
101 |
+
],
|
102 |
+
"attention_probs_dropout_prob": 0.0,
|
103 |
+
"bad_words_ids": null,
|
104 |
+
"begin_suppress_tokens": null,
|
105 |
+
"bos_token_id": null,
|
106 |
+
"chunk_size_feed_forward": 0,
|
107 |
+
"cross_attention_hidden_size": null,
|
108 |
+
"decoder_start_token_id": null,
|
109 |
+
"diversity_penalty": 0.0,
|
110 |
+
"do_sample": false,
|
111 |
+
"early_stopping": false,
|
112 |
+
"encoder_no_repeat_ngram_size": 0,
|
113 |
+
"encoder_stride": 16,
|
114 |
+
"eos_token_id": null,
|
115 |
+
"exponential_decay_length_penalty": null,
|
116 |
+
"finetuning_task": null,
|
117 |
+
"forced_bos_token_id": null,
|
118 |
+
"forced_eos_token_id": null,
|
119 |
+
"hidden_act": "gelu",
|
120 |
+
"hidden_dropout_prob": 0.0,
|
121 |
+
"hidden_size": 768,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"image_size": 224,
|
127 |
+
"initializer_range": 0.02,
|
128 |
+
"intermediate_size": 3072,
|
129 |
+
"is_decoder": false,
|
130 |
+
"is_encoder_decoder": false,
|
131 |
+
"label2id": {
|
132 |
+
"LABEL_0": 0,
|
133 |
+
"LABEL_1": 1
|
134 |
+
},
|
135 |
+
"layer_norm_eps": 1e-12,
|
136 |
+
"length_penalty": 1.0,
|
137 |
+
"max_length": 20,
|
138 |
+
"min_length": 0,
|
139 |
+
"model_type": "vit",
|
140 |
+
"no_repeat_ngram_size": 0,
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_beam_groups": 1,
|
143 |
+
"num_beams": 1,
|
144 |
+
"num_channels": 3,
|
145 |
+
"num_hidden_layers": 12,
|
146 |
+
"num_return_sequences": 1,
|
147 |
+
"output_attentions": false,
|
148 |
+
"output_hidden_states": false,
|
149 |
+
"output_scores": false,
|
150 |
+
"pad_token_id": null,
|
151 |
+
"patch_size": 16,
|
152 |
+
"prefix": null,
|
153 |
+
"problem_type": null,
|
154 |
+
"pruned_heads": {},
|
155 |
+
"qkv_bias": true,
|
156 |
+
"remove_invalid_values": false,
|
157 |
+
"repetition_penalty": 1.0,
|
158 |
+
"return_dict": true,
|
159 |
+
"return_dict_in_generate": false,
|
160 |
+
"sep_token_id": null,
|
161 |
+
"suppress_tokens": null,
|
162 |
+
"task_specific_params": null,
|
163 |
+
"temperature": 1.0,
|
164 |
+
"tf_legacy_loss": false,
|
165 |
+
"tie_encoder_decoder": false,
|
166 |
+
"tie_word_embeddings": true,
|
167 |
+
"tokenizer_class": null,
|
168 |
+
"top_k": 50,
|
169 |
+
"top_p": 1.0,
|
170 |
+
"torch_dtype": null,
|
171 |
+
"torchscript": false,
|
172 |
+
"typical_p": 1.0,
|
173 |
+
"use_bfloat16": false
|
174 |
+
},
|
175 |
+
"is_encoder_decoder": true,
|
176 |
+
"length_penalty": 2.0,
|
177 |
+
"max_length": 100,
|
178 |
+
"model_type": "vision-encoder-decoder",
|
179 |
+
"no_repeat_ngram_size": 3,
|
180 |
+
"num_beams": 4,
|
181 |
+
"pad_token_id": 50257,
|
182 |
+
"tie_word_embeddings": false,
|
183 |
+
"torch_dtype": "float32",
|
184 |
+
"transformers_version": "4.41.2"
|
185 |
+
}
|
checkpoint-10/generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"decoder_start_token_id": 50257,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 50256,
|
7 |
+
"length_penalty": 2.0,
|
8 |
+
"max_length": 100,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 50257,
|
12 |
+
"transformers_version": "4.41.2"
|
13 |
+
}
|
checkpoint-10/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:624fbdd5ab3cbaa0f79ad463034ce85e72ba18528b3a1941a5cf9b68fceb8fc5
|
3 |
+
size 884375032
|
