MohamedAhmedAE
commited on
Commit
•
e24a74e
1
Parent(s):
cb1f2bf
Training in progress, step 10, checkpoint
Browse files
last-checkpoint/config.json
CHANGED
@@ -8,11 +8,9 @@
|
|
8 |
"model_type": "vision-text-dual-encoder",
|
9 |
"projection_dim": 512,
|
10 |
"text_config": {
|
11 |
-
"_name_or_path": "
|
12 |
"add_cross_attention": false,
|
13 |
-
"architectures":
|
14 |
-
"RobertaForMaskedLM"
|
15 |
-
],
|
16 |
"attention_probs_dropout_prob": 0.1,
|
17 |
"bad_words_ids": null,
|
18 |
"begin_suppress_tokens": null,
|
@@ -90,7 +88,7 @@
|
|
90 |
"torch_dtype": "float32",
|
91 |
"transformers_version": "4.41.2",
|
92 |
"vision_config": {
|
93 |
-
"_name_or_path": "openai/clip-vit-
|
94 |
"add_cross_attention": false,
|
95 |
"architectures": null,
|
96 |
"attention_dropout": 0.0,
|
@@ -111,15 +109,15 @@
|
|
111 |
"forced_bos_token_id": null,
|
112 |
"forced_eos_token_id": null,
|
113 |
"hidden_act": "quick_gelu",
|
114 |
-
"hidden_size":
|
115 |
"id2label": {
|
116 |
"0": "LABEL_0",
|
117 |
"1": "LABEL_1"
|
118 |
},
|
119 |
-
"image_size":
|
120 |
"initializer_factor": 1.0,
|
121 |
"initializer_range": 0.02,
|
122 |
-
"intermediate_size":
|
123 |
"is_decoder": false,
|
124 |
"is_encoder_decoder": false,
|
125 |
"label2id": {
|
@@ -132,20 +130,20 @@
|
|
132 |
"min_length": 0,
|
133 |
"model_type": "clip_vision_model",
|
134 |
"no_repeat_ngram_size": 0,
|
135 |
-
"num_attention_heads":
|
136 |
"num_beam_groups": 1,
|
137 |
"num_beams": 1,
|
138 |
"num_channels": 3,
|
139 |
-
"num_hidden_layers":
|
140 |
"num_return_sequences": 1,
|
141 |
"output_attentions": false,
|
142 |
"output_hidden_states": false,
|
143 |
"output_scores": false,
|
144 |
"pad_token_id": null,
|
145 |
-
"patch_size":
|
146 |
"prefix": null,
|
147 |
"problem_type": null,
|
148 |
-
"projection_dim":
|
149 |
"pruned_heads": {},
|
150 |
"remove_invalid_values": false,
|
151 |
"repetition_penalty": 1.0,
|
|
|
8 |
"model_type": "vision-text-dual-encoder",
|
9 |
"projection_dim": 512,
|
10 |
"text_config": {
|
11 |
+
"_name_or_path": "allenai/biomed_roberta_base",
|
12 |
"add_cross_attention": false,
|
13 |
+
"architectures": null,
|
|
|
|
|
14 |
"attention_probs_dropout_prob": 0.1,
|
15 |
"bad_words_ids": null,
|
16 |
"begin_suppress_tokens": null,
|
|
|
88 |
"torch_dtype": "float32",
|
89 |
"transformers_version": "4.41.2",
|
90 |
"vision_config": {
|
91 |
+
"_name_or_path": "openai/clip-vit-large-patch14-336",
|
92 |
"add_cross_attention": false,
|
93 |
"architectures": null,
|
94 |
"attention_dropout": 0.0,
|
|
|
109 |
"forced_bos_token_id": null,
|
110 |
"forced_eos_token_id": null,
|
111 |
"hidden_act": "quick_gelu",
|
112 |
+
"hidden_size": 1024,
|
113 |
"id2label": {
|
114 |
"0": "LABEL_0",
|
115 |
"1": "LABEL_1"
|
116 |
},
|
117 |
+
"image_size": 336,
|
118 |
"initializer_factor": 1.0,
|
119 |
"initializer_range": 0.02,
|
120 |
+
"intermediate_size": 4096,
|
121 |
"is_decoder": false,
|
122 |
"is_encoder_decoder": false,
|
123 |
"label2id": {
|
|
|
130 |
"min_length": 0,
|
131 |
"model_type": "clip_vision_model",
|
132 |
"no_repeat_ngram_size": 0,
|
133 |
+
"num_attention_heads": 16,
|
134 |
"num_beam_groups": 1,
|
135 |
"num_beams": 1,
|
136 |
"num_channels": 3,
|
137 |
+
