End of training
Browse files- README.md +7 -2
- all_results.json +14 -0
- test_results.json +10 -0
- tokenizer.json +2 -16
- train_results.json +10 -0
- trainer_state.json +148 -0
- validation_results.json +10 -0
README.md
CHANGED
@@ -4,7 +4,7 @@ base_model: BridgeTower/bridgetower-large-itm-mlm-itc
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
- newyorker_caption_contest
|
8 |
model-index:
|
9 |
- name: test-bridgetower
|
10 |
results: []
|
@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# test-bridgetower
|
17 |
|
18 |
-
This model is a fine-tuned version of [BridgeTower/bridgetower-large-itm-mlm-itc](https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-itc) on the newyorker_caption_contest dataset.
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- jmhessel/newyorker_caption_contest
|
8 |
model-index:
|
9 |
- name: test-bridgetower
|
10 |
results: []
|
|
|
15 |
|
16 |
# test-bridgetower
|
17 |
|
18 |
+
This model is a fine-tuned version of [BridgeTower/bridgetower-large-itm-mlm-itc](https://huggingface.co/BridgeTower/bridgetower-large-itm-mlm-itc) on the jmhessel/newyorker_caption_contest matching dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1163
|
21 |
+
- Memory Allocated (gb): 17.72
|
22 |
+
- Max Memory Allocated (gb): 94.43
|
23 |
+
- Total Memory Available (gb): 94.61
|
24 |
|
25 |
## Model description
|
26 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.11634299904108047,
|
4 |
+
"eval_runtime": 0.4543,
|
5 |
+
"eval_samples_per_second": 1162.27,
|
6 |
+
"eval_steps_per_second": 11.006,
|
7 |
+
"max_memory_allocated (GB)": 94.43,
|
8 |
+
"memory_allocated (GB)": 17.72,
|
9 |
+
"total_memory_available (GB)": 94.61,
|
10 |
+
"train_loss": 0.08891021746855515,
|
11 |
+
"train_runtime": 341.352,
|
12 |
+
"train_samples_per_second": 429.544,
|
13 |
+
"train_steps_per_second": 1.141
|
14 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.11634299904108047,
|
4 |
+
"eval_runtime": 0.4543,
|
5 |
+
"eval_samples_per_second": 1162.27,
|
6 |
+
"eval_steps_per_second": 11.006,
|
7 |
+
"max_memory_allocated (GB)": 94.43,
|
8 |
+
"memory_allocated (GB)": 17.72,
|
9 |
+
"total_memory_available (GB)": 94.61
|
10 |
+
}
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 128,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 128
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 1,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
train_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"max_memory_allocated (GB)": 94.43,
|
4 |
+
"memory_allocated (GB)": 17.74,
|
5 |
+
"total_memory_available (GB)": 94.61,
|
6 |
+
"train_loss": 0.08891021746855515,
|
7 |
+
"train_runtime": 341.352,
|
8 |
+
"train_samples_per_second": 429.544,
|
9 |
+
"train_steps_per_second": 1.141
|
10 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 130,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.38,
|
13 |
+
"learning_rate": 9.230769230769232e-06,
|
14 |
+
"loss": 0.2471,
|
15 |
+
"max_memory_allocated (GB)": 94.4,
|
16 |
+
"memory_allocated (GB)": 17.88,
|
17 |
+
"step": 10,
|
18 |
+
"total_memory_available (GB)": 94.61
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.77,
|
22 |
+
"learning_rate": 8.461538461538462e-06,
|
23 |
+
"loss": 0.1034,
|
24 |
+
"max_memory_allocated (GB)": 94.42,
|
25 |
+
"memory_allocated (GB)": 17.88,
|
26 |
+
"step": 20,
|
27 |
+
"total_memory_available (GB)": 94.61
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.15,
|
31 |
+
"learning_rate": 7.692307692307694e-06,
|
32 |
+
"loss": 0.0834,
|
33 |
+
"max_memory_allocated (GB)": 94.42,
|
34 |
+
"memory_allocated (GB)": 17.88,
|
35 |
+
"step": 30,
|
36 |
+
"total_memory_available (GB)": 94.61
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.54,
|
40 |
+
"learning_rate": 6.923076923076923e-06,
|
41 |
+