checkpoint-10/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98545a63146d022b1b99af19fa504f01aa18d482c27ef28721d6381a20658a7
|
3 |
+
size 1764138362
|
checkpoint-10/preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTFeatureExtractor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
checkpoint-10/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adcf9c7421618a659a0327428c695ca77be1f562f1cc8b26fc712d053ba99fbd
|
3 |
+
size 14244
|
checkpoint-10/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40e79f4b58dd69865c798e34f64061006ba6df983d2559011edcc94e9c255389
|
3 |
+
size 1064
|
checkpoint-10/trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.22598870056497175,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 10,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04519774011299435,
|
13 |
+
"grad_norm": 6.134562969207764,
|
14 |
+
"learning_rate": 1.9090909090909094e-05,
|
15 |
+
"loss": 10.8188,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0903954802259887,
|
20 |
+
"grad_norm": 6.219421863555908,
|
21 |
+
"learning_rate": 1.8181818181818182e-05,
|
22 |
+
"loss": 10.7835,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.13559322033898305,
|
27 |
+
"grad_norm": 6.437071800231934,
|
28 |
+
"learning_rate": 1.7272727272727274e-05,
|
29 |
+
"loss": 10.7424,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1807909604519774,
|
34 |
+
"grad_norm": 6.489596843719482,
|
35 |
+
"learning_rate": 1.6363636363636366e-05,
|
36 |
+
"loss": 10.6919,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22598870056497175,
|
41 |
+
"grad_norm": 6.816253185272217,
|
42 |
+
"learning_rate": 1.5454545454545454e-05,
|
43 |
+
"loss": 10.631,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22598870056497175,
|
48 |
+
"eval_loss": 10.573423385620117,
|
49 |
+
"eval_runtime": 557.6088,
|
50 |
+
"eval_samples_per_second": 2.252,
|
51 |
+
"eval_steps_per_second": 0.072,
|
52 |
+
"step": 10
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"logging_steps": 2,
|
56 |
+
"max_steps": 44,
|
57 |
+
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 1,
|
59 |
+
"save_steps": 10,
|
60 |
+
"stateful_callbacks": {
|
61 |
+
"TrainerControl": {
|
62 |
+
"args": {
|
63 |
+
"should_epoch_stop": false,
|
64 |
+
"should_evaluate": false,
|
65 |
+
"should_log": false,
|
66 |
+
"should_save": true,
|
67 |
+
"should_training_stop": false
|
68 |
+
},
|
69 |
+
"attributes": {}
|
70 |
+
}
|
71 |
+
},
|
72 |
+
"total_flos": 4.201094396982067e+17,
|
73 |
+
"train_batch_size": 32,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
checkpoint-10/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f579a1c85563781ce014e1d8e22f221ac4ed13f8c49396f27d9d8683cdbea6f
|
3 |
+
size 5304
|
checkpoint-20/config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BhashaAI/iamgeing-3",
|
3 |
+
"architectures": [
|
4 |
+
"VisionEncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "surajp/gpt2-hindi",
|
8 |
+
"activation_function": "gelu_new",
|
9 |
+
"add_cross_attention": true,
|
10 |
+
"architectures": [
|
11 |
+
"GPT2LMHeadModel"
|
12 |
+
],
|
13 |
+
"attn_pdrop": 0.1,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 50256,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"cross_attention_hidden_size": null,
|
19 |
+
"decoder_start_token_id": null,