"num_hidden_layers": 24,
|
138 |
"num_return_sequences": 1,
|
139 |
"output_attentions": false,
|
140 |
"output_hidden_states": false,
|
141 |
"output_scores": false,
|
142 |
"pad_token_id": null,
|
143 |
+
"patch_size": 14,
|
144 |
"prefix": null,
|
145 |
"problem_type": null,
|
146 |
+
"projection_dim": 768,
|
147 |
"pruned_heads": {},
|
148 |
"remove_invalid_values": false,
|
149 |
"repetition_penalty": 1.0,
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d93e1447df338cb82425c676ee327e29e6ccdf6b0fcb1e6b1e8bcc1b9790a47
|
3 |
+
size 1716360444
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9a2844302fb6bb266b84b60df234bff01243f6e34895e273c410eeacbbc97e6
|
3 |
+
size 3433062021
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7775cfb857ea8d5dad4e55d621fe6b664e7f7e01b9a13925f47757ea28a71912
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b32c228988998aa7f8c86d4c26da16835ba6d8d022fa594dfdc2c5ed5b7a666
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,58 +1,23 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 4.
|
15 |
-
"loss":
|
16 |
"step": 10
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 1.4678899082568808,
|
20 |
-
"grad_norm": 0.1586851328611374,
|
21 |
-
"learning_rate": 4.267766952966369e-05,
|
22 |
-
"loss": 2.763,
|
23 |
-
"step": 20
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 2.2018348623853212,
|
27 |
-
"grad_norm": 0.08846019953489304,
|
28 |
-
"learning_rate": 3.147047612756302e-05,
|
29 |
-
"loss": 2.7628,
|
30 |
-
"step": 30
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 2.9357798165137616,
|
34 |
-
"grad_norm": 0.03923465684056282,
|
35 |
-
"learning_rate": 1.852952387243698e-05,
|
36 |
-
"loss": 2.773,
|
37 |
-
"step": 40
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 3.669724770642202,
|
41 |
-
"grad_norm": 0.045462485402822495,
|
42 |
-
"learning_rate": 7.3223304703363135e-06,
|
43 |
-
"loss": 2.7624,
|
44 |
-
"step": 50
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 4.4036697247706424,
|
48 |
-
"grad_norm": 0.0461534820497036,
|
49 |
-
"learning_rate": 8.51854342773295e-07,
|
50 |
-
"loss": 2.7624,
|
51 |
-
"step": 60
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 10,
|
55 |
-
"max_steps":
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 5,
|
58 |
"save_steps": 10,
|
@@ -68,8 +33,8 @@
|
|
68 |
"attributes": {}
|
69 |
}
|
70 |
},
|
71 |
-
"total_flos":
|
72 |
-
"train_batch_size":
|
73 |
"trial_name": null,
|
74 |
"trial_params": null
|
75 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04608294930875576,
|
5 |
"eval_steps": 100,
|
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": 0.04608294930875576,
|
13 |
+
"grad_norm": 3.232759714126587,
|
14 |
+
"learning_rate": 4.999735579817769e-05,
|
15 |
+
"loss": 1.4008,
|
16 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 10,
|
20 |
+
"max_steps": 1085,
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 5,
|
23 |
"save_steps": 10,
|
|
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
+
"total_flos": 23929694515200.0,
|
37 |
+
"train_batch_size": 4,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43d91b1496178ac406352964cea26801514f7d8531618943d63c80852c83fa37
|
3 |
size 5112
|