"loss": 0.0813,
|
42 |
+
"max_memory_allocated (GB)": 94.42,
|
43 |
+
"memory_allocated (GB)": 17.88,
|
44 |
+
"step": 40,
|
45 |
+
"total_memory_available (GB)": 94.61
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.92,
|
49 |
+
"learning_rate": 6.153846153846155e-06,
|
50 |
+
"loss": 0.0771,
|
51 |
+
"max_memory_allocated (GB)": 94.42,
|
52 |
+
"memory_allocated (GB)": 17.83,
|
53 |
+
"step": 50,
|
54 |
+
"total_memory_available (GB)": 94.61
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 2.31,
|
58 |
+
"learning_rate": 5.384615384615385e-06,
|
59 |
+
"loss": 0.0732,
|
60 |
+
"max_memory_allocated (GB)": 94.42,
|
61 |
+
"memory_allocated (GB)": 17.88,
|
62 |
+
"step": 60,
|
63 |
+
"total_memory_available (GB)": 94.61
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.69,
|
67 |
+
"learning_rate": 4.615384615384616e-06,
|
68 |
+
"loss": 0.0714,
|
69 |
+
"max_memory_allocated (GB)": 94.43,
|
70 |
+
"memory_allocated (GB)": 17.89,
|
71 |
+
"step": 70,
|
72 |
+
"total_memory_available (GB)": 94.61
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 3.08,
|
76 |
+
"learning_rate": 3.846153846153847e-06,
|
77 |
+
"loss": 0.0715,
|
78 |
+
"max_memory_allocated (GB)": 94.43,
|
79 |
+
"memory_allocated (GB)": 17.89,
|
80 |
+
"step": 80,
|
81 |
+
"total_memory_available (GB)": 94.61
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 3.46,
|
85 |
+
"learning_rate": 3.0769230769230774e-06,
|
86 |
+
"loss": 0.0693,
|
87 |
+
"max_memory_allocated (GB)": 94.43,
|
88 |
+
"memory_allocated (GB)": 17.88,
|
89 |
+
"step": 90,
|
90 |
+
"total_memory_available (GB)": 94.61
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 3.85,
|
94 |
+
"learning_rate": 2.307692307692308e-06,
|
95 |
+
"loss": 0.0691,
|
96 |
+
"max_memory_allocated (GB)": 94.43,
|
97 |
+
"memory_allocated (GB)": 17.88,
|
98 |
+
"step": 100,
|
99 |
+
"total_memory_available (GB)": 94.61
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.23,
|
103 |
+
"learning_rate": 1.5384615384615387e-06,
|
104 |
+
"loss": 0.0691,
|
105 |
+
"max_memory_allocated (GB)": 94.43,
|
106 |
+
"memory_allocated (GB)": 17.88,
|
107 |
+
"step": 110,
|
108 |
+
"total_memory_available (GB)": 94.61
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 4.62,
|
112 |
+
"learning_rate": 7.692307692307694e-07,
|
113 |
+
"loss": 0.0702,
|
114 |
+
"max_memory_allocated (GB)": 94.43,
|
115 |
+
"memory_allocated (GB)": 17.88,
|
116 |
+
"step": 120,
|
117 |
+
"total_memory_available (GB)": 94.61
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 5.0,
|
121 |
+
"learning_rate": 0.0,
|
122 |
+
"loss": 0.0698,
|
123 |
+
"max_memory_allocated (GB)": 94.43,
|
124 |
+
"memory_allocated (GB)": 17.74,
|
125 |
+
"step": 130,
|
126 |
+
"total_memory_available (GB)": 94.61
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 5.0,
|
130 |
+
"max_memory_allocated (GB)": 94.43,
|
131 |
+
"memory_allocated (GB)": 17.74,
|
132 |
+
"step": 130,
|
133 |
+
"total_flos": 3.117345829342413e+16,
|
134 |
+
"total_memory_available (GB)": 94.61,
|
135 |
+
"train_loss": 0.08891021746855515,
|
136 |
+
"train_runtime": 341.352,
|
137 |
+
"train_samples_per_second": 429.544,
|
138 |
+
"train_steps_per_second": 1.141
|
139 |
+
}
|
140 |
+
],
|
141 |
+
"logging_steps": 10,
|
142 |
+
"max_steps": 130,
|
143 |
+
"num_train_epochs": 5,
|
144 |
+
"save_steps": 500,
|
145 |
+
"total_flos": 3.117345829342413e+16,
|
146 |
+
"trial_name": null,
|
147 |
+
"trial_params": null
|
148 |
+
}
|
validation_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.11108700931072235,
|
4 |
+
"eval_runtime": 7.8437,
|
5 |
+
"eval_samples_per_second": 67.697,
|
6 |
+
"eval_steps_per_second": 0.637,
|
7 |
+
"max_memory_allocated (GB)": 94.43,
|
8 |
+
"memory_allocated (GB)": 17.71,
|
9 |
+
"total_memory_available (GB)": 94.61
|
10 |
+
}
|