|
20 |
+
"diversity_penalty": 0.0,
|
21 |
+
"do_sample": false,
|
22 |
+
"early_stopping": false,
|
23 |
+
"embd_pdrop": 0.1,
|
24 |
+
"encoder_no_repeat_ngram_size": 0,
|
25 |
+
"eos_token_id": 50256,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"is_decoder": true,
|
36 |
+
"is_encoder_decoder": false,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1
|
40 |
+
},
|
41 |
+
"layer_norm_epsilon": 1e-05,
|
42 |
+
"length_penalty": 1.0,
|
43 |
+
"max_length": 20,
|
44 |
+
"min_length": 0,
|
45 |
+
"model_type": "gpt2",
|
46 |
+
"n_ctx": 1024,
|
47 |
+
"n_embd": 768,
|
48 |
+
"n_head": 12,
|
49 |
+
"n_inner": null,
|
50 |
+
"n_layer": 6,
|
51 |
+
"n_positions": 1024,
|
52 |
+
"no_repeat_ngram_size": 0,
|
53 |
+
"num_beam_groups": 1,
|
54 |
+
"num_beams": 1,
|
55 |
+
"num_return_sequences": 1,
|
56 |
+
"output_attentions": false,
|
57 |
+
"output_hidden_states": false,
|
58 |
+
"output_scores": false,
|
59 |
+
"pad_token_id": 50257,
|
60 |
+
"prefix": null,
|
61 |
+
"problem_type": null,
|
62 |
+
"pruned_heads": {},
|
63 |
+
"remove_invalid_values": false,
|
64 |
+
"reorder_and_upcast_attn": false,
|
65 |
+
"repetition_penalty": 1.0,
|
66 |
+
"resid_pdrop": 0.1,
|
67 |
+
"return_dict": true,
|
68 |
+
"return_dict_in_generate": false,
|
69 |
+
"scale_attn_by_inverse_layer_idx": false,
|
70 |
+
"scale_attn_weights": true,
|
71 |
+
"sep_token_id": null,
|
72 |
+
"summary_activation": null,
|
73 |
+
"summary_first_dropout": 0.1,
|
74 |
+
"summary_proj_to_labels": true,
|
75 |
+
"summary_type": "cls_index",
|
76 |
+
"summary_use_proj": true,
|
77 |
+
"suppress_tokens": null,
|
78 |
+
"task_specific_params": null,
|
79 |
+
"temperature": 1.0,
|
80 |
+
"tf_legacy_loss": false,
|
81 |
+
"tie_encoder_decoder": false,
|
82 |
+
"tie_word_embeddings": true,
|
83 |
+
"tokenizer_class": null,
|
84 |
+
"top_k": 50,
|
85 |
+
"top_p": 1.0,
|
86 |
+
"torch_dtype": null,
|
87 |
+
"torchscript": false,
|
88 |
+
"typical_p": 1.0,
|
89 |
+
"use_bfloat16": false,
|
90 |
+
"use_cache": true,
|
91 |
+
"vocab_size": 50258
|
92 |
+
},
|
93 |
+
"decoder_start_token_id": 50257,
|
94 |
+
"device_map": "cuda",
|
95 |
+
"early_stopping": true,
|
96 |
+
"encoder": {
|
97 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
98 |
+
"add_cross_attention": false,
|
99 |
+
"architectures": [
|
100 |
+
"ViTModel"
|
101 |
+
],
|
102 |
+
"attention_probs_dropout_prob": 0.0,
|
103 |
+
"bad_words_ids": null,
|
104 |
+
"begin_suppress_tokens": null,
|
105 |
+
"bos_token_id": null,
|
106 |
+
"chunk_size_feed_forward": 0,
|
107 |
+
"cross_attention_hidden_size": null,
|
108 |
+
"decoder_start_token_id": null,
|
109 |
+
"diversity_penalty": 0.0,
|
110 |
+
"do_sample": false,
|
111 |
+
"early_stopping": false,
|
112 |
+
"encoder_no_repeat_ngram_size": 0,
|
113 |
+
"encoder_stride": 16,
|
114 |
+
"eos_token_id": null,
|
115 |
+
"exponential_decay_length_penalty": null,
|
116 |
+
"finetuning_task": null,
|
117 |
+
"forced_bos_token_id": null,
|
118 |
+
"forced_eos_token_id": null,
|
119 |
+
"hidden_act": "gelu",
|
120 |
+
"hidden_dropout_prob": 0.0,
|
121 |
+
"hidden_size": 768,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"image_size": 224,
|
127 |
+
"initializer_range": 0.02,
|
128 |
+
"intermediate_size": 3072,
|
129 |
+
"is_decoder": false,
|
130 |
+
"is_encoder_decoder": false,
|
131 |
+
"label2id": {
|
132 |
+
"LABEL_0": 0,
|
133 |
+
"LABEL_1": 1
|
134 |
+
},
|
135 |
+
"layer_norm_eps": 1e-12,
|
136 |
+
"length_penalty": 1.0,
|
137 |
+
"max_length": 20,
|
138 |
+
"min_length": 0,
|
139 |
+
"model_type": "vit",
|
140 |
+
"no_repeat_ngram_size": 0,
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_beam_groups": 1,
|
143 |
+
"num_beams": 1,
|
144 |
+
"num_channels": 3,
|
145 |
+
"num_hidden_layers": 12,
|
146 |
+
"num_return_sequences": 1,
|
147 |
+
"output_attentions": false,
|
148 |
+
"output_hidden_states": false,
|
149 |
+
"output_scores": false,
|
150 |
+
"pad_token_id": null,
|
151 |
+
"patch_size": 16,
|
152 |
+
"prefix": null,
|
153 |
+
"problem_type": null,
|
154 |
+
"pruned_heads": {},
|
155 |
+
"qkv_bias": true,
|
156 |
+
"remove_invalid_values": false,
|
157 |
+
"repetition_penalty": 1.0,
|
158 |
+
"return_dict": true,
|
159 |
+
"return_dict_in_generate": false,
|
160 |
+
"sep_token_id": null,
|
161 |
+
"suppress_tokens": null,
|
162 |
+
"task_specific_params": null,
|
163 |
+
"temperature": 1.0,
|
164 |
+
"tf_legacy_loss": false,
|
165 |
+
"tie_encoder_decoder": false,
|
166 |
+
"tie_word_embeddings": true,
|
167 |
+
"tokenizer_class": null,
|
168 |
+
"top_k": 50,
|
169 |
+
"top_p": 1.0,
|
170 |
+
"torch_dtype": null,
|
171 |
+
"torchscript": false,
|
172 |
+
"typical_p": 1.0,
|
173 |
+
"use_bfloat16": false
|
174 |
+
},
|
175 |
+
"is_encoder_decoder": true,
|
176 |
+
"length_penalty": 2.0,
|
177 |
+
"max_length": 100,
|
178 |
+
"model_type": "vision-encoder-decoder",
|
179 |
+
"no_repeat_ngram_size": 3,
|
180 |
+
"num_beams": 4,
|
181 |
+
"pad_token_id": 50257,
|
182 |
+
"tie_word_embeddings": false,
|
183 |
+
"torch_dtype": "float32",
|
184 |
+
"transformers_version": "4.41.2"
|
185 |
+
}
|
checkpoint-20/generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"decoder_start_token_id": 50257,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 50256,
|
7 |
+
"length_penalty": 2.0,
|
8 |
+
"max_length": 100,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 50257,
|
12 |
+
"transformers_version": "4.41.2"
|
13 |
+
}
|
checkpoint-20/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074acedd1fb76dba7bf77d5e4fcc0d5ab34f266f05763c99d6eab4481a095384
|
3 |
+
size 884375032
|
checkpoint-20/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09105d354868d4fe77ac5c892332626514da756fc8d779faea7cd1af9654a546
|
3 |
+
size 1764138362
|
checkpoint-20/preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTFeatureExtractor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
checkpoint-20/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ebac1f31ffa94ad4f56f0825aec447abcf0cf1d915304f3622d4ca8fe34142d
|
3 |
+
size 14244
|
checkpoint-20/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae70a1422367ad7d19ae955834bfa23a1ee86febf2433c33e1c9568f46215f2
|
3 |
+
size 1064
|
checkpoint-20/trainer_state.json
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4519774011299435,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 20,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04519774011299435,
|
13 |
+
"grad_norm": 6.134562969207764,
|
14 |
+
"learning_rate": 1.9090909090909094e-05,
|
15 |
+
"loss": 10.8188,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0903954802259887,
|
20 |
+
"grad_norm": 6.219421863555908,
|
21 |
+
"learning_rate": 1.8181818181818182e-05,
|
22 |
+
"loss": 10.7835,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.13559322033898305,
|
27 |
+
"grad_norm": 6.437071800231934,
|
28 |
+
"learning_rate": 1.7272727272727274e-05,
|
29 |
+
"loss": 10.7424,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1807909604519774,
|
34 |
+
"grad_norm": 6.489596843719482,
|
35 |
+
"learning_rate": 1.6363636363636366e-05,
|
36 |
+
"loss": 10.6919,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22598870056497175,
|
41 |
+
"grad_norm": 6.816253185272217,
|
42 |
+
"learning_rate": 1.5454545454545454e-05,
|
43 |
+
"loss": 10.631,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22598870056497175,
|
48 |
+
"eval_loss": 10.573423385620117,
|
49 |
+
"eval_runtime": 557.6088,
|
50 |
+
"eval_samples_per_second": 2.252,
|
51 |
+
"eval_steps_per_second": 0.072,
|
52 |
+
"step": 10
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.2711864406779661,
|
56 |
+
"grad_norm": 7.1319050788879395,
|
57 |
+
"learning_rate": 1.4545454545454546e-05,
|
58 |
+
"loss": 10.5635,
|
59 |
+
"step": 12
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.3163841807909605,
|
63 |
+
"grad_norm": 7.451786041259766,
|
64 |
+
"learning_rate": 1.3636363636363637e-05,
|
65 |
+
"loss": 10.4988,
|
66 |
+
"step": 14
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.3615819209039548,
|
70 |
+
"grad_norm": 7.592668533325195,
|
71 |
+
"learning_rate": 1.2727272727272728e-05,
|
72 |
+
"loss": 10.4368,
|
73 |
+
"step": 16
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.4067796610169492,
|
77 |
+
"grad_norm": 7.819246768951416,
|
78 |
+
"learning_rate": 1.181818181818182e-05,
|
79 |
+
"loss": 10.3739,
|
80 |
+
"step": 18
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.4519774011299435,
|
84 |
+
"grad_norm": 7.926428318023682,
|
85 |
+
"learning_rate": 1.0909090909090909e-05,
|
86 |
+
"loss": 10.3155,
|
87 |
+
"step": 20
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.4519774011299435,
|
91 |
+
"eval_loss": 10.254356384277344,
|
92 |
+
"eval_runtime": 584.4893,
|
93 |
+
"eval_samples_per_second": 2.149,
|
94 |
+
"eval_steps_per_second": 0.068,
|
95 |
+
"step": 20
|
96 |
+
}
|
97 |
+
],
|
98 |
+
"logging_steps": 2,
|
99 |
+
"max_steps": 44,
|
100 |
+
"num_input_tokens_seen": 0,
|
101 |
+
"num_train_epochs": 1,
|
102 |
+
"save_steps": 10,
|
103 |
+
"stateful_callbacks": {
|
104 |
+
"TrainerControl": {
|
105 |
+
"args": {
|
106 |
+
"should_epoch_stop": false,
|
107 |
+
"should_evaluate": false,
|
108 |
+
"should_log": false,
|
109 |
+
"should_save": true,
|
110 |
+
"should_training_stop": false
|
111 |
+
},
|
112 |
+
"attributes": {}
|
113 |
+
}
|
114 |
+
},
|
115 |
+
"total_flos": 8.402188793964134e+17,
|
116 |
+
"train_batch_size": 32,
|
117 |
+
"trial_name": null,
|
118 |
+
"trial_params": null
|
119 |
+
}
|
checkpoint-20/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f579a1c85563781ce014e1d8e22f221ac4ed13f8c49396f27d9d8683cdbea6f
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BhashaAI/iamgeing-3",
|
3 |
+
"architectures": [
|
4 |
+
"VisionEncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "surajp/gpt2-hindi",
|
8 |
+
"activation_function": "gelu_new",
|
9 |
+
"add_cross_attention": true,
|
10 |
+
"architectures": [
|
11 |
+
"GPT2LMHeadModel"
|
12 |
+
],
|
13 |
+
"attn_pdrop": 0.1,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 50256,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"cross_attention_hidden_size": null,
|
19 |
+
"decoder_start_token_id": null,
|
20 |
+
"diversity_penalty": 0.0,
|
21 |
+
"do_sample": false,
|
22 |
+
"early_stopping": false,
|
23 |
+
"embd_pdrop": 0.1,
|
24 |
+
"encoder_no_repeat_ngram_size": 0,
|
25 |
+
"eos_token_id": 50256,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"is_decoder": true,
|
36 |
+
"is_encoder_decoder": false,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1
|
40 |
+
},
|
41 |
+
"layer_norm_epsilon": 1e-05,
|
42 |
+
"length_penalty": 1.0,
|
43 |
+
"max_length": 20,
|
44 |
+
"min_length": 0,
|
45 |
+
"model_type": "gpt2",
|
46 |
+
"n_ctx": 1024,
|
47 |
+
"n_embd": 768,
|
48 |
+
"n_head": 12,
|
49 |
+
"n_inner": null,
|
50 |
+
"n_layer": 6,
|
51 |
+
"n_positions": 1024,
|
52 |
+
"no_repeat_ngram_size": 0,
|
53 |
+
"num_beam_groups": 1,
|
54 |
+
"num_beams": 1,
|
55 |
+
"num_return_sequences": 1,
|
56 |
+
"output_attentions": false,
|
57 |
+
"output_hidden_states": false,
|
58 |
+
"output_scores": false,
|
59 |
+
"pad_token_id": 50257,
|
60 |
+
"prefix": null,
|
61 |
+
"problem_type": null,
|
62 |
+
"pruned_heads": {},
|
63 |
+
"remove_invalid_values": false,
|
64 |
+
"reorder_and_upcast_attn": false,
|
65 |
+
"repetition_penalty": 1.0,
|
66 |
+
"resid_pdrop": 0.1,
|
67 |
+
"return_dict": true,
|
68 |
+
"return_dict_in_generate": false,
|
69 |
+
"scale_attn_by_inverse_layer_idx": false,
|
70 |
+
"scale_attn_weights": true,
|
71 |
+
"sep_token_id": null,
|
72 |
+
"summary_activation": null,
|
73 |
+
"summary_first_dropout": 0.1,
|
74 |
+
"summary_proj_to_labels": true,
|
75 |
+
"summary_type": "cls_index",
|
76 |
+
"summary_use_proj": true,
|
77 |
+
"suppress_tokens": null,
|
78 |
+
"task_specific_params": null,
|
79 |
+
"temperature": 1.0,
|
80 |
+
"tf_legacy_loss": false,
|
81 |
+
"tie_encoder_decoder": false,
|
82 |
+
"tie_word_embeddings": true,
|
83 |
+
"tokenizer_class": null,
|
84 |
+
"top_k": 50,
|
85 |
+
"top_p": 1.0,
|
86 |
+
"torch_dtype": null,
|
87 |
+
"torchscript": false,
|
88 |
+
"typical_p": 1.0,
|
89 |
+
"use_bfloat16": false,
|
90 |
+
"use_cache": true,
|
91 |
+
"vocab_size": 50258
|
92 |
+
},
|
93 |
+
"decoder_start_token_id": 50257,
|
94 |
+
"device_map": "cuda",
|
95 |
+
"early_stopping": true,
|
96 |
+
"encoder": {
|
97 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
98 |
+
"add_cross_attention": false,
|
99 |
+
"architectures": [
|
100 |
+
"ViTModel"
|
101 |
+
],
|
102 |
+
"attention_probs_dropout_prob": 0.0,
|
103 |
+
"bad_words_ids": null,
|
104 |
+
"begin_suppress_tokens": null,
|
105 |
+
"bos_token_id": null,
|
106 |
+
"chunk_size_feed_forward": 0,
|
107 |
+
"cross_attention_hidden_size": null,
|
108 |
+
"decoder_start_token_id": null,
|
109 |
+
"diversity_penalty": 0.0,
|
110 |
+
"do_sample": false,
|
111 |
+
"early_stopping": false,
|
112 |
+
"encoder_no_repeat_ngram_size": 0,
|
113 |
+
"encoder_stride": 16,
|
114 |
+
"eos_token_id": null,
|
115 |
+
"exponential_decay_length_penalty": null,
|
116 |
+
"finetuning_task": null,
|
117 |
+
"forced_bos_token_id": null,
|
118 |
+
"forced_eos_token_id": null,
|
119 |
+
"hidden_act": "gelu",
|
120 |
+
"hidden_dropout_prob": 0.0,
|
121 |
+
"hidden_size": 768,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"image_size": 224,
|
127 |
+
"initializer_range": 0.02,
|
128 |
+
"intermediate_size": 3072,
|
129 |
+
"is_decoder": false,
|
130 |
+
"is_encoder_decoder": false,
|
131 |
+
"label2id": {
|
132 |
+
"LABEL_0": 0,
|
133 |
+
"LABEL_1": 1
|
134 |
+
},
|
135 |
+
"layer_norm_eps": 1e-12,
|
136 |
+
"length_penalty": 1.0,
|
137 |
+
"max_length": 20,
|
138 |
+
"min_length": 0,
|
139 |
+
"model_type": "vit",
|
140 |
+
"no_repeat_ngram_size": 0,
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_beam_groups": 1,
|
143 |
+
"num_beams": 1,
|
144 |
+
"num_channels": 3,
|
145 |
+
"num_hidden_layers": 12,
|
146 |
+
"num_return_sequences": 1,
|
147 |
+
"output_attentions": false,
|
148 |
+
"output_hidden_states": false,
|
149 |
+
"output_scores": false,
|
150 |
+
"pad_token_id": null,
|
151 |
+
"patch_size": 16,
|
152 |
+
"prefix": null,
|
153 |
+
"problem_type": null,
|
154 |
+
"pruned_heads": {},
|
155 |
+
"qkv_bias": true,
|
156 |
+
"remove_invalid_values": false,
|
157 |
+
"repetition_penalty": 1.0,
|
158 |
+
"return_dict": true,
|
159 |
+
"return_dict_in_generate": false,
|
160 |
+
"sep_token_id": null,
|
161 |
+
"suppress_tokens": null,
|
162 |
+
"task_specific_params": null,
|
163 |
+
"temperature": 1.0,
|
164 |
+
"tf_legacy_loss": false,
|
165 |
+
"tie_encoder_decoder": false,
|
166 |
+
"tie_word_embeddings": true,
|
167 |
+
"tokenizer_class": null,
|
168 |
+
"top_k": 50,
|
169 |
+
"top_p": 1.0,
|
170 |
+
"torch_dtype": null,
|
171 |
+
"torchscript": false,
|
172 |
+
"typical_p": 1.0,
|
173 |
+
"use_bfloat16": false
|
174 |
+
},
|
175 |
+
"is_encoder_decoder": true,
|
176 |
+
"length_penalty": 2.0,
|
177 |
+
"max_length": 100,
|
178 |
+
"model_type": "vision-encoder-decoder",
|
179 |
+
"no_repeat_ngram_size": 3,
|
180 |
+
"num_beams": 4,
|
181 |
+
"pad_token_id": 50257,
|
182 |
+
"tie_word_embeddings": false,
|
183 |
+
"torch_dtype": "float32",
|
184 |
+
"transformers_version": "4.41.2"
|
185 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074acedd1fb76dba7bf77d5e4fcc0d5ab34f266f05763c99d6eab4481a095384
|
3 |
+
size 884375032
|
preprocessor_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"return_tensors",
|
13 |
+
"data_format",
|
14 |
+
"input_data_format"
|
15 |
+
],
|
16 |
+
"do_normalize": true,
|
17 |
+
"do_rescale": true,
|
18 |
+
"do_resize": true,
|
19 |
+
"image_mean": [
|
20 |
+
0.5,
|
21 |
+
0.5,
|
22 |
+
0.5
|
23 |
+
],
|
24 |
+
"image_processor_type": "ViTFeatureExtractor",
|
25 |
+
"image_std": [
|
26 |
+
0.5,
|
27 |
+
0.5,
|
28 |
+
0.5
|
29 |
+
],
|
30 |
+
"resample": 2,
|
31 |
+
"rescale_factor": 0.00392156862745098,
|
32 |
+
"size": {
|
33 |
+
"height": 224,
|
34 |
+
"width": 224
|
35 |
+
}
|
36 |
+
}
|
runs/Jun11_09-10-35_ip-10-192-12-224/events.out.tfevents.1718097036.ip-10-192-12-224.1762.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bc440d8fb6b0a400a95eaf9019307cfdfd2ab335f1d36ac9ea2fe167e10830
|
3 |
+
size 11917
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f579a1c85563781ce014e1d8e22f221ac4ed13f8c49396f27d9d8683cdbea6f
|
3 |
+
size 5304
|